WO2024098259A1 - Sample set generation method and device - Google Patents

Sample set generation method and device Download PDF

Info

Publication number
WO2024098259A1
WO2024098259A1 PCT/CN2022/130674 CN2022130674W WO2024098259A1 WO 2024098259 A1 WO2024098259 A1 WO 2024098259A1 CN 2022130674 W CN2022130674 W CN 2022130674W WO 2024098259 A1 WO2024098259 A1 WO 2024098259A1
Authority
WO
WIPO (PCT)
Prior art keywords
matrix
basis vector
task
csi
basis
Prior art date
Application number
PCT/CN2022/130674
Other languages
French (fr)
Chinese (zh)
Inventor
肖寒
Original Assignee
Oppo广东移动通信有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Oppo广东移动通信有限公司 filed Critical Oppo广东移动通信有限公司
Priority to PCT/CN2022/130674 priority Critical patent/WO2024098259A1/en
Publication of WO2024098259A1 publication Critical patent/WO2024098259A1/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B7/00—Radio transmission systems, i.e. using radiation field
    • H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/0413—MIMO systems
    • H04B7/0417—Feedback systems
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L27/00—Modulated-carrier systems

Definitions

  • the embodiments of the present application relate to the field of communications, and in particular to a method and device for generating a sample set.
  • the terminal device needs to feed back Channel State Information (CSI) to the network device so that the network device can determine the precoding matrix for downlink transmission.
  • CSI Channel State Information
  • CSI feedback based on meta-learning is considered.
  • building a meta-model requires a large amount of CSI data from different scenarios. Collecting a large amount of CSI samples with high diversity is challenging in terms of actual collection cost and difficulty. Therefore, how to implement CSI feedback based on meta-learning is an urgent problem to be solved.
  • the present application provides a method and device for generating a sample set, which is conducive to reducing the cost and difficulty of obtaining CSI samples.
  • a method for generating a sample set comprising: constructing a first basis vector space and a second basis vector space, wherein the first basis vector space comprises O basis vector groups, each basis vector group comprises N 1 *N 2 spatial domain basis vectors, and the second basis vector space comprises N sb frequency domain basis vectors, wherein O is a positive integer, N 1 is the number of antenna ports of a first dimension of a transmitting end of channel state information CSI, N 2 is the number of antenna ports of a second dimension of a transmitting end of CSI, and N sb represents the number of subbands;
  • a CSI sample set corresponding to each task in a plurality of tasks is constructed, wherein the CSI sample set corresponding to each task is constructed based on some spatial domain basis vectors in a basis vector group in the first basis vector space and some frequency domain basis vectors in the second basis vector space, and the CSI sample sets corresponding to the plurality of tasks are respectively used to train a first model, and the first model is used to obtain a second model based on the CSI sample set of a target scene for training, and the second model is adapted to the target scene.
  • a device for generating a sample set is provided, which is used to execute the method in the above-mentioned first aspect or its various implementations.
  • the terminal device includes a functional module for executing the method in the above-mentioned first aspect or its various implementation modes.
  • a device for generating a sample set comprising a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method in the first aspect or its implementations.
  • a chip is provided for implementing the method in the first aspect or its various implementations.
  • the chip includes: a processor, which is used to call and run a computer program from a memory, so that a device equipped with the device executes the method in the above-mentioned first aspect or its various implementation modes.
  • a computer-readable storage medium for storing a computer program, wherein the computer program enables a computer to execute the method in the above-mentioned first aspect or its various implementations.
  • a computer program product comprising computer program instructions, wherein the computer program instructions enable a computer to execute the method in the above-mentioned first aspect or its various implementations.
  • a computer program which, when executed on a computer, enables the computer to execute the method in the first aspect or its various implementations.
  • a first basis vector space corresponding to the spatial domain basis vectors and a second basis vector space corresponding to the frequency domain basis vectors can be constructed. Furthermore, a CSI sample set corresponding to each of multiple tasks for training the meta-model (i.e., the first model) can be generated based on the first basis vector space and the second basis vector space. By automatically generating a data set for meta-model training, the cost and difficulty of obtaining CSI data can be reduced.
  • FIG1 is a schematic diagram of a communication system architecture provided in an embodiment of the present application.
  • FIG. 2 is a schematic diagram of a neuron structure.
  • FIG3 is a schematic diagram of a neural network provided in the present application.
  • FIG4 is a schematic diagram of a convolutional neural network provided in the present application.
  • FIG5 is a schematic diagram of an LSTM unit provided in the present application.
  • FIG6 is a schematic diagram of a channel information feedback provided by the present application.
  • FIG. 7 is a schematic diagram of another channel information feedback provided by the present application.
  • FIG8 is a schematic flowchart of a method for generating a sample set according to an embodiment of the present application.
  • FIG. 9 is a schematic block diagram of a device for generating a sample set according to an embodiment of the present application.
  • FIG10 is a schematic block diagram of a communication device provided according to an embodiment of the present application.
  • FIG. 11 is a schematic block diagram of a chip provided according to an embodiment of the present application.
  • GSM Global System of Mobile communication
  • CDMA Code Division Multiple Access
  • WCDMA Wideband Code Division Multiple Access
  • GPRS General Packet Radio Service
  • LTE Long Term Evolution
  • LTE-A Advanced long term evolution
  • NR New Radio
  • LTE-based access to unlicensed spectrum (LTE-U) systems LTE-based access to unlicensed spectrum (LTE-U) systems
  • NR-based access to unlicensed spectrum (NR-U) systems NTN-based access to unlicensed spectrum (NR-U) systems
  • NTN non-terrestrial communication networks
  • UMTS universal mobile telecommunication systems
  • WLAN wireless local area networks
  • WiFi wireless fidelity
  • 5G fifth-generation communication
  • D2D Device to Device
  • M2M Machine to Machine
  • MTC Machine Type Communication
  • V2V vehicle to vehicle
  • V2X vehicle to everything
  • the communication system in the embodiment of the present application can be applied to a carrier aggregation (CA) scenario, a dual connectivity (DC) scenario, or a standalone (SA) networking scenario.
  • CA carrier aggregation
  • DC dual connectivity
  • SA standalone
  • the communication system in the embodiment of the present application can be applied to an unlicensed spectrum, wherein the unlicensed spectrum can also be considered as a shared spectrum; or, the communication system in the embodiment of the present application can also be applied to an authorized spectrum, wherein the authorized spectrum can also be considered as an unshared spectrum.
  • the embodiments of the present application describe various embodiments in conjunction with network equipment and terminal equipment, wherein the terminal equipment may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication equipment, user agent or user device, etc.
  • UE user equipment
  • the terminal device can be a station (STA) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a wearable device, a terminal device in the next generation communication system such as the NR network, or a terminal device in the future evolved Public Land Mobile Network (PLMN) network, etc.
  • STA station
  • WLAN Wireless Local Loop
  • PDA Personal Digital Assistant
  • the terminal device can be deployed on land, including indoors or outdoors, handheld, wearable or vehicle-mounted; it can also be deployed on the water surface (such as ships, etc.); it can also be deployed in the air (for example, on airplanes, balloons and satellites, etc.).
  • the terminal device may be a mobile phone, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical, a wireless terminal device in smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, or a wireless terminal device in a smart home, etc.
  • VR virtual reality
  • AR augmented reality
  • the terminal device may also be a wearable device.
  • Wearable devices may also be referred to as wearable smart devices, which are a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing, and shoes.
  • a wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also powerful functions achieved through software support, data interaction, and cloud interaction.
  • wearable smart devices include full-featured, large-sized, and fully or partially independent of smartphones, such as smart watches or smart glasses, as well as devices that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various types of smart bracelets and smart jewelry for vital sign monitoring.
  • the network device may be a device for communicating with a mobile device.
  • the network device may be an access point (AP) in WLAN, a base station (Base Transceiver Station, BTS) in GSM or CDMA, a base station (NodeB, NB) in WCDMA, an evolved base station (Evolutional Node B, eNB or eNodeB) in LTE, or a relay station or access point, or a vehicle-mounted device, a wearable device, and a network device (gNB) in an NR network, or a network device in a future evolved PLMN network, or a network device in an NTN network, etc.
  • AP access point
  • BTS Base Transceiver Station
  • NodeB, NB base station
  • Evolutional Node B, eNB or eNodeB evolved base station
  • gNB network device
  • gNB network device
  • the network device may have a mobile feature, for example, the network device may be a mobile device.
  • the network device may be a satellite or a balloon station.
  • the satellite may be a low earth orbit (LEO) satellite, a medium earth orbit (MEO) satellite, a geostationary earth orbit (GEO) satellite, a high elliptical orbit (HEO) satellite, etc.
  • the network device may also be a base station set up in a location such as land or water.
  • a network device can provide services for a cell, and a terminal device communicates with the network device through transmission resources used by the cell (for example, frequency domain resources, or spectrum resources).
  • the cell can be a cell corresponding to a network device (for example, a base station), and the cell can belong to a macro base station or a base station corresponding to a small cell.
  • the small cells here may include: metro cells, micro cells, pico cells, femto cells, etc. These small cells have the characteristics of small coverage and low transmission power, and are suitable for providing high-speed data transmission services.
  • the communication system 100 may include a network device 110, which may be a device that communicates with a terminal device 120 (or referred to as a communication terminal or terminal).
  • the network device 110 may provide communication coverage for a specific geographic area and may communicate with terminal devices located in the coverage area.
  • FIG1 exemplarily shows a network device and two terminal devices.
  • the communication system 100 may include multiple network devices and each network device may include another number of terminal devices within its coverage area, which is not limited in the embodiments of the present application.
  • the communication system 100 may also include other network entities such as a network controller and a mobility management entity, which is not limited in the embodiments of the present application.
  • network entities such as a network controller and a mobility management entity, which is not limited in the embodiments of the present application.
  • the device with communication function in the network/system in the embodiment of the present application can be called a communication device.
  • the communication device may include a network device 110 and a terminal device 120 with communication function, and the network device 110 and the terminal device 120 may be the specific devices described above, which will not be repeated here; the communication device may also include other devices in the communication system 100, such as other network entities such as a network controller and a mobile management entity, which is not limited in the embodiment of the present application.
  • the "indication" mentioned in the embodiments of the present application can be a direct indication, an indirect indication, or an indication of an association relationship.
  • a indicates B which can mean that A directly indicates B, for example, B can be obtained through A; it can also mean that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; it can also mean that there is an association relationship between A and B.
  • corresponding may indicate a direct or indirect correspondence between two items, or an association relationship between the two items, or a relationship of indication and being indicated, configuration and being configured, etc.
  • pre-definition can be implemented by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in a device (for example, including a terminal device and a network device), and the present application does not limit the specific implementation method.
  • pre-definition can refer to what is defined in the protocol.
  • the "protocol” may refer to a standard protocol in the communication field, for example, it may include an LTE protocol, an NR protocol, and related protocols used in future communication systems, and the present application does not limit this.
  • the codebook-based eigenvector feedback is mainly used to enable the base station to obtain the downlink CSI.
  • the base station sends a downlink channel state information reference signal (Channel State Information Reference Signal, CSI-RS) to the terminal device.
  • CSI-RS Channel State Information Reference Signal
  • the terminal device uses CSI-RS to estimate the CSI of the downlink channel and performs eigenvalue decomposition on the estimated downlink channel to obtain the eigenvector corresponding to the downlink channel.
  • the NR system provides three codebook design schemes: Type 1 (Type I), Type 2 (TypeII) and enhanced Type 2 (eTypeII).
  • the precoding matrix to be fed back is expressed as W ⁇ C Nt ⁇ Nsb , where C represents the complex space, Nt represents the number of transmit antenna ports, Nsb represents the number of subbands, and each column of the matrix W represents the precoding vector shared by multiple subcarriers on each subband.
  • the eTypeII codebook considers feedback of the following information:
  • a neural network is a computing model consisting of multiple interconnected neuron nodes, where the connection between nodes represents the weighted value from the input signal to the output signal, called the weight; each node performs weighted summation (SUM) on different input signals and outputs them through a specific activation function (f).
  • Figure 2 is a schematic diagram of a neuron structure, where a1, a2, ..., an represent input signals, w1, w2, ..., wn represent weights, f represents the activation function, and t represents the output.
  • a simple neural network is shown in Figure 3, which includes an input layer, a hidden layer, and an output layer. Through different connection methods, weights, and activation functions of multiple neurons, different outputs can be generated, thereby fitting the mapping relationship from input to output. Among them, each upper-level node is connected to all its lower-level nodes.
  • This neural network is a fully connected neural network, which can also be called a deep neural network (DNN).
  • DNN deep neural network
  • Deep learning uses a deep neural network with multiple hidden layers, which greatly improves the network's ability to learn features and fits complex nonlinear mappings from input to output. Therefore, it is widely used in speech and image processing.
  • deep learning also includes common basic structures such as convolutional neural networks (CNN) and recurrent neural networks (RNN) for different tasks.
  • CNN convolutional neural networks
  • RNN recurrent neural networks
  • the basic structure of a convolutional neural network includes: input layer, multiple convolutional layers, multiple pooling layers, fully connected layer and output layer, as shown in Figure 4.
  • Each neuron of the convolution kernel in the convolutional layer is locally connected to its input, and the maximum or average value of a certain layer is extracted by introducing the pooling layer, which effectively reduces the parameters of the network and mines the local features, so that the convolutional neural network can converge quickly and obtain excellent performance.
  • RNN is a neural network that models sequential data and has achieved remarkable results in the field of natural language processing, such as machine translation and speech recognition. Specifically, the network memorizes information from the past and uses it in the calculation of the current output, that is, the nodes between the hidden layers are no longer disconnected but connected, and the input of the hidden layer includes not only the input layer but also the output of the hidden layer at the previous moment.
  • Commonly used RNNs include structures such as Long Short-Term Memory (LSTM) and gated recurrent unit (GRU).
  • Figure 5 shows a basic LSTM unit structure, which can include a tanh activation function. Unlike RNN, which only considers the most recent state, the cell state of LSTM determines which states should be retained and which states should be forgotten, solving the defects of traditional RNN in long-term memory.
  • the neural network architecture commonly used in deep learning is nonlinear and data-driven. It can extract features from actual channel matrix data and restore the channel matrix information compressed and fed back by the terminal side as much as possible on the base station side. While ensuring the restoration of channel information, it also provides the possibility of reducing CSI feedback overhead on the terminal side.
  • the deep learning-based CSI feedback regards the channel information as an image to be compressed, uses a deep learning autoencoder to compress and feedback the channel information, and reconstructs the compressed channel image at the transmitting end, which can retain the channel information to a greater extent, as shown in Figure 6.
  • a typical channel information feedback system is shown in Figure 7.
  • the entire feedback system is divided into an encoder and a decoder, which are deployed at the transmitter and the receiver respectively.
  • the transmitter obtains the channel information through channel estimation
  • the channel information matrix is compressed and encoded through the neural network of the encoder, and the compressed bit stream is fed back to the receiver through the air interface feedback link.
  • the receiver recovers the channel information according to the feedback bit stream through the decoder to obtain complete feedback channel information.
  • the encoder shown in Figure 7 uses the superposition of multiple fully connected layers, and the decoder uses the design of convolutional layers and residual structures. When the encoding and decoding framework remains unchanged, the network model structure inside the encoder and decoder can be flexibly designed.
  • meta-learning The main idea of meta-learning is to "let the machine learn to learn". For example, first use a large amount of data from different scenarios and categories, and use a meta-learning algorithm (including but not limited to MAML, Reptile, etc.) to train the model with randomly initialized weights as the starting point to obtain a meta-model that has learned a lot of basic knowledge. Since the meta-model is trained on a large amount of scenario data (the data for training the meta-model can be divided into different scenarios, which can be called different "tasks"), a model adapted to the target scenario can be trained based on the meta-model using a small amount of target scenario data.
  • a meta-learning algorithm including but not limited to MAML, Reptile, etc.
  • FIG8 is a schematic flow chart of a method 200 for generating a sample set according to an embodiment of the present application. As shown in FIG8 , the method 200 includes the following contents:
  • S210 constructing a first basis vector space and a second basis vector space, wherein the first basis vector space includes O basis vector groups, each basis vector group includes N 1 *N 2 spatial domain basis vectors, and the second basis vector space includes N sb frequency domain basis vectors, where O is a positive integer;
  • the method 200 can be executed by a terminal device, or it can also be executed by a network device, and the present application does not limit this.
  • N sb represents the number of subbands.
  • the transmitter of the CSI has a two-dimensional array antenna
  • N1 is the number of antenna ports in a first dimension of the two-dimensional array antenna
  • N2 is the number of antenna ports in a second dimension of the two-dimensional array antenna.
  • this application only uses the example of the antenna at the transmitting end of the CSI being a two-dimensional array antenna for illustration.
  • the dimensions of the spatial basis vectors included in the basis vector group can be adjusted for applicability, and this application does not limit this.
  • the CSI sample sets corresponding to the multiple tasks are used to train the first model, that is, the first model is a meta-model, that is, a starting point training model. Further, the first model can be trained based on the CSI sample set of the target scene to obtain a second model adapted to the target scene.
  • the first model is trained based on a large number of CSI sample sets of tasks, only a small number of CSI sample sets of target scenes are needed to train a second model that quickly adapts to the target scene. Furthermore, the CSI data of the target scene can be compressed and fed back according to the second model, which is conducive to reducing the feedback overhead of CSI.
  • the multiple tasks are d tasks, and the CSI sample set corresponding to each task may include k CSI samples.
  • the number of CSI samples included in the CSI sample set corresponding to each task may be the same, or may also be different.
  • O is a positive integer greater than 1, and increasing the number of spatial basis vectors by O times is beneficial to increasing the accuracy of CSI samples in the spatial domain.
  • the matrix composed of N 1 *N 2 spatial basis vectors in each basis vector group of the O basis vector groups is a unitary matrix, that is, the spatial basis vectors in the same basis vector group are orthogonal
  • the matrix composed of N sb frequency domain basis vectors is a unitary matrix, that is, the frequency domain basis vectors in the second basis vector space are orthogonal.
  • the first basis vector space and the second basis vector space in the embodiment of the present application are complete, and therefore, the data set for training the meta-model generated based on the first basis vector space and the second basis vector space is also complete.
  • the matrix formed by all spatial basis vectors in each basis vector group in the first basis vector space is a unitary matrix. Therefore, any vector of the same dimension as the spatial basis vector can be linearly represented using all spatial basis vectors in the basis vector group.
  • the matrix formed by all frequency domain basis vectors in the second basis vector space is a unitary matrix. Therefore, any vector with the same dimension as the frequency domain basis vector can be linearly represented using all frequency domain basis vectors in the second basis vector space.
  • the embodiments of the present application are not limited to the specific implementation of constructing the O basis vector groups in the first basis vector space and the second basis vector space. Any method for constructing a unitary matrix can be used as the O basis vector groups in the first basis vector space and the method for constructing the second basis vector space. The present application does not limit this.
  • constructing the first basis vector space includes:
  • a first matrix (denoted as X h ) is obtained by random sampling based on a first distribution
  • a second matrix (denoted as X v ) is obtained by random sampling based on a second distribution
  • the first matrix is a matrix of N 1 *N 1 dimensions (ie, X h ⁇ CN1 ⁇ N1 )
  • the second matrix is a matrix of N 2 *N 2 dimensions (ie, X v ⁇ CN2 ⁇ N2 );
  • a column of the target matrix is used as a spatial basis vector in a basis vector group in the first basis vector space.
  • the first distribution may include but is not limited to complex Gaussian distribution and complex uniform distribution.
  • the second distribution may include but is not limited to complex Gaussian distribution and complex uniform distribution.
  • the first distribution and the second distribution may be the same, or may be different.
  • the first matrix is obtained by random sampling based on a first distribution, so the elements in the first matrix obey the first distribution.
  • the second matrix is obtained by random sampling based on a second distribution, so the elements in the second matrix obey the second distribution.
  • the orthogonal matrix corresponding to the first matrix may be an orthogonal matrix determined according to the first matrix
  • the orthogonal matrix corresponding to the second matrix may refer to an orthogonal matrix determined according to the second matrix.
  • the present application does not limit the specific method for determining the orthogonal matrix corresponding to the first matrix and the orthogonal matrix corresponding to the second matrix. For example, it can be obtained by singular value decomposition, or it can be obtained by Schmidt orthogonalization, etc.
  • determining an orthogonal matrix corresponding to the first matrix and an orthogonal matrix corresponding to the second matrix includes:
  • determining an orthogonal matrix corresponding to the first matrix and an orthogonal matrix corresponding to the second matrix includes:
  • constructing the second basis vector space includes:
  • a third matrix (denoted as X f ) is obtained by random sampling based on the third distribution, wherein the third matrix is a matrix of N sb *N sb dimensions (ie, X f ⁇ CNsb ⁇ Nsb );
  • a column of the orthogonal matrix (ie, U f ) corresponding to the third matrix is used as a frequency domain basis vector in the second basis vector space.
  • the third distribution may include but is not limited to complex Gaussian distribution and complex uniform distribution.
  • the third matrix is obtained by random sampling based on a third distribution, and therefore, elements in the third matrix obey the third distribution.
  • the orthogonal matrix corresponding to the third matrix may be an orthogonal matrix determined according to the third matrix.
  • the present application does not limit the specific method for determining the orthogonal matrix corresponding to the third matrix. For example, it may be obtained by SVD, or it may be obtained by Schmidt orthogonalization, etc.
  • determining an orthogonal matrix corresponding to the third matrix includes:
  • the S220 may include:
  • the following steps are executed d times in a loop to obtain a CSI sample set corresponding to each task in the multiple tasks, where d is the number of the multiple tasks:
  • a CSI sample set corresponding to one of the multiple tasks is constructed according to L task spatial domain basis vectors in the one basis vector group and M task frequency domain basis vectors in the second basis vector space, where L task , L task are positive integers greater than 1.
  • the one basis vector group is randomly selected from the O basis vector groups.
  • the Ltask is smaller than N 1 *N 2
  • the Mtask is smaller than N sb .
  • the L task spatial domain basis vectors are part of the spatial domain basis vectors in a basis vector group, and the M task frequency domain basis vectors are part of the frequency domain basis vectors in the second basis vector space.
  • the L task spatial basis vectors are randomly selected from the one basis vector group.
  • the M task frequency domain basis vectors are randomly selected from N sb frequency domain basis vectors in the second basis vector space.
  • a basis vector group (referred to as the first basis vector group) is randomly selected from the O basis vector groups in the first basis vector space, and M task frequency domain basis vectors are randomly selected from the N sb frequency domain basis vectors in the second basis vector space, and the CSI sample set corresponding to the first task is further constructed based on some spatial domain basis vectors in the first basis vector group and some frequency domain basis vectors in the M task frequency domain basis vectors.
  • the first basis vector group i.e., the L task spatial domain basis vectors in the first basis vector group
  • the M task frequency domain basis vectors can be considered as the task basis vector set corresponding to the first task (referred to as the first task basis vector set), that is, the CSI sample set corresponding to the first task is constructed based on the basis vectors in the first task basis vector set.
  • a basis vector group is randomly selected from the O basis vector groups in the first basis vector space (referred to as the second basis vector group), and M task frequency domain basis vectors are randomly selected from the N sb frequency domain basis vectors in the second basis vector space, and the CSI sample set corresponding to the second task is further constructed based on some spatial domain basis vectors in the second basis vector group and some frequency domain basis vectors in the M task frequency domain basis vectors.
  • the second basis vector group i.e., the L task spatial domain basis vectors in the second basis vector group
  • the M task frequency domain basis vectors can be considered as a task basis vector set corresponding to the second task (referred to as the second task basis vector set), that is, the CSI sample set corresponding to the second task is constructed based on the basis vectors in the second task basis vector set.
  • the first basis vector space and the second basis vector space can be considered as the complete set of orthogonal basis vectors. Therefore, in an embodiment of the present application, the orthogonal basis vectors (i.e., the task basis vector set) used to construct CSI sample sets corresponding to different tasks are different subsets of the complete set of orthogonal basis vectors. For example, generating the CSI sample set corresponding to the first task is based on the basis vectors in the first task basis vector set, and constructing the CSI sample set corresponding to the second task is based on the basis vectors in the second task basis vector set, which is conducive to achieving diversity of CSI samples between different tasks.
  • the orthogonal basis vectors i.e., the task basis vector set
  • basis vectors in a task basis vector set corresponding to a task can be considered to have similar or consistent characteristics.
  • L task spatial domain basis vectors randomly selected in the first basis vector group can be considered to have similar or consistent characteristics
  • L task spatial domain basis vectors randomly selected in the second basis vector group can be considered to have similar or consistent characteristics
  • M task frequency domain basis vectors randomly selected in the second basis vector space can be considered to have similar or consistent characteristics. Therefore, a CSI sample set for a specific scenario (i.e., a specific task) can be generated based on the basis vectors in the task basis vector set.
  • constructing a CSI sample set corresponding to one of the multiple tasks according to L task spatial domain basis vectors in the one basis vector group and M task frequency domain basis vectors in the second basis vector space includes:
  • the following steps are executed k times in a loop to obtain k CSI samples included in a CSI sample set corresponding to a task, where k is greater than 1:
  • a CSI sample in a CSI sample set corresponding to a task is generated.
  • L ⁇ L task M ⁇ M task .
  • the random number matrix W 2 is obtained by sampling based on the fourth distribution, that is, the elements in W 2 obey the fourth distribution.
  • the first basis vector space and the second basis vector space can be used to provide spatial and frequency domain characteristics, and the random number matrix can be used to expand the scale of the CSI sample set. Therefore, the method for generating a sample set according to an embodiment of the present application can take into account the spatial and frequency domain characteristics and scale of the generated CSI samples.
  • the fourth distribution may include, but is not limited to, complex Gaussian distribution and complex uniform distribution.
  • generating a CSI sample in a CSI sample set corresponding to a task according to the diagonal block matrix W 1 , the matrix W f and the random number matrix W 2 includes:
  • Each column in the matrix of the first CSI samples is normalized to obtain a target CSI sample.
  • the normalization process may include but is not limited to a two-norm process.
  • the target CSI sample W [w 1 /norm(w 1 ), ..., w Nsb /norm(w Nsb )], where norm() represents a binary norm.
  • a CSI sample set corresponding to each of the d tasks may be generated based on the following steps.
  • Step a randomly selecting a basis vector group from the O basis vector groups in the first basis vector space, denoted as basis vector group Q;
  • Step b randomly select L task spatial basis vectors from the basis vector group Q to obtain the basis vector group Q';
  • Step c randomly selecting M task frequency domain basis vectors from the N sb frequency domain basis vectors in the second basis vector space to obtain a basis vector group P;
  • the basis vector group Q’ and the basis vector group P can be considered as the task basis vector set corresponding to the current task.
  • Step e randomly select M ⁇ M task basis vectors from the basis vector group P and arrange them in rows to form a matrix W f , where W f ⁇ C M ⁇ Nsb .
  • Step f constructing a random number matrix W 2 ⁇ C 2L ⁇ M , wherein each element in the random number matrix W 2 obeys a fourth distribution, such as a complex Gaussian distribution or a complex uniform distribution;
  • each column of the first CSI sample is normalized to obtain a target CSI sample.
  • Step h determining whether the k CSI samples in the CSI sample set corresponding to the current task have been constructed. If so, returning to step a to generate the CSI sample in the CSI sample set corresponding to the next task; if not, returning to step d to construct the next CSI sample in the CSI sample set corresponding to the current task;
  • step i it is determined whether the CSI sample sets corresponding to the d tasks have been constructed. If so, the process ends. If not, the process returns to step a to construct the CSI sample set corresponding to the next task.
  • the device for constructing the CSI sample set and the device for training the first model may be the same device, or may be different devices.
  • the device for constructing the CSI sample set may send the constructed CSI sample set to the device for training the first model, so that the device trains the first model based on the CSI sample set.
  • a communication device (such as a terminal device or a network device) can construct a first basis vector space corresponding to a spatial basis vector and a second basis vector space corresponding to a frequency domain basis vector, wherein the first basis vector space includes O basis vector groups, the matrix composed of N 1 *N 2 spatial basis vectors in each basis vector group is a unitary matrix, and the matrix composed of the frequency domain basis vectors in the second basis vector space is a unitary matrix. That is, the first basis vector space and the second basis vector space are complete, and therefore, the data set for training the meta-model generated based on the first basis vector space and the second basis vector space is also complete.
  • different subsets in the task basis vector set are used to construct different CSI samples in the CSI sample set corresponding to the task, which is conducive to achieving diversity of different samples in the same task.
  • the first basis vector space can provide the spatial domain characteristics of the CSI data
  • the second basis vector space can provide the frequency domain characteristics of the CSI data. Therefore, constructing the CSI sample set corresponding to each task based on the first basis vector space, the second basis vector space and the random number matrix can ensure the spatial and frequency domain characteristics and scale of the generated CSI samples.
  • Fig. 9 shows a schematic block diagram of a device 400 for generating a sample set according to an embodiment of the present application.
  • the device 400 includes:
  • the processing unit 410 is configured to construct a first basis vector space and a second basis vector space, wherein the first basis vector space includes O basis vector groups, each basis vector group includes N 1 *N 2 spatial basis vectors, and the second basis vector space includes N sb frequency domain basis vectors, wherein O is a positive integer, N 1 is the number of antenna ports in a first dimension of a transmitting end of the channel state information CSI, N 2 is the number of antenna ports in a second dimension of the transmitting end of the CSI, and N sb represents the number of subbands; and
  • a CSI sample set corresponding to each task in a plurality of tasks is constructed, wherein the CSI sample set corresponding to each task is constructed based on some spatial domain basis vectors in a basis vector group in the first basis vector space and some frequency domain basis vectors in the second basis vector space, and the CSI sample sets corresponding to the plurality of tasks are respectively used to train a first model, and the first model is used to obtain a second model based on the CSI sample set of a target scene for training, and the second model is adapted to the target scene.
  • the matrix composed of N 1 *N 2 spatial basis vectors in each basis vector group of the O basis vector groups is a unitary matrix
  • the matrix composed of the N sb frequency domain basis vectors is a unitary matrix
  • processing unit 410 is further configured to:
  • a column of the target matrix is used as a spatial basis vector in a basis vector group in the first basis vector space.
  • processing unit 410 is further configured to:
  • processing unit 410 is further configured to:
  • the first distribution is a complex Gaussian distribution or a complex uniform distribution
  • the second distribution is a complex Gaussian distribution or a complex uniform distribution.
  • processing unit 410 is further configured to:
  • a column of the orthogonal matrix corresponding to the third matrix is used as a frequency domain basis vector in the second basis vector space.
  • processing unit 410 is further configured to:
  • the third distribution is a complex Gaussian distribution or a complex uniform distribution.
  • processing unit 410 is further configured to:
  • the following steps are executed d times in a loop to obtain a CSI sample set corresponding to each task in the multiple tasks, where d is the number of the multiple tasks:
  • a CSI sample set corresponding to one of the multiple tasks is constructed according to L task spatial domain basis vectors in the one basis vector group and M task frequency domain basis vectors in the second basis vector space, where L task and M task are positive integers greater than 1.
  • the one basis vector group is randomly selected from the O basis vector groups.
  • the L task spatial basis vectors are randomly selected from the one basis vector group
  • the M task frequency domain basis vectors are randomly selected from the N sb frequency domain basis vectors in the second basis vector space.
  • the Ltask is smaller than N 1 *N 2
  • the Mtask is smaller than N sb .
  • processing unit 410 is further configured to:
  • the following steps are executed k times in a loop to obtain k CSI samples included in a CSI sample set corresponding to a task, where k is greater than 1:
  • a CSI sample in a CSI sample set corresponding to a task is generated.
  • L ⁇ L task M ⁇ M task .
  • the elements in the random number matrix W 2 obey a fourth distribution.
  • the fourth distribution is a complex Gaussian distribution or a complex uniform distribution.
  • processing unit 410 is further configured to:
  • Each column in the matrix of the first CSI samples is normalized to obtain a target CSI sample.
  • the target CSI sample W [w 1 /norm(w 1 ), ..., w Nsb /norm(w Nsb )], wherein norm() represents a binary norm.
  • the communication unit may be a communication interface or a transceiver, or an input/output interface of a communication chip or a system on chip.
  • the processing unit may be one or more processors.
  • Fig. 10 is a schematic structural diagram of a communication device 600 provided in an embodiment of the present application.
  • the communication device 600 shown in Fig. 10 includes a processor 610, and the processor 610 can call and run a computer program from a memory to implement the method in the embodiment of the present application.
  • the communication device 600 may further include a memory 620.
  • the processor 610 may call and run a computer program from the memory 620 to implement the method in the embodiment of the present application.
  • the memory 620 may be a separate device independent of the processor 610 , or may be integrated into the processor 610 .
  • the communication device 600 may further include a transceiver 630 , and the processor 610 may control the transceiver 630 to communicate with other devices, specifically, may send information or data to other devices, or receive information or data sent by other devices.
  • the transceiver 630 may include a transmitter and a receiver.
  • the transceiver 630 may further include an antenna, and the number of the antennas may be one or more.
  • the communication device 600 may specifically be a network device of an embodiment of the present application, and the communication device 600 may implement the corresponding processes implemented by the network device in each method of the embodiment of the present application, which will not be described in detail here for the sake of brevity.
  • the communication device 600 may specifically be a mobile terminal/terminal device of an embodiment of the present application, and the communication device 600 may implement the corresponding processes implemented by the mobile terminal/terminal device in each method of the embodiment of the present application, which will not be described in detail here for the sake of brevity.
  • Fig. 11 is a schematic structural diagram of a chip according to an embodiment of the present application.
  • the chip 700 shown in Fig. 11 includes a processor 710, and the processor 710 can call and run a computer program from a memory to implement the method according to the embodiment of the present application.
  • the chip 700 may further include a memory 720.
  • the processor 710 may call and run a computer program from the memory 720 to implement the method in the embodiment of the present application.
  • the memory 720 may be a separate device independent of the processor 710 , or may be integrated into the processor 710 .
  • the chip 700 may further include an input interface 730.
  • the processor 710 may control the input interface 730 to communicate with other devices or chips, and specifically, may obtain information or data sent by other devices or chips.
  • the chip 700 may further include an output interface 740.
  • the processor 710 may control the output interface 740 to communicate with other devices or chips, and specifically, may output information or data to other devices or chips.
  • the chip can be applied to the network device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the network device in each method of the embodiments of the present application. For the sake of brevity, they will not be repeated here.
  • the chip can be applied to the mobile terminal/terminal device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the mobile terminal/terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.
  • the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.
  • the processor of the embodiment of the present application may be an integrated circuit chip with signal processing capabilities.
  • each step of the above method embodiment can be completed by the hardware integrated logic circuit in the processor or the instruction in the form of software.
  • the above processor can be a general processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.
  • DSP Digital Signal Processor
  • ASIC Application Specific Integrated Circuit
  • FPGA Field Programmable Gate Array
  • the methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed.
  • the general processor can be a microprocessor or the processor can also be any conventional processor, etc.
  • the steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to perform, or the hardware and software modules in the decoding processor can be combined to perform.
  • the software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc.
  • the storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.
  • the memory in the embodiment of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.
  • the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory.
  • the volatile memory can be a random access memory (RAM), which is used as an external cache.
  • RAM Direct Rambus RAM
  • SRAM Static RAM
  • DRAM Dynamic RAM
  • SDRAM Synchronous DRAM
  • DDR SDRAM Double Data Rate SDRAM
  • ESDRAM Enhanced SDRAM
  • SLDRAM Synchlink DRAM
  • DR RAM Direct Rambus RAM
  • the memory in the embodiment of the present application may also be static random access memory (static RAM, SRAM), dynamic random access memory (dynamic RAM, DRAM), synchronous dynamic random access memory (synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous link dynamic random access memory (synch link DRAM, SLDRAM) and direct memory bus random access memory (Direct Rambus RAM, DR RAM), etc. That is to say, the memory in the embodiment of the present application is intended to include but not limited to these and any other suitable types of memory.
  • An embodiment of the present application also provides a computer-readable storage medium for storing a computer program.
  • the computer-readable storage medium can be applied to the network device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.
  • the computer-readable storage medium can be applied to the mobile terminal/terminal device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the mobile terminal/terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.
  • An embodiment of the present application also provides a computer program product, including computer program instructions.
  • the computer program product can be applied to the network device in the embodiments of the present application, and the computer program instructions enable the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.
  • the computer program product can be applied to the mobile terminal/terminal device in the embodiments of the present application, and the computer program instructions enable the computer to execute the corresponding processes implemented by the mobile terminal/terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.
  • the embodiment of the present application also provides a computer program.
  • the computer program can be applied to the network device in the embodiments of the present application.
  • the computer program runs on a computer, the computer executes the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, they are not described here.
  • the computer program can be applied to the mobile terminal/terminal device in the embodiments of the present application.
  • the computer program When the computer program is run on a computer, the computer executes the corresponding processes implemented by the mobile terminal/terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.
  • the disclosed systems, devices and methods can be implemented in other ways.
  • the device embodiments described above are only schematic.
  • the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.
  • Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium.
  • the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art.
  • the computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

A sample set generation method and device. The method comprises: constructing a first basis vector space and a second basis vector space, wherein the first basis vector space comprises O basis vector groups, each basis vector group comprises N1*N2 spatial domain basis vectors, the second basis vector space comprises Nsb frequency domain basis vectors, O is a positive integer, N1 is the number of antenna ports of a first dimension of a transmitting end of channel state information (CSI), N2 is the number of antenna ports of a second dimension of the transmitting end of the CSI, and Nsb represents the number of sub-bands; and constructing a CSI sample set corresponding to each task in a plurality of tasks according to the first basis vector space and the second basis vector space, wherein the CSI sample set corresponding to each task is constructed on the basis of some of spatial domain basis vectors in one basis vector group in the first basis vector space and some of frequency domain basis vectors in the second basis vector space, the CSI sample sets respectively corresponding to the plurality of tasks are used for training a first model, the first model is used for performing training on the basis of a CSI sample set of a target scenario to obtain a second model, and the second model is adapted to the target scenario.

Description

生成样本集的方法和设备Method and device for generating sample set 技术领域Technical Field
本申请实施例涉及通信领域，具体涉及一种生成样本集的方法和设备。The embodiments of the present application relate to the field of communications, and in particular to a method and device for generating a sample set.
背景技术Background technique
在新无线(New Radio，NR)***中，终端设备需要向网络设备反馈信道状态信息(Channel State Information，CSI)，以用于网络设备确定用于下行传输的预编码矩阵。In the New Radio (NR) system, the terminal device needs to feed back Channel State Information (CSI) to the network device so that the network device can determine the precoding matrix for downlink transmission.
在一些场景中，考虑基于元学习的方式进行CSI反馈，但是，构建元模型需要海量的不同场景的CSI数据，采集海量的、具有较高多样性的CSI样本从实际采集成本上和采集难度上都具有一定的挑战。因此，如何实现基于元学习的CSI反馈是一项亟需解决的问题。In some scenarios, CSI feedback based on meta-learning is considered. However, building a meta-model requires a large amount of CSI data from different scenarios. Collecting a large amount of CSI samples with high diversity is challenging in terms of actual collection cost and difficulty. Therefore, how to implement CSI feedback based on meta-learning is an urgent problem to be solved.
发明内容Summary of the invention
本申请提供了一种生成样本集的方法和设备，有利于降低获得CSI样本的成本开销和难度。The present application provides a method and device for generating a sample set, which is conducive to reducing the cost and difficulty of obtaining CSI samples.
第一方面，提供了一种生成样本集的方法，包括：构建第一基向量空间和第二基向量空间，所述第一基向量空间包括O个基向量组，每个基向量组包括N 1*N 2个空域基向量，所述第二基向量空间包括N sb个频域基向量，其中，O是正整数，所述N 1为信道状态信息CSI的发射端的第一维度的天线端口数，所述N 2为CSI的发射端的第二维度的天线端口数，N sb表示子带数量； In a first aspect, a method for generating a sample set is provided, comprising: constructing a first basis vector space and a second basis vector space, wherein the first basis vector space comprises O basis vector groups, each basis vector group comprises N 1 *N 2 spatial domain basis vectors, and the second basis vector space comprises N sb frequency domain basis vectors, wherein O is a positive integer, N 1 is the number of antenna ports of a first dimension of a transmitting end of channel state information CSI, N 2 is the number of antenna ports of a second dimension of a transmitting end of CSI, and N sb represents the number of subbands;
根据所述第一基向量空间和所述第二基向量空间，构建多个任务中的每个任务对应的CSI样本集，其中，每个任务对应的CSI样本集是基于所述第一基向量空间中的一个基向量组中的部分空域基向量和所述第二基向量空间中的部分频域基向量构建的，所述多个任务分别对应的CSI样本集用于训练第一模型，所述第一模型用于基于目标场景的CSI样本集训练得到第二模型，所述第二模型适配所述目标场景。According to the first basis vector space and the second basis vector space, a CSI sample set corresponding to each task in a plurality of tasks is constructed, wherein the CSI sample set corresponding to each task is constructed based on some spatial domain basis vectors in a basis vector group in the first basis vector space and some frequency domain basis vectors in the second basis vector space, and the CSI sample sets corresponding to the plurality of tasks are respectively used to train a first model, and the first model is used to obtain a second model based on the CSI sample set of a target scene for training, and the second model is adapted to the target scene.
第二方面，提供了一种生成样本集的设备，用于执行上述第一方面或其各实现方式中的方法。In a second aspect, a device for generating a sample set is provided, which is used to execute the method in the above-mentioned first aspect or its various implementations.
具体地，该终端设备包括用于执行上述第一方面或其各实现方式中的方法的功能模块。Specifically, the terminal device includes a functional module for executing the method in the above-mentioned first aspect or its various implementation modes.
第三方面，提供了一种生成样本集的设备，包括处理器和存储器。该存储器用于存储计算机程序，该处理器用于调用并运行该存储器中存储的计算机程序，执行上述第一方面或其各实现方式中的方法。In a third aspect, a device for generating a sample set is provided, comprising a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method in the first aspect or its implementations.
第四方面，提供了一种芯片，用于实现上述第一方面或其各实现方式中的方法。In a fourth aspect, a chip is provided for implementing the method in the first aspect or its various implementations.
具体地，该芯片包括：处理器，用于从存储器中调用并运行计算机程序，使得安装有该装置的设备执行如上述第一方面或其各实现方式中的方法。Specifically, the chip includes: a processor, which is used to call and run a computer program from a memory, so that a device equipped with the device executes the method in the above-mentioned first aspect or its various implementation modes.
第五方面，提供了一种计算机可读存储介质，用于存储计算机程序，该计算机程序使得计算机执行上述第一方面或其各实现方式中的方法。In a fifth aspect, a computer-readable storage medium is provided for storing a computer program, wherein the computer program enables a computer to execute the method in the above-mentioned first aspect or its various implementations.
第六方面，提供了一种计算机程序产品，包括计算机程序指令，所述计算机程序指令使得计算机执行上述第一方面或其各实现方式中的方法。In a sixth aspect, a computer program product is provided, comprising computer program instructions, wherein the computer program instructions enable a computer to execute the method in the above-mentioned first aspect or its various implementations.
第七方面，提供了一种计算机程序，当其在计算机上运行时，使得计算机执行上述第一方面或其各实现方式中的方法。In a seventh aspect, a computer program is provided, which, when executed on a computer, enables the computer to execute the method in the first aspect or its various implementations.
通过上述技术方案，可以构建空域基向量对应的第一基向量空间以及频域基向量对应的第二基向量空间，进一步地，基于该第一基向量空间和第二基向量空间生成用于训练元模型(即第一模型)的多个任务中的每个任务对应的CSI样本集，通过自动生成用于元模型训练的数据集，能够降低获得CSI数据的成本开销和难度。Through the above technical solution, a first basis vector space corresponding to the spatial domain basis vectors and a second basis vector space corresponding to the frequency domain basis vectors can be constructed. Furthermore, a CSI sample set corresponding to each of multiple tasks for training the meta-model (i.e., the first model) can be generated based on the first basis vector space and the second basis vector space. By automatically generating a data set for meta-model training, the cost and difficulty of obtaining CSI data can be reduced.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
图1是本申请实施例提供的一种通信***架构的示意性图。FIG1 is a schematic diagram of a communication system architecture provided in an embodiment of the present application.
图2是一种神经元结构的示意图。FIG. 2 is a schematic diagram of a neuron structure.
图3是本申请提供的一种神经网络的示意性图。FIG3 is a schematic diagram of a neural network provided in the present application.
图4是本申请提供的一种卷积神经网络的示意性图。FIG4 is a schematic diagram of a convolutional neural network provided in the present application.
图5是本申请提供的一种LSTM单元的示意性图。FIG5 is a schematic diagram of an LSTM unit provided in the present application.
图6是本申请提供的一种信道信息反馈的示意性图。FIG6 is a schematic diagram of a channel information feedback provided by the present application.
图7是本申请提供的另一种信道信息反馈的示意性图。FIG. 7 is a schematic diagram of another channel information feedback provided by the present application.
图8是根据本申请实施例提供的一种生成样本集的方法的示意性流程图。FIG8 is a schematic flowchart of a method for generating a sample set according to an embodiment of the present application.
图9是根据本申请实施例提供的一种生成样本集的设备的示意性框图。FIG. 9 is a schematic block diagram of a device for generating a sample set according to an embodiment of the present application.
图10是根据本申请实施例提供的一种通信设备的示意性框图。FIG10 is a schematic block diagram of a communication device provided according to an embodiment of the present application.
图11是根据本申请实施例提供的一种芯片的示意性框图。FIG. 11 is a schematic block diagram of a chip provided according to an embodiment of the present application.
具体实施方式Detailed ways
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行描述，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。针对本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。The following will describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. For the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
本申请实施例的技术方案可以应用于各种通信***，例如：全球移动通讯(Global System of Mobile communication，GSM)***、码分多址(Code Division Multiple Access，CDMA)***、宽带码分多址(Wideband Code Division Multiple Access，WCDMA)***、通用分组无线业务(General Packet Radio Service，GPRS)、长期演进(Long Term Evolution，LTE)***、先进的长期演进(Advanced long term evolution，LTE-A)***、新无线(New Radio，NR)***、NR***的演进***、非授权频谱上的LTE(LTE-based access to unlicensed spectrum，LTE-U)***、非授权频谱上的NR(NR-based access to unlicensed spectrum，NR-U)***、非地面通信网络(Non-Terrestrial Networks，NTN)***、通用移动通信***(Universal Mobile Telecommunication System，UMTS)、无线局域网(Wireless Local Area Networks，WLAN)、无线保真(Wireless Fidelity，WiFi)、第五代通信(5th-Generation，5G)***或其他通信***等。The technical solutions of the embodiments of the present application can be applied to various communication systems, such as: Global System of Mobile communication (GSM) system, Code Division Multiple Access (CDMA) system, Wideband Code Division Multiple Access (WCDMA) system, General Packet Radio Service (GPRS), Long Term Evolution (LTE) system, Advanced long term evolution (LTE-A) system, New Radio (NR) system, and NR system. Evolved systems, LTE-based access to unlicensed spectrum (LTE-U) systems, NR-based access to unlicensed spectrum (NR-U) systems, non-terrestrial communication networks (NTN) systems, universal mobile telecommunication systems (UMTS), wireless local area networks (WLAN), wireless fidelity (WiFi), fifth-generation communication (5th-Generation, 5G) systems or other communication systems, etc.
通常来说，传统的通信***支持的连接数有限，也易于实现，然而，随着通信技术的发展，移动通信***将不仅支持传统的通信，还将支持例如，设备到设备(Device to Device，D2D)通信，机器到机器(Machine to Machine，M2M)通信，机器类型通信(Machine Type Communication，MTC)，车辆间(Vehicle to Vehicle，V2V)通信，或车联网(Vehicle to everything，V2X)通信等，本申请实施例也可以应用于这些通信***。Generally speaking, traditional communication systems support a limited number of connections and are easy to implement. However, with the development of communication technology, mobile communication systems will not only support traditional communications, but will also support, for example, device to device (Device to Device, D2D) communication, machine to machine (Machine to Machine, M2M) communication, machine type communication (Machine Type Communication, MTC), vehicle to vehicle (V2V) communication, or vehicle to everything (V2X) communication, etc. The embodiments of the present application can also be applied to these communication systems.
可选地，本申请实施例中的通信***可以应用于载波聚合(Carrier Aggregation，CA)场景，也可以应用于双连接(Dual Connectivity，DC)场景，还可以应用于独立(Standalone，SA)布网场景。Optionally, the communication system in the embodiment of the present application can be applied to a carrier aggregation (CA) scenario, a dual connectivity (DC) scenario, or a standalone (SA) networking scenario.
可选地，本申请实施例中的通信***可以应用于非授权频谱，其中，非授权频谱也可以认为是共享频谱；或者，本申请实施例中的通信***也可以应用于授权频谱，其中，授权频谱也可以认为是非共享频谱。Optionally, the communication system in the embodiment of the present application can be applied to an unlicensed spectrum, wherein the unlicensed spectrum can also be considered as a shared spectrum; or, the communication system in the embodiment of the present application can also be applied to an authorized spectrum, wherein the authorized spectrum can also be considered as an unshared spectrum.
本申请实施例结合网络设备和终端设备描述了各个实施例，其中，终端设备也可以称为用户设备(User Equipment，UE)、接入终端、用户单元、用户站、移动站、移动台、远方站、远程终端、移动设备、用户终端、终端、无线通信设备、用户代理或用户装置等。The embodiments of the present application describe various embodiments in conjunction with network equipment and terminal equipment, wherein the terminal equipment may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication equipment, user agent or user device, etc.
终端设备可以是WLAN中的站点(STATION，STA)，可以是蜂窝电话、无绳电话、会话启动协议(Session Initiation Protocol，SIP)电话、无线本地环路(Wireless Local Loop，WLL)站、个人数字助理(Personal Digital Assistant，PDA)设备、具有无线通信功能的手持设备、计算设备或连接到无线调制解调器的其它处理设备、车载设备、可穿戴设备、下一代通信***例如NR网络中的终端设备，或者未来演进的公共陆地移动网络(Public Land Mobile Network，PLMN)网络中的终端设备等。The terminal device can be a station (STA) in a WLAN, a cellular phone, a cordless phone, a Session Initiation Protocol (SIP) phone, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA) device, a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a vehicle-mounted device, a wearable device, a terminal device in the next generation communication system such as the NR network, or a terminal device in the future evolved Public Land Mobile Network (PLMN) network, etc.
在本申请实施例中，终端设备可以部署在陆地上，包括室内或室外、手持、穿戴或车载；也可以部署在水面上(如轮船等)；还可以部署在空中(例如飞机、气球和卫星上等)。In the embodiments of the present application, the terminal device can be deployed on land, including indoors or outdoors, handheld, wearable or vehicle-mounted; it can also be deployed on the water surface (such as ships, etc.); it can also be deployed in the air (for example, on airplanes, balloons and satellites, etc.).
在本申请实施例中，终端设备可以是手机(Mobile Phone)、平板电脑(Pad)、带无线收发功能的电脑、虚拟现实(Virtual Reality，VR)终端设备、增强现实(Augmented Reality，AR)终端设备、工业控制(industrial control)中的无线终端设备、无人驾驶(self driving)中的无线终端设备、远程医疗(remote medical)中的无线终端设备、智能电网(smart grid)中的无线终端设备、运输安全(transportation safety)中的无线终端设备、智慧城市(smart city)中的无线终端设备或智慧家庭(smart home)中的无线终端设备等。In the embodiments of the present application, the terminal device may be a mobile phone, a tablet computer, a computer with wireless transceiver function, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical, a wireless terminal device in smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, or a wireless terminal device in a smart home, etc.
作为示例而非限定，在本申请实施例中，该终端设备还可以是可穿戴设备。可穿戴设备也可以称为穿戴式智能设备，是应用穿戴式技术对日常穿戴进行智能化设计、开发出可以穿戴的设备的总称，如眼镜、手套、手表、服饰及鞋等。可穿戴设备即直接穿在身上，或是整合到用户的衣服或配件的一种便携式设备。可穿戴设备不仅仅是一种硬件设备，更是通过软件支持以及数据交互、云端交互来实现强大的功能。广义穿戴式智能设备包括功能全、尺寸大、可不依赖智能手机实现完整或者部分的功能，例如：智能手表或智能眼镜等，以及只专注于某一类应用功能，需要和其它设备如智能手机配合使用，如各类进行体征监测的智能手环、智能首饰等。As an example but not limitation, in the embodiments of the present application, the terminal device may also be a wearable device. Wearable devices may also be referred to as wearable smart devices, which are a general term for wearable devices that are intelligently designed and developed using wearable technology for daily wear, such as glasses, gloves, watches, clothing, and shoes. A wearable device is a portable device that is worn directly on the body or integrated into the user's clothes or accessories. Wearable devices are not only hardware devices, but also powerful functions achieved through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include full-featured, large-sized, and fully or partially independent of smartphones, such as smart watches or smart glasses, as well as devices that only focus on a certain type of application function and need to be used in conjunction with other devices such as smartphones, such as various types of smart bracelets and smart jewelry for vital sign monitoring.
在本申请实施例中，网络设备可以是用于与移动设备通信的设备，网络设备可以是WLAN中的接入点(Access Point，AP)，GSM或CDMA中的基站(Base Transceiver Station，BTS)，也可以是 WCDMA中的基站(NodeB，NB)，还可以是LTE中的演进型基站(Evolutional Node B，eNB或eNodeB)，或者中继站或接入点，或者车载设备、可穿戴设备以及NR网络中的网络设备(gNB)或者未来演进的PLMN网络中的网络设备或者NTN网络中的网络设备等。In an embodiment of the present application, the network device may be a device for communicating with a mobile device. The network device may be an access point (AP) in WLAN, a base station (Base Transceiver Station, BTS) in GSM or CDMA, a base station (NodeB, NB) in WCDMA, an evolved base station (Evolutional Node B, eNB or eNodeB) in LTE, or a relay station or access point, or a vehicle-mounted device, a wearable device, and a network device (gNB) in an NR network, or a network device in a future evolved PLMN network, or a network device in an NTN network, etc.
作为示例而非限定，在本申请实施例中，网络设备可以具有移动特性，例如网络设备可以为移动的设备。可选地，网络设备可以为卫星、气球站。例如，卫星可以为低地球轨道(low earth orbit，LEO)卫星、中地球轨道(medium earth orbit，MEO)卫星、地球同步轨道(geostationary earth orbit，GEO)卫星、高椭圆轨道(High Elliptical Orbit，HEO)卫星等。可选地，网络设备还可以为设置在陆地、水域等位置的基站。As an example but not limitation, in an embodiment of the present application, the network device may have a mobile feature, for example, the network device may be a mobile device. Optionally, the network device may be a satellite or a balloon station. For example, the satellite may be a low earth orbit (LEO) satellite, a medium earth orbit (MEO) satellite, a geostationary earth orbit (GEO) satellite, a high elliptical orbit (HEO) satellite, etc. Optionally, the network device may also be a base station set up in a location such as land or water.
在本申请实施例中，网络设备可以为小区提供服务，终端设备通过该小区使用的传输资源(例如，频域资源，或者说，频谱资源)与网络设备进行通信，该小区可以是网络设备(例如基站)对应的小区，小区可以属于宏基站，也可以属于小小区(Small cell)对应的基站，这里的小小区可以包括：城市小区(Metro cell)、微小区(Micro cell)、微微小区(Pico cell)、毫微微小区(Femto cell)等，这些小小区具有覆盖范围小、发射功率低的特点，适用于提供高速率的数据传输服务。In an embodiment of the present application, a network device can provide services for a cell, and a terminal device communicates with the network device through transmission resources used by the cell (for example, frequency domain resources, or spectrum resources). The cell can be a cell corresponding to a network device (for example, a base station), and the cell can belong to a macro base station or a base station corresponding to a small cell. The small cells here may include: metro cells, micro cells, pico cells, femto cells, etc. These small cells have the characteristics of small coverage and low transmission power, and are suitable for providing high-speed data transmission services.
示例性的，本申请实施例应用的通信***100如图1所示。该通信***100可以包括网络设备110，网络设备110可以是与终端设备120(或称为通信终端、终端)通信的设备。网络设备110可以为特定的地理区域提供通信覆盖，并且可以与位于该覆盖区域内的终端设备进行通信。Exemplarily, a communication system 100 used in an embodiment of the present application is shown in FIG1. The communication system 100 may include a network device 110, which may be a device that communicates with a terminal device 120 (or referred to as a communication terminal or terminal). The network device 110 may provide communication coverage for a specific geographic area and may communicate with terminal devices located in the coverage area.
图1示例性地示出了一个网络设备和两个终端设备，可选地，该通信***100可以包括多个网络设备并且每个网络设备的覆盖范围内可以包括其它数量的终端设备，本申请实施例对此不做限定。FIG1 exemplarily shows a network device and two terminal devices. Optionally, the communication system 100 may include multiple network devices and each network device may include another number of terminal devices within its coverage area, which is not limited in the embodiments of the present application.
可选地，该通信***100还可以包括网络控制器、移动管理实体等其他网络实体，本申请实施例对此不作限定。Optionally, the communication system 100 may also include other network entities such as a network controller and a mobility management entity, which is not limited in the embodiments of the present application.
应理解，本申请实施例中网络/***中具有通信功能的设备可称为通信设备。以图1示出的通信***100为例，通信设备可包括具有通信功能的网络设备110和终端设备120，网络设备110和终端设备120可以为上文所述的具体设备，此处不再赘述；通信设备还可包括通信***100中的其他设备，例如网络控制器、移动管理实体等其他网络实体，本申请实施例中对此不做限定。It should be understood that the device with communication function in the network/system in the embodiment of the present application can be called a communication device. Taking the communication system 100 shown in Figure 1 as an example, the communication device may include a network device 110 and a terminal device 120 with communication function, and the network device 110 and the terminal device 120 may be the specific devices described above, which will not be repeated here; the communication device may also include other devices in the communication system 100, such as other network entities such as a network controller and a mobile management entity, which is not limited in the embodiment of the present application.
应理解，本文中术语“***”和“网络”在本文中常被可互换使用。本文中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本文中字符“/”，一般表示前后关联对象是一种“或”的关系。It should be understood that the terms "system" and "network" are often used interchangeably in this article. The term "and/or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and/or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character "/" in this article generally indicates that the associated objects before and after are in an "or" relationship.
应理解，在本申请的实施例中提到的“指示”可以是直接指示，也可以是间接指示，还可以是表示具有关联关系。举例说明，A指示B，可以表示A直接指示B，例如B可以通过A获取；也可以表示A间接指示B，例如A指示C，B可以通过C获取；还可以表示A和B之间具有关联关系。It should be understood that the "indication" mentioned in the embodiments of the present application can be a direct indication, an indirect indication, or an indication of an association relationship. For example, A indicates B, which can mean that A directly indicates B, for example, B can be obtained through A; it can also mean that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; it can also mean that there is an association relationship between A and B.
在本申请实施例的描述中，术语“对应”可表示两者之间具有直接对应或间接对应的关系，也可以表示两者之间具有关联关系，也可以是指示与被指示、配置与被配置等关系。In the description of the embodiments of the present application, the term "corresponding" may indicate a direct or indirect correspondence between two items, or an association relationship between the two items, or a relationship of indication and being indicated, configuration and being configured, etc.
本申请实施例中，"预定义"可以通过在设备(例如，包括终端设备和网络设备)中预先保存相应的代码、表格或其他可用于指示相关信息的方式来实现，本申请对于其具体的实现方式不做限定。比如预定义可以是指协议中定义的。In the embodiments of the present application, "pre-definition" can be implemented by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in a device (for example, including a terminal device and a network device), and the present application does not limit the specific implementation method. For example, pre-definition can refer to what is defined in the protocol.
本申请实施例中，所述"协议"可以指通信领域的标准协议，例如可以包括LTE协议、NR协议以及应用于未来的通信***中的相关协议，本申请对此不做限定。In the embodiments of the present application, the "protocol" may refer to a standard protocol in the communication field, for example, it may include an LTE protocol, an NR protocol, and related protocols used in future communication systems, and the present application does not limit this.
为便于理解本申请实施例的技术方案，以下通过具体实施例详述本申请的技术方案。以下相关技术作为可选方案与本申请实施例的技术方案可以进行任意结合，其均属于本申请实施例的保护范围。本申请实施例包括以下内容中的至少部分内容。To facilitate understanding of the technical solutions of the embodiments of the present application, the technical solutions of the present application are described in detail below through specific embodiments. The following related technologies can be arbitrarily combined with the technical solutions of the embodiments of the present application as optional solutions, and they all belong to the protection scope of the embodiments of the present application. The embodiments of the present application include at least part of the following contents.
为便于更好的理解本申请实施例，对本申请相关的信道信息反馈进行说明。In order to better understand the embodiments of the present application, the channel information feedback related to the present application is explained.
在NR***中，针对信道状态信息(Channel State Information，CSI)反馈方案，主要采用基于码本的特征向量反馈使得基站获取下行CSI。具体地，基站向终端设备发送下行信道状态信息参考信号(Channel State Information Reference Signal，CSI-RS，终端设备利用CSI-RS估计得到下行信道的CSI，并对估计得到的下行信道进行特征值分解，得到该下行信道对应的特征向量。NR***提供了类型1(Type I)、类型2(TypeII)增强类型2(eTypeII)三种码本设计方案。In the NR system, for the channel state information (CSI) feedback scheme, the codebook-based eigenvector feedback is mainly used to enable the base station to obtain the downlink CSI. Specifically, the base station sends a downlink channel state information reference signal (Channel State Information Reference Signal, CSI-RS) to the terminal device. The terminal device uses CSI-RS to estimate the CSI of the downlink channel and performs eigenvalue decomposition on the estimated downlink channel to obtain the eigenvector corresponding to the downlink channel. The NR system provides three codebook design schemes: Type 1 (Type I), Type 2 (TypeII) and enhanced Type 2 (eTypeII).
对于eTypeII的码本反馈，待反馈的预编码矩阵表示为W∈C Nt×Nsb，其中，C表示复数空间，Nt表示发送天线端口数，Nsb表示子带数量，矩阵W的每一列表示每个子带上多个子载波共用的预编码向量。eTypeII码本首先考虑将W压缩表示为W’＝W 1W 2W f，其中，对角块矩阵W 1＝[B,0；0,B]∈C Nt×2L，B∈C Nt/2×L中的所有列为DFT向量空间中选择的一组L个正交基向量，W f∈C M×Nsb中的所有行也为DFT向量空间中选择的一组M个正交基向量，W 2∈C 2L×M为预编码矩阵W在该两组基向量上投影后 的投影系数。eTypeII码本考虑反馈如下信息： For the eTypeII codebook feedback, the precoding matrix to be fed back is expressed as W∈C Nt×Nsb , where C represents the complex space, Nt represents the number of transmit antenna ports, Nsb represents the number of subbands, and each column of the matrix W represents the precoding vector shared by multiple subcarriers on each subband. The eTypeII codebook first considers compressing W as W'＝W 1 W 2 W f , where the diagonal block matrix W 1 ＝[B,0；0,B]∈C Nt×2L , all columns in B∈C Nt/2×L are a set of L orthogonal basis vectors selected in the DFT vector space, all rows in W f ∈C M×Nsb are also a set of M orthogonal basis vectors selected in the DFT vector space, and W 2 ∈C 2L×M are the projection coefficients of the precoding matrix W after being projected on the two sets of basis vectors. The eTypeII codebook considers feedback of the following information:
DFT向量空间中选择的用于构成正交基矩阵B的L个基向量的索引；The indices of the L basis vectors selected in the DFT vector space to form the orthogonal basis matrix B;
DFT向量空间中选择的用于构成正交基矩阵W f的M个基向量的索引； The indices of the M basis vectors selected in the DFT vector space to form the orthogonal basis matrix Wf ;
投影系数矩阵W 2中的系数。 The coefficients in the projection coefficient matrix W2 .
接收端根据反馈的上述信息利用W’＝W 1W 2W f对预编码矩阵进行恢复。 The receiving end restores the precoding matrix using W'=W 1 W 2 W f according to the above fed-back information.
为便于更好的理解本申请实施例，对本申请相关的神经网络进行说明。In order to better understand the embodiments of the present application, the neural network related to the present application is described.
神经网络是一种由多个神经元节点相互连接构成的运算模型，其中节点间的连接代表从输入信号到输出信号的加权值，称为权重；每个节点对不同的输入信号进行加权求和(summation，SUM)，并通过特定的激活函数(f)输出，图2是一种神经元结构的示意图，其中，a1，a2，…，an表示输入信号，w1，w2，…，wn表示权重，f表示激励函数，t表示输出。A neural network is a computing model consisting of multiple interconnected neuron nodes, where the connection between nodes represents the weighted value from the input signal to the output signal, called the weight; each node performs weighted summation (SUM) on different input signals and outputs them through a specific activation function (f). Figure 2 is a schematic diagram of a neuron structure, where a1, a2, ..., an represent input signals, w1, w2, ..., wn represent weights, f represents the activation function, and t represents the output.
一个简单的神经网络如图3所示，包含输入层、隐藏层和输出层，通过多个神经元不同的连接方式，权重和激活函数，可以产生不同的输出，进而拟合从输入到输出的映射关系。其中，每一个上一级节点都与其全部的下一级节点相连，该神经网络是一种全连接神经网络，也可以称为深度神经网络(Deep Neural Network，DNN)。A simple neural network is shown in Figure 3, which includes an input layer, a hidden layer, and an output layer. Through different connection methods, weights, and activation functions of multiple neurons, different outputs can be generated, thereby fitting the mapping relationship from input to output. Among them, each upper-level node is connected to all its lower-level nodes. This neural network is a fully connected neural network, which can also be called a deep neural network (DNN).
深度学习采用多隐藏层的深度神经网络，极大提升了网络学习特征的能力，能够拟合从输入到输出的复杂的非线性映射，因而语音和图像处理领域得到广泛的应用。除了深度神经网络，面对不同任务，深度学习还包括卷积神经网络(Convolutional Neural Network，CNN)、循环神经网络(Recurrent Neural Network，RNN)等常用基本结构。Deep learning uses a deep neural network with multiple hidden layers, which greatly improves the network's ability to learn features and fits complex nonlinear mappings from input to output. Therefore, it is widely used in speech and image processing. In addition to deep neural networks, deep learning also includes common basic structures such as convolutional neural networks (CNN) and recurrent neural networks (RNN) for different tasks.
一个卷积神经网络的基本结构包括：输入层、多个卷积层、多个池化层、全连接层及输出层，如图4所示。卷积层中卷积核的每个神经元与其输入进行局部连接，并通过引入池化层提取某一层局部的最大值或者平均值特征，有效减少了网络的参数，并挖掘了局部特征，使得卷积神经网络能够快速收敛，获得优异的性能。The basic structure of a convolutional neural network includes: input layer, multiple convolutional layers, multiple pooling layers, fully connected layer and output layer, as shown in Figure 4. Each neuron of the convolution kernel in the convolutional layer is locally connected to its input, and the maximum or average value of a certain layer is extracted by introducing the pooling layer, which effectively reduces the parameters of the network and mines the local features, so that the convolutional neural network can converge quickly and obtain excellent performance.
RNN是一种对序列数据建模的神经网络，在自然语言处理领域，如机器翻译、语音识别等应用取得显著成绩。具体表现为，网络对过去时刻的信息进行记忆，并用于当前输出的计算中，即隐藏层之间的节点不再是无连接的而是有连接的，并且隐藏层的输入不仅包括输入层还包括上一时刻隐藏层的输出。常用的RNN包括长短期记忆网络(Long Short-Term Memory，LSTM)和门控循环单元(gated recurrent unit，GRU)等结构。图5所示为一个基本的LSTM单元结构，其可以包含tanh激活函数，不同于RNN只考虑最近的状态，LSTM的细胞状态会决定哪些状态应该被留下来，哪些状态应该被遗忘，解决了传统RNN在长期记忆上存在的缺陷。RNN is a neural network that models sequential data and has achieved remarkable results in the field of natural language processing, such as machine translation and speech recognition. Specifically, the network memorizes information from the past and uses it in the calculation of the current output, that is, the nodes between the hidden layers are no longer disconnected but connected, and the input of the hidden layer includes not only the input layer but also the output of the hidden layer at the previous moment. Commonly used RNNs include structures such as Long Short-Term Memory (LSTM) and gated recurrent unit (GRU). Figure 5 shows a basic LSTM unit structure, which can include a tanh activation function. Unlike RNN, which only considers the most recent state, the cell state of LSTM determines which states should be retained and which states should be forgotten, solving the defects of traditional RNN in long-term memory.
为便于更好的理解本申请实施例，对本申请相关的基于人工智能(Artificial Intelligence，AI)的CSI反馈方法进行说明。In order to facilitate a better understanding of the embodiments of the present application, the CSI feedback method based on artificial intelligence (AI) related to the present application is explained.
鉴于AI技术在计算机视觉、自然语言处理等方面取得了巨大的成功，通信领域开始尝试利用深度学习来解决传统通信方法难以解决的技术难题，例如深度学习。深度学习中常用的神经网络架构是非线性且是数据驱动的，可以对实际信道矩阵数据进行特征提取并在基站侧尽可能还原终端侧压缩反馈的信道矩阵信息，在保证还原信道信息的同时也为终端侧降低CSI反馈开销提供了可能性。Given the great success of AI technology in computer vision, natural language processing, and other fields, the communications field has begun to try to use deep learning to solve technical problems that are difficult to solve with traditional communication methods, such as deep learning. The neural network architecture commonly used in deep learning is nonlinear and data-driven. It can extract features from actual channel matrix data and restore the channel matrix information compressed and fed back by the terminal side as much as possible on the base station side. While ensuring the restoration of channel information, it also provides the possibility of reducing CSI feedback overhead on the terminal side.
基于深度学习的CSI反馈将信道信息视作待压缩图像，利用深度学习自编码器对信道信息进行压缩反馈，并在发送端对压缩后的信道图像进行重构，可以更大程度地保留信道信息，如图6所示。The deep learning-based CSI feedback regards the channel information as an image to be compressed, uses a deep learning autoencoder to compress and feedback the channel information, and reconstructs the compressed channel image at the transmitting end, which can retain the channel information to a greater extent, as shown in Figure 6.
一种典型的信道信息反馈***如图7所示。整个反馈***分为编码器及解码器部分，分别部署在发送端与接收端。发送端通过信道估计得到信道信息后，通过编码器的神经网络对信道信息矩阵进行压缩编码，并将压缩后的比特流通过空口反馈链路反馈给接收端，接收端通过解码器根据反馈比特流对信道信息进行恢复，以获得完整的反馈信道信息。图7中所示的编码器采用了多层全连接层的叠加，解码器中采用了卷积层与残差结构的设计。在该编解码框架不变的情况下，编码器和解码器内部的网络模型结构可进行灵活设计。A typical channel information feedback system is shown in Figure 7. The entire feedback system is divided into an encoder and a decoder, which are deployed at the transmitter and the receiver respectively. After the transmitter obtains the channel information through channel estimation, the channel information matrix is compressed and encoded through the neural network of the encoder, and the compressed bit stream is fed back to the receiver through the air interface feedback link. The receiver recovers the channel information according to the feedback bit stream through the decoder to obtain complete feedback channel information. The encoder shown in Figure 7 uses the superposition of multiple fully connected layers, and the decoder uses the design of convolutional layers and residual structures. When the encoding and decoding framework remains unchanged, the network model structure inside the encoder and decoder can be flexibly designed.
为便于更好的理解本申请实施例，对本申请相关的元学习(Meta-learning)进行说明。In order to better understand the embodiments of the present application, meta-learning related to the present application is explained.
元学习的主要思想为“让机器学会学习”。例如，首先利用大量不同场景、不同类别的数据，利用元学习算法(包括但不限于MAML、Reptile等)以随机初始化的权重作为起点训练模型，获得学会了大量基础知识的元模型。该元模型由于进行了针对大量场景数据的训练(训练元模型的数据可划分为不同场景，可称作不同“任务”)，因此基于该元模型使用少量目标场景的数据即可训练得到适配目标场景的模型。The main idea of meta-learning is to "let the machine learn to learn". For example, first use a large amount of data from different scenarios and categories, and use a meta-learning algorithm (including but not limited to MAML, Reptile, etc.) to train the model with randomly initialized weights as the starting point to obtain a meta-model that has learned a lot of basic knowledge. Since the meta-model is trained on a large amount of scenario data (the data for training the meta-model can be divided into different scenarios, which can be called different "tasks"), a model adapted to the target scenario can be trained based on the meta-model using a small amount of target scenario data.
因此，如果基于元学习进行CSI反馈，则需要采集海量的不同场景的数据支撑元模型的构建，要采集如此海量的、具有较高多样性的信道数据从采集成本上和采集难度上都具有一定的挑战。Therefore, if CSI feedback is performed based on meta-learning, it is necessary to collect a large amount of data from different scenarios to support the construction of the meta-model. Collecting such a large amount of channel data with high diversity is challenging in terms of collection cost and difficulty.
图8是根据本申请实施例的生成样本集的方法200的示意性流程图，如图8所示，该方法200包 括如下内容：FIG8 is a schematic flow chart of a method 200 for generating a sample set according to an embodiment of the present application. As shown in FIG8 , the method 200 includes the following contents:
S210，构建第一基向量空间和第二基向量空间，所述第一基向量空间包括O个基向量组，每个基向量组包括N 1*N 2个空域基向量，所述第二基向量空间包括N sb个频域基向，O是正整数； S210, constructing a first basis vector space and a second basis vector space, wherein the first basis vector space includes O basis vector groups, each basis vector group includes N 1 *N 2 spatial domain basis vectors, and the second basis vector space includes N sb frequency domain basis vectors, where O is a positive integer;
S220，根据所述第一基向量空间和所述第二基向量空间，构建多个任务中的每个任务对应的CSI样本集，其中，每个任务对应的CSI样本集是基于所述第一基向量空间中的一个基向量组中的部分空域基向量和所述第二基向量空间中的部分频域基向量构建的。S220, constructing a CSI sample set corresponding to each task in a plurality of tasks according to the first basis vector space and the second basis vector space, wherein the CSI sample set corresponding to each task is constructed based on part of the spatial domain basis vectors in a basis vector group in the first basis vector space and part of the frequency domain basis vectors in the second basis vector space.
应理解，在本申请实施例中，该方法200可以由终端设备执行，或者，也可以由网络设备执行，本申请对此不作限定。It should be understood that in the embodiment of the present application, the method 200 can be executed by a terminal device, or it can also be executed by a network device, and the present application does not limit this.
在一些实施例中，N sb表示子带数量。 In some embodiments, N sb represents the number of subbands.
在一些实施例中，CSI的发射端具有二维阵列天线，N 1为该二维阵列天线的第一维度的天线端口数，所述N 2为该二维阵列天线的第二维度的天线端口数。 In some embodiments, the transmitter of the CSI has a two-dimensional array antenna, N1 is the number of antenna ports in a first dimension of the two-dimensional array antenna, and N2 is the number of antenna ports in a second dimension of the two-dimensional array antenna.
应理解，本申请仅以CSI的发射端的天线为二维阵列天线为例进行说明，在CSI的发射端的天线为其他形态时，基向量组包括的空域基向量的维度可作适用性调整，本申请对此不作限定。It should be understood that this application only uses the example of the antenna at the transmitting end of the CSI being a two-dimensional array antenna for illustration. When the antenna at the transmitting end of the CSI is in other forms, the dimensions of the spatial basis vectors included in the basis vector group can be adjusted for applicability, and this application does not limit this.
在一些实施例中，所述多个任务分别对应的CSI样本集用于训练第一模型，即第一模型是元模型，也就是起点训练模型。进一步地，可以基于目标场景的CSI样本集对所述第一模型进行训练得到适配目标场景的第二模型。In some embodiments, the CSI sample sets corresponding to the multiple tasks are used to train the first model, that is, the first model is a meta-model, that is, a starting point training model. Further, the first model can be trained based on the CSI sample set of the target scene to obtain a second model adapted to the target scene.
在本申请实施例中，由于该第一模型是基于大量任务的CSI样本集进行训练得到的，因此只需使用少量目标场景的CSI样本集即可训练得到快速适配目标场景的第二模型。进一步地，可以根据第二模型对目标场景的CSI数据进行压缩反馈，有利于降低CSI的反馈开销。In the embodiment of the present application, since the first model is trained based on a large number of CSI sample sets of tasks, only a small number of CSI sample sets of target scenes are needed to train a second model that quickly adapts to the target scene. Furthermore, the CSI data of the target scene can be compressed and fed back according to the second model, which is conducive to reducing the feedback overhead of CSI.
在一些实施例中，所述多个任务为d个任务，每个任务对应的CSI样本集可以包括k个CSI样本，可选地，每个任务对应的CSI样本集包括的CSI样本的数量可以相同，或者，也可以不同。In some embodiments, the multiple tasks are d tasks, and the CSI sample set corresponding to each task may include k CSI samples. Optionally, the number of CSI samples included in the CSI sample set corresponding to each task may be the same, or may also be different.
可选地，每个CSI样本的维度可以是N t×N sb，即CSI样本表示为W∈C Nt×Nsb，其中，C表示复数空间，N t＝2N 1N 2表示发送天线端口数。 Optionally, the dimension of each CSI sample may be N t ×N sb , that is, the CSI sample is expressed as W∈C Nt×Nsb , where C represents a complex number space, and N t =2N 1 N 2 represents the number of transmitting antenna ports.
在一些实施例中，所述O为大于1的正整数，通过将空域基向量的数量增加O倍，有利于增加CSI样本在空域上的精度。In some embodiments, O is a positive integer greater than 1, and increasing the number of spatial basis vectors by O times is beneficial to increasing the accuracy of CSI samples in the spatial domain.
在一些实施例中，所述O个基向量组中的每个基向量组中的N 1*N 2个空域基向量组成的矩阵为酉矩阵，即同一个基向量组中的空域基向量是正交的，所述N sb个频域基向量组成的矩阵为酉矩阵，即第二基向量空间中的频域基向量是正交的。 In some embodiments, the matrix composed of N 1 *N 2 spatial basis vectors in each basis vector group of the O basis vector groups is a unitary matrix, that is, the spatial basis vectors in the same basis vector group are orthogonal, and the matrix composed of N sb frequency domain basis vectors is a unitary matrix, that is, the frequency domain basis vectors in the second basis vector space are orthogonal.
也就是说，本申请实施例中的第一基向量空间和第二基向量空间是完备的，因此，基于该第一基向量空间和第二基向量空间生成的用于训练元模型的数据集也具有完备性。That is to say, the first basis vector space and the second basis vector space in the embodiment of the present application are complete, and therefore, the data set for training the meta-model generated based on the first basis vector space and the second basis vector space is also complete.
在本申请实施例中，第一基向量空间中每个基向量组中的全部空域基向量构成的矩阵为酉矩阵，因此，任意与该空域基向量同维度的向量都可以利用该基向量组中的全部空域基向量进行线性表示。In an embodiment of the present application, the matrix formed by all spatial basis vectors in each basis vector group in the first basis vector space is a unitary matrix. Therefore, any vector of the same dimension as the spatial basis vector can be linearly represented using all spatial basis vectors in the basis vector group.
类似地，第二基向量空间中全部频域基向量构成的矩阵为酉矩阵，因此，任意与该频域基向量同维度的向量都可以利用该第二基向量空间中的全部频域基向量进行线性表示。Similarly, the matrix formed by all frequency domain basis vectors in the second basis vector space is a unitary matrix. Therefore, any vector with the same dimension as the frequency domain basis vector can be linearly represented using all frequency domain basis vectors in the second basis vector space.
应理解，本申请实施例并不限定构建第一基向量空间中的O个基向量组，以及构建所述第二基向量空间的具体实现，任意用于构建酉矩阵的方式均可以作为第一基向量空间中的O个基向量组，以及第二基向量空间的构建方法，本申请对此不作限定。It should be understood that the embodiments of the present application are not limited to the specific implementation of constructing the O basis vector groups in the first basis vector space and the second basis vector space. Any method for constructing a unitary matrix can be used as the O basis vector groups in the first basis vector space and the method for constructing the second basis vector space. The present application does not limit this.
以下，结合具体示例，说明第一基向量空间和第二基向量的构建方法，但本申请并不限于此。The following describes a method for constructing the first basis vector space and the second basis vector space in conjunction with specific examples, but the present application is not limited thereto.
在本申请一些实施例中，所述构建第一基向量空间，包括：In some embodiments of the present application, constructing the first basis vector space includes:
循环执行如下步骤O次，得到所述O个基向量组中的每个基向量组的空域基向量：The following steps are executed in a loop O times to obtain the spatial basis vector of each basis vector group in the O basis vector groups:
基于第一分布进行随机采样得到第一矩阵(记为X h)，以及基于第二分布进行随机采样得到第二矩阵(记为X v)，其中，所述第一矩阵为N 1*N 1维度的矩阵(即X h∈C N1×N1)，所述第二矩阵为N 2*N 2维度的矩阵(即X v∈C N2×N2)； A first matrix (denoted as X h ) is obtained by random sampling based on a first distribution, and a second matrix (denoted as X v ) is obtained by random sampling based on a second distribution, wherein the first matrix is a matrix of N 1 *N 1 dimensions (ie, X h ∈ CN1×N1 ), and the second matrix is a matrix of N 2 *N 2 dimensions (ie, X v ∈ CN2×N2 );
确定所述第一矩阵对应的正交矩阵(记为U h)和所述第二矩阵对应的正交矩阵(记为U v)； Determine an orthogonal matrix (denoted as U h ) corresponding to the first matrix and an orthogonal matrix (denoted as U v ) corresponding to the second matrix;
将所述第一矩阵对应的正交矩阵和所述第二矩阵对应的正交矩阵进行克罗内克积，得到目标矩阵(记为S)，即
Figure PCTCN2022130674-appb-000001
其中，
Figure PCTCN2022130674-appb-000002
表示克罗内克积； Perform the Kronecker product of the orthogonal matrix corresponding to the first matrix and the orthogonal matrix corresponding to the second matrix to obtain the target matrix (denoted as S), that is,
Figure PCTCN2022130674-appb-000001
in,
Figure PCTCN2022130674-appb-000002
represents the Kronecker product;
将所述目标矩阵的一列作为所述第一基向量空间中的一个基向量组中的一个空域基向量。A column of the target matrix is used as a spatial basis vector in a basis vector group in the first basis vector space.
可选地，第一分布可以包括但不限于复高斯分布、复均匀分布。Optionally, the first distribution may include but is not limited to complex Gaussian distribution and complex uniform distribution.
可选地，第二分布可以包括但不限于复高斯分布、复均匀分布。Optionally, the second distribution may include but is not limited to complex Gaussian distribution and complex uniform distribution.
可选地，第一分布和第二分布可以相同，或者，也可以不同。Optionally, the first distribution and the second distribution may be the same, or may be different.
在一些实施例中，第一矩阵是基于第一分布随机采样得到的，因此，第一矩阵中的元素服从第一分布，类似地，第二矩阵是基于第二分布随机采样得到的，因此，第二矩阵中的元素服从第二分布。In some embodiments, the first matrix is obtained by random sampling based on a first distribution, so the elements in the first matrix obey the first distribution. Similarly, the second matrix is obtained by random sampling based on a second distribution, so the elements in the second matrix obey the second distribution.
在一些实施例中，所述第一矩阵对应的正交矩阵可以是根据第一矩阵确定的正交矩阵，第二矩阵对应的正交矩阵可以指根据第二矩阵确定的正交矩阵。本申请对于确定第一矩阵对应的正交矩阵以及第二矩阵对应的正交矩阵的具体方法不作限定。例如，可以通过奇异值分解(Singular Value Decomposition)方式得到，或者，也可以通过施密特正交化方式得到等。In some embodiments, the orthogonal matrix corresponding to the first matrix may be an orthogonal matrix determined according to the first matrix, and the orthogonal matrix corresponding to the second matrix may refer to an orthogonal matrix determined according to the second matrix. The present application does not limit the specific method for determining the orthogonal matrix corresponding to the first matrix and the orthogonal matrix corresponding to the second matrix. For example, it can be obtained by singular value decomposition, or it can be obtained by Schmidt orthogonalization, etc.
在一些实施例中，所述确定所述第一矩阵对应的正交矩阵和所述第二矩阵对应的正交矩阵，包括：In some embodiments, determining an orthogonal matrix corresponding to the first matrix and an orthogonal matrix corresponding to the second matrix includes:
对所述第一矩阵进行SVD，将得到的左奇异矩阵作为所述第一矩阵对应的正交矩阵；Performing SVD on the first matrix, and using the obtained left singular matrix as the orthogonal matrix corresponding to the first matrix;
对所述第二矩阵进行SVD，将得到的左奇异矩阵作为所述第二矩阵对应的正交矩阵。Perform SVD on the second matrix, and use the obtained left singular matrix as the orthogonal matrix corresponding to the second matrix.
在另一些实施例中，所述确定第一矩阵对应的正交矩阵和第二矩阵对应的正交矩阵，包括：In some other embodiments, determining an orthogonal matrix corresponding to the first matrix and an orthogonal matrix corresponding to the second matrix includes:
对所述第一矩阵进行施密特正交化，将得到的正交矩阵作为所述第一矩阵对应的正交矩阵；Performing Schmidt orthogonalization on the first matrix, and using the obtained orthogonal matrix as the orthogonal matrix corresponding to the first matrix;
对所述第二矩阵进行施密特正交化，将得到的正交矩阵作为所述第二矩阵对应的正交矩阵。Perform Schmidt orthogonalization on the second matrix, and use the obtained orthogonal matrix as the orthogonal matrix corresponding to the second matrix.
在本申请一些实施例中，所述构建第二基向量空间，包括：In some embodiments of the present application, constructing the second basis vector space includes:
基于第三分布进行随机采样得到第三矩阵(记为X f)，所述第三矩阵为N sb*N sb维度的矩阵(即，X f∈C Nsb×Nsb)； A third matrix (denoted as X f ) is obtained by random sampling based on the third distribution, wherein the third matrix is a matrix of N sb *N sb dimensions (ie, X f ∈CNsb ×Nsb );
确定所述第三矩阵对应的正交矩阵(记为U f)； Determine the orthogonal matrix (denoted as U f ) corresponding to the third matrix;
将所述第三矩阵对应的正交矩阵(即U f)的一列作为所述第二基向量空间中的一个频域基向量。 A column of the orthogonal matrix (ie, U f ) corresponding to the third matrix is used as a frequency domain basis vector in the second basis vector space.
可选地，所述第三分布可以包括但不限于复高斯分布、复均匀分布。Optionally, the third distribution may include but is not limited to complex Gaussian distribution and complex uniform distribution.
在一些实施例中，第三矩阵是基于第三分布随机采样得到的，因此，第三矩阵中的元素服从第三分布。In some embodiments, the third matrix is obtained by random sampling based on a third distribution, and therefore, elements in the third matrix obey the third distribution.
在一些实施例中，所述第三矩阵对应的正交矩阵可以是根据第三矩阵确定的正交矩阵。本申请对于确定第三矩阵对应的正交矩阵的具体方法不作限定。例如，可以通过SVD方式得到，或者，也可以通过施密特正交化方式得到等。In some embodiments, the orthogonal matrix corresponding to the third matrix may be an orthogonal matrix determined according to the third matrix. The present application does not limit the specific method for determining the orthogonal matrix corresponding to the third matrix. For example, it may be obtained by SVD, or it may be obtained by Schmidt orthogonalization, etc.
在一些实施例中，所述确定所述第三矩阵对应的正交矩阵，包括：In some embodiments, determining an orthogonal matrix corresponding to the third matrix includes:
对所述第三矩阵进行SVD，将得到的左奇异矩阵作为所述第三矩阵对应的正交矩阵；或Perform SVD on the third matrix, and use the obtained left singular matrix as the orthogonal matrix corresponding to the third matrix; or
对所述第三矩阵进行施密特正交化，将得到的正交矩阵作为所述第三矩阵对应的正交矩阵。Perform Schmidt orthogonalization on the third matrix, and use the obtained orthogonal matrix as the orthogonal matrix corresponding to the third matrix.
在本申请一些实施例中，所述S220可以包括：In some embodiments of the present application, the S220 may include:
循环执行如下步骤d次，得到所述多个任务中的每个任务对应的CSI样本集，其中，d为多个任务的个数：The following steps are executed d times in a loop to obtain a CSI sample set corresponding to each task in the multiple tasks, where d is the number of the multiple tasks:
在所述第一基向量空间中的O个基向量组中选择一个基向量组；Selecting a basis vector group from the O basis vector groups in the first basis vector space;
根据所述一个基向量组中的L task个空域基向量和所述第二基向量空间中的M task个频域基向量，构建所述多个任务中的一个任务对应的CSI样本集，其中，L task，L task是大于1的正整数。 A CSI sample set corresponding to one of the multiple tasks is constructed according to L task spatial domain basis vectors in the one basis vector group and M task frequency domain basis vectors in the second basis vector space, where L task , L task are positive integers greater than 1.
应理解，对于多个任务中的不同任务，在构建对应的CSI样本集时，所使用的参数L task，M task可以相同，或者，也可以不同，本申请对此不作限定。 It should be understood that for different tasks among the multiple tasks, when constructing corresponding CSI sample sets, the parameters L task and M task used may be the same or different, and this application does not limit this.
在一些实施例中，所述一个基向量组是在所述O个基向量组中随机选择的。In some embodiments, the one basis vector group is randomly selected from the O basis vector groups.
在一些实施例中，所述L task小于N 1*N 2，所述M task小于N sb。 In some embodiments, the Ltask is smaller than N 1 *N 2 , and the Mtask is smaller than N sb .
即，L task个空域基向量是一个基向量组中的部分空域基向量，M task个频域基向量是第二基向量空间中的部分频域基向量。 That is, the L task spatial domain basis vectors are part of the spatial domain basis vectors in a basis vector group, and the M task frequency domain basis vectors are part of the frequency domain basis vectors in the second basis vector space.
在一些实施例中，所述L task个空域基向量是在所述一个基向量组中随机选择的。 In some embodiments, the L task spatial basis vectors are randomly selected from the one basis vector group.
在一些实施例中，所述M task个频域基向量是在所述第二基向量空间中的N sb个频域基向量中随机选择的。 In some embodiments, the M task frequency domain basis vectors are randomly selected from N sb frequency domain basis vectors in the second basis vector space.
例如，在构建多个任务中的第一任务对应的CSI样本集时，在第一基向量空间中的O个基向量组中随机选择一个基向量组(记为第一基向量组)，以及在第二基向量空间中的N sb个频域基向量随机选择M task个频域基向量，进一步基于该第一基向量组中的部分空域基向量和该M task个频域基向量中的部分频域基向量构建第一任务对应的CSI样本集。其中，该第一基向量组(即第一基向量组中的L task个空域基向量)和该M task个频域基向量可以认为是第一任务对应的任务基向量集合(记为第一任务基向量集合)，即该第一任务对应的CSI样本集是基于该第一任务基向量集合中的基向量构建的。 For example, when constructing a CSI sample set corresponding to the first task among multiple tasks, a basis vector group (referred to as the first basis vector group) is randomly selected from the O basis vector groups in the first basis vector space, and M task frequency domain basis vectors are randomly selected from the N sb frequency domain basis vectors in the second basis vector space, and the CSI sample set corresponding to the first task is further constructed based on some spatial domain basis vectors in the first basis vector group and some frequency domain basis vectors in the M task frequency domain basis vectors. The first basis vector group (i.e., the L task spatial domain basis vectors in the first basis vector group) and the M task frequency domain basis vectors can be considered as the task basis vector set corresponding to the first task (referred to as the first task basis vector set), that is, the CSI sample set corresponding to the first task is constructed based on the basis vectors in the first task basis vector set.
又例如，在构建多个任务中的第二任务对应的CSI样本集时，在第一基向量空间中的O个基向量组中随机选择一个基向量组(记为第二基向量组)，以及在第二基向量空间中的N sb个频域基向量随机选择M task个频域基向量，进一步基于该第二基向量组中的部分空域基向量和该M task个频域基向量中的部分频域基向量构建第二任务对应的CSI样本集。其中，该第二基向量组(即第二基向量组中的L task个空域基向量)和该M task个频域基向量可以认为是第二任务对应的任务基向量集合(记为第二任务基向量集合)，即该第二任务对应的CSI样本集是基于该第二任务基向量集合中的基向量构建的。 For another example, when constructing a CSI sample set corresponding to a second task among multiple tasks, a basis vector group is randomly selected from the O basis vector groups in the first basis vector space (referred to as the second basis vector group), and M task frequency domain basis vectors are randomly selected from the N sb frequency domain basis vectors in the second basis vector space, and the CSI sample set corresponding to the second task is further constructed based on some spatial domain basis vectors in the second basis vector group and some frequency domain basis vectors in the M task frequency domain basis vectors. The second basis vector group (i.e., the L task spatial domain basis vectors in the second basis vector group) and the M task frequency domain basis vectors can be considered as a task basis vector set corresponding to the second task (referred to as the second task basis vector set), that is, the CSI sample set corresponding to the second task is constructed based on the basis vectors in the second task basis vector set.
第一基向量空间和第二基向量空间可以认为是正交基向量的全集，因此，在本申请实施例中，构建不同任务对应的CSI样本集时所使用的正交基向量(即任务基向量集合)为该正交基向量全集的不同子集，例如，生成第一任务对应的CSI样本集是基于第一任务基向量集合中的基向量，构建第二任务对应的CSI样本集是基于第二任务基向量集合中的基向量，有利于实现不同任务间的CSI样本的多样性。The first basis vector space and the second basis vector space can be considered as the complete set of orthogonal basis vectors. Therefore, in an embodiment of the present application, the orthogonal basis vectors (i.e., the task basis vector set) used to construct CSI sample sets corresponding to different tasks are different subsets of the complete set of orthogonal basis vectors. For example, generating the CSI sample set corresponding to the first task is based on the basis vectors in the first task basis vector set, and constructing the CSI sample set corresponding to the second task is based on the basis vectors in the second task basis vector set, which is conducive to achieving diversity of CSI samples between different tasks.
在一些实施例中，一个任务对应的任务基向量集合中的基向量可以认为具有相似或一致的特性，例如，在第一基向量组中随机选择的L task个空域基向量可以认为具有相似或一致的特性，在第二基向量组中随机选择的L task个空域基向量可以认为具有相似或一致的特性，在第二基向量空间中随机选择的M task个频域基向量可以认为具有相似或一致的特性，因此，可以基于该任务基向量集合中的基向量生成针对特定场景(即特定任务)的CSI样本集。 In some embodiments, basis vectors in a task basis vector set corresponding to a task can be considered to have similar or consistent characteristics. For example, L task spatial domain basis vectors randomly selected in the first basis vector group can be considered to have similar or consistent characteristics, L task spatial domain basis vectors randomly selected in the second basis vector group can be considered to have similar or consistent characteristics, and M task frequency domain basis vectors randomly selected in the second basis vector space can be considered to have similar or consistent characteristics. Therefore, a CSI sample set for a specific scenario (i.e., a specific task) can be generated based on the basis vectors in the task basis vector set.
在一些实施例中，所述根据所述一个基向量组中的L task个空域基向量和所述第二基向量空间中的M task个频域基向量，构建所述多个任务中的一个任务对应的CSI样本集，包括： In some embodiments, constructing a CSI sample set corresponding to one of the multiple tasks according to L task spatial domain basis vectors in the one basis vector group and M task frequency domain basis vectors in the second basis vector space includes:
循环执行如下步骤k次，得到一个任务对应的CSI样本集包括的k个CSI样本，其中，k大于1：The following steps are executed k times in a loop to obtain k CSI samples included in a CSI sample set corresponding to a task, where k is greater than 1:
在所述L task个空域基向量中随机选择L个空域基向量，并将所述L个空域基向量按列排列得到矩阵B，其中，L为正整数； Randomly select L spatial basis vectors from the L task spatial basis vectors, and arrange the L spatial basis vectors in columns to obtain a matrix B, where L is a positive integer;
根据矩阵B构建对角块矩阵W 1＝[B,0；0,B]； Construct a diagonal block matrix W 1 = [B, 0; 0, B] according to the matrix B;
在所述M task个频域基向量中随机选择M个频域基向量，并将所述M个频域基向量按行排列得到矩阵W f，其中，M为正整数； Randomly select M frequency domain basis vectors from the M task frequency domain basis vectors, and arrange the M frequency domain basis vectors in rows to obtain a matrix W f , where M is a positive integer;
根据对角块矩阵W 1，矩阵W f和随机数矩阵W 2，生成一个任务对应的CSI样本集中的一个CSI样本。 According to the diagonal block matrix W 1 , the matrix W f and the random number matrix W 2 , a CSI sample in a CSI sample set corresponding to a task is generated.
在一些实施例中，L＜L task，M＜M task。 In some embodiments, L<L task , M<M task .
因此，在本申请实施例中，在构建一个任务对应的CSI样本集中的不同CSI样本时，可以是基于该任务对应的任务基向量集合中的不同子集，有利于实现同一任务中的不同样本的多样性。Therefore, in an embodiment of the present application, when constructing different CSI samples in a CSI sample set corresponding to a task, it can be based on different subsets in a task basis vector set corresponding to the task, which is conducive to achieving diversity of different samples in the same task.
在一些实施例中，随机数矩阵W 2是基于第四分布采样得到的，即W 2中的元素服从第四分布。 In some embodiments, the random number matrix W 2 is obtained by sampling based on the fourth distribution, that is, the elements in W 2 obey the fourth distribution.
由于基于第四分布可进行无穷多次随机采样，从而能够构建足量的、大规模的CSI样本。Since an infinite number of random samplings can be performed based on the fourth distribution, sufficient and large-scale CSI samples can be constructed.
在本申请实施例中，第一基向量空间和第二基向量空间可以用于提供空域和频域的特性，随机数矩阵可以用于扩展CSI样本集的规模，因此，根据本申请实施例的生成样本集的方法，能够兼顾生成的CSI样本的空域和频域特性以及规模。In an embodiment of the present application, the first basis vector space and the second basis vector space can be used to provide spatial and frequency domain characteristics, and the random number matrix can be used to expand the scale of the CSI sample set. Therefore, the method for generating a sample set according to an embodiment of the present application can take into account the spatial and frequency domain characteristics and scale of the generated CSI samples.
可选地，第四分布可以包括但不限于复高斯分布、复均匀分布。Optionally, the fourth distribution may include, but is not limited to, complex Gaussian distribution and complex uniform distribution.
在一些实施例中，所述根据对角块矩阵W 1，矩阵W f和随机数矩阵W 2，生成一个任务对应的CSI样本集中的一个CSI样本，包括： In some embodiments, generating a CSI sample in a CSI sample set corresponding to a task according to the diagonal block matrix W 1 , the matrix W f and the random number matrix W 2 includes:
将所述对角块矩阵W 1，矩阵W f和随机数矩阵W 2相乘得到第一CSI样本； Multiplying the diagonal block matrix W 1 , the matrix W f and the random number matrix W 2 to obtain a first CSI sample;
将所述第一CSI样本的矩阵中的每一列进行归一化处理，得到目标CSI样本。Each column in the matrix of the first CSI samples is normalized to obtain a target CSI sample.
在一些实施例中，所述第一CSI样本W’＝W 1W 2W f＝[w 1,...,w Nsb]。 In some embodiments, the first CSI samples W′=W 1 W 2 W f =[w 1 , ..., w Nsb ].
可选地，该归一化处理可以包括但不限于二范数处理。Optionally, the normalization process may include but is not limited to a two-norm process.
例如，目标CSI样本W＝[w 1/norm(w 1),...,w Nsb/norm(w Nsb)]，其中，norm()表示二范数。 For example, the target CSI sample W=[w 1 /norm(w 1 ), ..., w Nsb /norm(w Nsb )], where norm() represents a binary norm.
在一个具体实施例中，可以基于如下步骤生成d个任务中的每个任务对应的CSI样本集。In a specific embodiment, a CSI sample set corresponding to each of the d tasks may be generated based on the following steps.
步骤a，从第一基向量空间的O组基向量组中随机选择一个基向量组，记为基向量组Q；Step a, randomly selecting a basis vector group from the O basis vector groups in the first basis vector space, denoted as basis vector group Q;
步骤b，从基向量组Q中随机选择L task个空域基向量，得到基向量组Q’； Step b, randomly select L task spatial basis vectors from the basis vector group Q to obtain the basis vector group Q';
步骤c，从第二基向量空间的N sb个频域基向量中随机选择M task个频域基向量，得到基向量组P； Step c, randomly selecting M task frequency domain basis vectors from the N sb frequency domain basis vectors in the second basis vector space to obtain a basis vector group P;
其中，该基向量组Q’和基向量组P可以认为是当前任务对应的任务基向量集合。Among them, the basis vector group Q’ and the basis vector group P can be considered as the task basis vector set corresponding to the current task.
步骤d，从基向量组Q’中随机选择L<L task个基向量，按列排列构成矩阵B，并根据矩阵B构建对角块矩阵W 1＝[B,0；0,B]，其中，B∈C N1N2×L，W 1∈C 2N1N2×2L。 Step d, randomly select L<L task basis vectors from the basis vector group Q', arrange them in columns to form a matrix B, and construct a diagonal block matrix W 1 =[B,0;0,B] based on the matrix B, where B∈C N1N2×L , W 1 ∈C 2N1N2×2L .
步骤e，从基向量组P中随机选择M<M task个基向量，按行排列构成矩阵W f，其中W f∈C M×Nsb。 Step e: randomly select M<M task basis vectors from the basis vector group P and arrange them in rows to form a matrix W f , where W f ∈ C M×Nsb .
步骤f，构建随机数矩阵W 2∈C 2L×M，随机数矩阵W 2中每个元素均服从第四分布，例如复高斯分布或复均匀分布等； Step f, constructing a random number matrix W 2 ∈C 2L×M , wherein each element in the random number matrix W 2 obeys a fourth distribution, such as a complex Gaussian distribution or a complex uniform distribution;
步骤g，根据对角块矩阵W 1，矩阵W f样本和随机数矩阵W 2生成第一CSI样本W’＝W 1W 2W f＝[w 1,...,w Nsb]。 Step g: Generate the first CSI samples W′=W 1 W 2 W f =[w 1 , ..., w Nsb ] according to the diagonal block matrix W 1 , the matrix W f samples and the random number matrix W 2 .
进一步地，对该第一CSI样本的每一列进行归一化处理，获得目标CSI样本，例如利用二范数对第一CSI样本中的每一列进行归一化处理，得到目标CSI样本W＝[w 1/norm(w 1),...,w Nsb/norm(w Nsb)]，其中norm()表示二范数； Further, each column of the first CSI sample is normalized to obtain a target CSI sample. For example, each column of the first CSI sample is normalized using a binary norm to obtain a target CSI sample W=[w 1 /norm(w 1 ),...,w Nsb /norm(w Nsb )], where norm() represents a binary norm;
步骤h，确定当前任务对应的CSI样本集中的k个CSI样本是否构建完毕，若是，则返回步骤a， 生成下一个任务对应的CSI样本集中的CSI样本，若否，则返回步骤d，构建当前任务对应的CSI样本集中的下一个CSI样本；Step h, determining whether the k CSI samples in the CSI sample set corresponding to the current task have been constructed. If so, returning to step a to generate the CSI sample in the CSI sample set corresponding to the next task; if not, returning to step d to construct the next CSI sample in the CSI sample set corresponding to the current task;
步骤i，确定d个任务对应的CSI样本集是否构建完毕，若是，则结束流程，若否，则返回步骤a，构建下一个任务对应的CSI样本集。In step i, it is determined whether the CSI sample sets corresponding to the d tasks have been constructed. If so, the process ends. If not, the process returns to step a to construct the CSI sample set corresponding to the next task.
在d个任务对应的CSI样本集均构建完毕时，可以得到CSI样本集T＝{T 1,...,T d}，其中，CSI样本集T i表示任务i对应的CSI样本集，i＝1,...d。由前文描述可知，第一基向量空间和第二基向量空间是完备的，因此，基于该第一基向量空间和第二基向量空间生成的CSI样本集T＝{T 1,...,T d}也具有完备性。 When the CSI sample sets corresponding to d tasks are constructed, the CSI sample set T = {T 1 , ..., T d } can be obtained, where CSI sample set Ti represents the CSI sample set corresponding to task i, i = 1, ... d. As can be seen from the foregoing description, the first basis vector space and the second basis vector space are complete, so the CSI sample set T = {T 1 , ..., T d } generated based on the first basis vector space and the second basis vector space is also complete.
进一步地，可以基于该CSI样本集T＝{T 1,...,T d}可以训练第一模型，也就是起点训练模型。进一步地，可以基于目标场景的CSI样本集对所述第一模型进行训练得到适配目标场景的第二模型。由于该第一模型是基于大量任务的CSI样本集进行训练得到的，因此只需使用少量目标场景的CSI样本集即可训练得到快速适配目标场景的第二模型。进一步地，可以根据第二模型对目标场景的CSI数据进行压缩反馈，有利于降低CSI的反馈开销。 Further, a first model, that is, a starting point training model, can be trained based on the CSI sample set T={T 1 ,...,T d }. Further, the first model can be trained based on the CSI sample set of the target scene to obtain a second model adapted to the target scene. Since the first model is trained based on a large number of CSI sample sets of tasks, only a small number of CSI sample sets of the target scene are needed to train a second model that quickly adapts to the target scene. Further, the CSI data of the target scene can be compressed and fed back according to the second model, which is beneficial to reducing the feedback overhead of CSI.
应理解，在本申请实施例中，构建CSI样本集的设备和训练第一模型的设备可以是同一设备，或者，也可以是不同设备，在二者是不同设备时，构建CSI样本集的设备可以将构建的CSI样本集发送给训练第一模型的设备，以便该设备基于该CSI样本集训练第一模型。It should be understood that in an embodiment of the present application, the device for constructing the CSI sample set and the device for training the first model may be the same device, or may be different devices. When the two are different devices, the device for constructing the CSI sample set may send the constructed CSI sample set to the device for training the first model, so that the device trains the first model based on the CSI sample set.
综上，在本申请实施例中，通信设备(例如终端设备或网络设备)可以构建空域基向量对应的第一基向量空间以及频域基向量对应的第二基向量空间，其中，第一基向量空间包括O个基向量组，每个基向量组中的N 1*N 2个空域基向量组成的矩阵为酉矩阵，第二基向量空间中的频域基向量组成的矩阵为酉矩阵。即第一基向量空间和第二基向量空间是完备的，因此，基于该第一基向量空间和第二基向量空间生成的用于训练元模型的数据集也具有完备性。 In summary, in the embodiment of the present application, a communication device (such as a terminal device or a network device) can construct a first basis vector space corresponding to a spatial basis vector and a second basis vector space corresponding to a frequency domain basis vector, wherein the first basis vector space includes O basis vector groups, the matrix composed of N 1 *N 2 spatial basis vectors in each basis vector group is a unitary matrix, and the matrix composed of the frequency domain basis vectors in the second basis vector space is a unitary matrix. That is, the first basis vector space and the second basis vector space are complete, and therefore, the data set for training the meta-model generated based on the first basis vector space and the second basis vector space is also complete.
进一步地，使用不同的任务基向量集合构建不同任务对应的CSI样本集，有利于实现不同任务间的CSI样本的多样性。Furthermore, using different task basis vector sets to construct CSI sample sets corresponding to different tasks is conducive to achieving diversity of CSI samples between different tasks.
进一步地，使用任务基向量集合中的不同子集构建该任务对应的CSI样本集中的不同CSI样本，有利于实现同一任务中的不同样本的多样性。Furthermore, different subsets in the task basis vector set are used to construct different CSI samples in the CSI sample set corresponding to the task, which is conducive to achieving diversity of different samples in the same task.
进一步地，由于随机数矩阵可以进行无穷多次随机采样，第一基向量空间能够提供CSI数据的空域特性，第二基向量空间能够提供CSI数据的频域特性，因此，根据第一基向量空间、第二基向量空间和随机数矩阵构建每个任务对应的CSI样本集，能够保证生成的CSI样本的空域和频域特性以及规模。Furthermore, since the random number matrix can perform random sampling infinitely many times, the first basis vector space can provide the spatial domain characteristics of the CSI data, and the second basis vector space can provide the frequency domain characteristics of the CSI data. Therefore, constructing the CSI sample set corresponding to each task based on the first basis vector space, the second basis vector space and the random number matrix can ensure the spatial and frequency domain characteristics and scale of the generated CSI samples.
上文结合图8，详细描述了本申请的方法实施例，下文结合图9至图11，详细描述本申请的装置实施例，应理解，装置实施例与方法实施例相互对应，类似的描述可以参照方法实施例。The above text, in combination with Figure 8, describes in detail the method embodiment of the present application. The following text, in combination with Figures 9 to 11, describes in detail the device embodiment of the present application. It should be understood that the device embodiment and the method embodiment correspond to each other, and similar descriptions can refer to the method embodiment.
图9示出了根据本申请实施例的生成样本集的设备400的示意性框图。如图4所示，该设备400包括：Fig. 9 shows a schematic block diagram of a device 400 for generating a sample set according to an embodiment of the present application. As shown in Fig. 4, the device 400 includes:
处理单元410，用于构建第一基向量空间和第二基向量空间，所述第一基向量空间包括O个基向量组，每个基向量组包括N 1*N 2个空域基向量，所述第二基向量空间包括N sb个频域基向量，其中，O是正整数，所述N 1为信道状态信息CSI的发射端的第一维度的天线端口数，所述N 2为CSI的发射端的第二维度的天线端口数，N sb表示子带数量；以及 The processing unit 410 is configured to construct a first basis vector space and a second basis vector space, wherein the first basis vector space includes O basis vector groups, each basis vector group includes N 1 *N 2 spatial basis vectors, and the second basis vector space includes N sb frequency domain basis vectors, wherein O is a positive integer, N 1 is the number of antenna ports in a first dimension of a transmitting end of the channel state information CSI, N 2 is the number of antenna ports in a second dimension of the transmitting end of the CSI, and N sb represents the number of subbands; and
根据所述第一基向量空间和所述第二基向量空间，构建多个任务中的每个任务对应的CSI样本集，其中，每个任务对应的CSI样本集是基于所述第一基向量空间中的一个基向量组中的部分空域基向量和所述第二基向量空间中的部分频域基向量构建的，所述多个任务分别对应的CSI样本集用于训练第一模型，所述第一模型用于基于目标场景的CSI样本集训练得到第二模型，所述第二模型适配所述目标场景。According to the first basis vector space and the second basis vector space, a CSI sample set corresponding to each task in a plurality of tasks is constructed, wherein the CSI sample set corresponding to each task is constructed based on some spatial domain basis vectors in a basis vector group in the first basis vector space and some frequency domain basis vectors in the second basis vector space, and the CSI sample sets corresponding to the plurality of tasks are respectively used to train a first model, and the first model is used to obtain a second model based on the CSI sample set of a target scene for training, and the second model is adapted to the target scene.
在一些实施例中，所述O个基向量组中的每个基向量组中的N 1*N 2个空域基向量组成的矩阵为酉矩阵，所述N sb个频域基向量组成的矩阵为酉矩阵。 In some embodiments, the matrix composed of N 1 *N 2 spatial basis vectors in each basis vector group of the O basis vector groups is a unitary matrix, and the matrix composed of the N sb frequency domain basis vectors is a unitary matrix.
在一些实施例中，所述处理单元410还用于：In some embodiments, the processing unit 410 is further configured to:
循环执行如下步骤O次，得到所述O个基向量组中的每个基向量组的空域基向量：The following steps are executed in a loop O times to obtain the spatial basis vector of each basis vector group in the O basis vector groups:
基于第一分布进行随机采样得到第一矩阵，以及基于第二分布进行随机采样得到第二矩阵，其中，所述第一矩阵为N 1*N 1维度的矩阵，所述第二矩阵为N 2*N 2维度的矩阵； Performing random sampling based on a first distribution to obtain a first matrix, and performing random sampling based on a second distribution to obtain a second matrix, wherein the first matrix is a matrix of N 1 *N 1 dimensions, and the second matrix is a matrix of N 2 *N 2 dimensions;
确定所述第一矩阵对应的正交矩阵和所述第二矩阵对应的正交矩阵；Determine an orthogonal matrix corresponding to the first matrix and an orthogonal matrix corresponding to the second matrix;
将所述第一矩阵对应的正交矩阵和所述第二矩阵对应的正交矩阵进行克罗内克积，得到目标矩阵；Performing a Kronecker product on an orthogonal matrix corresponding to the first matrix and an orthogonal matrix corresponding to the second matrix to obtain a target matrix;
将所述目标矩阵的一列作为所述第一基向量空间中的一个基向量组中的一个空域基向量。A column of the target matrix is used as a spatial basis vector in a basis vector group in the first basis vector space.
在一些实施例中，所述处理单元410还用于：In some embodiments, the processing unit 410 is further configured to:
对所述第一矩阵进行奇异值分解SVD，将得到的左奇异矩阵作为所述第一矩阵对应的正交矩阵；Performing singular value decomposition (SVD) on the first matrix, and using the obtained left singular matrix as the orthogonal matrix corresponding to the first matrix;
对所述第二矩阵进行SVD，将得到的左奇异矩阵作为所述第二矩阵对应的正交矩阵。Perform SVD on the second matrix, and use the obtained left singular matrix as the orthogonal matrix corresponding to the second matrix.
在一些实施例中，所述处理单元410还用于：In some embodiments, the processing unit 410 is further configured to:
对所述第一矩阵进行施密特正交化，将得到的正交矩阵作为所述第一矩阵对应的正交矩阵；Performing Schmidt orthogonalization on the first matrix, and using the obtained orthogonal matrix as the orthogonal matrix corresponding to the first matrix;
对所述第二矩阵进行施密特正交化，将得到的正交矩阵作为所述第二矩阵对应的正交矩阵。Perform Schmidt orthogonalization on the second matrix, and use the obtained orthogonal matrix as the orthogonal matrix corresponding to the second matrix.
在一些实施例中，所述第一分布为复高斯分布或复均匀分布；In some embodiments, the first distribution is a complex Gaussian distribution or a complex uniform distribution;
所述第二分布为复高斯分布或复均匀分布。The second distribution is a complex Gaussian distribution or a complex uniform distribution.
在一些实施例中，所述处理单元410还用于：In some embodiments, the processing unit 410 is further configured to:
基于第三分布进行随机采样得到第三矩阵，所述第三矩阵为N sb*N sb维度的矩阵； Performing random sampling based on a third distribution to obtain a third matrix, wherein the third matrix is a matrix of N sb *N sb dimensions;
确定所述第三矩阵对应的正交矩阵；Determine an orthogonal matrix corresponding to the third matrix;
将所述第三矩阵对应的正交矩阵的一列作为所述第二基向量空间中的一个频域基向量。A column of the orthogonal matrix corresponding to the third matrix is used as a frequency domain basis vector in the second basis vector space.
在一些实施例中，所述处理单元410还用于：In some embodiments, the processing unit 410 is further configured to:
对所述第三矩阵进行SVD，将得到的左奇异矩阵作为所述第三矩阵对应的正交矩阵；或Perform SVD on the third matrix, and use the obtained left singular matrix as the orthogonal matrix corresponding to the third matrix; or
对所述第三矩阵进行施密特正交化，将得到的正交矩阵作为所述第三矩阵对应的正交矩阵。Perform Schmidt orthogonalization on the third matrix, and use the obtained orthogonal matrix as the orthogonal matrix corresponding to the third matrix.
在一些实施例中，所述第三分布为复高斯分布或复均匀分布。In some embodiments, the third distribution is a complex Gaussian distribution or a complex uniform distribution.
在一些实施例中，所述处理单元410还用于：In some embodiments, the processing unit 410 is further configured to:
循环执行如下步骤d次，得到所述多个任务中的每个任务对应的CSI样本集，其中，d为多个任务的个数：The following steps are executed d times in a loop to obtain a CSI sample set corresponding to each task in the multiple tasks, where d is the number of the multiple tasks:
在所述第一基向量空间中的O个基向量组中选择一个基向量组；Selecting a basis vector group from the O basis vector groups in the first basis vector space;
根据所述一个基向量组中的L task个空域基向量和所述第二基向量空间中的M task个频域基向量，构建所述多个任务中的一个任务对应的CSI样本集，其中，L task，M task是大于1的正整数。 A CSI sample set corresponding to one of the multiple tasks is constructed according to L task spatial domain basis vectors in the one basis vector group and M task frequency domain basis vectors in the second basis vector space, where L task and M task are positive integers greater than 1.
在一些实施例中，所述一个基向量组是在所述O个基向量组中随机选择的。In some embodiments, the one basis vector group is randomly selected from the O basis vector groups.
在一些实施例中，所述L task个空域基向量是在所述一个基向量组中随机选择的； In some embodiments, the L task spatial basis vectors are randomly selected from the one basis vector group;
所述M task个频域基向量是在所述第二基向量空间中的N sb个频域基向量中随机选择的。 The M task frequency domain basis vectors are randomly selected from the N sb frequency domain basis vectors in the second basis vector space.
在一些实施例中，所述L task小于N 1*N 2，所述M task小于N sb。 In some embodiments, the Ltask is smaller than N 1 *N 2 , and the Mtask is smaller than N sb .
在一些实施例中，所述处理单元410还用于：In some embodiments, the processing unit 410 is further configured to:
循环执行如下步骤k次，得到一个任务对应的CSI样本集包括的k个CSI样本，其中，k大于1：The following steps are executed k times in a loop to obtain k CSI samples included in a CSI sample set corresponding to a task, where k is greater than 1:
在所述L task个空域基向量中随机选择L个空域基向量，并将所述L个空域基向量按列排列得到矩阵B，其中，L为正整数； Randomly select L spatial basis vectors from the L task spatial basis vectors, and arrange the L spatial basis vectors in columns to obtain a matrix B, where L is a positive integer;
根据矩阵B构建对角块矩阵W 1＝[B,0；0,B]； Construct a diagonal block matrix W 1 = [B, 0; 0, B] according to the matrix B;
在所述M task个频域基向量中随机选择M个频域基向量，并将所述M个频域基向量按行排列得到矩阵W f，其中，M为正整数； Randomly select M frequency domain basis vectors from the M task frequency domain basis vectors, and arrange the M frequency domain basis vectors in rows to obtain a matrix W f , where M is a positive integer;
根据对角块矩阵W 1，矩阵W f和随机数矩阵W 2，生成一个任务对应的CSI样本集中的一个CSI样本。 According to the diagonal block matrix W 1 , the matrix W f and the random number matrix W 2 , a CSI sample in a CSI sample set corresponding to a task is generated.
在一些实施例中，所述L＜L task，M＜M task。 In some embodiments, L<L task , M<M task .
在一些实施例中，所述随机数矩阵W 2中的元素服从第四分布。 In some embodiments, the elements in the random number matrix W 2 obey a fourth distribution.
在一些实施例中，所述第四分布为复高斯分布或复均匀分布。In some embodiments, the fourth distribution is a complex Gaussian distribution or a complex uniform distribution.
在一些实施例中，所述处理单元410还用于：In some embodiments, the processing unit 410 is further configured to:
将所述对角块矩阵W 1，矩阵W f和随机数矩阵W 2相乘得到第一CSI样本； Multiplying the diagonal block matrix W 1 , the matrix W f and the random number matrix W 2 to obtain a first CSI sample;
将所述第一CSI样本的矩阵中的每一列进行归一化处理，得到目标CSI样本。Each column in the matrix of the first CSI samples is normalized to obtain a target CSI sample.
在一些实施例中，所述第一CSI样本W’＝W 1W 2W f＝[w 1,...,w Nsb]， In some embodiments, the first CSI samples W'=W 1 W 2 W f =[w 1 ,...,w Nsb ],
所述目标CSI样本W＝[w 1/norm(w 1),...,w Nsb/norm(w Nsb)]，其中，norm()表示二范数。 The target CSI sample W=[w 1 /norm(w 1 ), ..., w Nsb /norm(w Nsb )], wherein norm() represents a binary norm.
可选地，在一些实施例中，上述通信单元可以是通信接口或收发器，或者是通信芯片或者片上***的输入输出接口。上述处理单元可以是一个或多个处理器。Optionally, in some embodiments, the communication unit may be a communication interface or a transceiver, or an input/output interface of a communication chip or a system on chip. The processing unit may be one or more processors.
应理解，根据本申请实施例的设备400中的各个单元的上述和其它操作和/或功能分别用于实现图8所示方法200中的相应流程，为了简洁，在此不再赘述。It should be understood that the above and other operations and/or functions of each unit in the device 400 according to the embodiment of the present application are respectively used to implement the corresponding processes in the method 200 shown in Figure 8, and for the sake of brevity, they are not repeated here.
图10是本申请实施例提供的一种通信设备600示意性结构图。图10所示的通信设备600包括处理器610，处理器610可以从存储器中调用并运行计算机程序，以实现本申请实施例中的方法。Fig. 10 is a schematic structural diagram of a communication device 600 provided in an embodiment of the present application. The communication device 600 shown in Fig. 10 includes a processor 610, and the processor 610 can call and run a computer program from a memory to implement the method in the embodiment of the present application.
可选地，如图10所示，通信设备600还可以包括存储器620。其中，处理器610可以从存储器620中调用并运行计算机程序，以实现本申请实施例中的方法。Optionally, as shown in Fig. 10, the communication device 600 may further include a memory 620. The processor 610 may call and run a computer program from the memory 620 to implement the method in the embodiment of the present application.
其中，存储器620可以是独立于处理器610的一个单独的器件，也可以集成在处理器610中。The memory 620 may be a separate device independent of the processor 610 , or may be integrated into the processor 610 .
可选地，如图10所示，通信设备600还可以包括收发器630，处理器610可以控制该收发器630与其他设备进行通信，具体地，可以向其他设备发送信息或数据，或接收其他设备发送的信息或数据。Optionally, as shown in FIG. 10 , the communication device 600 may further include a transceiver 630 , and the processor 610 may control the transceiver 630 to communicate with other devices, specifically, may send information or data to other devices, or receive information or data sent by other devices.
其中，收发器630可以包括发射机和接收机。收发器630还可以进一步包括天线，天线的数量可以为一个或多个。The transceiver 630 may include a transmitter and a receiver. The transceiver 630 may further include an antenna, and the number of the antennas may be one or more.
可选地，该通信设备600具体可为本申请实施例的网络设备，并且该通信设备600可以实现本申请实施例的各个方法中由网络设备实现的相应流程，为了简洁，在此不再赘述。Optionally, the communication device 600 may specifically be a network device of an embodiment of the present application, and the communication device 600 may implement the corresponding processes implemented by the network device in each method of the embodiment of the present application, which will not be described in detail here for the sake of brevity.
可选地，该通信设备600具体可为本申请实施例的移动终端/终端设备，并且该通信设备600可以实现本申请实施例的各个方法中由移动终端/终端设备实现的相应流程，为了简洁，在此不再赘述。Optionally, the communication device 600 may specifically be a mobile terminal/terminal device of an embodiment of the present application, and the communication device 600 may implement the corresponding processes implemented by the mobile terminal/terminal device in each method of the embodiment of the present application, which will not be described in detail here for the sake of brevity.
图11是本申请实施例的芯片的示意性结构图。图11所示的芯片700包括处理器710，处理器710可以从存储器中调用并运行计算机程序，以实现本申请实施例中的方法。Fig. 11 is a schematic structural diagram of a chip according to an embodiment of the present application. The chip 700 shown in Fig. 11 includes a processor 710, and the processor 710 can call and run a computer program from a memory to implement the method according to the embodiment of the present application.
可选地，如图11所示，芯片700还可以包括存储器720。其中，处理器710可以从存储器720中调用并运行计算机程序，以实现本申请实施例中的方法。Optionally, as shown in Fig. 11, the chip 700 may further include a memory 720. The processor 710 may call and run a computer program from the memory 720 to implement the method in the embodiment of the present application.
其中，存储器720可以是独立于处理器710的一个单独的器件，也可以集成在处理器710中。The memory 720 may be a separate device independent of the processor 710 , or may be integrated into the processor 710 .
可选地，该芯片700还可以包括输入接口730。其中，处理器710可以控制该输入接口730与其他设备或芯片进行通信，具体地，可以获取其他设备或芯片发送的信息或数据。Optionally, the chip 700 may further include an input interface 730. The processor 710 may control the input interface 730 to communicate with other devices or chips, and specifically, may obtain information or data sent by other devices or chips.
可选地，该芯片700还可以包括输出接口740。其中，处理器710可以控制该输出接口740与其他设备或芯片进行通信，具体地，可以向其他设备或芯片输出信息或数据。Optionally, the chip 700 may further include an output interface 740. The processor 710 may control the output interface 740 to communicate with other devices or chips, and specifically, may output information or data to other devices or chips.
可选地，该芯片可应用于本申请实施例中的网络设备，并且该芯片可以实现本申请实施例的各个方法中由网络设备实现的相应流程，为了简洁，在此不再赘述。Optionally, the chip can be applied to the network device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the network device in each method of the embodiments of the present application. For the sake of brevity, they will not be repeated here.
可选地，该芯片可应用于本申请实施例中的移动终端/终端设备，并且该芯片可以实现本申请实施例的各个方法中由移动终端/终端设备实现的相应流程，为了简洁，在此不再赘述。Optionally, the chip can be applied to the mobile terminal/terminal device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the mobile terminal/terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.
应理解，本申请实施例提到的芯片还可以称为***级芯片，***芯片，芯片***或片上***芯片等。It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.
应理解，本申请实施例的处理器可能是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方法实施例的各步骤可以通过处理器中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器可以是通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器，处理器读取存储器中的信息，结合其硬件完成上述方法的步骤。It should be understood that the processor of the embodiment of the present application may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method embodiment can be completed by the hardware integrated logic circuit in the processor or the instruction in the form of software. The above processor can be a general processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to perform, or the hardware and software modules in the decoding processor can be combined to perform. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.
可以理解，本申请实施例中的存储器可以是易失性存储器或非易失性存储器，或可包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(Read-Only Memory，ROM)、可编程只读存储器(Programmable ROM，PROM)、可擦除可编程只读存储器(Erasable PROM，EPROM)、电可擦除可编程只读存储器(Electrically EPROM，EEPROM)或闪存。易失性存储器可以是随机存取存储器(Random Access Memory，RAM)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的RAM可用，例如静态随机存取存储器(Static RAM，SRAM)、动态随机存取存储器(Dynamic RAM，DRAM)、同步动态随机存取存储器(Synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(Double Data Rate SDRAM，DDR SDRAM)、增强型同步动态随机存取存储器(Enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(Synchlink DRAM，SLDRAM)和直接内存总线随机存取存储器(Direct Rambus RAM，DR RAM)。应注意，本文描述的***和方法的存储器旨在包括但不限于这些和任意其它适合类型的存储器。It can be understood that the memory in the embodiment of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.
应理解，上述存储器为示例性但不是限制性说明，例如，本申请实施例中的存储器还可以是静态随机存取存储器(static RAM，SRAM)、动态随机存取存储器(dynamic RAM，DRAM)、同步动态随机存取存储器(synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(double data rate SDRAM，DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(synch link DRAM，SLDRAM)以及直接内存总线随机存取存储器(Direct Rambus RAM，DR RAM)等等。也就是说，本申请实施例中的存储器旨在包括但不限于这些和任意其它适合类型的存储器。It should be understood that the above-mentioned memory is exemplary but not restrictive. For example, the memory in the embodiment of the present application may also be static random access memory (static RAM, SRAM), dynamic random access memory (dynamic RAM, DRAM), synchronous dynamic random access memory (synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous link dynamic random access memory (synch link DRAM, SLDRAM) and direct memory bus random access memory (Direct Rambus RAM, DR RAM), etc. That is to say, the memory in the embodiment of the present application is intended to include but not limited to these and any other suitable types of memory.
本申请实施例还提供了一种计算机可读存储介质，用于存储计算机程序。An embodiment of the present application also provides a computer-readable storage medium for storing a computer program.
可选的，该计算机可读存储介质可应用于本申请实施例中的网络设备，并且该计算机程序使得计算机执行本申请实施例的各个方法中由网络设备实现的相应流程，为了简洁，在此不再赘述。Optionally, the computer-readable storage medium can be applied to the network device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.
可选地，该计算机可读存储介质可应用于本申请实施例中的移动终端/终端设备，并且该计算机程序使得计算机执行本申请实施例的各个方法中由移动终端/终端设备实现的相应流程，为了简洁，在此不再赘述。Optionally, the computer-readable storage medium can be applied to the mobile terminal/terminal device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the mobile terminal/terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.
本申请实施例还提供了一种计算机程序产品，包括计算机程序指令。An embodiment of the present application also provides a computer program product, including computer program instructions.
可选的，该计算机程序产品可应用于本申请实施例中的网络设备，并且该计算机程序指令使得计算机执行本申请实施例的各个方法中由网络设备实现的相应流程，为了简洁，在此不再赘述。Optionally, the computer program product can be applied to the network device in the embodiments of the present application, and the computer program instructions enable the computer to execute the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.
可选地，该计算机程序产品可应用于本申请实施例中的移动终端/终端设备，并且该计算机程序指令使得计算机执行本申请实施例的各个方法中由移动终端/终端设备实现的相应流程，为了简洁，在此不再赘述。Optionally, the computer program product can be applied to the mobile terminal/terminal device in the embodiments of the present application, and the computer program instructions enable the computer to execute the corresponding processes implemented by the mobile terminal/terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.
本申请实施例还提供了一种计算机程序。The embodiment of the present application also provides a computer program.
可选的，该计算机程序可应用于本申请实施例中的网络设备，当该计算机程序在计算机上运行时，使得计算机执行本申请实施例的各个方法中由网络设备实现的相应流程，为了简洁，在此不再赘述。Optionally, the computer program can be applied to the network device in the embodiments of the present application. When the computer program runs on a computer, the computer executes the corresponding processes implemented by the network device in the various methods of the embodiments of the present application. For the sake of brevity, they are not described here.
可选地，该计算机程序可应用于本申请实施例中的移动终端/终端设备，当该计算机程序在计算机上运行时，使得计算机执行本申请实施例的各个方法中由移动终端/终端设备实现的相应流程，为了简洁，在此不再赘述。Optionally, the computer program can be applied to the mobile terminal/terminal device in the embodiments of the present application. When the computer program is run on a computer, the computer executes the corresponding processes implemented by the mobile terminal/terminal device in the various methods of the embodiments of the present application. For the sake of brevity, they are not repeated here.
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的***、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
在本申请所提供的几个实施例中，应该理解到，所揭露的***、装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个***，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应所述以权利要求的保护范围为准。The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims (43)

  1. 一种生成样本集的方法，其特征在于，包括：A method for generating a sample set, characterized by comprising:
    构建第一基向量空间和第二基向量空间，所述第一基向量空间包括O个基向量组，每个基向量组包括N 1*N 2个空域基向量，所述第二基向量空间包括N sb个频域基向量，其中，O是正整数，所述N 1为信道状态信息CSI的发射端的第一维度的天线端口数，所述N 2为CSI的发射端的第二维度的天线端口数，N sb表示子带数量； Constructing a first basis vector space and a second basis vector space, wherein the first basis vector space includes O basis vector groups, each basis vector group includes N1 * N2 spatial domain basis vectors, and the second basis vector space includes Nsb frequency domain basis vectors, wherein O is a positive integer, N1 is the number of antenna ports of the first dimension of the transmitting end of the channel state information CSI, N2 is the number of antenna ports of the second dimension of the transmitting end of the CSI, and Nsb represents the number of subbands;
    根据所述第一基向量空间和所述第二基向量空间，构建多个任务中的每个任务对应的CSI样本集，其中，每个任务对应的CSI样本集是基于所述第一基向量空间中的一个基向量组中的部分空域基向量和所述第二基向量空间中的部分频域基向量构建的，所述多个任务分别对应的CSI样本集用于训练第一模型，所述第一模型用于基于目标场景的CSI样本集训练得到第二模型，所述第二模型适配所述目标场景。According to the first basis vector space and the second basis vector space, a CSI sample set corresponding to each task in a plurality of tasks is constructed, wherein the CSI sample set corresponding to each task is constructed based on some spatial domain basis vectors in a basis vector group in the first basis vector space and some frequency domain basis vectors in the second basis vector space, and the CSI sample sets corresponding to the plurality of tasks are respectively used to train a first model, and the first model is used to obtain a second model based on the CSI sample set of a target scene for training, and the second model is adapted to the target scene.
  2. 根据权利要求1所述的方法，其特征在于，所述O个基向量组中的每个基向量组中的N 1*N 2个空域基向量组成的矩阵为酉矩阵，所述N sb个频域基向量组成的矩阵为酉矩阵。 The method according to claim 1 is characterized in that the matrix composed of N 1 *N 2 spatial basis vectors in each basis vector group of the O basis vector groups is a unitary matrix, and the matrix composed of N sb frequency domain basis vectors is a unitary matrix.
  3. 根据权利要求1或2所述的方法，其特征在于，所述构建第一基向量空间，包括：The method according to claim 1 or 2, characterized in that constructing the first basis vector space comprises:
    循环执行如下步骤O次，得到所述O个基向量组中的每个基向量组的空域基向量：The following steps are executed in a loop O times to obtain the spatial basis vector of each basis vector group in the O basis vector groups:
    基于第一分布进行随机采样得到第一矩阵，以及基于第二分布进行随机采样得到第二矩阵，其中，所述第一矩阵为N 1*N 1维度的矩阵，所述第二矩阵为N 2*N 2维度的矩阵； Performing random sampling based on a first distribution to obtain a first matrix, and performing random sampling based on a second distribution to obtain a second matrix, wherein the first matrix is a matrix of N 1 *N 1 dimensions, and the second matrix is a matrix of N 2 *N 2 dimensions;
    确定所述第一矩阵对应的正交矩阵和所述第二矩阵对应的正交矩阵；Determine an orthogonal matrix corresponding to the first matrix and an orthogonal matrix corresponding to the second matrix;
    将所述第一矩阵对应的正交矩阵和所述第二矩阵对应的正交矩阵进行克罗内克积，得到目标矩阵；Performing a Kronecker product on an orthogonal matrix corresponding to the first matrix and an orthogonal matrix corresponding to the second matrix to obtain a target matrix;
    将所述目标矩阵的一列作为所述第一基向量空间中的一个基向量组中的一个空域基向量。A column of the target matrix is used as a spatial basis vector in a basis vector group in the first basis vector space.
  4. 根据权利要求3所述的方法，其特征在于，所述确定所述第一矩阵对应的正交矩阵和所述第二矩阵对应的正交矩阵，包括：The method according to claim 3, characterized in that the determining the orthogonal matrix corresponding to the first matrix and the orthogonal matrix corresponding to the second matrix comprises:
    对所述第一矩阵进行奇异值分解SVD，将得到的左奇异矩阵作为所述第一矩阵对应的正交矩阵；Performing singular value decomposition (SVD) on the first matrix, and using the obtained left singular matrix as the orthogonal matrix corresponding to the first matrix;
    对所述第二矩阵进行SVD，将得到的左奇异矩阵作为所述第二矩阵对应的正交矩阵。Perform SVD on the second matrix, and use the obtained left singular matrix as the orthogonal matrix corresponding to the second matrix.
  5. 根据权利要求3所述的方法，其特征在于，所述确定所述第一矩阵对应的正交矩阵和所述第二矩阵对应的正交矩阵，包括：The method according to claim 3, characterized in that the determining the orthogonal matrix corresponding to the first matrix and the orthogonal matrix corresponding to the second matrix comprises:
    对所述第一矩阵进行施密特正交化，将得到的正交矩阵作为所述第一矩阵对应的正交矩阵；Performing Schmidt orthogonalization on the first matrix, and using the obtained orthogonal matrix as the orthogonal matrix corresponding to the first matrix;
    对所述第二矩阵进行施密特正交化，将得到的正交矩阵作为所述第二矩阵对应的正交矩阵。Perform Schmidt orthogonalization on the second matrix, and use the obtained orthogonal matrix as the orthogonal matrix corresponding to the second matrix.
  6. 根据权利要求3-5中任一项所述的方法，其特征在于，The method according to any one of claims 3 to 5, characterized in that
    所述第一分布为复高斯分布或复均匀分布；The first distribution is a complex Gaussian distribution or a complex uniform distribution;
    所述第二分布为复高斯分布或复均匀分布。The second distribution is a complex Gaussian distribution or a complex uniform distribution.
  7. 根据权利要求6所述的方法，其特征在于，所述构建第二基向量空间，包括：The method according to claim 6, characterized in that constructing the second basis vector space comprises:
    基于第三分布进行随机采样得到第三矩阵，所述第三矩阵为N sb*N sb维度的矩阵； Performing random sampling based on a third distribution to obtain a third matrix, wherein the third matrix is a matrix of N sb *N sb dimensions;
    确定所述第三矩阵对应的正交矩阵；Determine an orthogonal matrix corresponding to the third matrix;
    将所述第三矩阵对应的正交矩阵的一列作为所述第二基向量空间中的一个频域基向量。A column of the orthogonal matrix corresponding to the third matrix is used as a frequency domain basis vector in the second basis vector space.
  8. 根据权利要求7所述的方法，其特征在于，所述确定所述第三矩阵对应的正交矩阵，包括：The method according to claim 7, characterized in that determining the orthogonal matrix corresponding to the third matrix comprises:
    对所述第三矩阵进行SVD，将得到的左奇异矩阵作为所述第三矩阵对应的正交矩阵；或Perform SVD on the third matrix, and use the obtained left singular matrix as the orthogonal matrix corresponding to the third matrix; or
    对所述第三矩阵进行施密特正交化，将得到的正交矩阵作为所述第三矩阵对应的正交矩阵。Perform Schmidt orthogonalization on the third matrix, and use the obtained orthogonal matrix as the orthogonal matrix corresponding to the third matrix.
  9. 根据权利要求7或8所述的方法，其特征在于，The method according to claim 7 or 8, characterized in that
    所述第三分布为复高斯分布或复均匀分布。The third distribution is a complex Gaussian distribution or a complex uniform distribution.
  10. 根据权利要求1-9中任一项所述的方法，其特征在于，所述根据所述第一基向量空间和所述第二基向量空间，构建多个任务中的每个任务对应的CSI样本集，包括：The method according to any one of claims 1 to 9, characterized in that constructing a CSI sample set corresponding to each task in a plurality of tasks according to the first basis vector space and the second basis vector space comprises:
    循环执行如下步骤d次，得到所述多个任务中的每个任务对应的CSI样本集，其中，d为多个任务的个数：The following steps are executed d times in a loop to obtain a CSI sample set corresponding to each task in the multiple tasks, where d is the number of the multiple tasks:
    在所述第一基向量空间中的O个基向量组中选择一个基向量组；Selecting a basis vector group from the O basis vector groups in the first basis vector space;
    根据所述一个基向量组中的L task个空域基向量和所述第二基向量空间中的M task个频域基向量，构建所述多个任务中的一个任务对应的CSI样本集，其中，L task，M task是大于1的正整数。 A CSI sample set corresponding to one of the multiple tasks is constructed according to L task spatial domain basis vectors in the one basis vector group and M task frequency domain basis vectors in the second basis vector space, where L task and M task are positive integers greater than 1.
  11. 根据权利要求10所述的方法，其特征在于，所述一个基向量组是在所述O个基向量组中随机选择的。The method according to claim 10 is characterized in that the one basis vector group is randomly selected from the O basis vector groups.
  12. 根据权利要求10或11所述的方法，其特征在于，The method according to claim 10 or 11, characterized in that
    所述L task个空域基向量是在所述一个基向量组中随机选择的； The L task spatial domain basis vectors are randomly selected from the one basis vector group;
    所述M task个频域基向量是在所述第二基向量空间中的N sb个频域基向量中随机选择的。 The M task frequency domain basis vectors are randomly selected from the N sb frequency domain basis vectors in the second basis vector space.
  13. 根据权利要求10-12中任一项所述的方法，其特征在于，所述L task小于N 1*N 2，所述M task小于N sb。 The method according to any one of claims 10-12, characterized in that the L task is smaller than N 1 *N 2 , and the M task is smaller than N sb .
  14. 根据权利要求10-13中任一项所述的方法，其特征在于，所述根据所述一个基向量组中的L task个空域基向量和所述第二基向量空间中的所述M task个频域基向量，构建所述多个任务中的一个任务对应的CSI样本集，包括： The method according to any one of claims 10 to 13, characterized in that constructing a CSI sample set corresponding to one of the multiple tasks according to the L task spatial domain basis vectors in the one basis vector group and the M task frequency domain basis vectors in the second basis vector space, comprises:
    循环执行如下步骤k次，得到一个任务对应的CSI样本集包括的k个CSI样本，其中，k大于1：The following steps are executed k times in a loop to obtain k CSI samples included in a CSI sample set corresponding to a task, where k is greater than 1:
    在所述L task个空域基向量中随机选择L个空域基向量，并将所述L个空域基向量按列排列得到矩阵B，其中，L为正整数； Randomly select L spatial basis vectors from the L task spatial basis vectors, and arrange the L spatial basis vectors in columns to obtain a matrix B, where L is a positive integer;
    根据矩阵B构建对角块矩阵W 1＝[B,0；0,B]； Construct a diagonal block matrix W 1 = [B, 0; 0, B] according to the matrix B;
    在所述M task个频域基向量中随机选择M个频域基向量，并将所述M个频域基向量按行排列得到矩阵W f，其中，M为正整数； Randomly select M frequency domain basis vectors from the M task frequency domain basis vectors, and arrange the M frequency domain basis vectors in rows to obtain a matrix W f , where M is a positive integer;
    根据对角块矩阵W 1，矩阵W f和随机数矩阵W 2，生成一个任务对应的CSI样本集中的一个CSI样本。 According to the diagonal block matrix W 1 , the matrix W f and the random number matrix W 2 , a CSI sample in a CSI sample set corresponding to a task is generated.
  15. 根据权利要求14所述的方法，其特征在于，所述L＜L task，M＜M task。 The method according to claim 14, characterized in that L＜L task , M＜M task .
  16. 根据权利要求14或15所述的方法，其特征在于，所述随机数矩阵W 2中的元素服从第四分布。 The method according to claim 14 or 15, characterized in that the elements in the random number matrix W2 obey a fourth distribution.
  17. 根据权利要求16所述的方法，其特征在于，所述第四分布为复高斯分布或复均匀分布。The method according to claim 16, characterized in that the fourth distribution is a complex Gaussian distribution or a complex uniform distribution.
  18. 根据权利要求14-17中任一项所述的方法，其特征在于，所述根据对角块矩阵W 1，矩阵W f和随机数矩阵W 2，生成一个任务对应的CSI样本集中的一个CSI样本，包括： The method according to any one of claims 14 to 17, characterized in that generating a CSI sample in a CSI sample set corresponding to a task according to the diagonal block matrix W 1 , the matrix W f and the random number matrix W 2 comprises:
    将所述对角块矩阵W 1，矩阵W f和随机数矩阵W 2相乘得到第一CSI样本； Multiplying the diagonal block matrix W 1 , the matrix W f and the random number matrix W 2 to obtain a first CSI sample;
    将所述第一CSI样本的矩阵中的每一列进行归一化处理，得到目标CSI样本。Each column in the matrix of the first CSI samples is normalized to obtain a target CSI sample.
  19. 根据权利要求18所述的方法，其特征在于，The method according to claim 18, characterized in that
    所述第一CSI样本W’＝W 1W 2W f＝[w 1,...,w Nsb]， The first CSI samples W'=W 1 W 2 W f =[w 1 ,...,w Nsb ],
    所述目标CSI样本W＝[w 1/norm(w 1),...,w Nsb/norm(w Nsb)]，其中，norm()表示二范数。 The target CSI sample W=[w 1 /norm(w 1 ), ..., w Nsb /norm(w Nsb )], wherein norm() represents a binary norm.
  20. 一种生成样本集的设备，其特征在于，包括：A device for generating a sample set, comprising:
    处理单元，用于构建第一基向量空间和第二基向量空间，所述第一基向量空间包括O个基向量组，每个基向量组包括N 1*N 2个空域基向量，所述第二基向量空间包括N sb个频域基向量，其中，O是正整数，所述N 1为信道状态信息CSI的发射端的第一维度的天线端口数，所述N 2为CSI的发射端的第二维度的天线端口数，N sb表示子带数量；以及 a processing unit, configured to construct a first basis vector space and a second basis vector space, wherein the first basis vector space includes O basis vector groups, each basis vector group includes N1 * N2 spatial domain basis vectors, and the second basis vector space includes Nsb frequency domain basis vectors, wherein O is a positive integer, N1 is the number of antenna ports of a first dimension of a transmitting end of channel state information CSI, N2 is the number of antenna ports of a second dimension of a transmitting end of CSI, and Nsb represents the number of subbands; and
    根据所述第一基向量空间和所述第二基向量空间，构建多个任务中的每个任务对应的CSI样本集，其中，每个任务对应的CSI样本集是基于所述第一基向量空间中的一个基向量组中的部分空域基向量和所述第二基向量空间中的部分频域基向量构建的，所述多个任务分别对应的CSI样本集用于训练第一模型，所述第一模型用于基于目标场景的CSI样本集训练得到第二模型，所述第二模型适配所述目标场景。According to the first basis vector space and the second basis vector space, a CSI sample set corresponding to each task in a plurality of tasks is constructed, wherein the CSI sample set corresponding to each task is constructed based on some spatial domain basis vectors in a basis vector group in the first basis vector space and some frequency domain basis vectors in the second basis vector space, and the CSI sample sets corresponding to the plurality of tasks are respectively used to train a first model, and the first model is used to obtain a second model based on the CSI sample set of a target scene for training, and the second model is adapted to the target scene.
  21. 根据权利要求20所述的设备，其特征在于，所述O个基向量组中的每个基向量组中的N 1*N 2个空域基向量组成的矩阵为酉矩阵，所述N sb个频域基向量组成的矩阵为酉矩阵。 The device according to claim 20 is characterized in that the matrix composed of N 1 *N 2 spatial basis vectors in each basis vector group in the O basis vector groups is a unitary matrix, and the matrix composed of N sb frequency domain basis vectors is a unitary matrix.
  22. 根据权利要求20或21所述的设备，其特征在于，所述处理单元还用于：The device according to claim 20 or 21, characterized in that the processing unit is further used for:
    循环执行如下步骤O次，得到所述O个基向量组中的每个基向量组的空域基向量：The following steps are executed in a loop O times to obtain the spatial basis vector of each basis vector group in the O basis vector groups:
    基于第一分布进行随机采样得到第一矩阵，以及基于第二分布进行随机采样得到第二矩阵，其中，所述第一矩阵为N 1*N 1维度的矩阵，所述第二矩阵为N 2*N 2维度的矩阵； Performing random sampling based on a first distribution to obtain a first matrix, and performing random sampling based on a second distribution to obtain a second matrix, wherein the first matrix is a matrix of N 1 *N 1 dimensions, and the second matrix is a matrix of N 2 *N 2 dimensions;
    确定所述第一矩阵对应的正交矩阵和所述第二矩阵对应的正交矩阵；Determine an orthogonal matrix corresponding to the first matrix and an orthogonal matrix corresponding to the second matrix;
    将所述第一矩阵对应的正交矩阵和所述第二矩阵对应的正交矩阵进行克罗内克积，得到目标矩阵；Performing a Kronecker product on an orthogonal matrix corresponding to the first matrix and an orthogonal matrix corresponding to the second matrix to obtain a target matrix;
    将所述目标矩阵的一列作为所述第一基向量空间中的一个基向量组中的一个空域基向量。A column of the target matrix is used as a spatial basis vector in a basis vector group in the first basis vector space.
  23. 根据权利要求22所述的设备，其特征在于，所述处理单元还用于：The device according to claim 22, characterized in that the processing unit is further used for:
    对所述第一矩阵进行奇异值分解SVD，将得到的左奇异矩阵作为所述第一矩阵对应的正交矩阵；Performing singular value decomposition (SVD) on the first matrix, and using the obtained left singular matrix as the orthogonal matrix corresponding to the first matrix;
    对所述第二矩阵进行SVD，将得到的左奇异矩阵作为所述第二矩阵对应的正交矩阵。Perform SVD on the second matrix, and use the obtained left singular matrix as the orthogonal matrix corresponding to the second matrix.
  24. 根据权利要求22所述的设备，其特征在于，所述处理单元还用于：The device according to claim 22, characterized in that the processing unit is further used for:
    对所述第一矩阵进行施密特正交化，将得到的正交矩阵作为所述第一矩阵对应的正交矩阵；Performing Schmidt orthogonalization on the first matrix, and using the obtained orthogonal matrix as the orthogonal matrix corresponding to the first matrix;
    对所述第二矩阵进行施密特正交化，将得到的正交矩阵作为所述第二矩阵对应的正交矩阵。Perform Schmidt orthogonalization on the second matrix, and use the obtained orthogonal matrix as the orthogonal matrix corresponding to the second matrix.
  25. 根据权利要求22-24中任一项所述的设备，其特征在于，The device according to any one of claims 22 to 24, characterized in that
    所述第一分布为复高斯分布或复均匀分布；The first distribution is a complex Gaussian distribution or a complex uniform distribution;
    所述第二分布为复高斯分布或复均匀分布。The second distribution is a complex Gaussian distribution or a complex uniform distribution.
  26. 根据权利要求25所述的设备，其特征在于，所述处理单元还用于：The device according to claim 25, characterized in that the processing unit is further used for:
    基于第三分布进行随机采样得到第三矩阵，所述第三矩阵为N sb*N sb维度的矩阵； Performing random sampling based on a third distribution to obtain a third matrix, wherein the third matrix is a matrix of N sb *N sb dimensions;
    确定所述第三矩阵对应的正交矩阵；Determine an orthogonal matrix corresponding to the third matrix;
    将所述第三矩阵对应的正交矩阵的一列作为所述第二基向量空间中的一个频域基向量。A column of the orthogonal matrix corresponding to the third matrix is used as a frequency domain basis vector in the second basis vector space.
  27. 根据权利要求26所述的设备，其特征在于，所述处理单元还用于：The device according to claim 26, characterized in that the processing unit is further used for:
    对所述第三矩阵进行SVD，将得到的左奇异矩阵作为所述第三矩阵对应的正交矩阵；或Perform SVD on the third matrix, and use the obtained left singular matrix as the orthogonal matrix corresponding to the third matrix; or
    对所述第三矩阵进行施密特正交化，将得到的正交矩阵作为所述第三矩阵对应的正交矩阵。Perform Schmidt orthogonalization on the third matrix, and use the obtained orthogonal matrix as the orthogonal matrix corresponding to the third matrix.
  28. 根据权利要求26或27所述的设备，其特征在于，The device according to claim 26 or 27, characterized in that
    所述第三分布为复高斯分布或复均匀分布。The third distribution is a complex Gaussian distribution or a complex uniform distribution.
  29. 根据权利要求20-28中任一项所述的设备，其特征在于，所述处理单元还用于：The device according to any one of claims 20 to 28, characterized in that the processing unit is further used for:
    循环执行如下步骤d次，得到所述多个任务中的每个任务对应的CSI样本集，其中，d为多个任务的个数：The following steps are executed d times in a loop to obtain a CSI sample set corresponding to each task in the multiple tasks, where d is the number of the multiple tasks:
    在所述第一基向量空间中的O个基向量组中选择一个基向量组；Selecting a basis vector group from the O basis vector groups in the first basis vector space;
    根据所述一个基向量组中的L task个空域基向量和所述第二基向量空间中的M task个频域基向量，构建所述多个任务中的一个任务对应的CSI样本集，其中，L task，M task是大于1的正整数。 A CSI sample set corresponding to one of the multiple tasks is constructed according to L task spatial domain basis vectors in the one basis vector group and M task frequency domain basis vectors in the second basis vector space, where L task and M task are positive integers greater than 1.
  30. 根据权利要求29所述的设备，其特征在于，所述一个基向量组是在所述O个基向量组中随机选择的。The device according to claim 29 is characterized in that the one basis vector group is randomly selected from the O basis vector groups.
  31. 根据权利要求29或30所述的设备，其特征在于，The device according to claim 29 or 30, characterized in that
    所述L task个空域基向量是在所述一个基向量组中随机选择的； The L task spatial domain basis vectors are randomly selected from the one basis vector group;
    所述M task个频域基向量是在所述第二基向量空间中的N sb个频域基向量中随机选择的。 The M task frequency domain basis vectors are randomly selected from the N sb frequency domain basis vectors in the second basis vector space.
  32. 根据权利要求29-31中任一项所述的设备，其特征在于，所述L task小于N 1*N 2，所述M task小于N sb。 The device according to any one of claims 29 to 31, characterized in that the L task is smaller than N 1 *N 2 , and the M task is smaller than N sb .
  33. 根据权利要求29-32中任一项所述的设备，其特征在于，所述处理单元还用于：The device according to any one of claims 29 to 32, characterized in that the processing unit is further used for:
    循环执行如下步骤k次，得到一个任务对应的CSI样本集包括的k个CSI样本，其中，k大于1：The following steps are executed k times in a loop to obtain k CSI samples included in a CSI sample set corresponding to a task, where k is greater than 1:
    在所述L task个空域基向量中随机选择L个空域基向量，并将所述L个空域基向量按列排列得到矩阵B，其中，L为正整数； Randomly select L spatial basis vectors from the L task spatial basis vectors, and arrange the L spatial basis vectors in columns to obtain a matrix B, where L is a positive integer;
    根据矩阵B构建对角块矩阵W 1＝[B,0；0,B]； Construct a diagonal block matrix W 1 = [B, 0; 0, B] according to the matrix B;
    在所述M task个频域基向量中随机选择M个频域基向量，并将所述M个频域基向量按行排列得到矩阵W f，其中，M为正整数； Randomly select M frequency domain basis vectors from the M task frequency domain basis vectors, and arrange the M frequency domain basis vectors in rows to obtain a matrix W f , where M is a positive integer;
    根据对角块矩阵W 1，矩阵W f和随机数矩阵W 2，生成一个任务对应的CSI样本集中的一个CSI样本。 According to the diagonal block matrix W 1 , the matrix W f and the random number matrix W 2 , a CSI sample in a CSI sample set corresponding to a task is generated.
  34. 根据权利要求33所述的设备，其特征在于，L＜L task，M＜M task。 The apparatus according to claim 33, characterized in that L＜L task , M＜M task .
  35. 根据权利要求33或34所述的设备，其特征在于，所述随机数矩阵W 2中的元素服从第四分布。 The device according to claim 33 or 34 is characterized in that the elements in the random number matrix W2 obey a fourth distribution.
  36. 根据权利要求35所述的设备，其特征在于，所述第四分布为复高斯分布或复均匀分布。The device according to claim 35 is characterized in that the fourth distribution is a complex Gaussian distribution or a complex uniform distribution.
  37. 根据权利要求34-36中任一项所述的设备，其特征在于，所述处理单元还用于：The device according to any one of claims 34 to 36, characterized in that the processing unit is further used for:
    将所述对角块矩阵W 1，矩阵W f和随机数矩阵W 2相乘得到第一CSI样本； Multiplying the diagonal block matrix W 1 , the matrix W f and the random number matrix W 2 to obtain a first CSI sample;
    将所述第一CSI样本的矩阵中的每一列进行归一化处理，得到目标CSI样本。Each column in the matrix of the first CSI samples is normalized to obtain a target CSI sample.
  38. 根据权利要求37所述的设备，其特征在于，The device according to claim 37, characterized in that
    所述第一CSI样本W’＝W 1W 2W f＝[w 1,...,w Nsb]， The first CSI samples W'=W 1 W 2 W f =[w 1 ,...,w Nsb ],
    所述目标CSI样本W＝[w 1/norm(w 1),...,w Nsb/norm(w Nsb)]，其中，norm()表示二范数。 The target CSI sample W=[w 1 /norm(w 1 ), ..., w Nsb /norm(w Nsb )], wherein norm() represents a binary norm.
  39. 一种生成样本集的设备，其特征在于，包括：处理器和存储器，该存储器用于存储计算机程序，所述处理器用于调用并运行所述存储器中存储的计算机程序，执行如权利要求1至18中任一项所述的设备。A device for generating a sample set, characterized in that it comprises: a processor and a memory, the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the device according to any one of claims 1 to 18.
  40. 一种芯片，其特征在于，包括：处理器，用于从存储器中调用并运行计算机程序，使得安装有所述芯片的设备执行如权利要求1至18中任一项所述的方法。A chip, characterized in that it comprises: a processor, used to call and run a computer program from a memory, so that a device equipped with the chip executes the method as described in any one of claims 1 to 18.
  41. 一种计算机可读存储介质，其特征在于，用于存储计算机程序，所述计算机程序使得计算机执行如权利要求1至18中任一项所述的方法。A computer-readable storage medium, characterized in that it is used to store a computer program, wherein the computer program enables a computer to execute the method according to any one of claims 1 to 18.
  42. 一种计算机程序产品，其特征在于，包括计算机程序指令，该计算机程序指令使得计算机执行如权利要求1至18中任一项所述的方法。A computer program product, characterized in that it comprises computer program instructions, wherein the computer program instructions enable a computer to execute the method according to any one of claims 1 to 18.
  43. 一种计算机程序，其特征在于，所述计算机程序使得计算机执行如权利要求1至18中任一项所述的方法。A computer program, characterized in that the computer program enables a computer to execute the method according to any one of claims 1 to 18.
PCT/CN2022/130674 2022-11-08 2022-11-08 Sample set generation method and device WO2024098259A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/130674 WO2024098259A1 (en) 2022-11-08 2022-11-08 Sample set generation method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/130674 WO2024098259A1 (en) 2022-11-08 2022-11-08 Sample set generation method and device

Publications (1)

Publication Number Publication Date
WO2024098259A1 true WO2024098259A1 (en) 2024-05-16

Family

ID=91031775

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/130674 WO2024098259A1 (en) 2022-11-08 2022-11-08 Sample set generation method and device

Country Status (1)

Country Link
WO (1) WO2024098259A1 (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112152741A (en) * 2019-06-28 2020-12-29 华为技术有限公司 Channel model training method and device
WO2021102917A1 (en) * 2019-11-29 2021-06-03 Nokia Shanghai Bell Co., Ltd. Feedback of channel state information
CN114557073A (en) * 2019-11-29 2022-05-27 中兴通讯股份有限公司 Method for wireless channel reference signal transmission and channel state information feedback
CN114616762A (en) * 2019-10-25 2022-06-10 Oppo广东移动通信有限公司 Method and apparatus for transmitting channel state information

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112152741A (en) * 2019-06-28 2020-12-29 华为技术有限公司 Channel model training method and device
CN114616762A (en) * 2019-10-25 2022-06-10 Oppo广东移动通信有限公司 Method and apparatus for transmitting channel state information
WO2021102917A1 (en) * 2019-11-29 2021-06-03 Nokia Shanghai Bell Co., Ltd. Feedback of channel state information
CN114557073A (en) * 2019-11-29 2022-05-27 中兴通讯股份有限公司 Method for wireless channel reference signal transmission and channel state information feedback

Similar Documents

Publication Publication Date Title
Wang et al. Cost-effective resource allocation in C-RAN with mobile cloud
CN107210783A (en) The system and method for carrying out joint MIMO transmission and compression using cooperating relay to reduce interference
EP4243492A1 (en) Data transmission method and apparatus
WO2024098259A1 (en) Sample set generation method and device
WO2022217506A1 (en) Channel information feedback method, sending end device, and receiving end device
WO2022236785A1 (en) Channel information feedback method, receiving end device, and transmitting end device
WO2023123062A1 (en) Quality evaluation method for virtual channel sample, and device
WO2024108356A1 (en) Csi feedback method, transmitter device and receiver device
WO2024011456A1 (en) Data processing method and apparatus, communication method and apparatus, and terminal device and network device
EP4398527A1 (en) Model processing method, electronic device, network device, and terminal device
WO2023004638A1 (en) Channel information feedback methods, transmitting end devices, and receiving end devices
WO2024077621A1 (en) Channel information feedback method, transmitting end device, and receiving end device
WO2024020793A1 (en) Channel state information (csi) feedback method, terminal device and network device
WO2023070675A1 (en) Data processing method and apparatus
WO2024065696A1 (en) Wireless communication method, terminal device and network device
WO2023092310A1 (en) Information processing method, model generation method, and devices
Sande et al. Fast convergence for efficient beamforming in massive MIMO heterogeneous networks
WO2022222116A1 (en) Channel recovery method and receiving end device
WO2023115254A1 (en) Data processing method and device
WO2024044881A1 (en) Data processing method, training method and related apparatus
WO2022267633A1 (en) Information transmission method and apparatus
WO2023092307A1 (en) Communication method, model training method, and device
WO2024130739A1 (en) Wireless communication method and device
WO2023004563A1 (en) Method for obtaining reference signal and communication devices
WO2024138527A1 (en) Wireless communication methods, terminal devices and network devices

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22964734

Country of ref document: EP

Kind code of ref document: A1