WO2024120445A1 - 模型输入信息的确定方法、装置、设备、***及存储介质 - Google Patents

模型输入信息的确定方法、装置、设备、***及存储介质 Download PDF

Info

Publication number
WO2024120445A1
WO2024120445A1 PCT/CN2023/136808 CN2023136808W WO2024120445A1 WO 2024120445 A1 WO2024120445 A1 WO 2024120445A1 CN 2023136808 W CN2023136808 W CN 2023136808W WO 2024120445 A1 WO2024120445 A1 WO 2024120445A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
model
channel measurement
identification information
trp
Prior art date
Application number
PCT/CN2023/136808
Other languages
English (en)
French (fr)
Inventor
贾承璐
杨昂
Original Assignee
维沃移动通信有限公司
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 维沃移动通信有限公司 filed Critical 维沃移动通信有限公司
Publication of WO2024120445A1 publication Critical patent/WO2024120445A1/zh

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
    • H04W16/22—Traffic simulation tools or models
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/18—Information format or content conversion, e.g. adaptation by the network of the transmitted or received information for the purpose of wireless delivery to users or terminals

Definitions

  • the present application belongs to the field of communication technology, and specifically relates to a method, device, equipment, system and storage medium for determining model input information.
  • AI Artificial Intelligence
  • AI models such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc.
  • functions such as reasoning and prediction (such as channel prediction or terminal positioning, etc.) can be realized.
  • the input information of the AI models will affect the performance of the AI models (such as model accuracy), so how to constrain or determine the input information of the AI models is an urgent problem to be solved.
  • the embodiments of the present application provide a method, device, equipment, system and storage medium for determining model input information, which can solve the problem of how to constrain or determine the input information of an AI model.
  • a method for determining model input information comprising: a user equipment (UE) receiving model auxiliary information from a network side device, the model auxiliary information being used by the UE to determine input information of an AI model; wherein the model auxiliary information comprises at least one of the following: identification information of N transmission reception points (TRP) associated with the AI model, identification information of N positioning reference signals (PRS) associated with the AI model, identification information of N PRS resource sets associated with the AI model, and location information of N TRPs associated with the AI model; and N is a positive integer.
  • TRP transmission reception points
  • PRS N positioning reference signals
  • a device for determining model input information which is applied to a UE, and the device for determining model input information includes: a receiving module.
  • the receiving module is used to receive model auxiliary information from a network side device, and the model auxiliary information is used by the UE to determine the input information of the AI model; wherein the model auxiliary information includes at least one of the following: N TRP identification information associated with the AI model, N PRS identification information associated with the AI model, N PRS resource set identification information associated with the AI model, and N TRP location information associated with the AI model; N is a positive integer.
  • a method for determining model input information comprising: a network side device
  • the UE sends model auxiliary information, which is used by the UE to determine the input information of the AI model; wherein the model auxiliary information includes at least one of the following: N TRP identification information associated with the AI model, N PRS identification information associated with the AI model, N PRS resource set identification information associated with the AI model, and N TRP location information associated with the AI model; N is a positive integer.
  • a device for determining model input information which is applied to a network side device, and the device for determining model input information includes: a sending module.
  • the sending module is used to send model auxiliary information to the UE, and the model auxiliary information is used by the UE to determine the input information of the AI model;
  • the model auxiliary information includes at least one of the following: N TRP identification information associated with the AI model, N PRS identification information associated with the AI model, N PRS resource set identification information associated with the AI model, and N TRP location information associated with the AI model; N is a positive integer.
  • a UE which includes a processor and a memory, wherein the memory stores a program or instruction that can be executed on the processor, and when the program or instruction is executed by the processor, the steps of the method described in the first aspect are implemented.
  • a UE comprising a processor and a communication interface, wherein the communication interface is used to receive model auxiliary information from a network side device, and the model auxiliary information is used by the UE to determine the input information of the AI model; wherein the model auxiliary information includes at least one of the following: N TRP identification information associated with the AI model, N PRS identification information associated with the AI model, N PRS resource set identification information associated with the AI model, and N TRP location information associated with the AI model; N is a positive integer.
  • a network side device which includes a processor and a memory, wherein the memory stores programs or instructions that can be run on the processor, and when the program or instructions are executed by the processor, the steps of the method described in the third aspect are implemented.
  • a network side device comprising a processor and a communication interface, wherein the communication interface is used to send model auxiliary information to a UE, and the model auxiliary information is used by the UE to determine input information of an AI model; wherein the model auxiliary information comprises at least one of the following: N TRP identification information associated with the AI model, N PRS identification information associated with the AI model, N PRS resource set identification information associated with the AI model, and N TRP location information associated with the AI model; N is a positive integer.
  • a communication system including: a UE and a network side device, wherein the UE can be used to execute the steps of the method for determining the model input information as described in the first aspect, and the network side device can be used to execute the steps of the method for determining the model input information as described in the third aspect.
  • a readable storage medium on which a program or instruction is stored.
  • the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented, or the steps of the method described in the third aspect are implemented.
  • a chip comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instruction to implement the method described in the first aspect, or to implement the method described in the third aspect.
  • a computer program/program product is provided, wherein the computer program/program product is stored in a storage medium, and the computer program/program product is executed by at least one processor to implement the steps of the method for determining the model input information as described in the first aspect, or to implement the steps of the method for determining the model input information as described in the third aspect.
  • the UE may receive model auxiliary information from a network-side device to determine the input information of the AI model, and the model auxiliary information includes at least one of the following: N TRP identification information associated with the AI model, N PRS identification information, N PRS resource set identification information, and N TRP location information.
  • the UE can obtain model auxiliary information from the network-side device, that is, some auxiliary information such as TRP information and/or PRS information associated with the AI model, to determine the input information of the AI model based on these auxiliary information, that is, the input information of the AI model can be accurately determined through the model auxiliary information, so that when the AI model is applied, the function of the model (such as channel prediction or terminal positioning, etc.) can be accurately implemented based on the input information of the AI model, thereby improving the performance of the AI model (such as model accuracy).
  • some auxiliary information such as TRP information and/or PRS information associated with the AI model
  • FIG1 is a schematic diagram of the architecture of a wireless communication system provided in an embodiment of the present application.
  • FIG2 is a schematic diagram of the structure of a neural network provided by the related art
  • FIG3 is a schematic diagram of a neuron structure provided by the related art
  • FIG4 is a flowchart of a method for determining model input information provided by an embodiment of the present application.
  • FIG5 is a second flowchart of a method for determining model input information provided by an embodiment of the present application.
  • FIG6 is a flowchart of a method for determining model input information provided by an embodiment of the present application.
  • FIG7 is a schematic diagram of the type and format of input information of an AI model provided in an embodiment of the present application.
  • FIG8 is a schematic diagram of a structure of a device for determining model input information provided by an embodiment of the present application.
  • FIG9 is a second structural diagram of a device for determining model input information provided in an embodiment of the present application.
  • FIG10 is a third structural diagram of a device for determining model input information provided in an embodiment of the present application.
  • FIG11 is a schematic diagram of the hardware structure of a communication device provided in an embodiment of the present application.
  • FIG12 is a schematic diagram of a hardware structure of a UE provided in an embodiment of the present application.
  • FIG13 is a schematic diagram of the hardware structure of a network-side device provided in an embodiment of the present application.
  • first, second, etc. in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable under appropriate circumstances, so that the embodiments of this application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first” and “second” are generally of the same type, and do not limit the number of objects.
  • the first object can be one, or it can be two.
  • “and/or” means at least one of the connected objects, and the character “/” generally means that the objects connected before and after are in an “or” relationship.
  • LTE Long Term Evolution
  • LTE-A Long Term Evolution
  • CDMA Code Division Multiple Access
  • TDMA Time Division Multiple Access
  • FDMA Frequency Division Multiple Access
  • OFDMA Orthogonal Frequency Division Multiple Access
  • SC-FDMA Single-carrier Frequency Division Multiple Access
  • NR new radio
  • FIG1 shows a block diagram of a wireless communication system applicable to an embodiment of the present application.
  • the wireless communication system includes a UE 11 and a network side device 12.
  • UE 11 can be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer) or a notebook computer, a personal digital assistant (PDA), a handheld computer, a netbook, an ultra-mobile personal computer (UMPC), a mobile Internet device (Mobile Internet Device, MID), augmented reality (augmented reality, AR)/virtual reality (virtual reality, VR) equipment, a robot, a wearable device (Wearable Device), a vehicle-mounted device (VUE), a pedestrian terminal (PUE), a smart home (home appliances with wireless communication functions, such as refrigerators, televisions, washing machines or furniture, etc.), a game console, a personal computer (personal computer, PC), a teller machine or a self-service machine and other terminal side devices, and the wearable devices include: smart watches, smart bracelets, smart
  • the network side device 12 may include an access network device or a core network device, wherein the access network device 12 may also be referred to as a radio access network device, a radio access network (RAN), a radio access network function or a radio access network unit.
  • the access network device 12 may include a base station, a WLAN access point or a WiFi node, etc.
  • the base station may be referred to as a node B, an evolved node B (eNB), an access point, a base transceiver station (BTS), a radio base station, a radio transceiver, a basic service set (BSS), an extended service set (ESS), a home node B, a home evolved node B, a transmitting and receiving point (TRP) or some other appropriate term in the field, as long as the same technical effect is achieved, the base station is not limited to a specific technical vocabulary, it should be noted that in the embodiments of the present application, only the base station in the NR system is used as an example for introduction, and the specific type of the base station is not limited.
  • AI integrates artificial intelligence into wireless communication networks, significantly improving technical indicators such as throughput, latency, and user capacity. It is an important task for future wireless communication networks.
  • AI modules such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc. The embodiments of this application are described using neural networks as an example, but the specific type of AI modules is not limited.
  • the neural network includes an input layer, a hidden layer and an output layer, X1, X2, ..., Xn are inputs, and Y is output.
  • the neural network is composed of neurons, as shown in Figure 3, which is a schematic diagram of neurons.
  • a 1 , a 2 , ... a K are inputs
  • w is the weight (multiplicative coefficient)
  • b is the bias (additive coefficient)
  • z a 1 w 1 + ... + a k w k + ... + a K w K + b
  • ⁇ (z) is the activation function.
  • the activation function includes Sigmoid, tanh, ReLU (Rectified Linear Unit, linear rectification function, rectified linear unit), etc.
  • the parameters of the neural network are optimized using a gradient optimization algorithm.
  • the gradient optimization algorithm is a type of algorithm that minimizes or maximizes an objective function (also called a loss function), which is a mathematical combination of model parameters and data.
  • an objective function also called a loss function
  • a neural network model f(.) can be constructed. With the model, the predicted output f(x) can be obtained based on the input x, and the difference between the predicted value and the true value (f(x)-Y) can be calculated. This is the loss function. Find the appropriate W,b to minimize the value of the above loss function. The smaller the loss value, the closer the model is to the actual situation.
  • the most common optimization algorithm currently used is based on the BP (error Back Propagation) algorithm.
  • the basic idea of the BP algorithm is that the learning process consists of two processes: forward propagation of the signal and back propagation of the error.
  • the input sample is transmitted from the input layer, processed by each hidden layer layer by layer, and then transmitted to the output layer. If the actual output of the output layer does not match the expected output, the error back propagation stage is entered.
  • Error back propagation is to propagate the output error layer by layer through the hidden layer to the input layer in some form, and distribute the error to all units in each layer, so as to obtain the error signal of each layer unit, and this error signal is used as the basis for correcting the weights of each unit.
  • This process of adjusting the weights of each layer of the signal forward propagation and error back propagation is repeated over and over again.
  • the process of continuous adjustment of weights is the learning and training process of the network. This process continues until the error of the network output is reduced to an acceptable level, or until the pre-set number of learning times is reached.
  • the input information of the AI model will affect the performance of the AI model (such as model accuracy). Therefore, how to constrain or determine the input information of the AI model is an urgent problem to be solved.
  • the UE may receive model auxiliary information from the network side device to determine the input of the AI model.
  • Input information the model auxiliary information includes at least one of the following: N TRP identification information associated with the AI model, N PRS identification information, N PRS resource set identification information, and N TRP location information.
  • the UE can obtain model auxiliary information from the network side device, that is, some auxiliary information such as TRP information and/or PRS information associated with the AI model, to determine the input information of the AI model based on these auxiliary information, that is, the input information of the AI model can be accurately determined through the model auxiliary information, so that when the AI model is applied, the function of the model (such as channel prediction or terminal positioning, etc.) can be accurately implemented based on the input information of the AI model, thereby improving the performance of the AI model (such as model accuracy).
  • some auxiliary information such as TRP information and/or PRS information associated with the AI model
  • the present application embodiment provides a method for determining model input information
  • Figure 4 shows a flow chart of a method for determining model input information provided by the present application embodiment.
  • the method for determining model input information provided by the present application embodiment may include the following steps 201 and 202.
  • Step 201 The network side device sends model auxiliary information to the UE.
  • Step 202 The UE receives model auxiliary information from a network-side device.
  • the above-mentioned model auxiliary information is used by the UE to determine the input information of the AI model.
  • the above-mentioned model auxiliary information includes at least one of the following: N TRP identification information associated with the AI model, N PRS identification information associated with the AI model, N PRS resource set identification information associated with the AI model, and N TRP location information associated with the AI model.
  • N is a positive integer.
  • the above-mentioned AI model is a single-station model
  • the input information of the above-mentioned AI model includes information of a single TRP, that is, the input information of the AI model includes relevant information between the UE and one of the above-mentioned N TRPs.
  • the input information of the above-mentioned AI model includes channel measurement information and model auxiliary information (for example, one TRP identification information among the above-mentioned N TRP identification information).
  • the output information of the above-mentioned AI model is positioning information, which may include at least one of the following: time of arrival (TOA), angle of arrival (AOA), angle of departure (AOD), time difference of arrival (TDOA), reference signal time difference (RSTD), location coordinates, etc.
  • TOA time of arrival
  • AOA angle of arrival
  • AOD angle of departure
  • TDOA time difference of arrival
  • RSTD reference signal time difference
  • An embodiment of the present application provides a method for determining model input information, and a UE can receive model auxiliary information from a network-side device to determine the input information of an AI model, and the model auxiliary information includes at least one of the following: N TRP identification information associated with the AI model, N PRS identification information, N PRS resource set identification information, and N TRP location information.
  • the UE can obtain model auxiliary information from the network-side device, that is, some auxiliary information such as TRP information and/or PRS information associated with the AI model, to determine the input information of the AI model based on the auxiliary information, that is, the input information of the AI model can be accurately determined through the model auxiliary information, so that when the AI model is applied, the function of the model (such as channel prediction or terminal positioning, etc.) can be accurately implemented based on the input information of the AI model, thereby improving the performance of the AI model (such as model accuracy).
  • some auxiliary information such as TRP information and/or PRS information associated with the AI model
  • the method for determining the model input information provided in the embodiment of the present application also includes the following steps 301 to 303.
  • Step 301 The network side device sends first indication information to the UE.
  • Step 302 The UE receives first indication information from a network side device.
  • the above-mentioned first indication information is used to indicate any one of the following: an encoding method of model auxiliary information, a mapping relationship between model auxiliary information and codewords, and not encoding the model auxiliary information.
  • the encoding method of the above-mentioned model auxiliary information includes at least one of the following: one-hot encoding or binary encoding for each TRP identification information, one-hot encoding or binary encoding for each PRS identification information, one-hot encoding or binary encoding for each PRS resource set identification information, and one-hot encoding or binary encoding for each TRP location information.
  • a TRP identification information for each TRP identification information, includes at least one character, and the at least one character can be sorted in order from small to large or from large to small, and then the TRP identification information is uniquely encoded.
  • a PRS identification information for each PRS identification information, includes at least one character, and the at least one character can be sorted in order from small to large or from large to small, and then the PRS identification information is one-hot encoded.
  • a PRS resource set identification information includes at least one character, and the at least one character can be sorted in order from small to large or from large to small, and then the PRS resource set identification information is one-hot encoded.
  • each TRP location information can be sorted in order from small to large or from large to small according to the distance from each TRP to the reference TRP (or the distance, position and/or direction of the TRP relative to the UE), and then each TRP location information can be uniquely encoded.
  • the mapping relationship between the above-mentioned model auxiliary information and the codeword includes at least one of the following: a mapping relationship between each TRP identification information and a codeword, a mapping relationship between each PRS identification information and a codeword, a mapping relationship between each PRS resource set identification information and a codeword, and a mapping relationship between each TRP position information and a codeword.
  • Step 303 The UE determines input information of the AI model based on the model auxiliary information and the first indication information.
  • the input information of the above-mentioned AI model is determined by the UE based on the model auxiliary information and the first indication information. It can be understood that in one case, when the above-mentioned first indication information indicates the encoding method of the model auxiliary information, the UE can adopt the encoding method indicated by the first indication information to encode the above-mentioned model auxiliary information, and use the encoded model auxiliary information as the input information of the above-mentioned AI model.
  • the UE can use the codeword corresponding to the above-mentioned model auxiliary information in the mapping relationship as the input information of the above-mentioned AI model according to the mapping relationship indicated by the first indication information.
  • the TRP identification information includes TRP1, TRP2 and TRP3.
  • TRP1 has the same Mapping relationship
  • TRP2 has a mapping relationship with codeword 00010
  • TRP3 has a mapping relationship with codeword 00100. If the above-mentioned model auxiliary information includes N TRP identification information associated with the AI model as TRP2, then the UE can use the codeword 00010 corresponding to TRP2 as input information of the AI model.
  • the UE may not encode the model auxiliary information, but directly use the model auxiliary information as the input information of the AI model.
  • the embodiment of the present application does not limit the execution order of the above steps 301-302 and steps 201-202.
  • the above steps 201-202 may be executed first, and then the above steps 301-302; or, the above steps 301-302 may be executed first, and then the above steps 201-202; or, the above steps 201-202 and steps 301-302 may be executed simultaneously.
  • the above FIG. 5 is only used as an example to illustrate the method for determining the model input information.
  • the UE can obtain the first indication information from the network side device, which indicates the encoding method of the model auxiliary information, the mapping relationship between the model auxiliary information and the codeword, or whether the model auxiliary information is not encoded.
  • the UE can flexibly determine the model auxiliary information (i.e., the encoded model auxiliary information, the codeword corresponding to the model auxiliary information, and the non-encoded model auxiliary information) as the input information of the AI model according to the method indicated by the first indication information, thereby improving the performance of the AI model.
  • the input information of the above-mentioned AI model includes channel measurement information and model auxiliary information.
  • the above-mentioned channel measurement information includes at least one of the following: time domain channel impulse response (Channel Impulse Response, CIR), frequency domain channel impulse response (Channel Frequency Response, CFR), and time delay power spectrum (Power Delay Profile, PDP).
  • CIR time domain channel impulse response
  • CFR frequency domain channel impulse response
  • PDP time delay power spectrum
  • the method for determining the model input information provided in the embodiment of the present application further includes the following steps 401 to 403 .
  • Step 401 The network side device sends second indication information to the UE.
  • Step 402 The UE receives second indication information from the network side device.
  • the above-mentioned second indication information is used to indicate the type and/or format of the input information of the AI model.
  • the type of input information of the above AI model includes at least one of the following:
  • Channel measurement information and TRP identification information associated with the channel measurement information
  • Channel measurement information and PRS identification information associated with the channel measurement information
  • Channel measurement information and PRS resource set identification information associated with the channel measurement information
  • Channel measurement information and TRP location information associated with the channel measurement information.
  • the format of the input information of the above-mentioned AI model includes an arrangement of the input information of the AI model, and the arrangement includes at least one of the following:
  • the channel measurement information is in front, and the TRP identification information associated with the channel measurement information is in the back;
  • the channel measurement information is at the back, and the TRP identification information associated with the channel measurement information is at the front;
  • the channel measurement information is in front, and the PRS identification information associated with the channel measurement information is in the back;
  • the channel measurement information is at the back, and the PRS identification information associated with the channel measurement information is at the front;
  • the channel measurement information is in the front, and the PRS resource set identification information associated with the channel measurement information is in the back;
  • the channel measurement information is at the back, and the PRS resource set identification information associated with the channel measurement information is at the front;
  • the channel measurement information comes first, and the TRP location information associated with the channel measurement information comes second;
  • the channel measurement information comes at the end, and the TRP location information associated with the channel measurement information comes at the front.
  • the format of the input information of the above-mentioned AI model includes the size of the input information of the AI model, and the size includes at least one of the following:
  • the size of the channel measurement information includes: the dimension of the channel measurement information and the length of each dimension;
  • the size of the TRP identification information associated with the channel measurement information includes: the dimension of the TRP identification information associated with the channel measurement information, and the length of each dimension;
  • the size of the PRS identification information associated with the channel measurement information includes: the dimension of the PRS identification information associated with the channel measurement information, and the length of each dimension;
  • the size of the PRS resource set identification information associated with the channel measurement information includes: the dimension of the PRS resource set identification information associated with the channel measurement information, and the length of each dimension;
  • the size of the TRP position information associated with the channel measurement information includes: the dimension of the TRP position information associated with the channel measurement information, and the length of each dimension.
  • the dimension of the channel measurement information refers to the number of dimensions of the channel measurement information
  • the length of each dimension refers to the length of the information of the channel measurement information in each dimension.
  • the channel measurement information is CIR
  • CIR includes two dimensions.
  • the first dimension can represent the number of sampling points in the time domain
  • the second dimension represents the real part and imaginary part of the corresponding sampling point.
  • the type and format of the input information of the AI model are TRP encoding information and the channel impulse response between the UE and the TRP, wherein the length of the TRP encoding information is less than the length of the channel impulse response.
  • the type and format of the input information of the AI model are TRP encoding information and the channel impulse response between the UE and the TRP, wherein the channel impulse response comes first and the TRP encoding information comes later.
  • Step 403 The UE determines input information of the AI model based on the model auxiliary information and the second indication information.
  • the input information of the above-mentioned AI model is determined by the UE based on the model auxiliary information and the second indication information. It can be understood that the UE can determine that the type of input information of the AI model includes channel measurement information and model auxiliary information, as well as the arrangement and/or size of the channel measurement information and the model auxiliary information based on the model auxiliary information and the second indication information.
  • the embodiment of the present application does not limit the execution order of the above steps 401-402 and steps 201-202.
  • the above steps 201-202 may be executed first, and then the above steps 401-402; or, the above steps 401-402 may be executed first, and then the above steps 201-202; or, the above steps 201-202 and steps 401-402 may be executed simultaneously.
  • the above FIG. 6 is only used as an example to illustrate the method for determining the model input information.
  • the UE can obtain the second indication information from the network side device, that is, the input information indicating the AI model.
  • the type and/or format of the information can be determined by the UE, so that the UE can flexibly and accurately determine the input information of the AI model according to the type and/or format indicated by the second indication information, thereby improving the performance of the AI model.
  • the method for determining model input information provided in the embodiment of the present application can also be performed by a device for determining model input information.
  • the method for determining model input information performed by a UE and a network side device is used as an example to illustrate the device for determining model input information provided in the embodiment of the present application.
  • Fig. 8 shows a possible structural diagram of a device for determining model input information involved in an embodiment of the present application, and the device for determining model input information is applied to a UE.
  • the device 80 for determining model input information may include: a receiving module 81 .
  • the receiving module 81 is used to receive model auxiliary information from the network side device, and the model auxiliary information is used by the UE to determine the input information of the AI model; wherein the model auxiliary information includes at least one of the following: N TRP identification information associated with the AI model, N PRS identification information associated with the AI model, N PRS resource set identification information associated with the AI model, and N TRP location information associated with the AI model; N is a positive integer.
  • An embodiment of the present application provides a device for determining model input information.
  • the device for determining model input information can obtain model auxiliary information from a network side device, that is, some auxiliary information such as TRP information and/or PRS information associated with the AI model, to determine the input information of the AI model based on the auxiliary information, that is, the input information of the AI model can be accurately determined through the model auxiliary information, so that when the AI model is applied, the function of the model (such as channel prediction or terminal positioning, etc.) can be accurately implemented based on the input information of the AI model, thereby improving the performance of the AI model (such as model accuracy).
  • auxiliary information such as TRP information and/or PRS information associated with the AI model
  • the device 80 for determining the model input information further includes: a determination module 82.
  • the above-mentioned receiving module 81 is also used to receive a first indication information from a network side device, and the first indication information is used to indicate any of the following: an encoding method of the model auxiliary information, a mapping relationship between the model auxiliary information and the codeword, and no encoding of the model auxiliary information.
  • the determination module 82 is used to determine the input information of the AI model based on the model auxiliary information and the first indication information received by the receiving module 81.
  • the encoding method of the above-mentioned model auxiliary information includes at least one of the following: one-hot encoding or binary encoding of each TRP identification information, one-hot encoding or binary encoding of each PRS identification information, one-hot encoding or binary encoding of each PRS resource set identification information, and one-hot encoding or binary encoding of each TRP location information.
  • the mapping relationship between the above-mentioned model auxiliary information and the codeword includes at least one of the following: a mapping relationship between each TRP identification information and a codeword, a mapping relationship between each PRS identification information and a codeword, a mapping relationship between each PRS resource set identification information and a codeword, and a mapping relationship between each TRP position information and a codeword.
  • the input information of the above-mentioned AI model includes channel measurement information and model auxiliary information.
  • the device 80 for determining the model input information further includes: a determination module 82.
  • the above-mentioned receiving module 81 is also used to receive second indication information from the network side device, and the second indication information is used to indicate the type and/or format of the input information of the AI model.
  • the determination module 82 is used to determine the input information of the AI model based on the model auxiliary information and the second indication information received by the receiving module 81.
  • the type of input information of the AI model includes at least one of the following:
  • Channel measurement information and TRP identification information associated with the channel measurement information
  • Channel measurement information and PRS identification information associated with the channel measurement information
  • Channel measurement information and PRS resource set identification information associated with the channel measurement information
  • Channel measurement information and TRP location information associated with the channel measurement information.
  • the format of the input information of the AI model includes an arrangement of the input information of the AI model, and the arrangement includes at least one of the following:
  • the channel measurement information is in front, and the TRP identification information associated with the channel measurement information is in the back;
  • the channel measurement information is at the back, and the TRP identification information associated with the channel measurement information is at the front;
  • the channel measurement information is in front, and the PRS identification information associated with the channel measurement information is in the back;
  • the channel measurement information is at the back, and the PRS identification information associated with the channel measurement information is at the front;
  • the channel measurement information is in the front, and the PRS resource set identification information associated with the channel measurement information is in the back;
  • the channel measurement information is at the back, and the PRS resource set identification information associated with the channel measurement information is at the front;
  • the channel measurement information comes first, and the TRP location information associated with the channel measurement information comes second;
  • the channel measurement information comes at the end, and the TRP location information associated with the channel measurement information comes at the front.
  • the format of the input information of the AI model includes the size of the input information of the AI model, and the size includes at least one of the following:
  • the size of the channel measurement information includes: the dimension of the channel measurement information and the length of each dimension;
  • the size of the TRP identification information associated with the channel measurement information includes: the dimension of the TRP identification information associated with the channel measurement information, and the length of each dimension;
  • the size of the PRS identification information associated with the channel measurement information includes: the dimension of the PRS identification information associated with the channel measurement information, and the length of each dimension;
  • the size of the PRS resource set identification information associated with the channel measurement information includes: the dimension of the PRS resource set identification information associated with the channel measurement information, and the length of each dimension;
  • the size of the TRP position information associated with the channel measurement information includes: the dimension of the TRP position information associated with the channel measurement information, and the length of each dimension.
  • the channel measurement information includes at least one of the following: CIR, CFR, and PDP.
  • the device for determining the model input information in the embodiment of the present application may be a UE, such as a UE with an operating system, or a component in the UE, such as an integrated circuit or a chip.
  • the UE may be a terminal, or may be other devices other than a terminal.
  • the UE may include but is not limited to the types of UE 11 listed above, and other devices may be servers, network attached storage (NAS), etc., which are not specifically limited in the embodiment of the present application.
  • the device for determining the model input information provided in the embodiment of the present application can implement each process implemented by the UE in the above method embodiment and achieve the same technical effect. To avoid repetition, it will not be repeated here.
  • FIG. 10 is a schematic diagram showing a possible structure of a device for determining model input information involved in an embodiment of the present application.
  • the device for determining model input information is applied to a network side device.
  • the device for determining model input information 90 may include: a sending module 91 .
  • the sending module 91 is used to send model auxiliary information to the UE, and the model auxiliary information is used by the UE to determine the input information of the AI model; wherein the model auxiliary information includes at least one of the following: N TRP identification information associated with the AI model, N PRS identification information associated with the AI model, N PRS resource set identification information associated with the AI model, and N TRP location information associated with the AI model; N is a positive integer.
  • An embodiment of the present application provides a device for determining model input information.
  • the device for determining model input information can send model auxiliary information to the UE, that is, some auxiliary information such as TRP information and/or PRS information associated with the AI model, so that the UE can determine the input information of the AI model based on the auxiliary information, that is, the input information of the AI model can be accurately determined through the model auxiliary information, so that when the AI model is applied, the function of the model (such as channel prediction or terminal positioning, etc.) can be accurately implemented based on the input information of the AI model, thereby improving the performance of the AI model (such as model accuracy).
  • some auxiliary information such as TRP information and/or PRS information associated with the AI model
  • the above-mentioned sending module 91 is also used to send a first indication information to the UE, and the first indication information is used to indicate any one of the following: an encoding method of model auxiliary information, a mapping relationship between model auxiliary information and codewords, and no encoding of model auxiliary information; wherein, the input information of the AI model is determined by the UE based on the model auxiliary information and the first indication information.
  • the encoding method of the above-mentioned model auxiliary information includes at least one of the following: one-hot encoding or binary encoding of each TRP identification information, one-hot encoding or binary encoding of each PRS identification information, one-hot encoding or binary encoding of each PRS resource set identification information, and one-hot encoding or binary encoding of each TRP location information.
  • the mapping relationship between the above-mentioned model auxiliary information and the codeword includes at least one of the following: a mapping relationship between each TRP identification information and a codeword, a mapping relationship between each PRS identification information and a codeword, a mapping relationship between each PRS resource set identification information and a codeword, and a mapping relationship between each TRP position information and a codeword.
  • the input information of the above-mentioned AI model includes channel measurement information and model auxiliary information.
  • the above-mentioned sending module 91 is also used to send second indication information to the UE, where the second indication information is used to indicate the type and/or format of the input information of the AI model; wherein the input information of the AI model is determined by the UE based on the model auxiliary information and the second indication information.
  • the type of input information of the AI model includes at least one of the following:
  • Channel measurement information and TRP identification information associated with the channel measurement information
  • Channel measurement information and PRS identification information associated with the channel measurement information
  • Channel measurement information and PRS resource set identification information associated with the channel measurement information
  • Channel measurement information and TRP location information associated with the channel measurement information.
  • the format of the input information of the AI model includes an arrangement of the input information of the AI model, and the arrangement includes at least one of the following:
  • the channel measurement information comes first, and the TRP identification information associated with the channel measurement information comes second;
  • the channel measurement information is at the back, and the TRP identification information associated with the channel measurement information is at the front;
  • the channel measurement information is in front, and the PRS identification information associated with the channel measurement information is in the back;
  • the channel measurement information is at the back, and the PRS identification information associated with the channel measurement information is at the front;
  • the channel measurement information is in the front, and the PRS resource set identification information associated with the channel measurement information is in the back;
  • the channel measurement information is at the back, and the PRS resource set identification information associated with the channel measurement information is at the front;
  • the channel measurement information comes first, and the TRP location information associated with the channel measurement information comes second;
  • the channel measurement information comes at the end, and the TRP location information associated with the channel measurement information comes at the front.
  • the format of the input information of the AI model includes the size of the input information of the AI model, and the size includes at least one of the following:
  • the size of the channel measurement information includes: the dimension of the channel measurement information and the length of each dimension;
  • the size of the TRP identification information associated with the channel measurement information includes: the dimension of the TRP identification information associated with the channel measurement information, and the length of each dimension;
  • the size of the PRS identification information associated with the channel measurement information includes: the dimension of the PRS identification information associated with the channel measurement information, and the length of each dimension;
  • the size of the PRS resource set identification information associated with the channel measurement information includes: the dimension of the PRS resource set identification information associated with the channel measurement information, and the length of each dimension;
  • the size of the TRP position information associated with the channel measurement information includes: the dimension of the TRP position information associated with the channel measurement information, and the length of each dimension.
  • the channel measurement information includes at least one of the following: CIR, CFR, and PDP.
  • the device for determining the model input information provided in the embodiment of the present application can implement each process implemented by the network side device in the above method embodiment and achieve the same technical effect. To avoid repetition, it will not be repeated here.
  • an embodiment of the present application also provides a communication device 5000, including a processor 5001 and a memory 5002, and the memory 5002 stores programs or instructions that can be executed on the processor 5001.
  • the communication device 5000 is a UE
  • the program or instruction is executed by the processor 5001 to implement the various steps of the above-mentioned UE-side method embodiment, and can achieve the same technical effect.
  • the communication device 5000 is a network side device
  • the program or instruction is executed by the processor 5001 to implement the various steps of the above-mentioned network side device side method embodiment, and can achieve the same technical effect. To avoid repetition, it is not repeated here.
  • the embodiment of the present application also provides a UE, including a processor and a communication interface, the communication interface is used to receive model auxiliary information from a network side device, and the model auxiliary information is used for the UE to determine the input information of the AI model; wherein the model auxiliary information includes at least one of the following: N TRP identification information associated with the AI model, N PRS identification information associated with the AI model, N PRS resource set identification information associated with the AI model, and N TRP location information associated with the AI model; N is a positive integer.
  • This UE embodiment corresponds to the above-mentioned UE side method embodiment, and each implementation process and implementation method of the above-mentioned method embodiment can be applied to the UE embodiment and can achieve the same technical effect.
  • Figure 12 is a schematic diagram of the hardware structure of a UE that implements an embodiment of the present application.
  • the UE 7000 includes but is not limited to: a radio frequency unit 7001, a network module 7002, an audio output unit 7003, an input At least some of the components including the input unit 7004, the sensor 7005, the display unit 7006, the user input unit 7007, the interface unit 7008, the memory 7009 and the processor 7010.
  • UE 7000 may also include a power source (such as a battery) for supplying power to various components, and the power source may be logically connected to processor 7010 through a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system.
  • a power source such as a battery
  • the UE structure shown in FIG12 does not constitute a limitation on the UE, and the UE may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be described in detail here.
  • the input unit 7004 may include a graphics processing unit (GPU) 70041 and a microphone 70042, and the graphics processor 70041 processes the image data of the static picture or video obtained by the image capture device (such as a camera) in the video capture mode or the image capture mode.
  • the display unit 7006 may include a display panel 70061, and the display panel 70061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc.
  • the user input unit 7007 includes a touch panel 70071 and at least one of other input devices 70072.
  • the touch panel 70071 is also called a touch screen.
  • the touch panel 70071 may include two parts: a touch detection device and a touch controller.
  • Other input devices 70072 may include, but are not limited to, a physical keyboard, function keys (such as a volume control key, a switch key, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.
  • the RF unit 7001 can transmit the data to the processor 7010 for processing; in addition, the RF unit 7001 can send uplink data to the network side device.
  • the RF unit 7001 includes but is not limited to an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.
  • the memory 7009 can be used to store software programs or instructions and various data.
  • the memory 7009 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instruction required for at least one function (such as a sound playback function, an image playback function, etc.), etc.
  • the memory 7009 may include a volatile memory or a non-volatile memory, or the memory 7009 may include both volatile and non-volatile memories.
  • the non-volatile memory may 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 may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM).
  • the memory 7009 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.
  • the processor 7010 may include one or more processing units; optionally, the processor 7010 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to the operating system, user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the above-mentioned modem processor The processor may not be integrated into the processor 7010.
  • the radio frequency unit 7001 is used to receive model auxiliary information from the network side device, and the model auxiliary information is used by the UE to determine the input information of the AI model; wherein the model auxiliary information includes at least one of the following: N TRP identification information associated with the AI model, N PRS identification information associated with the AI model, N PRS resource set identification information associated with the AI model, and N TRP location information associated with the AI model; N is a positive integer.
  • An embodiment of the present application provides a UE, which can obtain model auxiliary information from a network side device, that is, some auxiliary information such as TRP information and/or PRS information associated with the AI model, to determine the input information of the AI model based on the auxiliary information, that is, the input information of the AI model can be accurately determined through the model auxiliary information, so that when the AI model is applied, the function of the model (such as channel prediction or terminal positioning, etc.) can be accurately implemented based on the input information of the AI model, thereby improving the performance of the AI model (such as model accuracy).
  • auxiliary information such as TRP information and/or PRS information associated with the AI model
  • the radio frequency unit 7001 is further used to receive first indication information from a network side device, where the first indication information is used to indicate any one of the following: an encoding method of model auxiliary information, a mapping relationship between model auxiliary information and codewords, and no encoding of model auxiliary information.
  • the processor 7010 is used to determine input information of the AI model based on the model auxiliary information and the first indication information.
  • the radio frequency unit 7001 is further configured to receive second indication information from a network side device, where the second indication information is used to indicate the type and/or format of the input information of the AI model.
  • the processor 7010 is configured to enable the UE to determine the input information of the AI model based on the model auxiliary information and the second indication information.
  • the UE provided in the embodiment of the present application can implement each process implemented by the UE in the above method embodiment and achieve the same technical effect. To avoid repetition, it will not be repeated here.
  • the embodiment of the present application also provides a network side device, including a processor and a communication interface, the communication interface is used to send model auxiliary information to the UE, and the model auxiliary information is used for the UE to determine the input information of the AI model; wherein the model auxiliary information includes at least one of the following: N TRP identification information associated with the AI model, N PRS identification information associated with the AI model, N PRS resource set identification information associated with the AI model, and N TRP location information associated with the AI model; N is a positive integer.
  • This network side device embodiment corresponds to the above-mentioned network side device method embodiment, and each implementation process and implementation method of the above-mentioned method embodiment can be applied to the network side device embodiment, and can achieve the same technical effect.
  • the embodiment of the present application also provides a network side device.
  • the network side device 600 includes: an antenna 61, a radio frequency device 62, a baseband device 63, a processor 64 and a memory 65.
  • the antenna 61 is connected to the radio frequency device 62.
  • the radio frequency device 62 receives information through the antenna 61 and sends the received information to the baseband device 63 for processing.
  • the baseband device 63 processes the information to be sent and sends it to the radio frequency device 62.
  • the radio frequency device 62 processes the received information and sends it out through the antenna 61.
  • the method executed by the network-side device in the above embodiment may be implemented in the baseband device 63, which includes a baseband processor.
  • the radio frequency device 62 is used to send model auxiliary information to the UE, where the model auxiliary information is used by the UE to determine the input information of the AI model; wherein the model auxiliary information includes at least one of the following: N TRP identification information associated with the AI model, N PRS identification information associated with the AI model, N PRS resource set identification information associated with the AI model, and AI The location information of N TRPs associated with the model; N is a positive integer.
  • An embodiment of the present application provides a network side device, which can send model auxiliary information to the UE, that is, some auxiliary information such as TRP information and/or PRS information associated with the AI model, so that the UE can determine the input information of the AI model based on the auxiliary information, that is, the input information of the AI model can be accurately determined through the model auxiliary information, so that when the AI model is applied, the function of the model (such as channel prediction or terminal positioning, etc.) can be accurately implemented based on the input information of the AI model, thereby improving the performance of the AI model (such as model accuracy).
  • some auxiliary information such as TRP information and/or PRS information associated with the AI model
  • the network side device provided in the embodiment of the present application can implement each process implemented by the network side device in the above method embodiment and achieve the same technical effect. To avoid repetition, it will not be repeated here.
  • the baseband device 63 may include, for example, at least one baseband board, on which a plurality of chips are arranged, as shown in FIG13 , wherein one of the chips is, for example, a baseband processor, which is connected to the memory 65 through a bus interface to call a program in the memory 65 and execute the network device operations shown in the above method embodiment.
  • the network side device may also include a network interface 66, which is, for example, a common public radio interface (CPRI).
  • a network interface 66 which is, for example, a common public radio interface (CPRI).
  • CPRI common public radio interface
  • the network side device 600 of the embodiment of the present application also includes: instructions or programs stored in the memory 65 and executable on the processor 64.
  • the processor 64 calls the instructions or programs in the memory 65 to execute the methods executed by the modules shown in Figure 10 and achieve the same technical effect. To avoid repetition, it will not be repeated here.
  • An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored.
  • a program or instruction is stored.
  • the various processes of the above-mentioned method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.
  • the processor is the processor in the communication device described in the above embodiment.
  • the readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.
  • An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned method embodiment, and can achieve the same technical effect. To avoid repetition, it 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 embodiments of the present application further provide a computer program/program product, which is stored in a storage medium and is executed by at least one processor to implement the various processes of the above-mentioned method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described here.
  • An embodiment of the present application also provides a communication system, including: a UE and a network side device, wherein the UE can be used to execute the steps of the method for determining the model input information as described above, and the network side device can be used to execute the steps of the method for determining the model input information as described above.
  • the technical solution of the present application can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM/RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.
  • a storage medium such as ROM/RAM, a magnetic disk, or an optical disk
  • a terminal which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请公开了一种模型输入信息的确定方法、装置、设备、***及存储介质，属于通信技术领域，本申请实施例的模型输入信息的确定方法包括：UE接收来自网络侧设备的模型辅助信息，该模型辅助信息用于UE确定AI模型的输入信息；其中，模型辅助信息包括以下至少一项：AI模型关联的N个TRP标识信息、AI模型关联的N个PRS标识信息、AI模型关联的N个PRS资源集标识信息、AI模型关联的N个TRP位置信息；N为正整数。

Description

模型输入信息的确定方法、装置、设备、***及存储介质
相关申请的交叉引用
本申请主张在2022年12月09日在中国提交的申请号为202211585958.2的中国专利的优先权，其全部内容通过引用包含于此。
技术领域
本申请属于通信技术领域，具体涉及一种模型输入信息的确定方法、装置、设备、***及存储介质。
背景技术
人工智能(Artificial Intelligence，AI)在各个领域获得了广泛的应用，将AI融入无线通信网络，以显著提升网络吞吐量、时延以及用户容量等技术指标，是未来无线通信网络的重要任务。
目前，AI模型有多种实现方式，例如神经网络、决策树、支持向量机、贝叶斯分类器等，通过应用这些模型可以实现推理、预测等功能(例如信道预测或终端定位等)。然而，在应用AI模型时，AI模型的输入信息会影响AI模型的性能(例如模型精度)，因此如何约束或确定AI模型的输入信息是亟待解决的问题。
发明内容
本申请实施例提供一种模型输入信息的确定方法、装置、设备、***及存储介质，能够解决如何约束或确定AI模型的输入信息的问题。
第一方面，提供了一种模型输入信息的确定方法，该方法包括：用户设备(User Equipment，UE)接收来自网络侧设备的模型辅助信息，该模型辅助信息用于UE确定AI模型的输入信息；其中，模型辅助信息包括以下至少一项：AI模型关联的N个发送接收点(Transmission Reception Point，TRP)标识信息、AI模型关联的N个定位参考信号(Positioning Reference Signal，PRS)标识信息、AI模型关联的N个PRS资源集标识信息、AI模型关联的N个TRP位置信息；N为正整数。
第二方面，提供了一种模型输入信息的确定装置，应用于UE，该模型输入信息的确定装置包括：接收模块。接收模块，用于接收来自网络侧设备的模型辅助信息，该模型辅助信息用于UE确定AI模型的输入信息；其中，模型辅助信息包括以下至少一项：AI模型关联的N个TRP标识信息、AI模型关联的N个PRS标识信息、AI模型关联的N个PRS资源集标识信息、AI模型关联的N个TRP位置信息；N为正整数。
第三方面，提供了一种模型输入信息的确定方法，该方法包括：网络侧设备向 UE发送模型辅助信息，该模型辅助信息用于UE确定AI模型的输入信息；其中，模型辅助信息包括以下至少一项：AI模型关联的N个TRP标识信息、AI模型关联的N个PRS标识信息、AI模型关联的N个PRS资源集标识信息、AI模型关联的N个TRP位置信息；N为正整数。
第四方面，提供了一种模型输入信息的确定装置，应用于网络侧设备，该模型输入信息的确定装置包括：发送模块。发送模块，用于向UE发送模型辅助信息，该模型辅助信息用于UE确定AI模型的输入信息；其中，模型辅助信息包括以下至少一项：AI模型关联的N个TRP标识信息、AI模型关联的N个PRS标识信息、AI模型关联的N个PRS资源集标识信息、AI模型关联的N个TRP位置信息；N为正整数。
第五方面，提供了一种UE，该UE包括处理器和存储器，所述存储器存储可在所述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时实现如第一方面所述的方法的步骤。
第六方面，提供了一种UE，包括处理器及通信接口，其中，所述通信接口用于接收来自网络侧设备的模型辅助信息，该模型辅助信息用于UE确定AI模型的输入信息；其中，模型辅助信息包括以下至少一项：AI模型关联的N个TRP标识信息、AI模型关联的N个PRS标识信息、AI模型关联的N个PRS资源集标识信息、AI模型关联的N个TRP位置信息；N为正整数。
第七方面，提供了一种网络侧设备，该网络侧设备包括处理器和存储器，所述存储器存储可在所述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时实现如第三方面所述的方法的步骤。
第八方面，提供了一种网络侧设备，包括处理器及通信接口，其中，所述通信接口用于向UE发送模型辅助信息，该模型辅助信息用于UE确定AI模型的输入信息；其中，模型辅助信息包括以下至少一项：AI模型关联的N个TRP标识信息、AI模型关联的N个PRS标识信息、AI模型关联的N个PRS资源集标识信息、AI模型关联的N个TRP位置信息；N为正整数。
第九方面，提供了一种通信***，包括：UE及网络侧设备，所述UE可用于执行如第一方面所述的模型输入信息的确定方法的步骤，所述网络侧设备可用于执行如第三方面所述的模型输入信息的确定方法的步骤。
第十方面，提供了一种可读存储介质，所述可读存储介质上存储程序或指令，所述程序或指令被处理器执行时实现如第一方面所述的方法的步骤，或者实现如第三方面所述的方法的步骤。
第十一方面，提供了一种芯片，所述芯片包括处理器和通信接口，所述通信接口和所述处理器耦合，所述处理器用于运行程序或指令，实现如第一方面所述的方法，或者实现如第三方面所述的方法。
第十二方面，提供了一种计算机程序/程序产品，所述计算机程序/程序产品被存储在存储介质中，所述计算机程序/程序产品被至少一个处理器执行以实现如第一方面所述的模型输入信息的确定方法的步骤，或者实现如第三方面所述的模型输入信息的确定方法的步骤。
在本申请实施例中，UE可以接收来自网络侧设备的模型辅助信息，以确定AI模型的输入信息，该模型辅助信息包括以下至少一项：AI模型关联的N个TRP标识信息、N个PRS标识信息、N个PRS资源集标识信息、N个TRP位置信息。本方案中，由于UE可以从网络侧设备获得模型辅助信息，即AI模型关联的一些TRP信息和/或PRS信息等辅助信息，以根据这些辅助信息确定AI模型的输入信息，即通过模型辅助信息能够准确地确定出AI模型的输入信息，从而使得在应用AI模型时，能够精确地基于AI模型的输入信息实现模型的功能(例如信道预测或终端定位等)，提升了AI模型的性能(例如模型精度)。
附图说明
图1是本申请实施例提供的一种无线通信***的架构示意图；
图2是相关技术提供的一种神经网络的结构示意图；
图3是相关技术提供的一种神经元的结构示意图；
图4是本申请实施例提供的一种模型输入信息的确定方法的流程图之一；
图5是本申请实施例提供的一种模型输入信息的确定方法的流程图之二；
图6是本申请实施例提供的一种模型输入信息的确定方法的流程图之三；
图7是本申请实施例提供的一种AI模型的输入信息的类型和格式的示意图；
图8是本申请实施例提供的一种模型输入信息的确定装置的结构示意图之一；
图9是本申请实施例提供的一种模型输入信息的确定装置的结构示意图之二；
图10是本申请实施例提供的一种模型输入信息的确定装置的结构示意图之三；
图11是本申请实施例提供的一种通信设备的硬件结构示意图；
图12是本申请实施例提供的一种UE的硬件结构示意图；
图13是本申请实施例提供的一种网络侧设备的硬件结构示意图。
具体实施方式
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清楚描述，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。基于本申请中的实施例，本领域普通技术人员所获得的所有其他实施例，都属于本申请保护的范围。
本申请的说明书和权利要求书中的术语“第一”、“第二”等是用于区别类似的对象，而不用于描述特定的顺序或先后次序。应该理解这样使用的术语在适当情况下可以互换，以便本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施，且“第一”、“第二”所区别的对象通常为一类，并不限定对象的个数，例如第一对象可以是一个，也可以 是多个。此外，说明书以及权利要求中“和/或”表示所连接对象的至少其中之一，字符“/”一般表示前后关联对象是一种“或”的关系。
值得指出的是，本申请实施例所描述的技术不限于长期演进型(Long Term Evolution，LTE)/LTE的演进(LTE-Advanced，LTE-A)***，还可用于其他无线通信***，诸如码分多址(Code Division Multiple Access，CDMA)、时分多址(Time Division Multiple Access，TDMA)、频分多址(Frequency Division Multiple Access，FDMA)、正交频分多址(Orthogonal Frequency Division Multiple Access，OFDMA)、单载波频分多址(Single-carrier Frequency Division Multiple Access，SC-FDMA)和其他***。本申请实施例中的术语“***”和“网络”常被可互换地使用，所描述的技术既可用于以上提及的***和无线电技术，也可用于其他***和无线电技术。以下描述出于示例目的描述了新空口(New Radio，NR)***，并且在以下大部分描述中使用NR术语，但是这些技术也可应用于NR***应用以外的应用，如第6代(6th Generation，6G)通信***。
图1示出本申请实施例可应用的一种无线通信***的框图。无线通信***包括UE 11和网络侧设备12。其中，UE 11可以是手机、平板电脑(Tablet Personal Computer)、膝上型电脑(Laptop Computer)或称为笔记本电脑、个人数字助理(Personal Digital Assistant，PDA)、掌上电脑、上网本、超级移动个人计算机(ultra-mobile personal computer，UMPC)、移动上网装置(Mobile Internet Device，MID)、增强现实(augmented reality，AR)/虚拟现实(virtual reality，VR)设备、机器人、可穿戴式设备(Wearable Device)、车载设备(VUE)、行人终端(PUE)、智能家居(具有无线通信功能的家居设备，如冰箱、电视、洗衣机或者家具等)、游戏机、个人计算机(personal computer，PC)、柜员机或者自助机等终端侧设备，可穿戴式设备包括：智能手表、智能手环、智能耳机、智能眼镜、智能首饰(智能手镯、智能手链、智能戒指、智能项链、智能脚镯、智能脚链等)、智能腕带、智能服装等。需要说明的是，在本申请实施例并不限定UE 11的具体类型。网络侧设备12可以包括接入网设备或核心网设备，其中，接入网设备12也可以称为无线接入网设备、无线接入网(Radio Access Network,RAN)、无线接入网功能或无线接入网单元。接入网设备12可以包括基站、WLAN接入点或WiFi节点等，基站可被称为节点B、演进节点B(eNB)、接入点、基收发机站(Base Transceiver Station，BTS)、无线电基站、无线电收发机、基本服务集(Basic Service Set，BSS)、扩展服务集(Extended Service Set，ESS)、家用B节点、家用演进型B节点、发送接收点(Transmitting Receiving Point，TRP)或所述领域中其他某个合适的术语，只要达到相同的技术效果，所述基站不限于特定技术词汇，需要说明的是，在本申请实施例中仅以NR***中的基站为例进行介绍，并不限定基站的具体类型。
下面对本申请实施例提供的一种模型输入信息的确定方法、装置、设备、***及存储介质中涉及的一些概念和/或术语做一下解释说明。
人工智能(AI)
AI是将人工智能融入无线通信网络，显著提升吞吐量、时延以及用户容量等技术指标 是未来的无线通信网络的重要任务。AI模块有多种实现方式，例如神经网络、决策树、支持向量机、贝叶斯分类器等。本申请实施例以神经网络为例进行说明，但是并不限定AI模块的具体类型。
示例性地，如图2所示，为一个神经网络的示意图。该神经网络包括输入层、隐层和输出层，X1,X2,…,Xn为输入，Y为输出。
其中，神经网络由神经元组成，如图3所示，为神经元的示意图。其中，a1,a2,…aK为输入，w为权值(乘性系数)，b为偏置(加性系数)，z＝a1w1+…+akwk+…+aKwK+b，σ(z)为激活函数。通常，激活函数包括Sigmoid、tanh、ReLU(Rectified Linear Unit、线性整流函数、修正线性单元)等。
神经网络的参数通过梯度优化算法进行优化。梯度优化算法是一类最小化或者最大化目标函数(也可以称为损失函数)的算法，而目标函数是模型参数和数据的数学组合。例如给定数据X和其对应的标签Y，可以构建一个神经网络模型f(.)，有了模型后，可以根据输入x就可以得到预测输出f(x)，并且可以计算出预测值和真实值之间的差距(f(x)-Y)，这个就是损失函数。找到合适的W,b使上述的损失函数的值达到最小，损失值越小，则说明模型越接近于真实情况。
目前常见的优化算法，为基于BP(error Back Propagation，误差反向传播)算法。BP算法的基本思想是，学习过程由信号的正向传播与误差的反向传播两个过程组成。正向传播时，输入样本从输入层传入，经各隐层逐层处理后，传向输出层。若输出层的实际输出与期望的输出不符，则转入误差的反向传播阶段。误差反传是将输出误差以某种形式通过隐层向输入层逐层反传，并将误差分摊给各层的所有单元，从而获得各层单元的误差信号，此误差信号即作为修正各单元权值的依据。这种信号正向传播与误差反向传播的各层权值调整过程，是周而复始地进行的。权值不断调整的过程，也就是网络的学习训练过程。此过程一直进行到网络输出的误差减少到可接受的程度，或进行到预先设定的学习次数为止。
常见的优化算法有梯度下降(Gradient Descent)、随机梯度下降(Stochastic Gradient Descent，SGD)、mini-batch gradient descent(小批量梯度下降)、动量法(Momentum)、Nesterov(发明者的名字，具体为带动量的随机梯度下降)、Adagrad(ADAptive GRADient descent，自适应梯度下降)、Adadelta、RMSprop(root mean square prop，均方根误差降速)、Adam(Adaptive Moment Estimation，自适应动量估计)等。
这些优化算法在误差反向传播时，都是根据损失函数得到的误差/损失，对当前神经元求导数/偏导，加上学习速率、之前的梯度/导数/偏导等影响，得到梯度，将梯度传给上一层。
下面结合附图，通过一些实施例及其应用场景对本申请实施例提供的模型输入信息的确定方法进行详细地说明。
如上述背景技术，在应用AI模型时，AI模型的输入信息会影响AI模型的性能(例如模型精度)，因此如何约束或确定AI模型的输入信息是亟待解决的问题。
本申请实施例中，UE可以接收来自网络侧设备的模型辅助信息，以确定AI模型的输 入信息，该模型辅助信息包括以下至少一项：AI模型关联的N个TRP标识信息、N个PRS标识信息、N个PRS资源集标识信息、N个TRP位置信息。本方案中，由于UE可以从网络侧设备获得模型辅助信息，即AI模型关联的一些TRP信息和/或PRS信息等辅助信息，以根据这些辅助信息确定AI模型的输入信息，即通过模型辅助信息能够准确地确定出AI模型的输入信息，从而使得在应用AI模型时，能够精确地基于AI模型的输入信息实现模型的功能(例如信道预测或终端定位等)，提升了AI模型的性能(例如模型精度)。
本申请实施例提供一种模型输入信息的确定方法，图4示出了本申请实施例提供的一种模型输入信息的确定方法的流程图。如图4所示，本申请实施例提供的模型输入信息的确定方法可以包括下述的步骤201和步骤202。
步骤201、网络侧设备向UE发送模型辅助信息。
步骤202、UE接收来自网络侧设备的模型辅助信息。
本申请实施例中，上述模型辅助信息用于UE确定AI模型的输入信息。其中，上述模型辅助信息包括以下至少一项：AI模型关联的N个TRP标识信息、AI模型关联的N个PRS标识信息、AI模型关联的N个PRS资源集标识信息、AI模型关联的N个TRP位置信息。N为正整数。
可选地，本申请实施例中，上述AI模型为单站模型，上述AI模型的输入信息包含单个TRP的信息，即AI模型的输入信息包含UE与上述N个TRP中的一个TRP的相关信息。
可选地，本申请实施例中，上述AI模型的输入信息包括信道测量信息和模型辅助信息(例如上述N个TRP标识信息中的一个TRP标识信息)。
可选地，本申请实施例中，上述AI模型的输出信息为定位信息，该定位信息可以包括以下至少一项：到达时间(Time of Arrival，TOA)、到达角(Angle of Arrival，AOA)、发射角(Angle of Departure，AOD)、到达时间差(Time Difference of Arrival，TDOA)、参考信号时间差(Reference Signal Time Difference，RSTD)、位置坐标等。
本申请实施例提供一种模型输入信息的确定方法，UE可以接收来自网络侧设备的模型辅助信息，以确定AI模型的输入信息，该模型辅助信息包括以下至少一项：AI模型关联的N个TRP标识信息、N个PRS标识信息、N个PRS资源集标识信息、N个TRP位置信息。本方案中，由于UE可以从网络侧设备获得模型辅助信息，即AI模型关联的一些TRP信息和/或PRS信息等辅助信息，以根据这些辅助信息确定AI模型的输入信息，即通过模型辅助信息能够准确地确定出AI模型的输入信息，从而使得在应用AI模型时，能够精确地基于AI模型的输入信息实现模型的功能(例如信道预测或终端定位等)，提升了AI模型的性能(例如模型精度)。
可选地，本申请实施例中，结合图4，如图5所示，在上述步骤202之后，本申请实施例提供的模型输入信息的确定方法还包括下述的步骤301至步骤303。
步骤301、网络侧设备向UE发送第一指示信息。
步骤302、UE接收来自网络侧设备的第一指示信息。
本申请实施例中，上述第一指示信息用于指示以下任一项：模型辅助信息的编码方法、模型辅助信息与码字的映射关系、对模型辅助信息不进行编码。
可选地，本申请实施例中，上述模型辅助信息的编码方法包括以下至少一项：每个TRP标识信息进行独热编码(One-hot编码)或二进制编码、每个PRS标识信息进行独热编码或二进制编码、每个PRS资源集标识信息进行独热编码或二进制编码、每个TRP位置信息进行独热编码或二进制编码。
可选地，本申请实施例中，针对每个TRP标识信息，一个TRP标识信息包括至少一个字符，可以按照从小到大或从大到小的顺序对该至少一个字符进行排序，然后再对该一个TRP标识信息进行独热编码。
可选地，本申请实施例中，针对每个PRS标识信息，一个PRS标识信息包括至少一个字符，可以按照从小到大或从大到小的顺序对该至少一个字符进行排序，然后再对该一个PRS标识信息进行独热编码。
可选地，本申请实施例中，针对每个PRS资源集标识信息，一个PRS资源集标识信息包括至少一个字符，可以按照从小到大或从大到小的顺序对该至少一个字符进行排序，然后再对该一个PRS资源集标识信息进行独热编码。
可选地，本申请实施例中，针对每个TRP位置信息，可以根据每个TRP到参考TRP的距离(或者，TRP相对UE的距离、位置和/或方向)，按照从小到大或从大到小的顺序进行排序，然后再对每个TRP位置信息进行独热编码。
可选地，本申请实施例中，上述模型辅助信息与码字的映射关系包括以下至少一项：每个TRP标识信息与码字的映射关系、每个PRS标识信息与码字的映射关系、每个PRS资源集标识信息与码字的映射关系、每个TRP位置信息与码字的映射关系。
步骤303、UE基于模型辅助信息和第一指示信息，确定AI模型的输入信息。
本申请实施例中，上述AI模型的输入信息由UE基于模型辅助信息和第一指示信息确定。可以理解，一种情况，在上述第一指示信息指示模型辅助信息的编码方法的情况下，UE可以采用第一指示信息指示的编码方法，对上述的模型辅助信息进行编码，并将编码后的模型辅助信息作为上述AI模型的输入信息。
另一种情况，在上述第一指示信息指示模型辅助信息与码字的映射关系的情况下，UE可以根据第一指示信息指示的映射关系，将映射关系中与上述的模型辅助信息对应的码字作为上述AI模型的输入信息。
示例性地，如下述表1所示，示出了模型辅助信息与码字的映射关系。
表1
在表1中，TRP标识信息包括TRP1、TRP2和TRP3。其中，TRP1与码字00001具有 映射关系；TRP2与码字00010具有映射关系；TRP3与码字00100具有映射关系。若上述的模型辅助信息包括AI模型关联的N个TRP标识信息为TRP2，那么UE可以将TRP2对应的码字00010作为AI模型的输入信息。
又一种情况，在上述第一指示信息指示对模型辅助信息不进行编码的情况下，UE可以不进行上述的模型辅助信息的编码，而是直接将模型辅助信息作为上述AI模型的输入信息。
需要说明的是，针对上述步骤301-步骤302与步骤201-步骤202的执行顺序，本申请实施例不做限制。例如：可以先执行上述步骤201-步骤202，再执行上述步骤301-步骤302；或者，可以先执行上述步骤301-步骤302，再执行上述步骤201-步骤202；或者，可以同时执行上述步骤201-步骤202，与步骤301-步骤302。上述图5仅是以其中一种情况为例对模型输入信息的确定方法进行示意。
本申请实施例中，UE可以从网络侧设备获得第一指示信息，即指示模型辅助信息的编码方法、模型辅助信息与码字的映射关系或对模型辅助信息不进行编码，从而UE根据第一指示信息指示的方式，灵活地将模型辅助信息(即编码后的模型辅助信息、模型辅助信息对应的码字、不进行编码的模型辅助信息)确定为AI模型的输入信息，提升AI模型的性能。
可选地，本申请实施例中，上述AI模型的输入信息包括信道测量信息和模型辅助信息。
可选地，本申请实施例中，上述信道测量信息包括以下至少一项：时域信道脉冲响应(Channel Impulse Response，CIR)、频域信道脉冲响应(Channel Frequency Response，CFR)、时延功率谱(Power Delay Profile，PDP)。
可选地，本申请实施例中，结合图4，如图6所示，在上述步骤202之后，本申请实施例提供的模型输入信息的确定方法还包括下述的步骤401至步骤403。
步骤401、网络侧设备向UE发送第二指示信息。
步骤402、UE接收来自网络侧设备的第二指示信息。
本申请实施例中，上述第二指示信息用于指示AI模型的输入信息的类型和/或格式。
可选地，本申请实施例中，上述AI模型的输入信息的类型包括以下至少一项：
信道测量信息，以及信道测量信息关联的TRP标识信息；
信道测量信息，以及信道测量信息关联的PRS标识信息；
信道测量信息，以及信道测量信息关联的PRS资源集标识信息；
信道测量信息，以及信道测量信息关联的TRP位置信息。
可选地，本申请实施例中，上述AI模型的输入信息的格式包括AI模型的输入信息的排列方式，该排列方式包括以下至少一项：
信道测量信息在前，且信道测量信息关联的TRP标识信息在后；
信道测量信息在后，且信道测量信息关联的TRP标识信息在前；
信道测量信息在前，且信道测量信息关联的PRS标识信息在后；
信道测量信息在后，且信道测量信息关联的PRS标识信息在前；
信道测量信息在前，且信道测量信息关联的PRS资源集标识信息在后；
信道测量信息在后，且信道测量信息关联的PRS资源集标识信息在前；
信道测量信息在前，且信道测量信息关联的TRP位置信息在后；
信道测量信息在后，且信道测量信息关联的TRP位置信息在前。
可选地，本申请实施例中，上述AI模型的输入信息的格式包括AI模型的输入信息的尺寸，该尺寸包括以下至少一项：
信道测量信息的尺寸，包括：信道测量信息的维度，以及各个维度的长度；
信道测量信息关联的TRP标识信息的尺寸，包括：信道测量信息关联的TRP标识信息的维度，以及各个维度的长度；
信道测量信息关联的PRS标识信息的尺寸，包括：信道测量信息关联的PRS标识信息的维度，以及各个维度的长度；
信道测量信息关联的PRS资源集标识信息的尺寸，包括：信道测量信息关联的PRS资源集标识信息的维度，以及各个维度的长度；
信道测量信息关联的TRP位置信息的尺寸，包括：信道测量信息关联的TRP位置信息的维度，以及各个维度的长度。
需要说明的是，信道测量信息的维度是指信道测量信息是几维的信息，各个维度的长度是指信道测量信息在各个维度的信息的长度。例如，信道测量信息为CIR，CIR包括两个维度，第1维可以表示时域采样点数，第2维表示对应采样点的实部和虚部。
示例性地，如图7中的(A)所示，AI模型的输入信息的类型和格式为TRP编码信息和UE与该TRP的信道脉冲响应，其中TRP编码信息的长度小于信道脉冲响应的长度。如图7中的(B)所示，AI模型的输入信息的类型和格式为TRP编码信息和UE与该TRP的信道脉冲响应，其中信道脉冲响应在前，TRP编码信息在后。
步骤403、UE基于模型辅助信息和第二指示信息，确定AI模型的输入信息。
本申请实施例中，上述AI模型的输入信息由UE基于模型辅助信息和第二指示信息确定。可以理解，UE可以根据模型辅助信息和第二指示信息，确定出AI模型的输入信息的类型包括信道测量信息和模型辅助信息，以及信道测量信息和模型辅助信息的排列方式和/或尺寸。
需要说明的是，针对上述步骤401-步骤402与步骤201-步骤202的执行顺序，本申请实施例不做限制。例如：可以先执行上述步骤201-步骤202，再执行上述步骤401-步骤402；或者，可以先执行上述步骤401-步骤402，再执行上述步骤201-步骤202；或者，可以同时执行上述步骤201-步骤202，与步骤401-步骤402。上述图6仅是以其中一种情况为例对模型输入信息的确定方法进行示意。
本申请实施例中，UE可以从网络侧设备获得第二指示信息，即指示AI模型的输入信 息的类型和/或格式，从而UE根据第二指示信息指示的类型和/或格式，灵活、精确地确定出AI模型的输入信息，提升AI模型的性能。
本申请实施例提供的模型输入信息的确定方法，执行主体还可以为模型输入信息的确定装置。本申请实施例中以UE和网络侧设备执行模型输入信息的确定方法为例，说明本申请实施例提供的模型输入信息的确定装置。
图8出了本申请实施例中涉及的模型输入信息的确定装置的一种可能的结构示意图，该模型输入信息的确定装置应用于UE。如图8所示，模型输入信息的确定装置80可以包括：接收模块81。
其中，接收模块81，用于接收来自网络侧设备的模型辅助信息，该模型辅助信息用于UE确定AI模型的输入信息；其中，模型辅助信息包括以下至少一项：AI模型关联的N个TRP标识信息、AI模型关联的N个PRS标识信息、AI模型关联的N个PRS资源集标识信息、AI模型关联的N个TRP位置信息；N为正整数。
本申请实施例提供一种模型输入信息的确定装置，模型输入信息的确定装置可以从网络侧设备获得模型辅助信息，即AI模型关联的一些TRP信息和/或PRS信息等辅助信息，以根据这些辅助信息确定AI模型的输入信息，即通过模型辅助信息能够准确地确定出AI模型的输入信息，从而使得在应用AI模型时，能够精确地基于AI模型的输入信息实现模型的功能(例如信道预测或终端定位等)，提升了AI模型的性能(例如模型精度)。
在一种可能的实现方式中，结合图8，如图9所示，模型输入信息的确定装置80还包括：确定模块82。上述接收模块81，还用于接收来自网络侧设备的第一指示信息，该第一指示信息用于指示以下任一项：模型辅助信息的编码方法、模型辅助信息与码字的映射关系、对模型辅助信息不进行编码。确定模块82，用于基于接收模块81接收的模型辅助信息和第一指示信息，确定AI模型的输入信息。
在一种可能的实现方式中，上述模型辅助信息的编码方法包括以下至少一项：每个TRP标识信息进行独热编码或二进制编码、每个PRS标识信息进行独热编码或二进制编码、每个PRS资源集标识信息进行独热编码或二进制编码、每个TRP位置信息进行独热编码或二进制编码。
在一种可能的实现方式中，上述模型辅助信息与码字的映射关系包括以下至少一项：每个TRP标识信息与码字的映射关系、每个PRS标识信息与码字的映射关系、每个PRS资源集标识信息与码字的映射关系、每个TRP位置信息与码字的映射关系。
在一种可能的实现方式中，上述AI模型的输入信息包括信道测量信息和模型辅助信息。
在一种可能的实现方式中，结合图8，如图9所示，模型输入信息的确定装置80还包括：确定模块82。上述接收模块81，还用于接收来自网络侧设备的第二指示信息，该第二指示信息用于指示AI模型的输入信息的类型和/或格式。确定模块82，用于基于接收模块81接收的模型辅助信息和第二指示信息，确定AI模型的输入信息。
在一种可能的实现方式中，上述AI模型的输入信息的类型包括以下至少一项：
信道测量信息，以及信道测量信息关联的TRP标识信息；
信道测量信息，以及信道测量信息关联的PRS标识信息；
信道测量信息，以及信道测量信息关联的PRS资源集标识信息；
信道测量信息，以及信道测量信息关联的TRP位置信息。
在一种可能的实现方式中，上述AI模型的输入信息的格式包括AI模型的输入信息的排列方式，排列方式包括以下至少一项：
信道测量信息在前，且信道测量信息关联的TRP标识信息在后；
信道测量信息在后，且信道测量信息关联的TRP标识信息在前；
信道测量信息在前，且信道测量信息关联的PRS标识信息在后；
信道测量信息在后，且信道测量信息关联的PRS标识信息在前；
信道测量信息在前，且信道测量信息关联的PRS资源集标识信息在后；
信道测量信息在后，且信道测量信息关联的PRS资源集标识信息在前；
信道测量信息在前，且信道测量信息关联的TRP位置信息在后；
信道测量信息在后，且信道测量信息关联的TRP位置信息在前。
在一种可能的实现方式中，上述AI模型的输入信息的格式包括AI模型的输入信息的尺寸，尺寸包括以下至少一项：
信道测量信息的尺寸，包括：信道测量信息的维度，以及各个维度的长度；
信道测量信息关联的TRP标识信息的尺寸，包括：信道测量信息关联的TRP标识信息的维度，以及各个维度的长度；
信道测量信息关联的PRS标识信息的尺寸，包括：信道测量信息关联的PRS标识信息的维度，以及各个维度的长度；
信道测量信息关联的PRS资源集标识信息的尺寸，包括：信道测量信息关联的PRS资源集标识信息的维度，以及各个维度的长度；
信道测量信息关联的TRP位置信息的尺寸，包括：信道测量信息关联的TRP位置信息的维度，以及各个维度的长度。
在一种可能的实现方式中，上述信道测量信息包括以下至少一项：CIR、CFR、PDP。
本申请实施例中的模型输入信息的确定装置可以是UE，例如具有操作***的UE，也可以是UE中的部件，例如集成电路或芯片。该UE可以是终端，也可以为除终端之外的其他设备。示例性的，UE可以包括但不限于上述所列举的UE 11的类型，其他设备可以为服务器、网络附属存储器(Network Attached Storage，NAS)等，本申请实施例不作具体限定。
本申请实施例提供的模型输入信息的确定装置能够实现上述方法实施例中UE实现的各个过程，并达到相同的技术效果，为避免重复，这里不再赘述。
图10出了本申请实施例中涉及的模型输入信息的确定装置的一种可能的结构示意图， 该模型输入信息的确定装置应用于网络侧设备。如图10所示，模型输入信息的确定装置90可以包括：发送模块91。
其中，发送模块91，用于向UE发送模型辅助信息，该模型辅助信息用于UE确定AI模型的输入信息；其中，模型辅助信息包括以下至少一项：AI模型关联的N个TRP标识信息、AI模型关联的N个PRS标识信息、AI模型关联的N个PRS资源集标识信息、AI模型关联的N个TRP位置信息；N为正整数。
本申请实施例提供一种模型输入信息的确定装置，模型输入信息的确定装置可以向UE发送模型辅助信息，即AI模型关联的一些TRP信息和/或PRS信息等辅助信息，以使得UE可以根据这些辅助信息确定AI模型的输入信息，即通过模型辅助信息能够准确地确定出AI模型的输入信息，从而使得在应用AI模型时，能够精确地基于AI模型的输入信息实现模型的功能(例如信道预测或终端定位等)，提升了AI模型的性能(例如模型精度)。
在一种可能的实现方式中，上述发送模块91，还用于向UE发送第一指示信息，该第一指示信息用于指示以下任一项：模型辅助信息的编码方法、模型辅助信息与码字的映射关系、对模型辅助信息不进行编码；其中，AI模型的输入信息由UE基于模型辅助信息和第一指示信息确定。
在一种可能的实现方式中，上述模型辅助信息的编码方法包括以下至少一项：每个TRP标识信息进行独热编码或二进制编码、每个PRS标识信息进行独热编码或二进制编码、每个PRS资源集标识信息进行独热编码或二进制编码、每个TRP位置信息进行独热编码或二进制编码。
在一种可能的实现方式中，上述模型辅助信息与码字的映射关系包括以下至少一项：每个TRP标识信息与码字的映射关系、每个PRS标识信息与码字的映射关系、每个PRS资源集标识信息与码字的映射关系、每个TRP位置信息与码字的映射关系。
在一种可能的实现方式中，上述AI模型的输入信息包括信道测量信息和模型辅助信息。
在一种可能的实现方式中，上述发送模块91，还用于向UE发送第二指示信息，该第二指示信息用于指示AI模型的输入信息的类型和/或格式；其中，AI模型的输入信息由UE基于模型辅助信息和第二指示信息确定。
在一种可能的实现方式中，上述AI模型的输入信息的类型包括以下至少一项：
信道测量信息，以及信道测量信息关联的TRP标识信息；
信道测量信息，以及信道测量信息关联的PRS标识信息；
信道测量信息，以及信道测量信息关联的PRS资源集标识信息；
信道测量信息，以及信道测量信息关联的TRP位置信息。
在一种可能的实现方式中，上述AI模型的输入信息的格式包括AI模型的输入信息的排列方式，排列方式包括以下至少一项：
信道测量信息在前，且信道测量信息关联的TRP标识信息在后；
信道测量信息在后，且信道测量信息关联的TRP标识信息在前；
信道测量信息在前，且信道测量信息关联的PRS标识信息在后；
信道测量信息在后，且信道测量信息关联的PRS标识信息在前；
信道测量信息在前，且信道测量信息关联的PRS资源集标识信息在后；
信道测量信息在后，且信道测量信息关联的PRS资源集标识信息在前；
信道测量信息在前，且信道测量信息关联的TRP位置信息在后；
信道测量信息在后，且信道测量信息关联的TRP位置信息在前。
在一种可能的实现方式中，上述AI模型的输入信息的格式包括AI模型的输入信息的尺寸，尺寸包括以下至少一项：
信道测量信息的尺寸，包括：信道测量信息的维度，以及各个维度的长度；
信道测量信息关联的TRP标识信息的尺寸，包括：信道测量信息关联的TRP标识信息的维度，以及各个维度的长度；
信道测量信息关联的PRS标识信息的尺寸，包括：信道测量信息关联的PRS标识信息的维度，以及各个维度的长度；
信道测量信息关联的PRS资源集标识信息的尺寸，包括：信道测量信息关联的PRS资源集标识信息的维度，以及各个维度的长度；
信道测量信息关联的TRP位置信息的尺寸，包括：信道测量信息关联的TRP位置信息的维度，以及各个维度的长度。
在一种可能的实现方式中，上述信道测量信息包括以下至少一项：CIR、CFR、PDP。
本申请实施例提供的模型输入信息的确定装置能够实现上述方法实施例中网络侧设备实现的各个过程，并达到相同的技术效果，为避免重复，这里不再赘述。
可选地，如图11所示，本申请实施例还提供一种通信设备5000，包括处理器5001和存储器5002，存储器5002上存储有可在所述处理器5001上运行的程序或指令，例如，该通信设备5000为UE时，该程序或指令被处理器5001执行时实现上述UE侧方法实施例的各个步骤，且能达到相同的技术效果，为避免重复，这里不再赘述；该通信设备5000为网络侧设备时，该程序或指令被处理器5001执行时实现上述网络侧设备侧方法实施例的各个步骤，且能达到相同的技术效果，为避免重复，这里不再赘述。
本申请实施例还提供一种UE，包括处理器和通信接口，通信接口用于接收来自网络侧设备的模型辅助信息，该模型辅助信息用于UE确定AI模型的输入信息；其中，模型辅助信息包括以下至少一项：AI模型关联的N个TRP标识信息、AI模型关联的N个PRS标识信息、AI模型关联的N个PRS资源集标识信息、AI模型关联的N个TRP位置信息；N为正整数。该UE实施例与上述UE侧方法实施例对应，上述方法实施例的各个实施过程和实现方式均可适用于该UE实施例中，且能达到相同的技术效果。具体地，图12为实现本申请实施例的一种UE的硬件结构示意图。
该UE 7000包括但不限于：射频单元7001、网络模块7002、音频输出单元7003、输 入单元7004、传感器7005、显示单元7006、用户输入单元7007、接口单元7008、存储器7009以及处理器7010等中的至少部分部件。
本领域技术人员可以理解，UE 7000还可以包括给各个部件供电的电源(比如电池)，电源可以通过电源管理***与处理器7010逻辑相连，从而通过电源管理***实现管理充电、放电、以及功耗管理等功能。图12中示出的UE结构并不构成对UE的限定，UE可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置，在此不再赘述。
应理解的是，本申请实施例中，输入单元7004可以包括图形处理单元(Graphics Processing Unit，GPU)70041和麦克风70042，图形处理器70041对在视频捕获模式或图像捕获模式中由图像捕获装置(如摄像头)获得的静态图片或视频的图像数据进行处理。显示单元7006可包括显示面板70061，可以采用液晶显示器、有机发光二极管等形式来配置显示面板70061。用户输入单元7007包括触控面板70071以及其他输入设备70072中的至少一种。触控面板70071，也称为触摸屏。触控面板70071可包括触摸检测装置和触摸控制器两个部分。其他输入设备70072可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆，在此不再赘述。
本申请实施例中，射频单元7001接收来自网络侧设备的下行数据后，可以传输给处理器7010进行处理；另外，射频单元7001可以向网络侧设备发送上行数据。通常，射频单元7001包括但不限于天线、放大器、收发信机、耦合器、低噪声放大器、双工器等。
存储器7009可用于存储软件程序或指令以及各种数据。存储器7009可主要包括存储程序或指令的第一存储区和存储数据的第二存储区，其中，第一存储区可存储操作***、至少一个功能所需的应用程序或指令(比如声音播放功能、图像播放功能等)等。此外，存储器7009可以包括易失性存储器或非易失性存储器，或者，存储器7009可以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)，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，DDRSDRAM)、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)和直接内存总线随机存取存储器(Direct Rambus RAM，DRRAM)。本申请实施例中的存储器7009包括但不限于这些和任意其它适合类型的存储器。
处理器7010可包括一个或多个处理单元；可选的，处理器7010集成应用处理器和调制解调处理器，其中，应用处理器主要处理涉及操作***、用户界面和应用程序等的操作，调制解调处理器主要处理无线通信信号，如基带处理器。可以理解的是，上述调制解调处 理器也可以不集成到处理器7010中。
其中，射频单元7001，用于接收来自网络侧设备的模型辅助信息，该模型辅助信息用于UE确定AI模型的输入信息；其中，模型辅助信息包括以下至少一项：AI模型关联的N个TRP标识信息、AI模型关联的N个PRS标识信息、AI模型关联的N个PRS资源集标识信息、AI模型关联的N个TRP位置信息；N为正整数。
本申请实施例提供一种UE，UE可以从网络侧设备获得模型辅助信息，即AI模型关联的一些TRP信息和/或PRS信息等辅助信息，以根据这些辅助信息确定AI模型的输入信息，即通过模型辅助信息能够准确地确定出AI模型的输入信息，从而使得在应用AI模型时，能够精确地基于AI模型的输入信息实现模型的功能(例如信道预测或终端定位等)，提升了AI模型的性能(例如模型精度)。
可选的，射频单元7001，还用于接收来自网络侧设备的第一指示信息，该第一指示信息用于指示以下任一项：模型辅助信息的编码方法、模型辅助信息与码字的映射关系、对模型辅助信息不进行编码。处理器7010，用于基于模型辅助信息和第一指示信息，确定AI模型的输入信息。
可选的，射频单元7001，还用于接收来自网络侧设备的第二指示信息，该第二指示信息用于指示AI模型的输入信息的类型和/或格式。处理器7010，用于UE基于模型辅助信息和第二指示信息，确定AI模型的输入信息。
本申请实施例提供的UE能够实现上述方法实施例中UE实现的各个过程，并达到相同的技术效果，为避免重复，这里不再赘述。
本申请实施例还提供一种网络侧设备，包括处理器和通信接口，通信接口用于向UE发送模型辅助信息，该模型辅助信息用于UE确定AI模型的输入信息；其中，模型辅助信息包括以下至少一项：AI模型关联的N个TRP标识信息、AI模型关联的N个PRS标识信息、AI模型关联的N个PRS资源集标识信息、AI模型关联的N个TRP位置信息；N为正整数。该网络侧设备实施例与上述网络侧设备方法实施例对应，上述方法实施例的各个实施过程和实现方式均可适用于该网络侧设备实施例中，且能达到相同的技术效果。
具体地，本申请实施例还提供了一种网络侧设备。如图13所示，该网络侧设备600包括：天线61、射频装置62、基带装置63、处理器64和存储器65。天线61与射频装置62连接。在上行方向上，射频装置62通过天线61接收信息，将接收的信息发送给基带装置63进行处理。在下行方向上，基带装置63对要发送的信息进行处理，并发送给射频装置62，射频装置62对收到的信息进行处理后经过天线61发送出去。
以上实施例中网络侧设备执行的方法可以在基带装置63中实现，该基带装置63包括基带处理器。
其中，射频装置62，用于向UE发送模型辅助信息，该模型辅助信息用于UE确定AI模型的输入信息；其中，模型辅助信息包括以下至少一项：AI模型关联的N个TRP标识信息、AI模型关联的N个PRS标识信息、AI模型关联的N个PRS资源集标识信息、AI 模型关联的N个TRP位置信息；N为正整数。
本申请实施例提供一种网络侧设备，网络侧设备可以向UE发送模型辅助信息，即AI模型关联的一些TRP信息和/或PRS信息等辅助信息，以使得UE可以根据这些辅助信息确定AI模型的输入信息，即通过模型辅助信息能够准确地确定出AI模型的输入信息，从而使得在应用AI模型时，能够精确地基于AI模型的输入信息实现模型的功能(例如信道预测或终端定位等)，提升了AI模型的性能(例如模型精度)。
本申请实施例提供的网络侧设备能够实现上述方法实施例中网络侧设备实现的各个过程，并达到相同的技术效果，为避免重复，这里不再赘述。
基带装置63例如可以包括至少一个基带板，该基带板上设置有多个芯片，如图13所示，其中一个芯片例如为基带处理器，通过总线接口与存储器65连接，以调用存储器65中的程序，执行以上方法实施例中所示的网络设备操作。
该网络侧设备还可以包括网络接口66，该接口例如为通用公共无线接口(common public radio interface，CPRI)。
具体地，本申请实施例的网络侧设备600还包括：存储在存储器65上并可在处理器64上运行的指令或程序，处理器64调用存储器65中的指令或程序执行图10所示各模块执行的方法，并达到相同的技术效果，为避免重复，故不在此赘述。
本申请实施例还提供一种可读存储介质，所述可读存储介质上存储有程序或指令，该程序或指令被处理器执行时实现上述方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
其中，所述处理器为上述实施例中所述的通信设备中的处理器。所述可读存储介质，包括计算机可读存储介质，如计算机只读存储器ROM、随机存取存储器RAM、磁碟或者光盘等。
本申请实施例另提供了一种芯片，所述芯片包括处理器和通信接口，所述通信接口和所述处理器耦合，所述处理器用于运行程序或指令，实现上述方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
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。
本申请实施例另提供了一种计算机程序/程序产品，所述计算机程序/程序产品被存储在存储介质中，所述计算机程序/程序产品被至少一个处理器执行以实现上述方法实施例的各个过程，且能达到相同的技术效果，为避免重复，这里不再赘述。
本申请实施例还提供了一种通信***，包括：UE及网络侧设备，所述UE可用于执行如上所述的模型输入信息的确定方法的步骤，所述网络侧设备可用于执行如上所述的模型输入信息的确定方法的步骤。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素， 而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。此外，需要指出的是，本申请实施方式中的方法和装置的范围不限按示出或讨论的顺序来执行功能，还可包括根据所涉及的功能按基本同时的方式或按相反的顺序来执行功能，例如，可以按不同于所描述的次序来执行所描述的方法，并且还可以添加、省去、或组合各种步骤。另外，参照某些示例所描述的特征可在其他示例中被组合。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到上述实施例方法可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件，但很多情况下前者是更佳的实施方式。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可以以计算机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(如ROM/RAM、磁碟、光盘)中，包括若干指令用以使得一台终端(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本申请各个实施例所述的方法。
上面结合附图对本申请的实施例进行了描述，但是本申请并不局限于上述的具体实施方式，上述的具体实施方式仅仅是示意性的，而不是限制性的，本领域的普通技术人员在本申请的启示下，在不脱离本申请宗旨和权利要求所保护的范围情况下，还可做出很多形式，均属于本申请的保护之内。

Claims (26)

  1. 一种模型输入信息的确定方法，包括：
    用户设备UE接收来自网络侧设备的模型辅助信息，所述模型辅助信息用于所述UE确定人工智能AI模型的输入信息；
    其中，所述模型辅助信息包括以下至少一项：所述AI模型关联的N个发送接收点TRP标识信息、所述AI模型关联的N个定位参考信号PRS标识信息、所述AI模型关联的N个PRS资源集标识信息、所述AI模型关联的N个TRP位置信息；N为正整数。
  2. 根据权利要求1所述的方法，其中，所述方法还包括：
    所述UE接收来自所述网络侧设备的第一指示信息，所述第一指示信息用于指示以下任一项：所述模型辅助信息的编码方法、所述模型辅助信息与码字的映射关系、对所述模型辅助信息不进行编码；
    所述UE基于所述模型辅助信息和所述第一指示信息，确定所述AI模型的输入信息。
  3. 根据权利要求2所述的方法，其中，所述模型辅助信息的编码方法包括以下至少一项：每个TRP标识信息进行独热编码或二进制编码、每个PRS标识信息进行独热编码或二进制编码、每个PRS资源集标识信息进行独热编码或二进制编码、每个TRP位置信息进行独热编码或二进制编码。
  4. 根据权利要求2所述的方法，其中，所述模型辅助信息与码字的映射关系包括以下至少一项：每个TRP标识信息与码字的映射关系、每个PRS标识信息与码字的映射关系、每个PRS资源集标识信息与码字的映射关系、每个TRP位置信息与码字的映射关系。
  5. 根据权利要求1至4中任一项所述的方法，其中，所述AI模型的输入信息包括信道测量信息和所述模型辅助信息。
  6. 根据权利要求5所述的方法，其中，所述方法还包括：
    所述UE接收来自所述网络侧设备的第二指示信息，所述第二指示信息用于指示所述AI模型的输入信息的类型和/或格式；
    所述UE基于所述模型辅助信息和所述第二指示信息，确定所述AI模型的输入信息。
  7. 根据权利要求6所述的方法，其中，所述AI模型的输入信息的类型包括以下至少一项：
    所述信道测量信息，以及所述信道测量信息关联的TRP标识信息；
    所述信道测量信息，以及所述信道测量信息关联的PRS标识信息；
    所述信道测量信息，以及所述信道测量信息关联的PRS资源集标识信息；
    所述信道测量信息，以及所述信道测量信息关联的TRP位置信息。
  8. 根据权利要求6所述的方法，其中，所述AI模型的输入信息的格式包括所述AI模型的输入信息的排列方式，所述排列方式包括以下至少一项：
    所述信道测量信息在前，且所述信道测量信息关联的TRP标识信息在后；
    所述信道测量信息在后，且所述信道测量信息关联的TRP标识信息在前；
    所述信道测量信息在前，且所述信道测量信息关联的PRS标识信息在后；
    所述信道测量信息在后，且所述信道测量信息关联的PRS标识信息在前；
    所述信道测量信息在前，且所述信道测量信息关联的PRS资源集标识信息在后；
    所述信道测量信息在后，且所述信道测量信息关联的PRS资源集标识信息在前；
    所述信道测量信息在前，且所述信道测量信息关联的TRP位置信息在后；
    所述信道测量信息在后，且所述信道测量信息关联的TRP位置信息在前。
  9. 根据权利要求6所述的方法，其中，所述AI模型的输入信息的格式包括所述AI模型的输入信息的尺寸，所述尺寸包括以下至少一项：
    所述信道测量信息的尺寸，包括：所述信道测量信息的维度，以及各个维度的长度；
    所述信道测量信息关联的TRP标识信息的尺寸，包括：所述信道测量信息关联的TRP标识信息的维度，以及各个维度的长度；
    所述信道测量信息关联的PRS标识信息的尺寸，包括：所述信道测量信息关联的PRS标识信息的维度，以及各个维度的长度；
    所述信道测量信息关联的PRS资源集标识信息的尺寸，包括：所述信道测量信息关联的PRS资源集标识信息的维度，以及各个维度的长度；
    所述信道测量信息关联的TRP位置信息的尺寸，包括：所述信道测量信息关联的TRP位置信息的维度，以及各个维度的长度。
  10. 根据权利要求5所述的方法，其中，所述信道测量信息包括以下至少一项：时域信道脉冲响应CIR、频域信道脉冲响应CFR、时延功率谱PDP。
  11. 一种模型输入信息的确定方法，包括：
    网络侧设备向用户设备UE发送模型辅助信息，所述模型辅助信息用于所述UE确定人工智能AI模型的输入信息；
    其中，所述模型辅助信息包括以下至少一项：所述AI模型关联的N个发送接收点TRP标识信息、所述AI模型关联的N个定位参考信号PRS标识信息、所述AI模型关联的N个PRS资源集标识信息、所述AI模型关联的N个TRP位置信息；N为正整数。
  12. 根据权利要求11所述的方法，其中，所述方法还包括：
    所述网络侧设备向所述UE发送第一指示信息，所述第一指示信息用于指示以下任一项：所述模型辅助信息的编码方法、所述模型辅助信息与码字的映射关系、对所述模型辅助信息不进行编码；
    其中，所述AI模型的输入信息由所述UE基于所述模型辅助信息和所述第一指示信息确定。
  13. 根据权利要求12所述的方法，其中，所述模型辅助信息的编码方法包括以下至少一项：每个TRP标识信息进行独热编码或二进制编码、每个PRS标识信息进行独热编码或二进制编码、每个PRS资源集标识信息进行独热编码或二进制编码、 每个TRP位置信息进行独热编码或二进制编码。
  14. 根据权利要求12所述的方法，其中，所述模型辅助信息与码字的映射关系包括以下至少一项：每个TRP标识信息与码字的映射关系、每个PRS标识信息与码字的映射关系、每个PRS资源集标识信息与码字的映射关系、每个TRP位置信息与码字的映射关系。
  15. 根据权利要求11至14中任一项所述的方法，其中，所述AI模型的输入信息包括信道测量信息和所述模型辅助信息。
  16. 根据权利要求15所述的方法，其中，所述方法还包括：
    所述网络侧设备向所述UE发送第二指示信息，所述第二指示信息用于指示所述AI模型的输入信息的类型和/或格式；
    其中，所述AI模型的输入信息由所述UE基于所述模型辅助信息和所述第二指示信息确定。
  17. 根据权利要求16所述的方法，其中，所述AI模型的输入信息的类型包括以下至少一项：
    所述信道测量信息，以及所述信道测量信息关联的TRP标识信息；
    所述信道测量信息，以及所述信道测量信息关联的PRS标识信息；
    所述信道测量信息，以及所述信道测量信息关联的PRS资源集标识信息；
    所述信道测量信息，以及所述信道测量信息关联的TRP位置信息。
  18. 根据权利要求16所述的方法，其中，所述AI模型的输入信息的格式包括所述AI模型的输入信息的排列方式，所述排列方式包括以下至少一项：
    所述信道测量信息在前，且所述信道测量信息关联的TRP标识信息在后；
    所述信道测量信息在后，且所述信道测量信息关联的TRP标识信息在前；
    所述信道测量信息在前，且所述信道测量信息关联的PRS标识信息在后；
    所述信道测量信息在后，且所述信道测量信息关联的PRS标识信息在前；
    所述信道测量信息在前，且所述信道测量信息关联的PRS资源集标识信息在后；
    所述信道测量信息在后，且所述信道测量信息关联的PRS资源集标识信息在前；
    所述信道测量信息在前，且所述信道测量信息关联的TRP位置信息在后；
    所述信道测量信息在后，且所述信道测量信息关联的TRP位置信息在前。
  19. 根据权利要求16所述的方法，其中，所述AI模型的输入信息的格式包括所述AI模型的输入信息的尺寸，所述尺寸包括以下至少一项：
    所述信道测量信息的尺寸，包括：所述信道测量信息的维度，以及各个维度的长度；
    所述信道测量信息关联的TRP标识信息的尺寸，包括：所述信道测量信息关联的TRP标识信息的维度，以及各个维度的长度；
    所述信道测量信息关联的PRS标识信息的尺寸，包括：所述信道测量信息关联的PRS标识信息的维度，以及各个维度的长度；
    所述信道测量信息关联的PRS资源集标识信息的尺寸，包括：所述信道测量信 息关联的PRS资源集标识信息的维度，以及各个维度的长度；
    所述信道测量信息关联的TRP位置信息的尺寸，包括：所述信道测量信息关联的TRP位置信息的维度，以及各个维度的长度。
  20. 根据权利要求15所述的方法，其中，所述信道测量信息包括以下至少一项：时域信道脉冲响应CIR、频域信道脉冲响应CFR、时延功率谱PDP。
  21. 一种模型输入信息的确定装置，应用于用户设备UE，包括：接收模块；
    所述接收模块，用于接收来自网络侧设备的模型辅助信息，所述模型辅助信息用于所述UE确定人工智能AI模型的输入信息；
    其中，所述模型辅助信息包括以下至少一项：所述AI模型关联的N个发送接收点TRP标识信息、所述AI模型关联的N个定位参考信号PRS标识信息、所述AI模型关联的N个PRS资源集标识信息、所述AI模型关联的N个TRP位置信息；N为正整数。
  22. 一种模型输入信息的确定装置，应用于网络侧设备，包括：发送模块；
    所述发送模块，用于向用户设备UE发送模型辅助信息，所述模型辅助信息用于所述UE确定人工智能AI模型的输入信息；
    其中，所述模型辅助信息包括以下至少一项：所述AI模型关联的N个发送接收点TRP标识信息、所述AI模型关联的N个定位参考信号PRS标识信息、所述AI模型关联的N个PRS资源集标识信息、所述AI模型关联的N个TRP位置信息；N为正整数。
  23. 一种用户设备UE，包括处理器，存储器及存储在所述存储器上并可在所述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时实现如权利要求1至10中任一项所述的模型输入信息的确定方法的步骤。
  24. 一种网络侧设备，包括处理器，存储器及存储在所述存储器上并可在所述处理器上运行的程序或指令，所述程序或指令被所述处理器执行时实现如权利要求11至20中任一项所述的模型输入信息的确定方法的步骤。
  25. 一种通信***，所述通信***包括如权利要求21所述的模型输入信息的确定装置以及如权利要求22所述的模型输入信息的确定装置；或者，
    所述通信***包括如权利要求23所述的用户设备UE和如权利要求24所述的网络侧设备。
  26. 一种可读存储介质，所述可读存储介质上存储程序或指令，所述程序或指令被处理器执行时实现如权利要求1至10中任一项所述的模型输入信息的确定方法的步骤，或者实现如权利要求11至20中任一项所述的模型输入信息的确定方法的步骤。
PCT/CN2023/136808 2022-12-09 2023-12-06 模型输入信息的确定方法、装置、设备、***及存储介质 WO2024120445A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211585958.2A CN118175513A (zh) 2022-12-09 2022-12-09 模型输入信息的确定方法、装置、设备、***及存储介质
CN202211585958.2 2022-12-09

Publications (1)

Publication Number Publication Date
WO2024120445A1 true WO2024120445A1 (zh) 2024-06-13

Family

ID=91349434

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/136808 WO2024120445A1 (zh) 2022-12-09 2023-12-06 模型输入信息的确定方法、装置、设备、***及存储介质

Country Status (2)

Country Link
CN (1) CN118175513A (zh)
WO (1) WO2024120445A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190379506A1 (en) * 2018-06-08 2019-12-12 FG Innovation Company Limited Methods and apparatuses for multi-trp transmission
CN111901080A (zh) * 2020-01-07 2020-11-06 中兴通讯股份有限公司 一种信息获取方法、装置、设备和存储介质
CN115119256A (zh) * 2021-03-18 2022-09-27 维沃移动通信有限公司 时间误差组指示方法、装置、终端及网络侧设备
US20220394712A1 (en) * 2021-06-03 2022-12-08 Qualcomm Incorporated Carrier aggregation optimization using machine learning

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190379506A1 (en) * 2018-06-08 2019-12-12 FG Innovation Company Limited Methods and apparatuses for multi-trp transmission
CN111901080A (zh) * 2020-01-07 2020-11-06 中兴通讯股份有限公司 一种信息获取方法、装置、设备和存储介质
CN115119256A (zh) * 2021-03-18 2022-09-27 维沃移动通信有限公司 时间误差组指示方法、装置、终端及网络侧设备
US20220394712A1 (en) * 2021-06-03 2022-12-08 Qualcomm Incorporated Carrier aggregation optimization using machine learning

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
AHMED MOHAMMED MIKAEIL, TCL COMMUNICATION LTD.: "Discussion on AI/ML Model Management Framework", 3GPP DRAFT; R2-2211293; TYPE DISCUSSION, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, vol. 3GPP RAN 2, no. Toulouse, FR; 20221114 - 20221118, 4 November 2022 (2022-11-04), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France, XP052215405 *
CHADI KHIRALLAH, SAMSUNG ELECTRONICS NORDIC AB: "AI/ML Model Management", 3GPP DRAFT; R2-2211990; TYPE DISCUSSION, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, vol. 3GPP RAN 2, no. Toulouse, FR; 20221114 - 20221118, 4 November 2022 (2022-11-04), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France, XP052216078 *

Also Published As

Publication number Publication date
CN118175513A (zh) 2024-06-11

Similar Documents

Publication Publication Date Title
WO2023143572A1 (zh) 基于人工智能ai模型的定位方法及通信设备
WO2024120445A1 (zh) 模型输入信息的确定方法、装置、设备、***及存储介质
WO2023134650A1 (zh) 信息交互方法、装置及通信设备
WO2024083004A1 (zh) Ai模型配置方法、终端及网络侧设备
WO2024120444A1 (zh) 模型监督方法、装置、终端、网络侧设备及可读存储介质
WO2023098662A1 (zh) 定位方法及通信设备
WO2024067281A1 (zh) Ai模型的处理方法、装置及通信设备
WO2024067280A1 (zh) 更新ai模型参数的方法、装置及通信设备
WO2024093799A1 (zh) 数据标注方法、装置、终端设备及网络侧设备
WO2023098585A1 (zh) 信息传输方法、装置及通信设备
WO2023179540A1 (zh) 信道预测方法、装置及无线通信设备
WO2023098661A1 (zh) 定位方法及通信设备
WO2024125525A1 (zh) Ai算力上报方法、终端及网络侧设备
WO2024067878A1 (zh) 信道预测方法、装置及通信设备
WO2023103911A1 (zh) 测量方法、装置、设备及存储介质
WO2024153013A1 (zh) 信息传输方法、装置及通信设备
WO2023098534A1 (zh) Ai模型切换的处理方法、装置及通信设备
WO2024120358A1 (zh) 信息传输方法、信息传输装置和通信设备
WO2023213270A1 (zh) 模型训练处理方法、装置、终端及网络侧设备
WO2023125951A1 (zh) 通信模型配置方法、装置和通信设备
WO2024067665A1 (zh) Csi预测处理方法、装置、通信设备及可读存储介质
WO2024120409A1 (zh) Ai网络模型的确定方法、信息传输方法、装置和通信设备
WO2023155839A1 (zh) Ai模型的在线学习方法、装置、通信设备及可读存储介质
CN118042399A (zh) 模型监督方法、终端及网络侧设备
WO2024032695A1 (zh) Csi预测处理方法、装置、通信设备及可读存储介质