WO2023151657A1 - 信息处理方法及通信设备 - Google Patents

信息处理方法及通信设备 Download PDF

Info

Publication number
WO2023151657A1
WO2023151657A1 PCT/CN2023/075442 CN2023075442W WO2023151657A1 WO 2023151657 A1 WO2023151657 A1 WO 2023151657A1 CN 2023075442 W CN2023075442 W CN 2023075442W WO 2023151657 A1 WO2023151657 A1 WO 2023151657A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
model
cir
target
processing method
Prior art date
Application number
PCT/CN2023/075442
Other languages
English (en)
French (fr)
Inventor
王园园
孙鹏
贾承璐
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 WO2023151657A1 publication Critical patent/WO2023151657A1/zh

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
    • G01S5/0273—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves using multipath or indirect path propagation signals in position determination
    • 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
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/06—Testing, supervising or monitoring using simulated traffic
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
    • H04W64/003—Locating users or terminals or network equipment for network management purposes, e.g. mobility management locating network equipment

Definitions

  • the present application belongs to the technical field of communication, and in particular relates to an information processing method and a communication device.
  • the positioning method based on the communication network includes that the communication device estimates the current geographic location of the target terminal by measuring the reference signal.
  • the positioning method based on the communication network mainly relies on the measurement results of the direct path for positioning. In the case of line-of-sight (LOS) paths, it can achieve high positioning accuracy with low implementation complexity; However, the positioning method based on the communication network is easily affected by non-line-of-sight (NLOS), especially when the direct path between the terminal and the positioning base station does not exist, the positioning accuracy is greatly reduced.
  • the positioning method based on the communication network is susceptible to the influence of synchronization and group delay, and the positioning accuracy decreases greatly as the synchronization and group delay errors increase.
  • the positioning method based on artificial intelligence (AI) or machine learning (ML) can solve the above-mentioned positioning problems in the case of NLOS and synchronization deterioration.
  • AI artificial intelligence
  • ML machine learning
  • the positioning method in the related art has a large amount of computation and low prediction performance.
  • Embodiments of the present application provide an information processing method and a communication device, which can solve the problems of a large amount of computation and low prediction performance of a positioning method in the related art.
  • an information processing method includes:
  • the communication device acquires first information related to the configuration information of the target AI model; the first information includes measurement-related information and/or at least one candidate data processing strategy;
  • the communication device determines input data or a target data processing strategy of the target AI model according to the measurement-related information and/or each of the candidate data processing strategies;
  • the target data processing strategy is used to indicate a preprocessing strategy for the measurement related information or a preprocessing strategy for the input data of the target AI model.
  • an information processing device which includes:
  • the first acquisition module is configured to acquire first information related to configuration information of the target AI model; the first information includes measurement-related information and/or at least one candidate data processing strategy;
  • a determining module configured to determine input data or a target data processing strategy of the target AI model according to the measurement-related information and/or each of the candidate data processing strategies; wherein, the target data processing strategy is used to indicate the The preprocessing strategy for the measurement-related information or the preprocessing strategy for the input data of the target AI model.
  • a communication device in a third aspect, includes a processor and a memory, the memory stores programs or instructions that can run on the processor, and the programs or instructions are implemented when executed by the processor The method as described in the first aspect.
  • a communication device including a processor and a communication interface; wherein the processor is configured to obtain first information related to configuration information of a target AI model; the first information includes measurement-related information and/or Or at least one candidate data processing strategy; according to the measurement-related information and/or each of the candidate data processing strategies, determine the input data or target data processing strategy of the target AI model; wherein, the target data processing strategy uses Indicates a preprocessing strategy for the measurement-related information or a preprocessing strategy for the input data of the target AI model.
  • a readable storage medium where a program or an instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, the method as described in the first aspect is implemented.
  • a sixth aspect provides a chip, the chip includes a processor and a communication interface, the communication interface is coupled to the processor, the processor is used to run programs or instructions, and implement the method as described in the first aspect .
  • a computer program/program product is provided, 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 method described in the first aspect method.
  • the first information related to the configuration information of the target AI model is acquired by the communication device, and the communication device determines the target AI model based on the measurement-related information included in the first information and/or at least one candidate data processing strategy input data or target data processing strategy, because the first information includes measurement-related information and/or at least one candidate data processing strategy, so that the input data of the target AI model determined by the communication device based on the first information eliminates a large amount of redundant information
  • the determined target data processing strategy can be used to preprocess measurement-related information to reduce redundant information, reduce the computational load of the target AI model, and improve the predictive performance of the target AI model.
  • FIG. 1 is a schematic diagram of a wireless communication system applicable to an embodiment of the present application
  • FIG. 2 is a schematic flowchart of an information processing method provided in an embodiment of the present application.
  • FIG. 3 is a schematic structural diagram of an information processing device provided in an embodiment of the present application.
  • FIG. 4 is one of the structural schematic diagrams of the communication device provided by the embodiment of the present application.
  • Fig. 5 is the second structural schematic diagram of the communication device provided by the embodiment of the present application.
  • FIG. 6 is a third structural schematic diagram of a communication device provided by an embodiment of the present application.
  • first, second and the like in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific sequence or sequence. It is to be understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments of the present application can be used in a manner other than that illustrated or described herein. It is implemented in an order other than those mentioned above, and the objects distinguished by “first” and “second” are usually of one type, and the number of objects is not limited, for example, there may be one or more first objects.
  • “and/or” in the description and claims means at least one of the connected objects, and the character “/” generally means that the related objects are an "or” relationship.
  • LTE Long Term Evolution
  • LTE-Advanced LTE-Advanced
  • LTE-A Long Term Evolution-Advanced
  • 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
  • system and “network” in the embodiments of the present application are often used interchangeably, and the described technology can be used for the above-mentioned system and radio technology, and can also be used for other systems and radio technologies.
  • NR New Radio
  • the following description describes the New Radio (NR) system for example purposes, and uses NR terms in most of the following descriptions, but these techniques can also be applied to communication systems other than NR system applications, such as the 6th generation (6th generation Generation, 6G) communication system.
  • 6G 6th generation Generation
  • FIG. 1 is a schematic diagram of a wireless communication system applicable to an embodiment of the present application.
  • the wireless communication system shown in FIG. 1 includes a terminal 11 and a network-side device 12; wherein:
  • the terminal 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 (Personal Digital Assistant, PDA), a palmtop computer, a netbook, an ultra mobile personal computer (ultra -mobile personal computer, UMPC), mobile Internet device (Mobile Internet Device, MID), augmented reality (augmented reality, AR) / virtual reality (virtual reality, VR) equipment, robot, wearable device (Wearable Device), vehicle Equipment (VUE), pedestrian terminal (PUE), smart home (household equipment with wireless communication functions, such as refrigerators, TVs, washing machines or furniture, etc.), game consoles, personal computers (personal computers, PCs), teller machines or self-service machines, etc.
  • a mobile Internet device Mobile Internet Device, MID
  • augmented reality augmented reality, AR
  • virtual reality virtual reality
  • VR virtual reality
  • robot wearable device
  • VUE vehicle Equipment
  • PUE pedestrian terminal
  • smart home household equipment with wireless communication functions, such as
  • Terminal-side devices, wearable devices include: smart watches, smart bracelets, smart headphones, smart eyes Mirrors, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. It should be noted that, the embodiment of the present application does not limit the specific type of the terminal 11 .
  • the network side device 12 may include an access network device or a core network device, where the access network device may also be called a radio access network device, a radio access network (Radio Access Network, RAN), a radio access network function, or a radio access network unit.
  • the access network equipment may include a base station, a WLAN access point, or a WiFi node, etc., and the base station may be called a node B, an evolved node B (eNB), an access point, a base transceiver station (Base Transceiver Station, BTS), a radio base station , radio transceiver, Basic Service Set (Basic Service Set, BSS), Extended Service Set (Extended Service Set, ESS), Home Node B, Home Evolved Node B, Transmitting Receiving Point (Transmitting Receiving Point, TRP) or the Any other suitable term in the field, as long as the same technical effect is achieved, the base station is not limited to a specific technical vocabulary.
  • the core network equipment may include but not limited to at least one of the following: core network node, core network function, mobility management entity (Mobility Management Entity, MME), access mobility management function (Access and Mobility Management Function, AMF), session management function (Session Management Function, SMF), user plane function (User Plane Function, UPF), policy control function (Policy Control Function, PCF), policy and charging rules function unit (Policy and Charging Rules Function, PCRF), edge application service Discovery function (Edge Application Server Discovery Function, EASDF), unified data management (Unified Data Management, UDM), unified data storage (Unified Data Repository, UDR), home subscriber server (Home Subscriber Server, HSS), centralized network configuration ( Centralized network configuration, CNC), network storage function (Network Repository Function, NRF), network exposure function (Network Exposure Function, NEF), local NEF (Local NEF, or L-NEF), binding support function (Binding Support Function, BSF), application function (Application Function,
  • MME mobility management entity
  • Fig. 2 is a schematic flowchart of the information processing method provided by the embodiment of the present application. As shown in Fig. 2, the method includes steps 201-202; wherein:
  • Step 201 The communication device acquires first information related to configuration information of a target AI model; the first information includes measurement-related information and/or at least one candidate data processing strategy.
  • Step 202 the communication device determines the input data or the target data processing strategy of the target AI model according to the measurement-related information and/or each of the candidate data processing strategies;
  • the target data processing strategy is used to indicate a preprocessing strategy for the measurement related information or a preprocessing strategy for the input data of the target AI model.
  • the embodiments of the present application can be applied to scenarios such as terminal positioning and channel state information (Channel State Information, CSI) estimation.
  • the target tasks performed by the target AI model may include tasks such as positioning and/or CSI estimation.
  • the first information includes: input data such as measurement-related information for AI positioning and/or at least one candidate data processing strategy for AI positioning.
  • the communication device includes at least one of the following: a terminal; a network side device; a positioning server; a monitoring device (Actor);
  • the terminal may include but not limited to the type of terminal 11 listed above;
  • the network side device may include but not limited to the type of network side device 12 listed above;
  • the positioning server may include E-SMLC, LMF or LMF evolution device.
  • the target AI model may be at least one AI network architecture obtained through deep learning or machine learning.
  • the communication device may acquire configuration information of the target AI model in advance. For example, the communication device determines the configuration information of the target AI model by itself; or, the communication device receives its The configuration information of the target AI model sent by other devices.
  • the communication device may determine at least one of the following according to the measurement-related information and/or each of the candidate data processing strategies:
  • the input data of the target AI model may include at least one of the input data format, input information and measurement information of the target AI model.
  • a preprocessing strategy for the measurement-related information may include: a strategy for indicating how to perform feature extraction, and/or a strategy for indicating how to perform measurement quantity selection Strategy.
  • the communication device may receive update information of configuration information of the target AI model and/or update information of the first information.
  • both the configuration information and the first information of the target AI model can be divided into variable parameters and fixed parameters; the update information of the configuration information of the target AI model can only be for the variable parameters and the fixed parameters in the configuration information of the target AI model.
  • Model; the update information of the first information may only be aimed at the variable parameters and the model in the first information.
  • the first information related to the configuration information of the target AI model is acquired through the communication device, and the communication device based on the measurement-related information included in the first information and/or at least one candidate data processing strategy, Determining input data or a target data processing strategy of the target AI model, since the first information includes measurement-related information and/or at least one candidate data processing strategy, the input data of the target AI model determined by the communication device based on the first information eliminates a large number of Redundant information, and the determined target data processing strategy can be used to preprocess measurement-related information to reduce redundant information, which can reduce the computational load of the target AI model and improve the predictive performance of the target AI model.
  • Model structure information may include at least one of the following:
  • Model type information may include at least one of the following: fully connected model; hybrid model; unsupervised model; supervised model.
  • model parameter information includes at least one of the following:
  • the description parameter information of the model may include the input format of the model parameters, and/or the output format of the model parameters, and the like.
  • Hyperparameter information of the model may include at least one of the following: the activation model used by the target AI model, the number of iterations, and the batch size (Batch size).
  • Initial parameter information of the model may include at least one of the following: initial parameters for meta-learning; initial parameters for training.
  • Weights of the model may include the weights and biases of the neurons of the neural network.
  • the input information of the model may include at least one of the following: the input data format of the model; the description of the data format; the data type of the model input; and the data size.
  • Model output information may include at least one of the following: model output data format; data format description; model output data.
  • Model inference process can be: the process of obtaining output information according to the configuration information of the target AI model and the measurement-related information used for AI positioning.
  • the configuration information of the target AI model may further include: a model usage indication; wherein, the model usage indication may be used to indicate: (a) the communication device independently executes the target AI model based on The target task; or, (b) the communication device assists in performing part of the target task based on the target AI model;
  • the communication device performs the first part or all of the target task based on the target AI model, obtains the first measurement result, and sends it to another communication device; the other communication device performs the second part or all of the target task, and obtains the second measurement result result; then, a prediction result of the target task is determined by the other communication device based on the first measurement result and the second measurement result.
  • the first and second portions of the target task may be the same, overlap, or be completely different.
  • the communication device performs part or all of the target task based on the target AI model, obtains the first measurement result, and sends it to another communication device; the other communication device determines the prediction result of the target task based on the first measurement result.
  • the configuration information of the target AI model provided in this embodiment of the application may include at least one of the following:
  • List information of the neural network including at least one of the following: the neuron type of each neural network; the neuron weight and/or bias of each neural network;
  • Hyperparameter information may include at least one of the following: the activation model used by the target AI model, the number of iterations and Batch size.
  • the input data of the target AI model may include at least one of the following:
  • the first channel impulse response (Channel Impulse Response, CIR) information the length of the first CIR information is N1, N1 is a positive integer;
  • the first CIR matrix is N2 ⁇ N3 dimension, and the translation parameter is M; N2, N3 and M are all positive integers;
  • the long-term long term is K1 CIR smoothed information.
  • the input data of the target AI model may also include at least one of the following: the final Positioning signal measurement information of the terminal; location information of the terminal; error information; power of the first path; delay of the first path; time of arrival TOA of the first path; reference signal time difference RSTD of the first path; angle of arrival of the first path; multipath antenna subcarrier phase difference; multipath power; multipath delay; multipath TOA; multipath RSTD; multipath angle of arrival; multipath antenna subcarrier phase difference; average excess delay; mean square Root delay extension; coherent bandwidth; multi-antenna channel impulse response; number of antennas; expected (Expected) AoA, Expected AoD; LOS/NLOS indication information; estimation error, measurement error.
  • AI model input format for example, the AI model input format may include: at least one of model input data format or format specification, length of CIR information, dimension of CIR matrix and/or translation parameters.
  • CIR-based AI positioning accuracy is higher.
  • the terminal transmits a high-dimensional CIR matrix (for example, 4096 ⁇ 18) to the core network, a large amount of feedback overhead is required; and there is a large amount of redundant information in the CIR, such as a large number of 0 elements in the middle and tail of the CIR, This not only increases the overhead of CIR feedback, but also increases the difficulty for AI models to learn CIR features.
  • the prediction accuracy of the AI model can be improved by truncating the CIR to infer the position.
  • CIR dimension expansion is to change the N1 ⁇ 1-dimensional CIR into (N1-M1) ⁇ M2-dimensional
  • Long term (Long term) smoothing method one embodiment, it may be the measurement information corresponding to K (K>1) samples, or it may be the smoothing result of the measurement information of the high-level L3.
  • a short-term smoothing method may be the measurement information corresponding to a sample, or the smoothing result of the measurement information of the physical layer L1.
  • the candidate data processing strategy provided by the embodiment of the present application may include at least one of the following: path-related information; characteristics of CIR information; normalization strategy; Long term indication; short term indication; CIR information of the average of L measurement results, where L is positive integer.
  • the characteristics of the CIR information include at least one of the following: a truncated length of the CIR information; the number of rows of the CIR matrix; the number of columns of the CIR matrix; and a CIR translation parameter.
  • the path-related information includes at least one of the following: number of paths; path feature information; path selection conditions.
  • the path feature information may include at least one of the following: time information; energy information; angle information.
  • the time information may include at least one of the following: multipath delay; multipath time of arrival (time of arrival, TOA); multipath reference signal time difference (Reference Signal Time Difference, RSTD).
  • the energy information may include at least one of the following items: multipath Reference Signal Received Power (Reference Signal Received Power, RSRP).
  • RSRP Reference Signal Received Power
  • the angle information may include at least one of the following: an angle of arrival (Angle Of Arrival, AOA) measurement result; an angle of departure (Angle of Departure, AoD) measurement result.
  • an angle of arrival Angle Of Arrival, AOA
  • an angle of departure Angle of Departure, AoD
  • the path selection condition includes at least one of the following: 1) a path whose energy is greater than a first threshold in the multipath, and the first threshold is the product value of the energy of the path with the largest energy and the first value; 2) the energy in the multipath ranks before N6 Bit path, N6 is a positive integer.
  • the normalization strategy includes at least one of the following: a time normalization strategy; an energy normalization strategy; indication information for indicating whether to normalize; a normalization coefficient.
  • the specific instructions are as follows:
  • the energy normalization strategy may include at least one of the following:
  • the terminal 1) Perform normalization processing based on the maximum value of multiple CIRs received by the terminal; for example, the multiple CIRs may include CIRs of multiple base stations and/or CIRs measured multiple times.
  • the time normalization strategy may include at least one of the following:
  • the time normalization strategy may include at least one of the following:
  • the measured CIR may be the CIR of a reference cell or a neighboring cell; the measured CIR may be a single-antenna or multi-antenna CIR; optionally, the CIR includes at least one of the following:
  • the measurement related information includes at least one of the following: signal measurement information; location information; error value; CIR information;
  • the specific instructions are as follows:
  • the signal measurement information may include at least one of the following: RSTD measurement results; RTT measurement results; AOA measurement results; AOD measurement results; RSRP; multipath measurement information; LOS indication information.
  • the multipath measurement information may include at least one of the following: power of the first path/multipath; delay of the first path/multipath; TOA of the first path/multipath; RSTD of the first path/multipath; Multipath antenna subcarrier phase difference; first path/multipath antenna subcarrier phase.
  • the location information may include at least one of the following: absolute location information (such as longitude and latitude information); relative location information.
  • the error value may include at least one of the following: a position error value; a measurement error value.
  • the CIR information may include at least one of the following: time-domain or frequency-domain CIR information; processing information (such as truncation information) of the time-domain or frequency-domain CIR information.
  • the CIR information may include at least one of the following: CIR information of a single antenna; CIR information of multiple antennas.
  • the manner in which the communication device acquires the measurement-related information may include: the communication device acquires the measurement-related information based on a target method or a target device;
  • the target method includes at least one of the following: Time Difference of Arrival (Observed Time Difference of Arrival, OTDOA); Global Navigation Satellite System (Global Navigation Satellite System, GNSS); Downlink Time Difference of Arrival TDOA; Uplink Time Difference of Arrival TDOA; Bluetooth AoA; Bluetooth AoD; RTT.
  • Time Difference of Arrival Observed Time Difference of Arrival, OTDOA
  • Global Navigation Satellite System Global Navigation Satellite System, GNSS
  • Downlink Time Difference of Arrival TDOA Uplink Time Difference of Arrival TDOA
  • Bluetooth AoA Bluetooth AoD
  • RTT Radio Timing Time Difference of Arrival
  • the target device may include at least one of the following: Bluetooth; sensor; wireless high-fidelity (WiFi).
  • the information processing method provided in the embodiment of the present application may be executed by an information processing device.
  • the information processing device provided in the embodiment of the present application is described by taking the information processing device executing the information processing method as an example.
  • FIG. 3 is a schematic structural diagram of an information processing device provided in an embodiment of the present application. As shown in FIG. 3 , the information processing device 300 can be applied to communication equipment, and the information processing device 300 includes:
  • the first acquiring module 301 is configured to acquire first information related to the configuration information of the target AI model; the first information includes measurement-related information and/or at least one candidate data processing strategy;
  • a determining module 302 configured to determine input data or a target data processing strategy of the target AI model according to the measurement-related information and/or each of the candidate data processing strategies; wherein, the target data processing strategy is used to indicate the The preprocessing strategy for the measurement-related information or the preprocessing strategy for the input data of the target AI model.
  • the communication device determines the target based on the measurement-related information included in the first information and/or at least one candidate data processing strategy.
  • the input data or target data processing strategy of the AI model since the first information includes measurement-related information and/or at least one candidate data processing strategy, the input data of the target AI model determined by the communication device based on the first information eliminates a large amount of redundancy information, and the determined target data processing strategy can be used to preprocess measurement-related information to reduce redundant information, which can reduce the computational load of the target AI model and improve the predictive performance of the target AI model.
  • the information processing device 300 also includes:
  • the second obtaining module is used for the communication device to obtain configuration information of the target AI model.
  • the configuration information of the target AI model includes at least one of the following:
  • Model ID information model structure information; model type information; model parameter information; model input information; model output information; model reasoning process; optimizer status information.
  • the input data of the target AI model includes at least one of the following:
  • the first CIR matrix is N2 ⁇ N3 dimension, and the translation parameter is M; N2, N3 and M are all positive integers;
  • the target data processing strategy includes at least one of the following:
  • the candidate data processing strategy includes at least one of the following: path-related information; features of CIR information; normalization strategy; Long term indication; short term indication; integer.
  • the path-related information includes at least one of the following: number of paths; path feature information; path selection conditions.
  • the path feature information includes at least one of the following: time information; energy information; angle information.
  • the path selection condition includes at least one of the following: a path with energy greater than a first threshold in the multipath, where the first threshold is the product value of the energy of the path with the largest energy and the first value; energy ranking in the multipath The path of the first N6 bits, where N6 is a positive integer.
  • the characteristics of the CIR information include at least one of the following:
  • the truncated length of the CIR information The truncated length of the CIR information; the number of rows of the CIR matrix; the number of columns of the CIR matrix; the CIR translation parameter number.
  • the normalization strategy includes at least one of the following: a time normalization strategy; an energy normalization strategy; indication information for indicating whether to normalize; a normalization coefficient.
  • the energy normalization strategy includes at least one of the following:
  • Amplification processing is performed based on the CIR received by the terminal.
  • the time normalization strategy includes at least one of the following:
  • the time normalization strategy includes at least one of the following:
  • the measured CIR is shifted relative to the received and transmitted Rx-Tx of the terminal and the TRP or base station.
  • the measurement related information includes at least one of the following: signal measurement information; location information; error value; CIR information;
  • the signal measurement information includes at least one of the following: reference signal time difference RSTD measurement results; round-trip time delay RTT measurement results; angle of arrival AOA measurement results; departure angle AOD measurement results; reference information received power RSRP; multipath measurement Information; line-of-sight LOS indication information.
  • the first obtaining module 301 is specifically configured to obtain the measurement-related information based on a target method or a target device; wherein the target method includes at least one of the following: time difference of arrival positioning method OTDOA; global navigation satellite system GNSS ; Downlink Time Difference of Arrival TDOA; Uplink Time Difference of Arrival TDOA; Bluetooth AoA; Bluetooth AoD; RTT;
  • the target device includes at least one of the following: bluetooth; sensor; wireless high-fidelity WiFi.
  • model structure information includes at least one of the following:
  • connection method between the input layer and the hidden layer The connection method between the input layer and the hidden layer
  • the number of neurons in each layer is the number of neurons in each layer.
  • the model type information includes at least one of the following:
  • model parameter information includes at least one of the following:
  • the configuration information of the target AI model includes at least one of the following:
  • the list information of the neural network includes at least one of the following: the neuron type of each neural network; the neuron weight and/or bias of each neural network;
  • the information processing device 300 also includes:
  • a receiving module configured to receive update information of configuration information of the target AI model, and/or update information of the first information.
  • the communication device includes at least one of the following:
  • NWADF Network data analysis function
  • LMF Location management function LMF or LMF evolved equipment.
  • the information processing apparatus in this embodiment of the present application may be a communication device, such as a communication device with an operating system, or a component of the communication device, such as an integrated circuit or a chip.
  • the operating system may be an Android (Android) operating system, an ios operating system, or other possible operating systems, which are not specifically limited in this embodiment of the present application.
  • the communication device may include at least one of the following: a terminal; a network side device; a positioning server; a monitoring device (Actor);
  • the terminal may include but not limited to the type of terminal 11 listed above;
  • the network side device may include but not limited to the type of network side device 12 listed above;
  • the positioning server may include E-SMLC, LMF or LMF evolution device.
  • the information processing device provided in the embodiment of the present application can realize each process implemented in the above information processing method embodiment, and achieve the same technical effect. To avoid repetition, details are not repeated here.
  • Fig. 4 is one of the schematic structural diagrams of the communication device provided by the embodiment of the present application.
  • the communication device 400 includes a processor 401 and a memory 402, and the memory 402 stores information that can run on the processor 401.
  • program or instruction when the program or instruction is executed by the processor 401, each step of the above-mentioned information processing method embodiment can be achieved, and the same technical effect can be achieved, in order to avoid duplication Again, no more details here.
  • the embodiment of the present application also provides a communication device, including a processor and a communication interface; wherein the processor is configured to obtain first information related to configuration information of the target AI model; the first information includes measurement-related information and/or Or at least one candidate data processing strategy; according to the measurement-related information and/or each of the candidate data processing strategies, determine the input data or target data processing strategy of the target AI model; wherein, the target data processing strategy uses Indicates a preprocessing strategy for the measurement-related information or a preprocessing strategy for the input data of the target AI model.
  • the communication device embodiment corresponds to the communication device side method embodiment above, and each implementation process and implementation mode of the above method embodiment can be applied to the communication device embodiment, and can achieve the same technical effect.
  • the communication device may include a terminal.
  • Fig. 5 is the second structural diagram of the communication device provided by the embodiment of the present application.
  • the communication device 500 includes but not limited to: a radio frequency unit 501, a network module 502, an audio output unit 503, an input unit 504, a sensor 505 , at least some components in the display unit 506 , the user input unit 507 , the interface unit 508 , the memory 509 , and the processor 510 .
  • the communication device 500 can also include a power supply (such as a battery) for supplying power to various components, and the power supply can be logically connected to the processor 510 through the power management system, so that the management of charging, discharging, and function can be realized through the power management system. Consumption management and other functions.
  • a power supply such as a battery
  • the structure of the communication device shown in FIG. 5 does not constitute a limitation to the communication device.
  • the communication device may include more or fewer components than shown in the figure, or combine some components, or arrange different components, which will not be repeated here. .
  • the input unit 504 may include a graphics processing unit (Graphics Processing Unit, GPU) 5041 and a microphone 5042, and the graphics processor 5041 is used in a video capture mode or an image capture mode by an image capture device (such as the image data of the static picture or video obtained by the camera) for processing.
  • the display unit 506 may include a display panel 5061, and the display panel 5061 may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like.
  • the user input unit 507 includes at least one of a touch panel 5071 and other input devices 5072 .
  • the touch panel 5071 is also called a touch screen.
  • the touch panel 5071 may include two touch detection devices and a touch controller part.
  • Other input devices 5072 may include, but are not limited to, physical keyboards, function keys (such as volume control keys, switch keys, etc.), trackballs, mice, and joysticks, which will not be repeated here.
  • the radio frequency unit 501 may transmit the downlink data from the network side device to the processor 510 for processing after receiving it; in addition, the radio frequency unit 501 may send uplink data to the network side device.
  • the radio frequency unit 501 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, and the like.
  • the memory 509 can be used to store software programs or instructions as well as various data.
  • the memory 509 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 instructions required by at least one function (such as a sound playing function, image playback function, etc.), etc.
  • memory 509 may include volatile memory or nonvolatile memory, or, memory 509 may include both volatile and nonvolatile memory.
  • the non-volatile memory can be read-only memory (Read-Only Memory, ROM), programmable read-only memory (Programmable ROM, PROM), erasable programmable read-only memory (Erasable PROM, EPROM), electronically programmable Erase Programmable Read-Only Memory (Electrically EPROM, EEPROM) or Flash.
  • ROM Read-Only Memory
  • PROM programmable read-only memory
  • Erasable PROM Erasable PROM
  • EPROM erasable programmable read-only memory
  • Electrical EPROM Electrical EPROM
  • EEPROM electronically programmable Erase Programmable Read-Only Memory
  • Volatile memory can be random access memory (Random Access Memory, RAM), static random access memory (Static RAM, SRAM), dynamic random access memory (Dynamic RAM, DRAM), synchronous dynamic random access memory (Synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (Double Data Rate SDRAM, DDRSDRAM), enhanced synchronous dynamic random access memory (Enhanced SDRAM, ESDRAM), synchronous connection dynamic random access memory (Synch link DRAM , SLDRAM) and Direct Memory Bus Random Access Memory (Direct Rambus RAM, DRRAM).
  • RAM Random Access Memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • DRAM synchronous dynamic random access memory
  • SDRAM double data rate synchronous dynamic random access memory
  • Double Data Rate SDRAM Double Data Rate SDRAM
  • DDRSDRAM double data rate synchronous dynamic random access memory
  • Enhanced SDRAM, ESDRAM enhanced synchronous dynamic random access memory
  • Synch link DRAM , SLDRAM
  • Direct Memory Bus Random Access Memory Direct Rambus
  • the processor 510 may include one or more processing units; optionally, the processor 510 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, etc., Modem processors mainly process wireless communication signals, such as baseband processors. It can be understood that the foregoing modem processor may not be integrated into the processor 510 .
  • the processor 510 is configured to acquire first information related to the configuration information of the target AI model;
  • the first information includes measurement-related information and/or at least one candidate data processing strategy; according to the measurement-related information and/or each of the candidate data processing strategies, determine input data or target data processing of the target AI model Policy; wherein, the target data processing policy is used to indicate a preprocessing policy for the measurement-related information or a preprocessing policy for the input data of the target AI model.
  • the communication device by acquiring the first information related to the configuration information of the target AI model, the communication device determines the target AI model based on the measurement-related information included in the first information and/or at least one candidate data processing strategy input data or target data processing strategy, because the first information includes measurement-related information and/or at least one candidate data processing strategy, so that the input data of the target AI model determined by the communication device based on the first information eliminates a large amount of redundant information,
  • the determined target data processing strategy can be used to preprocess measurement-related information to reduce redundant information, reduce the computational load of the target AI model, and improve the predictive performance of the target AI model.
  • the communication device may include a network side device.
  • FIG. 6 is the third schematic structural diagram of the communication device provided by the embodiment of the present application.
  • the antenna 601 is connected to the radio frequency device 602 .
  • the radio frequency device 602 receives information through the antenna 601, and sends the received information to the baseband device 603 for processing.
  • the baseband device 603 processes the information to be sent and sends it to the radio frequency device 602
  • the radio frequency device 602 processes the received information and sends it out through the antenna 601 .
  • the methods performed by the communication device in the above embodiments may be implemented in the baseband apparatus 603, where the baseband apparatus 603 includes a baseband processor.
  • the baseband device 603 may include at least one baseband board, for example, a plurality of chips are arranged on the baseband board, as shown in FIG.
  • the program executes the network device operations shown in the above method embodiments.
  • the communication device may further include a network interface 606, such as a common public radio interface (common public radio interface, CPRI).
  • a network interface 606 such as a common public radio interface (common public radio interface, CPRI).
  • the communication device 600 in the embodiment of the present application further includes: instructions or programs stored in the memory 605 and operable on the processor 604, and the processor 604 calls the instructions or programs in the memory 605 to execute the information processing method as described above steps, and achieve the same technical effect, in order to avoid repetition, it is not repeated here.
  • the embodiment of the present application also provides a readable storage medium.
  • the readable storage medium may be volatile or non-volatile.
  • Programs or instructions are stored on the readable storage medium.
  • the program when the instructions are executed by the processor, the various processes of the above information processing method embodiments can be realized, and the same technical effect can be achieved, so in order to avoid repetition, details are not repeated here.
  • the processor is the processor in the terminal described in the foregoing embodiments.
  • 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, and the like.
  • the embodiment of the present application further provides a chip, the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the above information processing method embodiment Each process can achieve the same technical effect, so in order to avoid repetition, it will not be repeated here.
  • the chip mentioned in the embodiment of the present application may also be called a system-on-chip, a system-on-chip, a system-on-a-chip, or a system-on-a-chip.
  • the embodiment of the present application further provides a computer program/program product, 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 above information processing method embodiment
  • a computer program/program product is stored in a storage medium
  • the computer program/program product is executed by at least one processor to implement the above information processing method embodiment
  • the methods of the above embodiments can be implemented by means of software plus a necessary general-purpose hardware platform, and of course also by hardware, but in many cases the former is better implementation.
  • the technical solution of the present application can be embodied in the form of computer software products, which are stored in a storage medium (such as ROM/RAM, magnetic disk, etc.) , CD-ROM), including several instructions to make a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) execute the methods described in the various embodiments of the present application.

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)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

本申请公开了一种信息处理方法及通信设备，属于通信技术领域，本申请实施例的信息处理方法包括：通信设备获取与目标AI模型的配置信息相关的第一信息；所述第一信息包括测量相关信息和/或至少一种候选数据处理策略；所述通信设备根据所述测量相关信息和/或各所述候选数据处理策略，确定目标AI模型的输入数据或目标数据处理策略；其中，所述目标数据处理策略用于指示针对所述测量相关信息的预处理策略或针对所述目标AI模型的输入数据的预处理策略。

Description

信息处理方法及通信设备
相关申请的交叉引用
本申请要求于2022年02月10日提交的申请号为202210126490.4，发明名称为“信息处理方法及通信设备”的中国专利申请的优先权，其通过引用方式全部并入本申请。
技术领域
本申请属于通信技术领域，具体涉及一种信息处理方法及通信设备。
背景技术
基于通信网的定位方法包括通信设备通过对参考信号进行测量，估计目标终端当前地理位置。基于通信网的定位方法主要依靠对直射径的测量结果进行定位，在存在视距(line-of-sight，LOS)径的情况下，能以较低的实现复杂度达到较高的定位精度；但是，基于通信网的定位方法容易受到非视距(NLOS)的影响，特别是当终端与定位基站之间的直射径不存在时，定位精度大幅度下降。此外，基于通信网的定位方法容易受到同步和群时延的影响，定位精度随着同步和群时延误差增大，定位精度大幅度下降。
基于人工智能(Artificial Intelligence，AI)或机器学习(ML)的定位方法，可以解决上述NLOS和同步恶化情况下的定位问题。但是，相关技术中定位方法的运算量大，预测性能低。
发明内容
本申请实施例提供一种信息处理方法及通信设备，能够解决相关技术中定位方法运算量大及预测性能低的问题。
第一方面，提供了一种信息处理方法，该方法包括：
通信设备获取与目标AI模型的配置信息相关的第一信息；所述第一信息包括测量相关信息和/或至少一种候选数据处理策略；
所述通信设备根据所述测量相关信息和/或各所述候选数据处理策略，确定所述目标AI模型的输入数据或目标数据处理策略；
其中，所述目标数据处理策略用于指示针对所述测量相关信息的预处理策略或针对所述目标AI模型的输入数据的预处理策略。
第二方面，提供了一种信息处理装置，该装置包括：
第一获取模块，用于获取与目标AI模型的配置信息相关的第一信息；所述第一信息包括测量相关信息和/或至少一种候选数据处理策略；
确定模块，用于根据所述测量相关信息和/或各所述候选数据处理策略，确定所述目标AI模型的输入数据或目标数据处理策略；其中，所述目标数据处理策略用于指示针对所述测量相关信息的预处理策略或针对所述目标AI模型的输入数据的预处理策略。
第三方面，提供了一种通信设备，该通信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一方面所述的方法。
第四方面，提供了一种通信设备，包括处理器及通信接口；其中，所述处理器用于获取与目标AI模型的配置信息相关的第一信息；所述第一信息包括测量相关信息和/或至少一种候选数据处理策略；根据所述测量相关信息和/或各所述候选数据处理策略，确定所述目标AI模型的输入数据或目标数据处理策略；其中，所述目标数据处理策略用于指示针对所述测量相关信息的预处理策略或针对所述目标AI模型的输入数据的预处理策略。
第五方面，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。
第六方面，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。
第七方面，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方法。
在本申请实施例中，通过通信设备获取与目标AI模型的配置信息相关的第一信息，通信设备基于第一信息包括的测量相关信息和/或至少一种候选数据处理策略，确定目标AI模型的输入数据或目标数据处理策略，由于第一信息包括测量相关信息和/或至少一种候选数据处理策略，使得通信设备基于第一信息确定的目标AI模型的输入数据消除了大量冗余信息，而所确定的目标数据处理策略可以用于对测量相关信息进行预处理以减少冗余信息，能够降低目标AI模型的运算量，提高目标AI模型的预测性能。
附图说明
图1是本申请实施例可应用的无线通信***的示意图；
图2是本申请实施例提供的信息处理方法的流程示意图；
图3是本申请实施例提供的信息处理装置的结构示意图；
图4是本申请实施例提供的通信设备的结构示意图之一；
图5是本申请实施例提供的通信设备的结构示意图之二；
图6是本申请实施例提供的通信设备的结构示意图之三。
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***应用以外的通信***，如第6代(6th Generation，6G)通信***。
图1是本申请实施例可应用的无线通信***的示意图，图1示出的无线通信***包括终端11和网络侧设备12；其中：
终端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终端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。核心网设备可以包含但不限于如下至少一项：核心网节点、核心网功能、移动管理实体(Mobility Management Entity，MME)、接入移动管理功能(Access and Mobility Management Function，AMF)、会话管理功能(Session Management Function，SMF)、用户平面功能(User Plane Function，UPF)、策略控制功能(Policy Control Function，PCF)、策略与计费规则功能单元(Policy and Charging Rules Function，PCRF)、边缘应用服务发现功能(Edge Application Server Discovery Function，EASDF)、统一数据管理(Unified Data Management，UDM)，统一数据仓储(Unified Data Repository，UDR)、归属用户服务器(Home Subscriber Server，HSS)、集中式网络配置(Centralized network configuration，CNC)、网络存储功能(Network Repository Function，NRF)，网络开放功能(Network Exposure Function，NEF)、本地NEF(Local NEF，或L-NEF)、绑定支持功能(Binding Support Function，BSF)、应用功能(Application Function，AF)、位置管理功能(location manage function，LMF)、增强服务移动定位中心(Enhanced Serving Mobile Location Centre，E-SMLC)、网络数据分析功 能(network data analytics function，NWDAF)等。需要说明的是，在本申请实施例中仅以NR***中的核心网设备为例进行介绍，并不限定核心网设备的具体类型。
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信息处理方法进行详细地说明。
图2是本申请实施例提供的信息处理方法的流程示意图，如图2所示，该方法包括步骤201-202；其中：
步骤201、通信设备获取与目标AI模型的配置信息相关的第一信息；所述第一信息包括测量相关信息和/或至少一种候选数据处理策略。
步骤202、通信设备根据所述测量相关信息和/或各所述候选数据处理策略，确定所述目标AI模型的输入数据或目标数据处理策略；
其中，所述目标数据处理策略用于指示针对所述测量相关信息的预处理策略或针对所述目标AI模型的输入数据的预处理策略。
需要说明的是，本申请实施例可应用于终端定位、信道状态信息(Channel State Information，CSI)估计等场景中。可选地，目标AI模型所执行的目标任务可以包括定位和/或CSI估计等任务。
以目标AI模型所执行的目标任务是定位任务为例，此时，第一信息包括：用于AI定位的测量相关信息等输入数据和/或用于AI定位的至少一种候选数据处理策略。
实际中，所述通信设备包括以下至少一项：终端；网络侧设备；定位服务器；监控设备(Actor)；NWADF；LMF或LMF演进设备。例如，终端可以包括但不限于上述所列举的终端11的类型；网络侧设备可以包括但不限于上述所列举的网络侧设备12的类型；定位服务器可以包括E-SMLC、LMF或LMF演进设备。
可选地，目标AI模型可以是通过深度学习或机器学习获得的至少一种AI网络架构。所述通信设备可以预先获取所述目标AI模型的配置信息。例如，通信设备自行确定所述目标AI模型的配置信息；或者，通信设备接收其 他设备发送的所述目标AI模型的配置信息。
通信设备获取与目标AI模型的配置信息相关的第一信息之后，通信设备可以根据所述测量相关信息和/或各所述候选数据处理策略，确定以下至少一项：
a)所述目标AI模型的输入数据；例如，目标AI模型的输入数据可以包括目标AI模型的输入数据格式、输入信息及测量信息中的至少一种。
b)针对所述测量相关信息的预处理策略；例如，针对所述测量相关信息的预处理策略可以包括：用于指示如何进行特征提取的策略，和/或用于指示如何进行测量量选择的策略。
c)针对所述目标AI模型的输入数据的预处理策略。
可选地，所述通信设备可以接收所述目标AI模型的配置信息的更新信息，和/或所述第一信息的更新信息。具体地，目标AI模型的配置信息和第一信息均可分为可变参数和固定参数；所述目标AI模型的配置信息的更新信息可以仅针对目标AI模型的配置信息中的可变参数和模型；第一信息的更新信息可以仅针对第一信息中的可变参数和模型。
本申请实施例提供的信息处理方法中，通过通信设备获取与目标AI模型的配置信息相关的第一信息，通信设备基于第一信息包括的测量相关信息和/或至少一种候选数据处理策略，确定目标AI模型的输入数据或目标数据处理策略，由于第一信息包括测量相关信息和/或至少一种候选数据处理策略，使得通信设备基于第一信息确定的目标AI模型的输入数据消除了大量冗余信息，而所确定的目标数据处理策略可以用于对测量相关信息进行预处理以减少冗余信息，能够降低目标AI模型的运算量，提高目标AI模型的预测性能。
本申请实施例提供的所述目标AI模型的配置信息可以包括以下至少一项：
1)模型标识ID信息；
2)模型结构信息；具体地，所述模型结构信息可以包括以下至少一项：
a)全连接神经网络、卷积神经网络、循环神经网络及残差网络中的任一 项或组合；
b)隐藏层的层数；
c)输入层与隐藏层的连接方式；
d)多个隐藏层之间的连接方式；
e)隐藏层与输出层的连接方式；
f)每层神经元的数目。
3)模型类型信息；例如，所述模型类型信息可以包括以下至少一项：全连接模型；混合模型；非监督模型；监督模型。
4)模型参数信息；具体地，所述模型参数信息包括以下至少一项：
a)模型应用文档；
b)模型的描述参数信息；例如，模型描述参数信息可以包括模型参数的输入格式、和/或模型参数的输出格式等。
c)模型的超参数信息；例如，模型的超参数信息可以包括以下至少一项：目标AI模型使用的激活模型、迭代次数和批尺寸(Batch size)。
d)模型的初始参数信息；例如，模型的初始参数信息可以包括以下至少一项：用于元学习的初始参数；用于训练的初始参数。
e)模型的权值；例如，模型的权值可以包括神经网络的神经元的权重和偏差。
5)模型的输入信息；其中，模型的输入信息可以包括以下至少一项：模型的输入数据格式；数据格式说明；模型输入的数据类型；数据大小。
6)模型输出信息；其中，模型输出信息可以包括以下至少一项：模型的输出数据格式；数据格式说明；模型输出的数据。
7)模型推理过程(AI inference)；例如，模型推理过程可以为：根据目标AI模型的配置信息和用于AI定位的测量相关信息，获取输出信息的过程。
8)优化器的状态信息。
可选地，所述目标AI模型的配置信息还可以包括：模型使用指示；其中，所述模型使用指示可以用于指示：(a)通信设备基于目标AI模型独立执行 目标任务；或者，(b)通信设备基于目标AI模型辅助执行目标任务的部分任务；
举例说明：通信设备基于目标AI模型执行目标任务的第一部分或全部，获得第一测量结果，并发送给另一通信设备；另一通信设备执行目标任务的第二部分或全部，获得第二测量结果；然后，由该另一通信设备基于第一测量结果和第二测量结果，确定目标任务的预测结果。可以理解的是，目标任务的第一部分和第二部分可以相同、交叠或完全不同。
再举例说明：通信设备基于目标AI模型执行目标任务的部分或全部，获得第一测量结果，发给另一通信设备；由该另一通信设备基于第一测量结果，确定目标任务的预测结果。
可选地，本申请实施例提供的所述目标AI模型的配置信息可以包括以下至少一项：
1)神经网络的列表信息，所述列表信息包括以下至少一项：每个神经网络的神经元类型；每个神经网络的神经元权值和/或偏置；
2)激活网元的类型和/或位置；
3)超参数信息；其中，超参数信息可以包括以下至少一项：目标AI模型使用的激活模型、迭代次数和Batch size。
4)损失函数信息。
可选地，所述目标AI模型的输入数据可以包括以下至少一项：
1)第一信道冲击响应(Channel Impulse Response，CIR)信息，所述第一CIR信息的长度为N1，N1为正整数；
2)第一CIR矩阵，所述第一CIR矩阵为N2×N3维，平移参数为M；N2、N3及M均为正整数；
3)N4条路径的路径相关信息，N4为正整数。
4)长期Long term的CIR信息。例如，长期long term为K1个CIR平滑后的信息。
可选地，所述目标AI模型的输入数据还可以包括以下至少一项：所述终 端的定位信号测量信息；所述终端的位置信息；误差信息；首径的功率；首径的时延；首径的到达时间TOA；首径的参考信号时间差RSTD；首径的到达角；首径的天线子载波相位差；多径的功率；多径的时延；多径的TOA；多径的RSTD；多径的到达角；多径的天线子载波相位差；平均过量时延；均方根时延拓展；相干带宽；多天线的信道冲击响应；天线数目；期望的(Expected)AoA，Expected AoD；LOS/NLOS指示信息；估计误差，测量误差。
本申请实施例提供的目标数据处理策略可以包括以下至少一项：
1)AI模型输入格式；例如，AI模型输入格式可以包括：模型输入数据格式或格式说明、CIR信息的长度、CIR矩阵的维数和/或平移参数中的至少一项。
2)CIR信息截断长度；
具体地，基于CIR的AI定位精度较高。但是，若终端向核心网传递高维CIR矩阵(例如4096×18)，则需要占用大量的反馈开销；并且，CIR中存在大量的冗余信息，如CIR的中间和尾部存在大量的0元素，这不仅增加了CIR反馈的开销，而且加大了AI模型学习CIR特征的难度。本申请实施例通过截断CIR去推断位置，能够提升AI模型的预测精度。
3)CIR矩阵的行数和/或列数；
4)CIR信息平移；
具体地，CIR维度拓展是将N1×1维的CIR，变成(N1-M1)×M2维的
5)N5条路径的路径相关信息，N5为正整数；
6)归一化策略；
7)长期(Long term)平滑方法；其中一个实施例，可以是K(K>1)个样本对应的测量信息，也可以是高层L3的测量信息的平滑结果。
8)短期(short term)平滑方法，其中一个实施例，可以是一个样本对应的测量信息，也可以是物理层L1的测量信息的平滑结果。
本申请实施例提供的候选数据处理策略可以包括以下至少一项：路径相关信息；CIR信息的特征；归一化策略；Long term指示；short term指示；L个测量结果平均的CIR信息，L为正整数。
需要说明的是，所述CIR信息的特征包括以下至少一项：CIR信息的截断长度；CIR矩阵的行数；CIR矩阵的列数；CIR平移参数。
可选地，路径相关信息包括以下至少一项：路径数目；路径特征信息；路径选择条件。具体地，路径特征信息可以包括以下至少一项：时间信息；能量信息；角度信息。
例如，时间信息可以包括以下至少一项：多径的时延；多径的到达时间(time of arrival，TOA)；多径的参考信号时间差(Reference Signal Time Difference，RSTD)。
例如，能量信息可以包括以下至少一项：多径的参考信息接收功率(Reference Signal Received Power，RSRP)。
例如，角度信息可以包括以下至少一项：到达角(Angle Of Arrival，AOA)测量结果；离开角(Angle of Departure，AoD)测量结果。
路径选择条件包括以下至少一项：1)多径中能量大于第一阈值的路径，所述第一阈值为能量最大路径的能量与第一值的乘积值；2)多径中能量排名前N6位的路径，N6为正整数。
可选地，所述归一化策略包括以下至少一项：时间归一化策略；能量归一化策略；用于指示是否归一化的指示信息；归一化系数。具体说明如下：
1、能量归一化策略可以包括以下至少一项：
1)基于终端接收到的多个CIR的最大值进行归一化处理；例如，多个CIR可以包括多个基站的CIR和/或多次测量的CIR。
2)基于终端接收到的多个TRP或基站的测量信息的最大值进行归一化处理；
3)基于终端接收到的一个CIR的最大值进行归一化处理；
4)基于终端接收到的一个TRP或基站的测量信息的最大值进行归一化处理；
5)基于终端接收到的最大径进行归一化处理；
6)基于终端接收到的CIR进行放大处理；例如，将终端接收到的CIR放大至N倍，或将终端接收到的CIR放大至最大值K。
2、时间归一化策略可以包括以下至少一项：
1)相对于多个TRP或基站的最大路径的CIR；
2)相对于参考TRP或基站的到达时间TOA对应的CIR；
3)相对于参考TRP或基站的RSTD对应的CIR；例如，将基站a的CIR变成RSTD的CIR，即CIR图样右移参考基站的TOA。
4)相对于探测参考信号(Sounding Reference Signal，SRS)的往返时延(round-trip time，RTT)对应的CIR；
5)相对于终端与TRP或基站的接收到发送(Rx-Tx)测量对应的CIR；例如，CIR图样右移TX对应的TS单位时间。
3、时间归一化策略可以包括以下至少一项：
1)相对于参考TRP或基站的最大路径的对应的时间，对其它TRP或基站的测量的CIR进行平移；
2)相对于参考TRP或基站的到达时间TOA，对测量的CIR进行平移；
3)相对于参考TRP或基站的RSTD，对测量的CIR进行平移；
4)相对于参考TRP或基站的Rx-Tx，对测量的CIR进行平移；
5)相对于SRS发送时间的TOA，对测量的CIR进行平移；
6)相对于终端与TRP或基站的Rx-Tx，对测量的CIR进行平移；例如，CIR图样右移TX对应的TS单位时间。
值得注意的是，所述测量的CIR可以是参考小区或者邻小区的CIR；所述测量的CIR可以是单天线或者多天线的CIR；可选地，所述CIR包括以下至少一项：
时域信道冲击响应；
时域互相关向量或矩阵；
时域自相关向量或矩阵；
频域信道响应；
频域互相关向量或矩阵；
频域自相关向量或矩阵；
频域子载波相位向量或矩阵；
频域子载波相位差向量或矩阵。
可选地，所述测量相关信息包括以下至少一项：信号测量信息；位置信息；误差值；CIR信息；功率时延谱PDP信息。具体说明如下：
1)信号测量信息可以包括以下至少一项：RSTD测量结果；RTT测量结果；AOA测量结果；AOD测量结果；RSRP；多径测量信息；LOS指示信息。具体地，多径测量信息可以包括以下至少一项：首径/多径的功率；首径/多径的时延；首径/多径的TOA；首径/多径的RSTD；首径/多径的天线子载波相位差；首径/多径的天线子载波相位。
2)位置信息可以包括以下至少一项：绝对位置信息(如经纬度信息)；相对位置信息。
3)误差值可以包括以下至少一项：位置误差值；测量误差值。
4)CIR信息可以包括以下至少一项：时域或频域CIR信息；时域或频域CIR信息的处理信息(如截断信息)。
5)CIR信息可以包括以下至少一项：单天线的CIR信息；多天线的CIR信息。
可选地，所述通信设备获取所述测量相关信息的实现方式可以包括：所述通信设备基于目标方式或目标设备，获取所述测量相关信息；
其中，所述目标方式包括以下至少一项：到达时间差定位法(Observed Time Difference of Arrival，OTDOA)；全球导航卫星***(Global Navigation Satellite System，GNSS)；下行到达时间差TDOA；上行到达时间差TDOA； 蓝牙AoA；蓝牙AoD；RTT。
实际中，目标设备可以包括以下至少一项：蓝牙；传感器；无线高保真(WiFi)。
本申请实施例提供的信息处理方法，执行主体可以为信息处理装置。本申请实施例中以信息处理装置执行信息处理方法为例，说明本申请实施例提供的信息处理装置。
图3是本申请实施例提供的信息处理装置的结构示意图，如图3所示，该信息处理装置300可以应用于通信设备，该信息处理装置300包括：
第一获取模块301，用于获取与目标AI模型的配置信息相关的第一信息；所述第一信息包括测量相关信息和/或至少一种候选数据处理策略；
确定模块302，用于根据所述测量相关信息和/或各所述候选数据处理策略，确定所述目标AI模型的输入数据或目标数据处理策略；其中，所述目标数据处理策略用于指示针对所述测量相关信息的预处理策略或针对所述目标AI模型的输入数据的预处理策略。
本申请实施例提供的信息处理装置中，通过获取与目标AI模型的配置信息相关的第一信息，通信设备基于第一信息包括的测量相关信息和/或至少一种候选数据处理策略，确定目标AI模型的输入数据或目标数据处理策略，由于第一信息包括测量相关信息和/或至少一种候选数据处理策略，使得通信设备基于第一信息确定的目标AI模型的输入数据消除了大量冗余信息，而所确定的目标数据处理策略可以用于对测量相关信息进行预处理以减少冗余信息，能够降低目标AI模型的运算量，提高目标AI模型的预测性能。
可选地，该信息处理装置300还包括：
第二获取模块，用于所述通信设备获取所述目标AI模型的配置信息。
可选地，所述目标AI模型的配置信息包括以下至少一项：
模型标识ID信息；模型结构信息；模型类型信息；模型参数信息；模型的输入信息；模型输出信息；模型推理过程；优化器的状态信息。
可选地，所述目标AI模型的输入数据包括以下至少一项：
第一信道冲击响应CIR信息，所述第一CIR信息的长度为N1，N1为正整数；
第一CIR矩阵，所述第一CIR矩阵为N2×N3维，平移参数为M；N2、N3及M均为正整数；
N4条路径的路径相关信息，N4为正整数；
长期Long term的CIR信息。
可选地，所述目标数据处理策略包括以下至少一项：
AI模型输入格式；
CIR信息截断长度；
CIR矩阵的行数和/或列数；
CIR信息平移；
N5条路径的路径相关信息，N5为正整数；
归一化策略；
长期Long term平滑方法；
短期short term平滑方法。
可选地，所述候选数据处理策略包括以下至少一项：路径相关信息；CIR信息的特征；归一化策略；Long term指示；short term指示；L个测量结果平均的CIR信息，L为正整数。
可选地，所述路径相关信息包括以下至少一项：路径数目；路径特征信息；路径选择条件。
可选地，所述路径特征信息包括以下至少一项：时间信息；能量信息；角度信息。
可选地，所述路径选择条件包括以下至少一项：多径中能量大于第一阈值的路径，所述第一阈值为能量最大路径的能量与第一值的乘积值；多径中能量排名前N6位的路径，N6为正整数。
可选地，所述CIR信息的特征包括以下至少一项：
CIR信息的截断长度；CIR矩阵的行数；CIR矩阵的列数；CIR平移参 数。
可选地，所述归一化策略包括以下至少一项：时间归一化策略；能量归一化策略；用于指示是否归一化的指示信息；归一化系数。
可选地，所述能量归一化策略包括以下至少一项：
基于终端接收到的多个CIR的最大值进行归一化处理；
基于终端接收到的多个发送接收点TRP或基站的测量信息的最大值进行归一化处理；
基于终端接收到的一个CIR的最大值进行归一化处理；
基于终端接收到的一个TRP或基站的测量信息的最大值进行归一化处理；
基于终端接收到的最大径进行归一化处理；
基于终端接收到的CIR进行放大处理。
可选地，所述时间归一化策略包括以下至少一项：
相对于多个TRP或基站的最大路径的CIR；
相对于参考TRP或基站的到达时间TOA对应的CIR；
相对于参考TRP或基站的参考信号时间差RSTD对应的CIR；
相对于探测参考信号SRS的往返时延RTT对应的CIR；
相对于终端与TRP或基站的接收到发送Rx-Tx测量对应的CIR。
可选地，所述时间归一化策略包括以下至少一项：
相对于参考TRP或基站的最大路径的对应的时间，对其它TRP或基站的测量的CIR进行平移；
相对于参考TRP或基站的到达时间TOA，对测量的CIR进行平移；
相对于参考TRP或基站的RSTD，对测量的CIR进行平移；
相对于参考TRP或基站的Rx-Tx，对测量的CIR进行平移；
相对于探测参考信号SRS发送时间的TOA，对测量的CIR进行平移；
相对于终端与TRP或基站的接收到发送Rx-Tx，对测量的CIR进行平移。
可选地，所述测量相关信息包括以下至少一项：信号测量信息；位置信息；误差值；CIR信息；功率时延谱PDP信息。
可选地，所述信号测量信息包括以下至少一项：参考信号时间差RSTD测量结果；往返时延RTT测量结果；到达角AOA测量结果；离开角AOD测量结果；参考信息接收功率RSRP；多径测量信息；视距LOS指示信息。
可选地，第一获取模块301，具体用于基于目标方式或目标设备，获取所述测量相关信息；其中，所述目标方式包括以下至少一项：到达时间差定位法OTDOA；全球导航卫星***GNSS；下行到达时间差TDOA；上行到达时间差TDOA；蓝牙AoA；蓝牙AoD；RTT；
所述目标设备包括以下至少一项：蓝牙；传感器；无线高保真WiFi。
可选地，所述模型结构信息包括以下至少一项：
全连接神经网络、卷积神经网络、循环神经网络及残差网络中的任一项或组合；
隐藏层的层数；
输入层与隐藏层的连接方式；
多个隐藏层之间的连接方式；
隐藏层与输出层的连接方式；
每层神经元的数目。
可选地，所述模型类型信息包括以下至少一项：
全连接模型；混合模型；非监督模型；监督模型。
可选地，所述模型参数信息包括以下至少一项：
模型应用文档；
模型的描述参数信息；
模型的超参数信息；
模型的初始参数信息；
模型的权值。
可选地，所述目标AI模型的配置信息包括以下至少一项：
神经网络的列表信息，所述列表信息包括以下至少一项：每个神经网络的神经元类型；每个神经网络的神经元权值和/或偏置；
激活网元的类型和/或位置；
超参数信息；
损失函数信息。
可选地，该信息处理装置300还包括：
接收模块，用于接收所述目标AI模型的配置信息的更新信息，和/或所述第一信息的更新信息。
可选地，所述通信设备包括以下至少一项：
终端；
网络侧设备；
定位服务器；
监控设备Actor；
网络数据分析功能NWADF；
位置管理功能LMF或LMF演进设备。
本申请实施例中的信息处理装置可以是通信设备，例如具有操作***的通信设备，也可以是通信设备中的部件，例如集成电路或芯片。该操作***可以为安卓(Android)操作***，可以为ios操作***，还可以为其他可能的操作***，本申请实施例不作具体限定。该通信设备可以包括以下至少一项：终端；网络侧设备；定位服务器；监控设备(Actor)；NWADF；LMF或LMF演进设备。例如，终端可以包括但不限于上述所列举的终端11的类型；网络侧设备可以包括但不限于上述所列举的网络侧设备12的类型；定位服务器可以包括E-SMLC、LMF或LMF演进设备。
本申请实施例提供的信息处理装置能够实现上述信息处理方法实施例实现的各个过程，并达到相同的技术效果，为避免重复，这里不再赘述。
图4是本申请实施例提供的通信设备的结构示意图之一，如图4所示，该通信设备400，包括处理器401和存储器402，存储器402上存储有可在所述处理器401上运行的程序或指令，该程序或指令被处理器401执行时实现上述信息处理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通信设备，包括处理器和通信接口；其中，所述处理器用于获取与目标AI模型的配置信息相关的第一信息；所述第一信息包括测量相关信息和/或至少一种候选数据处理策略；根据所述测量相关信息和/或各所述候选数据处理策略，确定所述目标AI模型的输入数据或目标数据处理策略；其中，所述目标数据处理策略用于指示针对所述测量相关信息的预处理策略或针对所述目标AI模型的输入数据的预处理策略。
该通信设备实施例与上述通信设备侧方法实施例对应，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通信设备实施例中，且能达到相同的技术效果。
可选地，通信设备可以包括终端。图5是本申请实施例提供的通信设备的结构示意图之二，如图5所示，该通信设备500包括但不限于：射频单元501、网络模块502、音频输出单元503、输入单元504、传感器505、显示单元506、用户输入单元507、接口单元508、存储器509以及处理器510等中的至少部分部件。
本领域技术人员可以理解，通信设备500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510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5中示出的通信设备结构并不构成对通信设备的限定，通信设备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504可以包括图形处理单元(Graphics Processing Unit，GPU)5041和麦克风5042，图形处理器5041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506可包括显示面板5061，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5061。用户输入单元507包括触控面板5071以及其他输入设备5072中的至少一种。触控面板5071，也称为触摸屏。触控面板5071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5072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501接收来自网络侧设备的下行数据后，可以传输给处理器510进行处理；另外，射频单元501可以向网络侧设备发送上行数据。通常，射频单元501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509可用于存储软件程序或指令以及各种数据。存储器509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509可以包括易失性存储器或非易失性存储器，或者，存储器509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509包括但不限于这些和任意其它适合类型的存储器。
处理器510可包括一个或多个处理单元；可选的，处理器510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510中。
其中，处理器510，用于获取与目标AI模型的配置信息相关的第一信息； 所述第一信息包括测量相关信息和/或至少一种候选数据处理策略；根据所述测量相关信息和/或各所述候选数据处理策略，确定所述目标AI模型的输入数据或目标数据处理策略；其中，所述目标数据处理策略用于指示针对所述测量相关信息的预处理策略或针对所述目标AI模型的输入数据的预处理策略。
本申请实施例提供的通信设备，通过获取与目标AI模型的配置信息相关的第一信息，通信设备基于第一信息包括的测量相关信息和/或至少一种候选数据处理策略，确定目标AI模型的输入数据或目标数据处理策略，由于第一信息包括测量相关信息和/或至少一种候选数据处理策略，使得通信设备基于第一信息确定的目标AI模型的输入数据消除了大量冗余信息，而所确定的目标数据处理策略可以用于对测量相关信息进行预处理以减少冗余信息，能够降低目标AI模型的运算量，提高目标AI模型的预测性能。
可选地，通信设备可以包括网络侧设备。图6是本申请实施例提供的通信设备的结构示意图之三，如图6所示，该通信设备600包括：天线601、射频装置602、基带装置603、处理器604和存储器605。天线601与射频装置602连接。在上行方向上，射频装置602通过天线601接收信息，将接收的信息发送给基带装置603进行处理。在下行方向上，基带装置603对要发送的信息进行处理，并发送给射频装置602，射频装置602对收到的信息进行处理后经过天线601发送出去。
以上实施例中通信设备执行的方法可以在基带装置603中实现，该基带装置603包括基带处理器。
基带装置603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6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605连接，以调用存储器605中的程序，执行以上方法实施例中所示的网络设备操作。
该通信设备还可以包括网络接口606，该接口例如为通用公共无线接口(common public radio interface，CPRI)。
具体地，本申请实施例的通信设备600还包括：存储在存储器605上并可在处理器604上运行的指令或程序，处理器604调用存储器605中的指令或程序执行如上所述信息处理方法的步骤，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，所述可读存储介质可以是以易失性的，也可以是非易失性的，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信息处理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终端中的处理器。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，实现上述信息处理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信息处理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。
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 (27)

  1. 一种信息处理方法，包括：
    通信设备获取与目标AI模型的配置信息相关的第一信息；所述第一信息包括测量相关信息和/或至少一种候选数据处理策略；
    所述通信设备根据所述测量相关信息和/或各所述候选数据处理策略，确定所述目标AI模型的输入数据或目标数据处理策略；
    其中，所述目标数据处理策略用于指示针对所述测量相关信息的预处理策略或针对所述目标AI模型的输入数据的预处理策略。
  2. 根据权利要求1所述的信息处理方法，其中，所述方法还包括：
    所述通信设备获取所述目标AI模型的配置信息。
  3. 根据权利要求1或2所述的信息处理方法，其中，所述目标AI模型的配置信息包括以下至少一项：
    模型标识ID信息；模型结构信息；模型类型信息；模型参数信息；模型的输入信息；模型输出信息；模型推理过程；优化器的状态信息。
  4. 根据权利要求1至3任一项所述的信息处理方法，其中，所述目标AI模型的输入数据包括以下至少一项：
    第一信道冲击响应CIR信息，所述第一CIR信息的长度为N1，N1为正整数；
    第一CIR矩阵，所述第一CIR矩阵为N2×N3维，平移参数为M；N2、N3及M均为正整数；
    N4条路径的路径相关信息，N4为正整数；
    长期Long term的CIR信息。
  5. 根据权利要求1至3任一项所述的信息处理方法，其中，所述目标数据处理策略包括以下至少一项：
    AI模型输入格式；
    CIR信息截断长度；
    CIR矩阵的行数和/或列数；
    CIR信息平移；
    N5条路径的路径相关信息，N5为正整数；
    归一化策略；
    长期Long term平滑方法；
    短期short term平滑方法。
  6. 根据权利要求1至3任一项所述的信息处理方法，其中，所述候选数据处理策略包括以下至少一项：
    路径相关信息；CIR信息的特征；归一化策略；Long term指示；short term指示；L个测量结果平均的CIR信息，L为正整数。
  7. 根据权利要求4至6任一项所述的信息处理方法，其中，所述路径相关信息包括以下至少一项：
    路径数目；路径特征信息；路径选择条件。
  8. 根据权利要求7所述的信息处理方法，其中，所述路径特征信息包括以下至少一项：
    时间信息；能量信息；角度信息。
  9. 根据权利要求7所述的信息处理方法，其中，所述路径选择条件包括以下至少一项：
    多径中能量大于第一阈值的路径，所述第一阈值为能量最大路径的能量与第一值的乘积值；
    多径中能量排名前N6位的路径，N6为正整数。
  10. 根据权利要求6所述的信息处理方法，其中，所述CIR信息的特征包括以下至少一项：
    CIR信息的截断长度；CIR矩阵的行数；CIR矩阵的列数；CIR平移参数。
  11. 根据权利要求5或6所述的信息处理方法，其中，所述归一化策略包括以下至少一项：
    时间归一化策略；能量归一化策略；用于指示是否归一化的指示信息；归一化系数。
  12. 根据权利要求11所述的信息处理方法，其中，所述能量归一化策略包括以下至少一项：
    基于终端接收到的多个CIR的最大值进行归一化处理；
    基于终端接收到的多个发送接收点TRP或基站的测量信息的最大值进行归一化处理；
    基于终端接收到的一个CIR的最大值进行归一化处理；
    基于终端接收到的一个TRP或基站的测量信息的最大值进行归一化处理；
    基于终端接收到的最大径进行归一化处理；
    基于终端接收到的CIR进行放大处理。
  13. 根据权利要求11所述的信息处理方法，其中，所述时间归一化策略包括以下至少一项：
    相对于多个TRP或基站的最大路径的CIR；
    相对于参考TRP或基站的到达时间TOA对应的CIR；
    相对于参考TRP或基站的参考信号时间差RSTD对应的CIR；
    相对于探测参考信号SRS的往返时延RTT对应的CIR；
    相对于终端与TRP或基站的接收到发送Rx-Tx测量对应的CIR。
  14. 根据权利要求11所述的信息处理方法，其中，所述时间归一化策略包括以下至少一项：
    相对于参考TRP或基站的最大路径的对应的时间，对其它TRP或基站的测量的CIR进行平移；
    相对于参考TRP或基站的到达时间TOA，对测量的CIR进行平移；
    相对于参考TRP或基站的RSTD，对测量的CIR进行平移；
    相对于参考TRP或基站的Rx-Tx，对测量的CIR进行平移；
    相对于探测参考信号SRS发送时间的TOA，对测量的CIR进行平移；
    相对于终端与TRP或基站的接收到发送Rx-Tx，对测量的CIR进行平移。
  15. 根据权利要求1至14任一项所述的信息处理方法，其中，所述测量相关信息包括以下至少一项：
    信号测量信息；位置信息；误差值；CIR信息；功率时延谱PDP信息。
  16. 根据权利要求15所述的信息处理方法，其中，所述信号测量信息包括以下至少一项：
    参考信号时间差RSTD测量结果；往返时延RTT测量结果；到达角AOA测量结果；离开角AOD测量结果；参考信息接收功率RSRP；多径测量信息；视距LOS指示信息。
  17. 根据权利要求4至16任一项所述的信息处理方法，其中，所述CIR包括以下至少一项：
    时域信道冲击响应；
    时域互相关向量或矩阵；
    时域自相关向量或矩阵；
    频域信道响应；
    频域互相关向量或矩阵；
    频域自相关向量或矩阵；
    频域子载波相位向量或矩阵；
    频域子载波相位差向量或矩阵。
  18. 根据权利要求1至17任一项所述的信息处理方法，其中，所述通信设备获取所述测量相关信息包括：
    所述通信设备基于目标方式或目标设备，获取所述测量相关信息；
    其中，所述目标方式包括以下至少一项：到达时间差定位法OTDOA；全球导航卫星***GNSS；下行到达时间差TDOA；上行到达时间差TDOA；蓝牙AoA；蓝牙AoD；RTT；
    所述目标设备包括以下至少一项：蓝牙；传感器；无线高保真WiFi。
  19. 根据权利要求3所述的信息处理方法，其中，所述模型结构信息包括以下至少一项：
    全连接神经网络、卷积神经网络、循环神经网络及残差网络中的任一项或组合；
    隐藏层的层数；
    输入层与隐藏层的连接方式；
    多个隐藏层之间的连接方式；
    隐藏层与输出层的连接方式；
    每层神经元的数目。
  20. 根据权利要求3所述的信息处理方法，其中，所述模型类型信息包括以下至少一项：
    全连接模型；混合模型；非监督模型；监督模型。
  21. 根据权利要求3所述的信息处理方法，其中，所述模型参数信息包括以下至少一项：
    模型应用文档；
    模型的描述参数信息；
    模型的超参数信息；
    模型的初始参数信息；
    模型的权值。
  22. 根据权利要求1或2所述的信息处理方法，其中，所述目标AI模型的配置信息包括以下至少一项：
    神经网络的列表信息，所述列表信息包括以下至少一项：每个神经网络的神经元类型；每个神经网络的神经元权值和/或偏置；
    激活网元的类型和/或位置；
    超参数信息；
    损失函数信息。
  23. 根据权利要求1至22任一项所述的信息处理方法，其中，所述方法还包括：
    所述通信设备接收所述目标AI模型的配置信息的更新信息，和/或所述 第一信息的更新信息。
  24. 根据权利要求1至23任一项所述的信息处理方法，其中，所述通信设备包括以下至少一项：
    终端；
    网络侧设备；
    定位服务器；
    监控设备Actor；
    网络数据分析功能NWADF；
    位置管理功能LMF或LMF演进设备。
  25. 一种信息处理装置，包括：
    第一获取模块，用于获取与目标AI模型的配置信息相关的第一信息；所述第一信息包括测量相关信息和/或至少一种候选数据处理策略；
    确定模块，用于根据所述测量相关信息和/或各所述候选数据处理策略，确定所述目标AI模型的输入数据或目标数据处理策略；其中，所述目标数据处理策略用于指示针对所述测量相关信息的预处理策略或针对所述目标AI模型的输入数据的预处理策略。
  26. 一种通信设备，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权利要求1至24任一项所述的信息处理方法。
  27. 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24任一项所述的信息处理方法。
PCT/CN2023/075442 2022-02-10 2023-02-10 信息处理方法及通信设备 WO2023151657A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210126490.4A CN116634553A (zh) 2022-02-10 2022-02-10 信息处理方法及通信设备
CN202210126490.4 2022-02-10

Publications (1)

Publication Number Publication Date
WO2023151657A1 true WO2023151657A1 (zh) 2023-08-17

Family

ID=87563680

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/075442 WO2023151657A1 (zh) 2022-02-10 2023-02-10 信息处理方法及通信设备

Country Status (2)

Country Link
CN (1) CN116634553A (zh)
WO (1) WO2023151657A1 (zh)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110636466A (zh) * 2019-09-06 2019-12-31 联泰集群（北京）科技有限责任公司 一种机器学习下基于信道状态信息的WiFi室内定位***
CN111357014A (zh) * 2018-09-19 2020-06-30 华为技术有限公司 一种ai模型的开发方法及装置
CN111738419A (zh) * 2020-06-19 2020-10-02 北京百度网讯科技有限公司 神经网络模型的量化方法和装置
CN112152948A (zh) * 2019-06-28 2020-12-29 华为技术有限公司 一种无线通信处理的方法和装置
WO2021035492A1 (zh) * 2019-08-26 2021-03-04 Oppo广东移动通信有限公司 一种信道状态信息处理方法、电子设备及存储介质
CN112533149A (zh) * 2020-11-27 2021-03-19 桂林理工大学 一种基于uwb移动节点的移动目标定位算法
CN113543305A (zh) * 2020-04-22 2021-10-22 维沃移动通信有限公司 定位方法、通信设备和网络设备

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111357014A (zh) * 2018-09-19 2020-06-30 华为技术有限公司 一种ai模型的开发方法及装置
CN112152948A (zh) * 2019-06-28 2020-12-29 华为技术有限公司 一种无线通信处理的方法和装置
WO2021035492A1 (zh) * 2019-08-26 2021-03-04 Oppo广东移动通信有限公司 一种信道状态信息处理方法、电子设备及存储介质
CN110636466A (zh) * 2019-09-06 2019-12-31 联泰集群（北京）科技有限责任公司 一种机器学习下基于信道状态信息的WiFi室内定位***
CN113543305A (zh) * 2020-04-22 2021-10-22 维沃移动通信有限公司 定位方法、通信设备和网络设备
CN111738419A (zh) * 2020-06-19 2020-10-02 北京百度网讯科技有限公司 神经网络模型的量化方法和装置
CN112533149A (zh) * 2020-11-27 2021-03-19 桂林理工大学 一种基于uwb移动节点的移动目标定位算法

Also Published As

Publication number Publication date
CN116634553A (zh) 2023-08-22

Similar Documents

Publication Publication Date Title
US10051423B1 (en) Time of flight estimation using a convolutional neural network
WO2023143572A1 (zh) 基于人工智能ai模型的定位方法及通信设备
WO2023151657A1 (zh) 信息处理方法及通信设备
WO2023098662A1 (zh) 定位方法及通信设备
WO2023236979A1 (zh) 定位模型的选择方法、终端及网络侧设备
WO2023098661A1 (zh) 定位方法及通信设备
WO2023185865A1 (zh) 模型有效性反馈方法、装置、终端及网络侧设备
WO2023179617A1 (zh) 定位方法、装置、终端及网络侧设备
WO2023088423A1 (zh) 定位方法、装置、终端及网络侧设备
WO2024008111A1 (zh) 数据采集方法及装置
WO2024083004A1 (zh) Ai模型配置方法、终端及网络侧设备
WO2023134653A1 (zh) 通信网络预测方法、终端及网络侧设备
WO2023125997A1 (zh) 定位方法、装置及通信设备
WO2024094036A1 (zh) 通信方法和通信装置
WO2023125986A1 (zh) 定位方法、装置及通信设备
WO2023231865A1 (zh) 感知终端的选择方法、装置及通信设备
WO2023174325A1 (zh) Ai模型的处理方法及设备
WO2023179540A1 (zh) 信道预测方法、装置及无线通信设备
WO2024027576A1 (zh) 一种ai网络模型的性能监督方法、装置和通信设备
WO2023160711A1 (zh) 组定位方法、装置及通信设备
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
WO2023088387A1 (zh) 信道预测方法、装置、ue及***
US20230319475A1 (en) Audio level adjustment based on uwb
WO2023125458A1 (zh) 通信方法、装置及相关设备
WO2023125951A1 (zh) 通信模型配置方法、装置和通信设备

Legal Events

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

Ref document number: 23752435

Country of ref document: EP

Kind code of ref document: A1