Information reporting method, information receiving method, and device

Abstract

The present application belongs to the technical field of communications. Disclosed are an information reporting method, an information receiving method, and a device. The information reporting method in the embodiments of the present application comprises: a first device sending first information to a second device, wherein the first information is used for indicating at least one type of the following information: information related to an AI function; information related to an AI model; and device capability information of the first device that is related to at least one of the AI function and the AI model.

Description

Information reporting method, information receiving method and device

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application number 202311018685.8 filed in China on August 11, 2023, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present application belongs to the field of communication technology, and specifically relates to an information reporting method, an information receiving method and a device. Background Art

[0004] Artificial Intelligence (AI) has been widely used in various fields. Integrating AI into wireless communication networks and significantly improving technical indicators such as throughput, latency, and user capacity is an important task for future wireless communication networks.

[0005] Currently, AI models can be used for business processing in a variety of scenarios, such as positioning based on AI models. The use of AI models typically requires interaction between terminals and network devices to implement AI-based business processing. Therefore, how to ensure consistent understanding of AI model-related information between terminals and networks is a problem that those skilled in the art need to solve.

[0006] Summary of the Invention

[0007] The embodiments of the present application provide an information reporting method, an information receiving method, and a device, which can solve the problem of how to ensure that the terminal side and the network side have a consistent understanding of AI model-related information.

[0008] In a first aspect, a method for reporting information is provided, comprising:

[0009] The first device sends first information to the second device, where the first information is used to indicate at least one of the following types of information: information related to an AI function; information related to an AI model; and device capability information related to the first device and at least one of the AI ​​function and the AI ​​model.

[0010] In a second aspect, a method for receiving information is provided, comprising:

[0011] The second device receives first information sent by the first device, where the first information is used to indicate at least one of the following types of information: information related to the AI ​​function; information related to the AI ​​model; and device capability information related to the first device and at least one of the AI ​​function and the AI ​​model.

[0012] In a third aspect, an information reporting device is provided, comprising:

[0013] A sending module is used to send first information to a second device, where the first information is used to indicate at least one of the following types of information: information related to the AI ​​function; information related to the AI ​​model; and device capability information related to the first device and at least one of the AI ​​function and the AI ​​model.

[0014] In a fourth aspect, an information receiving device is provided, comprising:

[0015] A receiving module is used to receive first information sent by a first device, where the first information is used to indicate at least one of the following types of information: information related to an AI function; information related to an AI model; and device capability information related to the first device and at least one of the AI ​​function and the AI ​​model.

[0016] In a fifth aspect, a first device is provided, which includes a processor and a memory, wherein the memory stores a program or instruction that can be run 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.

[0017] In a sixth aspect, a first device is provided, comprising a processor and a communication interface, wherein the processor is used to..., the communication interface is used to send first information to a second device, the first information being used to indicate at least one of the following types of information: AI function-related information; AI model-related information; device capability information of the first device related to at least one of the AI ​​function and the AI ​​model.

[0018] In the seventh aspect, a second device is provided, which includes a processor and a memory, wherein the memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the method described in the second aspect are implemented.

[0019] In an eighth aspect, a second device is provided, comprising a processor and a communication interface, wherein the communication interface is used to receive first information sent by a first device, and the first information is used to indicate at least one of the following types of information: information related to AI functions; information related to AI models; and device capability information of the first device related to at least one of the AI ​​functions and AI models.

[0020] In the ninth aspect, a readable storage medium is provided, on which a program or instruction is stored. When 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 second aspect are implemented.

[0021] In the tenth aspect, a wireless communication system is provided, comprising: a first device and a second device, wherein the first device can be used to execute the steps of the method described in the first aspect, and the second device can be used to execute the steps of the method described in the second aspect.

[0022] In the eleventh aspect, a chip is provided, comprising 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 method described in the first aspect, or to implement the method described in the second aspect.

[0023] In the twelfth aspect, a computer program / program product is provided, which is stored in a storage medium and is executed by at least one processor to implement the steps of the information reporting method described in the first aspect or the information receiving method described in the second aspect.

[0024] In an embodiment of the present application, a first device sends first information to a second device, where the first information is used to indicate at least one of the following types of information: information related to an AI function; information related to an AI model; and device capability information of the first device related to at least one of the AI ​​function and the AI ​​model. This enables the first device and the second device to have a consistent understanding of the AI ​​model, information related to the AI ​​function, and device capability information, so that the second device can assist in the lifecycle management of the first device model, and better support operations such as reasoning of the first device model, thereby improving the accuracy and reliability of the model reasoning results, and thereby improving the business processing performance of the AI ​​model. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] FIG1a is a schematic diagram of the architecture of a wireless communication system provided by an embodiment of the present application;

[0026] FIG1b is a schematic diagram of a neuron provided in an embodiment of the present application;

[0027] FIG2 is a flow chart of one of the information reporting methods provided in an embodiment of the present application;

[0028] FIG3 is a schematic diagram of a first information coding structure of an information reporting method provided in an embodiment of the present application;

[0029] FIG4 is a second flow chart of the information reporting method provided in an embodiment of the present application;

[0030] FIG5 is a schematic diagram of a structure of an information reporting device according to an embodiment of the present application;

[0031] FIG6 is a second structural diagram of the information reporting device provided in an embodiment of the present application;

[0032] FIG7 is a schematic structural diagram of a communication device provided in an embodiment of the present application;

[0033] FIG8 is a schematic structural diagram of a terminal according to an embodiment of the present application;

[0034] FIG9 is a schematic diagram of a structure of a network side device according to an embodiment of the present application;

[0035] FIG10 is a second schematic diagram of the structure of the network side device according to an embodiment of the present application. DETAILED DESCRIPTION

[0036] The following will be combined with the accompanying drawings in the embodiments of this application to clearly describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field are within the scope of protection of this application.

[0037] The terms "first", "second", etc. in 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 where appropriate, so that the embodiments of the present 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, for example, the first object can be one or more. In addition, "or" in this application represents at least one of the connected objects. For example, "A or B" covers three options, namely, Option 1: including A but not including B; Option 2: including B but not including A; Option 3: including both A and B. The character " / " generally indicates that the objects associated before and after are in an "or" relationship.

[0038] The term "indication" in this application can be either a direct indication (or explicit indication) or an indirect indication (or implicit indication). A direct indication can be understood as the sender explicitly informing the receiver of specific information, the operation to be performed, or the requested result, etc. in the instruction sent; an indirect indication can be understood as the receiver determining the corresponding information based on the instruction sent by the sender, or making a judgment and determining the operation to be performed or the requested result, etc. based on the judgment result.

[0039] It is worth noting that the technology described in the embodiments of the present application is not limited to the Long Term Evolution (LTE) / LTE-Advanced (LTE-A) system, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA) or other systems. The terms "system" and "network" in the embodiments of the present application are often used interchangeably, and the technology described can be used for the systems and radio technologies mentioned above, as well as for other systems and radio technologies. The following description describes a New Radio (NR) system for illustrative purposes, and NR terminology is used in most of the following description, but these technologies can also be applied to systems other than NR systems, such as 6th generation (6G) systems. th Generation, 6G) communication system.

[0040] FIG1a shows a block diagram of a wireless communication system applicable to an embodiment of the present application. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 may be a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer), a notebook computer, a personal digital assistant (PDA), a handheld computer, a netbook, an ultra-mobile personal computer (UMPC), a mobile internet device (MID), an augmented reality (AR), a virtual reality (VR) device, a robot, a wearable device (Wearable Device), an aircraft (flight vehicle), a vehicle user equipment (VUE), a ship-borne device, a pedestrian user equipment (PUE), a smart home (home appliances with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), a game console, a personal computer (PC), an ATM, or a self-service machine, or other terminal-side devices. Wearable devices include: smart watches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart bracelets, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among them, the vehicle-mounted device can also be called a vehicle-mounted terminal, a vehicle-mounted controller, a vehicle-mounted module, a vehicle-mounted component, a vehicle-mounted chip or a vehicle-mounted unit, etc. It should be noted that the specific type of the terminal 11 is not limited in the embodiment of the present application. The network side device 12 may include an access network device or a core network device, wherein the access network device may also be called a radio access network (Radio Access Network, RAN) device, a radio access network function or a radio access network unit. The access network device may include a base station, a wireless local area network (WLAN) access point (AP) or a wireless fidelity (WiFi) node, etc.Among them, the base station can be referred to as Node B (NB), Evolved Node B (eNB), the next generation Node B (gNB), New Radio Node B (NR Node B), access point, Relay Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), radio base station, radio transceiver, Basic Service Set (BSS), Extended Service Set (ESS), Home Node B (HNB), Home Evolved Node B (home evolved Node B), Transmission Reception Point (TRP) or other appropriate terms in the field. As long as the same technical effect is achieved, the base station is not limited to specific technical vocabulary. It should be noted that in the embodiment 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.

[0041] The core network equipment may include but is not limited to at least one of the following: core network node, core network function, mobility management entity (MME), access mobility management function (AMF), session management function (SMF), user plane function (UPF), policy control function (PCF), policy and charging rules function unit (PCRF), edge application service discovery function (EASDF), unified data management (UDM), unified data repository (UDR), home user server (HSS), centralized network configuration (CNC), network storage function (NRF), network exposure function (NEF), local NEF (L-NEF), binding support function (BSF), application function ( It should be noted that in the embodiments of the present application, only the core network device in the NR system is introduced as an example, and the specific type of the core network device is not limited.

[0042] First, the nouns and application scenarios involved in the embodiments of this application are introduced:

[0043] 1. The AI ​​unit / AI model described in the embodiments of the present application may also be referred to as an AI unit, AI model, machine learning (ML) model, ML unit, AI structure, AI function, AI feature, machine learning model, neural network, neural network function, neural network function, etc., or the AI ​​unit / AI model may also refer to a processing unit capable of implementing specific AI-related algorithms, formulas, processing flows, capabilities, etc., or the AI ​​unit / AI model may be a processing method, algorithm, function, module, or unit for a specific data set, or the AI ​​unit / AI model may be a processing method, algorithm, function, module, or unit running on AI / ML-related hardware such as a graphics processing unit (GPU), a neural network processing unit (NPU), a tensor processing unit (TPU), or an application-specific integrated circuit (ASIC), which is not specifically limited in the present invention. Optionally, the specific data set includes the input and / or output of the AI ​​unit / AI model.

[0044] Optionally, the identifier of the AI ​​unit / AI model may be an AI model identifier, an AI structure identifier, an AI algorithm identifier, or an identifier of a specific data set associated with the AI ​​unit / AI model, or an identifier of a specific scenario, environment, channel feature, or device related to the AI / ML, or an identifier of a function, feature, capability, or module related to the AI / ML. This embodiment of the present application does not specifically limit this.

[0045] 2. There are many ways to implement AI models, such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc. This application uses neural networks as an example for illustration, but does not limit the specific type of AI model.

[0046] Optionally, the neural network is composed of neurons, and a schematic diagram of a neuron is shown in FIG1b. Where a1, a2, ... a K is the input, w1,w2,…w K As weights (multiplicative coefficients), (w1,w2,…w K ) is denoted as W, b is the bias (additive coefficient), and σ(.) is the activation function. Common activation functions include Sigmoid, Tanh, and Rectified Linear Unit (ReLU).

[0047] Where z = a1w1+…+a k wk +…+a K w K +b.

[0048] Optionally, the neural network parameters are optimized using a gradient optimization algorithm. Gradient optimization algorithms are a class of algorithms that minimize or maximize an objective function (also called a loss function), which is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, a neural network model f(.) is 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. (f(x) - Y) is the loss function. The ultimate goal is to find the appropriate W,b to minimize the value of this loss function. The smaller the loss value, the closer the model is to the true value.

[0049] Currently, most common optimization algorithms are based on the BP (Error Back Propagation) algorithm. The basic concept of the BP algorithm is that the learning process consists of two steps: forward propagation of signals and backward propagation of errors. During forward propagation, input samples are passed from the input layer, processed layer by layer through each hidden layer, and then transmitted to the output layer. If the actual output of the output layer does not match the expected output, the error begins to propagate backward. Error backpropagation involves propagating the output error back through the hidden layers to the input layer layer by layer in some form, distributing the error to all units in each layer. This error signal is then generated for each unit in each layer, and used as the basis for correcting the weights of each unit. This process of adjusting the weights of each layer, including forward propagation of signals and backward propagation of errors, is repeated over and over again. This process of continuous weight adjustment is the network's learning and training process. This process continues until the error in the network output is reduced to an acceptable level, or until a pre-set number of learning cycles has been completed.

[0050] Common optimization algorithms include gradient descent, stochastic gradient descent (SGD), mini-batch gradient descent, momentum, Nesterov (name of the inventor, specifically stochastic gradient descent with momentum), adaptive gradient descent (Adagrad), root mean square prop (RMSprop), and adaptive momentum estimation (Adam).

[0051] When these optimization algorithms backpropagate errors, they all calculate the derivative / partial derivative of the current neuron based on the error / loss obtained by the loss function, add the influence of the learning rate, the previous gradient / derivative / partial derivative, etc., obtain the gradient, and pass the gradient to the previous layer.

[0052] The information reporting method provided by the embodiment of the present application is described in detail below through some embodiments and their application scenarios in combination with the accompanying drawings.

[0053] Referring to FIG. 2 , an embodiment of the present application provides an information reporting method. The execution subject of this embodiment is a first device. The method includes:

[0054] Step 101: A first device sends first information to a second device, where the first information is used to indicate at least one of the following types of information: information related to an AI function; information related to an AI model; and device capability information related to the first device and at least one of the AI ​​function and the AI ​​model.

[0055] Optionally, the first device can be a terminal or a network side device. When the first device is a terminal, the second device is a network side device, such as a core network device, for example, the core network device is a location management function (LMF); when the first device is a network side device, the second device is a different network side device, for example, the first device is an access network device, and the second device is a core network device, for example, the core network device is a location management function LMF.

[0056] Specifically, the first device sends information related to at least one of the AI ​​model and the AI ​​function, or device capability information related to at least one of the AI ​​model and the AI ​​function to the second device.

[0057] In the method of this embodiment, a first device sends first information to a second device, where the first information is used to indicate at least one of the following types of information: information related to the AI ​​function; information related to the AI ​​model; and device capability information of the first device related to at least one of the AI ​​function and the AI ​​model. This enables the first device and the second device to have a common understanding of the AI ​​model, information related to the AI ​​function, and device capability information, so that the second device can assist the first device in performing model lifecycle management, and better support operations such as model reasoning of the first device, thereby improving the accuracy and reliability of the model reasoning results, and thereby improving the business processing performance of the AI ​​model.

[0058] Optionally, when the first information is used to indicate AI function-related information, the first information includes at least one of the following:

[0059] AI function identifier, dataset identifier included in the AI ​​function, model input data type supported by the AI ​​function, model output data type supported by the AI ​​function, downlink positioning reference signal (PRS) identifier supported by the AI ​​function, PRS configuration information supported by the AI ​​function, inference latency range supported by the AI ​​function, Reference Signal Received Power (RSRP) range supported by the AI ​​function, RSRP distribution supported by the AI ​​function, Signal to Interference plus Noise Ratio (SINR) range supported by the AI ​​function, SINR distribution supported by the AI ​​function, implicit feature distribution supported by the AI ​​function, implicit feature acquisition method supported by the AI ​​function, area identifier supported by the AI ​​function, Transmission and Reception Point (TRP) identifier supported by the AI ​​function, cell identifier supported by the AI ​​function, number of TRPs supported by the AI ​​function, number of cells supported by the AI ​​function, inference accuracy supported by the AI ​​function.

[0060] Optionally, the scenario of this embodiment is that the AI ​​model comes from a network-side device or a non-network-side device.

[0061] Specifically, the AI ​​function identifier is, for example, the ID of the positioning function based on the AI ​​model;

[0062] Optionally, an AI function can contain one or more dataset IDs, and a dataset ID can correspond to one or more AI models;

[0063] Optionally, the inference latency range supported by the AI ​​function may include at least one of the following: maximum latency, minimum latency;

[0064] The RSRP range supported by the AI ​​function may, for example, indicate the minimum RSRP value supported by the AI ​​function;

[0065] The first information may include a distribution type and at least one of parameters of the RSRP distribution, for example, the distribution type is Gaussian distribution, and the parameters include mean and variance; optionally, the distribution type may be agreed upon by agreement.

[0066] The SINR range supported by the AI ​​function, for example, may indicate the minimum SINR value supported by the AI ​​function;

[0067] The first information may include a distribution type and at least one of parameters of the SINR distribution, for example, the distribution type is Gaussian distribution, and the parameters include mean and variance; optionally, the distribution type may be agreed upon by agreement.

[0068] Among them, implicit features can refer to features that have no actual physical meaning.

[0069] The area identifier supported by the AI ​​function means that the AI ​​function can be used in the area corresponding to the area identifier. For example, the AI ​​function, such as the positioning function, can be used when the terminal is in the area corresponding to the area identifier. If the area ID includes at least one;

[0070] The TRP ID supported by the AI ​​function means that the TRP corresponding to the TRP ID can use the AI ​​function, for example, the TRP ID can be one or more;

[0071] The cell identifier supported by the AI ​​function refers to the cell corresponding to the cell identifier that can use the AI ​​function. For example, the terminal can use the AI ​​function when it is in the cell corresponding to the cell identifier, such as the positioning function. It can be one or more, including at least one of the following: a global cell ID and a physical cell ID;

[0072] Optionally, the PRS identifier and cell identifier may be used to determine a specific TRP.

[0073] The inference accuracy supported by AI functions, for example, 90% of terminal positioning errors are less than or equal to 1 meter.

[0074] In one embodiment, the AI ​​function includes at least N AI models. Optionally, the AI ​​model network is not visible, for example, the model structure and parameter network of the AI ​​model are not visible.

[0075] Optionally, the type of model input data includes at least one of the following:

[0076] Time domain channel impulse response; delay power spectrum; delay spectrum; RSRP.

[0077] Specifically, the time-domain channel impulse response is used to represent the multipath delay, power, and phase of the channel. The multipath delay, power, and phase are used to represent the changes in signal delay, signal power, and signal phase caused by different paths of the channel, respectively.

[0078] Among them, the delay power spectrum is used to represent the multipath delay and power information of the channel; the delay spectrum is used to represent the delay information of the channel.

[0079] Optionally, the type of model output data includes at least one of the following:

[0080] Time of Arrival (TOA); Reference Signal Time Difference (RSTD); First indication information; Angle of Arrival (AOA); Angle of Departure (AOD); Location coordinates; The first indication information is used to indicate whether the first device and the second device are in line-of-sight (LOS) or non-line-of-sight (NLOS).

[0081] Specifically, when the first indication information indicates "1", for example, it indicates that the terminal is in line of sight to the TRP, and "0" indicates that the terminal is in non-line of sight to the TRP; the first indication information can also be a decimal between 0-1, such as 0.9, which indicates line of sight when it is greater than a certain threshold, and non-line of sight when it is less than or equal to the threshold.

[0082] Optionally, the PRS configuration information includes at least one of the following:

[0083] Signal bandwidth; comb structure, time domain multipath resolution.

[0084] Specifically, a comb-like Comb structure, such as Comb 2, 4 or 6.

[0085] Time domain multipath resolution refers to the resolution of two adjacent paths in a multipath scenario, that is, the minimum separation between the two paths required to identify them.

[0086] Optionally, the time domain multipath resolution is related to the PRS bandwidth, for example, the time domain multipath resolution is proportional to the inverse of the bandwidth a×1 / B, where B represents the bandwidth and a represents a constant.

[0087] Optionally, the inference accuracy includes at least one of the following:

[0088] The highest inference accuracy corresponding to each of the different types of model output data;

[0089] For any type of the model output data, the highest inference accuracy corresponding to each of the different types of model input data.

[0090] Specifically, this can be achieved through at least one of the following methods:

[0091] 1) The highest inference accuracy for different types of model output data supported by the AI ​​function; for example, when the model output data is location coordinates, the supported maximum inference accuracy is 90% and the terminal positioning error is 0.5 meters; or the average positioning error of the terminal is 0.5 meters; when the model output data is TOA, the supported maximum inference accuracy is 95% and the terminal positioning error is 0.5 meters; or the average positioning error of the terminal is 0.5. Optionally, the highest inference accuracy can also be the inference accuracy of the position estimated based on the TOA output of the model.

[0092] 2) Given the type of model output data, the highest inference accuracy for different input data supported by the AI ​​function; for example, when the model output data is position coordinates, the highest inference accuracy corresponding to the channel impulse response, power delay profile, delay profile, or RSRP when the model input data is respectively.

[0093] In the above embodiment, the first device reports AI function-related information to the second device, so that the first device and the second device can have a common understanding of the relevant information of the AI ​​function, so that the second device can assist the first device in the life cycle management of the model, such as activating or deactivating the model, and better support the reasoning of the first device model. For example, auxiliary information can be sent to the first device to help the first device perform operations such as model reasoning, thereby improving the accuracy and reliability of the model reasoning results, and thereby improving the business processing performance of the AI ​​model, such as positioning performance.

[0094] Optionally, all or part of the first information is reported through the capabilities of the first device.

[0095] Optionally, the first information further includes: a prerequisite feature group supporting the AI ​​function.

[0096] Optionally, the first information further includes: a feature group serial number corresponding to a feature group supporting the capability of the first device.

[0097] For example, the terminal capability is positioning capability, and the feature group supporting the positioning capability corresponds to the feature group number (index is 13-1, 13-1a, 13-2, 13-2a, etc.). For feature group 13-2 (DL PRS resources for DL ​​AOD), the prerequisite feature group is, for example, 13-1 (DLPRS processing capability).

[0098] Optionally, when the first information is used to indicate AI model-related information, the first information includes at least one of the following:

[0099] AI model identifier, dataset identifier associated with the AI ​​model, model input data type supported by the AI ​​model, model output data type supported by the AI ​​model, downlink positioning reference signal PRS identifier of the AI ​​model, PRS configuration information of the AI ​​model, inference delay range of the AI ​​model, RSRP range applicable to the AI ​​model, RSRP distribution applicable to the AI ​​model, SINR range applicable to the AI ​​model, SINR distribution applicable to the AI ​​model, implicit feature distribution applicable to the AI ​​model, implicit feature acquisition method applicable to the AI ​​model, area identifier applicable to the AI ​​model, transmission reception point TRP identifier applicable to the AI ​​model, cell identifier applicable to the AI ​​model, number of TRPs supported by the AI ​​model, number of cells supported by the AI ​​model, and inference accuracy of the AI ​​model.

[0100] The above information is similar to the information related to the AI ​​function in the aforementioned embodiment and will not be repeated here.

[0101] In the above embodiment, the first device reports AI model-related information to the second device, so that the first device and the second device have a common understanding of the relevant information of the AI ​​model, so that the second device can assist the first device in the lifecycle management of the model, and better support the reasoning and other operations of the first device model, thereby improving the accuracy and reliability of the model reasoning results, and thereby improving the business processing performance of the AI ​​model, such as positioning performance.

[0102] Optionally, the first information is represented by information of a preset length obtained by encoding, and information at different positions in the information of the preset length is used to represent different parameters in the first information.

[0103] Specifically, information can be indicated by a model identifier (ID). For example, the first information is a relatively long code (which can be fixed-length or variable-length). Codes at different positions represent different meanings. As shown in Figure 3, bits 1-10 represent the global AI model ID, bits 11-14 represent the dataset ID, bits 15-20 represent the model output type, and so on.

[0104] Optionally, all or part of the information included in the first information is reported via device capabilities;

[0105] Optionally, the encoding length of the first information and the meaning of each field may be agreed upon by a protocol.

[0106] In the above implementation, different parameters are represented by encoding at different positions of the first information, and the implementation is simple.

[0107] Optionally, model information can be reported in the following ways:

[0108] Method 1 (reporting the association information between models):

[0109] After the first device sends the first information of the first AI model to the second device, the method further includes:

[0110] If the first information of the second AI model contains at least one parameter identical to that of the first AI model, the first device sends the first information of the second AI model to the second device, where the first information of the second AI model includes at least one of the following: difference information between the second AI model and the first AI model, and association information between the first AI model and the second AI model.

[0111] Method 2 (feature-centered reporting):

[0112] When the first information includes information of multiple AI models, and the information of the multiple AI models has the same parameters, the first information includes:

[0113] The AI ​​model identifier corresponding to the same parameters.

[0114] Specifically, some information of multiple AI models may be the same. For example, multiple AI models have the same SINR range. If the information of each AI model is reported separately, this information may be reported repeatedly. To solve this problem, the above method 1 and method 2 can be used:

[0115] For method 1, if the terminal reports the information of model 1, and the model input type and output type of model 2 are the same as those of model 1, then when the terminal reports the information of model 2, it no longer reports the same information as model 1, but sends the association information between model 2 and model 1, for example, adding an indication associated with model 1 in the first information, indicating that the default information is the same as the corresponding information of model 1. The first information can also include: difference information between model 2 and model 1, such as TRP identification, inference accuracy, etc.

[0116] For method 2, for example, the AI ​​models included in the data set ID 1 include model 1, model 2 and model 3, and the AI ​​model IDs included in the model input data as the channel impulse response include model 1, model 4 and model 5, etc.

[0117] For example, the second model uses defaults at the same parameter position to indicate that the corresponding parameters of the previous model are continued to be used, in the following format: [xxx][xxx][default][default]; each [] represents a parameter, and [xxx][xxx] represents the difference information from the previous model; or the corresponding parameters of the Nth model (indicated by the model ID) are continued to be used; in the following format: [xxx][xxx][default][default], model ID, model ID is the ID of the associated model, that is, the associated information.

[0118] In the above implementation, by reporting the association information between models or reporting model information based on features, signaling overhead and resources can be saved.

[0119] Optionally, for the first parameter in the first information reported through the capability of the first device, the first information further includes: a prerequisite feature group that supports the first parameter.

[0120] Optionally, for the first information reported through the capability of the first device, the first information further includes: a feature group serial number corresponding to a feature group supporting the capability of the first device.

[0121] Optionally, the AI ​​function-related information and the AI ​​model-related information in the first information may be divided into two types of information, that is, the first information includes at least one of the following: second information and third information, the second information is used to indicate the AI ​​function-related information, and the third information is used to indicate the AI ​​model-related information;

[0122] The second information includes at least one of the following:

[0123] AI function identifier, model input data type supported by the AI ​​function, model output data type supported by the AI ​​function, and inference latency range supported by the AI ​​function;

[0124] The third information includes at least one of the following:

[0125] AI model identifier, dataset identifier associated with the AI ​​model, downlink positioning reference signal (PRS) identifier of the AI ​​model, PRS configuration information of the AI ​​model, RSRP range applicable to the AI ​​model, RSRP distribution applicable to the AI ​​model, SINR range applicable to the AI ​​model, SINR distribution applicable to the AI ​​model, implicit feature distribution applicable to the AI ​​model, implicit feature acquisition method applicable to the AI ​​model, area identifier applicable to the AI ​​model, transmission receiving point (TRP) identifier applicable to the AI ​​model, cell identifier applicable to the AI ​​model, number of TRPs supported by the AI ​​model, number of cells supported by the AI ​​model, and inference accuracy of the AI ​​model.

[0126] The above information is similar to the information related to the AI ​​function in the aforementioned embodiment and will not be repeated here.

[0127] Optionally, the second information is reported through the capability of the first device, and the third information is carried by the second information through radio resource control (RRC) signaling or media access control (MAC)-control element (CE) or long-term evolution positioning protocol (LTE Positioning Protocol, LPP) signaling.

[0128] Optionally, the device capability information of the first device related to at least one of the AI ​​function and the AI ​​model includes at least one of the following: capability to support model deployment; capability to measure model input data;

[0129] The support capabilities for model deployment include at least one of the following:

[0130] The maximum supported model computational complexity;

[0131] The maximum number of model parameters supported;

[0132] The maximum number of models supported;

[0133] Model storage capabilities;

[0134] Computing ability;

[0135] whether to support receiving the model from the second device;

[0136] Whether to support deployment of the model from the second device;

[0137] Ability to compile AI models;

[0138] The ability to measure model input data includes at least one of the following:

[0139] The data types supported for measurement;

[0140] The maximum number of paths supported for measurement;

[0141] The maximum number of additional paths supported for measurement;

[0142] Maximum number of channel taps supported for measurement;

[0143] The maximum number of TRPs supported for measurement;

[0144] The PRS that supports the maximum number of TRPs measured within the preset measurement time window;

[0145] Supported preprocessing methods for model input data.

[0146] Specifically, support capabilities for model deployment, such as those related to computing power and storage;

[0147] For example, the maximum AI model computational complexity supported by the terminal is 20 million floating-point operations per second (MFLOPs).

[0148] For example, the maximum model parameter amount supported by the terminal is 200KB. Optionally, the model parameter amount can be divided into levels based on different parameter scales, such as A: <100k, B: 100k~1M, C: >1M. Correspondingly, the maximum model parameter amount supported by the terminal can be expressed by level, for example, the level of the maximum model parameter amount supported by the terminal is B.

[0149] Optionally, the data type supported for measurement is consistent with the type of model input data, including at least one of the following: time domain channel impulse response; delay power spectrum; delay spectrum; RSRP.

[0150] Here, the maximum number of additional paths refers to the number of paths other than the primary path, for example;

[0151] The maximum number of TRPs supported for measurement, for example, refers to the maximum number of TRPs for one positioning;

[0152] Among them, the preset measurement time window refers to the measurement time window for measuring the PRS of the maximum TRP number TRP, that is, the PRS of the maximum TRP number TRP needs to be configured within the measurement time window.

[0153] Optionally, the preprocessing method of the model input data includes at least one of the following: truncation processing, fast Fourier transform FFT and normalization.

[0154] Optionally, the truncation process involves, for example, at least one of the following information: truncation length, position, and other information.

[0155] Optionally, the FFT information includes, for example, an FFT window length.

[0156] Optionally, the scenario of this embodiment may be that the AI ​​model of the first device comes from the second device.

[0157] In the above implementation, the first device reports device capability information to the second device, so that the first device and the second device have a common understanding of the device capability information of the first device, so that the second device can assist in the lifecycle management of the first device model, and better support the reasoning and other operations of the first device model, thereby improving the accuracy and reliability of the model reasoning results, and thereby improving the business processing performance of the AI ​​model, such as positioning performance.

[0158] For example, for AI positioning, there are two types of terminal-side models:

[0159] Case 1: AI / ML Direct Positioning Model

[0160] The model input data includes, for example, the following types: time domain channel impulse response CIR, delay power spectrum PDP or delay spectrum DP;

[0161] The type of model output data is position;

[0162] Case 2: AI / ML Assisted Positioning Model

[0163] The model input data includes, for example, the following types: time domain channel impulse response CIR, delay power spectrum PDP or delay spectrum DP;

[0164] Model output data includes the following types, for example: TOA, RSTD, or LoS / NLoS;

[0165] For example, the model source at the terminal includes the following cases:

[0166] a) Model transfer from NW side;

[0167] b) Model delivery from non-NW side;

[0168] Specifically, for a), the terminal side model comes entirely from the network NW side, so the NW side has all the information of the terminal side model, and the terminal can report the device capability information in the first information to the network side device; for b), the terminal side model comes entirely from the non-NW side, so the NW side has no information of the UE side model, and the terminal can report the first information to the network side device, such as AI function-related information, AI model-related information, and device capability information.

[0169] For example, AI model-related information can be divided into two categories:

[0170] a) Representation information of the model, which is used to reconstruct the model. The representation information of the model includes the model structure, parameters, computational complexity, and parameter quantity;

[0171] b) Underlying information of the model, which is used to represent the data set information used to train the model;

[0172] For example, the AI ​​model identifier, the inference delay range of the AI ​​model, the RSRP range applicable to the AI ​​model, the RSRP distribution applicable to the AI ​​model, the SINR range applicable to the AI ​​model, the SINR distribution applicable to the AI ​​model, the implicit feature distribution applicable to the AI ​​model, the implicit feature acquisition method applicable to the AI ​​model, the number of TRPs supported by the AI ​​model, the number of cells supported by the AI ​​model, the inference accuracy of the AI ​​model, the model calculation complexity, the number of model parameters, etc. can be called the characterization information of the model.

[0173] For example, the dataset identifier associated with the AI ​​model, the type of model input data supported by the AI ​​model, the type of model output data supported by the AI ​​model, etc. can be called the potential information of the model.

[0174] It should be noted that the developer of the model owns all the information of the model. The representation information of the model is just a bunch of parameters and operation logic, and the potential information of the model gives the model a soul.

[0175] The dataset-related information includes:

[0176] a) Input and output information (basic information, also called static information): Essentially, AI model training learns the relationship between input and output. This information is reflected in the model parameters, including the type of model input data, the type of model output data, size, preprocessing, post-processing, etc.

[0177] b) Dataset description information (also called dynamic information): used to describe the attributes of the dataset, such as area ID, SINR range, error distribution, etc.

[0178] It should be noted that the input and output information is the basic information required for the model to run; the descriptive information of the dataset is related to the model generalization and applicability conditions.

[0179] FIG4 is a second flow chart of the information reporting method provided in an embodiment of the present application. As shown in FIG4 , the method is applied to the second device, including:

[0180] Step 201: The second device receives first information sent by the first device, where the first information is used to indicate at least one of the following types of information: information related to AI functions; information related to AI models; and device capability information related to the first device and at least one of the AI ​​functions and AI models.

[0181] Optionally, the first information includes at least one of the following:

[0182] AI function identifier, dataset identifier included in the AI ​​function, model input data type supported by the AI ​​function, model output data type supported by the AI ​​function, downlink positioning reference signal PRS identifier supported by the AI ​​function, PRS configuration information supported by the AI ​​function, inference delay range supported by the AI ​​function, reference signal received power RSRP range supported by the AI ​​function, RSRP distribution supported by the AI ​​function, signal-to-interference and noise ratio SINR range supported by the AI ​​function, SINR distribution supported by the AI ​​function, implicit feature distribution supported by the AI ​​function, implicit feature acquisition method supported by the AI ​​function, area identifier supported by the AI ​​function, transmission receiving point TRP identifier supported by the AI ​​function, cell identifier supported by the AI ​​function, number of TRPs supported by the AI ​​function, number of cells supported by the AI ​​function, inference accuracy supported by the AI ​​function.

[0183] Optionally, the first information includes at least one of the following:

[0184] AI model identifier, dataset identifier associated with the AI ​​model, model input data type supported by the AI ​​model, model output data type supported by the AI ​​model, downlink positioning reference signal PRS identifier of the AI ​​model, PRS configuration information of the AI ​​model, inference delay range of the AI ​​model, RSRP range applicable to the AI ​​model, RSRP distribution applicable to the AI ​​model, SINR range applicable to the AI ​​model, SINR distribution applicable to the AI ​​model, implicit feature distribution applicable to the AI ​​model, implicit feature acquisition method applicable to the AI ​​model, area identifier applicable to the AI ​​model, transmission reception point TRP identifier applicable to the AI ​​model, cell identifier applicable to the AI ​​model, number of TRPs supported by the AI ​​model, number of cells supported by the AI ​​model, and inference accuracy of the AI ​​model.

[0185] Optionally, the first information includes at least one of the following: second information and third information, wherein the second information is used to indicate AI function-related information, and the third information is used to indicate AI model-related information;

[0186] The second information includes at least one of the following:

[0187] AI function identifier, model input data type supported by the AI ​​function, model output data type supported by the AI ​​function, and inference latency range supported by the AI ​​function;

[0188] The third information includes at least one of the following:

[0189] AI model identifier, dataset identifier associated with the AI ​​model, downlink positioning reference signal (PRS) identifier of the AI ​​model, PRS configuration information of the AI ​​model, RSRP range applicable to the AI ​​model, RSRP distribution applicable to the AI ​​model, SINR range applicable to the AI ​​model, SINR distribution applicable to the AI ​​model, implicit feature distribution applicable to the AI ​​model, implicit feature acquisition method applicable to the AI ​​model, area identifier applicable to the AI ​​model, transmission receiving point (TRP) identifier applicable to the AI ​​model, cell identifier applicable to the AI ​​model, number of TRPs supported by the AI ​​model, number of cells supported by the AI ​​model, and inference accuracy of the AI ​​model.

[0190] Optionally, the type of the model input data includes at least one of the following:

[0191] Time domain channel impulse response; delay power spectrum; delay spectrum; RSRP.

[0192] Optionally, the type of the model output data includes at least one of the following:

[0193] Arrival time TOA; reference signal time difference RSTD; first indication information; angle of arrival AOA; angle of departure AOD; position coordinates; the first indication information is used to indicate that the first device and the second device are in line-of-sight LOS or non-line-of-sight NLOS.

[0194] Optionally, the PRS configuration information includes at least one of the following:

[0195] Signal bandwidth; comb structure, time domain multipath resolution.

[0196] Optionally, the reasoning accuracy includes at least one of the following:

[0197] The highest inference accuracy corresponding to each of the different types of model output data;

[0198] For any type of the model output data, the highest inference accuracy corresponding to each of the different types of model input data.

[0199] Optionally, the AI ​​function includes at least one AI model.

[0200] Optionally, the first information is reported through the capability of the first device.

[0201] Optionally, the first information also includes: a prerequisite feature group that supports the AI ​​function.

[0202] Optionally, the first information further includes: a feature group serial number corresponding to a feature group supporting the capability of the first device.

[0203] Optionally, the first information is represented by information of a preset length obtained by encoding, and information at different positions in the information of the preset length is used to represent different parameters in the first information.

[0204] Optionally, after the second device receives the first information of the first AI model sent by the first device, the method further includes:

[0205] If the first information of the second AI model contains at least one parameter identical to that of the first AI model, the second device receives the first information of the second AI model sent by the first device, where the first information of the second AI model includes at least one of the following: difference information between the second AI model and the first AI model, and association information between the first AI model and the second AI model.

[0206] Optionally, when the first information includes information of multiple AI models, and the information of the multiple AI models has the same parameters, the first information includes:

[0207] The AI ​​model identifier corresponding to the same parameters.

[0208] Optionally, for the first parameter in the first information reported through the capability of the first device, the first information further includes: a prerequisite feature group that supports the first parameter.

[0209] Optionally, for the first information reported through the capability of the first device, the first information further includes: a feature group serial number corresponding to a feature group supporting the capability of the first device.

[0210] Optionally, the second information is reported through the capability of the first device, and the third information is carried by the second information through radio resource control RRC signaling or media access control MAC-control element CE or long term evolution positioning protocol LPP signaling.

[0211] Optionally, the device capability information of the first device related to at least one of the AI ​​function and the AI ​​model includes at least one of the following:

[0212] Support for model deployment;

[0213] The ability to measure model input data;

[0214] The support capabilities for model deployment include at least one of the following:

[0215] The maximum supported model computational complexity;

[0216] The maximum number of model parameters supported;

[0217] The maximum number of models supported;

[0218] Model storage capabilities;

[0219] Computing ability;

[0220] whether to support receiving the model from the second device;

[0221] Whether to support deployment of the model from the second device;

[0222] Ability to compile AI models;

[0223] The ability to measure model input data includes at least one of the following:

[0224] The data types supported for measurement;

[0225] The maximum number of paths supported for measurement;

[0226] The maximum number of additional paths supported for measurement;

[0227] Maximum number of channel taps supported for measurement;

[0228] The maximum number of TRPs supported for measurement;

[0229] The PRS that supports the maximum number of TRPs measured within the preset measurement time window;

[0230] Supported preprocessing methods for model input data.

[0231] Optionally, the preprocessing method of the model input data includes at least one of the following: truncation processing, fast Fourier transform FFT and normalization.

[0232] The specific implementation process and technical effects of the method of this embodiment are similar to those in the first device-side method embodiment. For details, please refer to the detailed introduction in the first device-side method embodiment, and no further details will be given here.

[0233] The information reporting method provided in the embodiment of the present application can be executed by an information reporting device. In the embodiment of the present application, the information reporting device performing the information reporting method is taken as an example to illustrate the information reporting device provided in the embodiment of the present application.

[0234] FIG5 is a schematic diagram of a structure of an information reporting device provided in an embodiment of the present application. As shown in FIG5 , the information reporting device is applied to a first device and includes:

[0235] The sending module 110 is used to send first information to the second device, where the first information is used to indicate at least one of the following types of information: information related to the AI ​​function; information related to the AI ​​model; and device capability information related to the first device and at least one of the AI ​​function and the AI ​​model.

[0236] Optionally, the first information includes at least one of the following:

[0237] AI function identifier, dataset identifier included in the AI ​​function, model input data type supported by the AI ​​function, model output data type supported by the AI ​​function, downlink positioning reference signal PRS identifier supported by the AI ​​function, PRS configuration information supported by the AI ​​function, inference delay range supported by the AI ​​function, reference signal received power RSRP range supported by the AI ​​function, RSRP distribution supported by the AI ​​function, signal-to-interference and noise ratio SINR range supported by the AI ​​function, SINR distribution supported by the AI ​​function, implicit feature distribution supported by the AI ​​function, implicit feature acquisition method supported by the AI ​​function, area identifier supported by the AI ​​function, transmission receiving point TRP identifier supported by the AI ​​function, cell identifier supported by the AI ​​function, number of TRPs supported by the AI ​​function, number of cells supported by the AI ​​function, inference accuracy supported by the AI ​​function.

[0238] Optionally, the first information includes at least one of the following:

[0239] AI model identifier, dataset identifier associated with the AI ​​model, model input data type supported by the AI ​​model, model output data type supported by the AI ​​model, downlink positioning reference signal PRS identifier of the AI ​​model, PRS configuration information of the AI ​​model, inference delay range of the AI ​​model, RSRP range applicable to the AI ​​model, RSRP distribution applicable to the AI ​​model, SINR range applicable to the AI ​​model, SINR distribution applicable to the AI ​​model, implicit feature distribution applicable to the AI ​​model, implicit feature acquisition method applicable to the AI ​​model, area identifier applicable to the AI ​​model, transmission reception point TRP identifier applicable to the AI ​​model, cell identifier applicable to the AI ​​model, number of TRPs supported by the AI ​​model, number of cells supported by the AI ​​model, and inference accuracy of the AI ​​model.

[0240] Optionally, the first information includes at least one of the following: second information and third information, wherein the second information is used to indicate AI function-related information, and the third information is used to indicate AI model-related information;

[0241] The second information includes at least one of the following:

[0242] AI function identifier, model input data type supported by the AI ​​function, model output data type supported by the AI ​​function, and inference latency range supported by the AI ​​function;

[0243] The third information includes at least one of the following:

[0244] AI model identifier, dataset identifier associated with the AI ​​model, downlink positioning reference signal (PRS) identifier of the AI ​​model, PRS configuration information of the AI ​​model, RSRP range applicable to the AI ​​model, RSRP distribution applicable to the AI ​​model, SINR range applicable to the AI ​​model, SINR distribution applicable to the AI ​​model, implicit feature distribution applicable to the AI ​​model, implicit feature acquisition method applicable to the AI ​​model, area identifier applicable to the AI ​​model, transmission receiving point (TRP) identifier applicable to the AI ​​model, cell identifier applicable to the AI ​​model, number of TRPs supported by the AI ​​model, number of cells supported by the AI ​​model, and inference accuracy of the AI ​​model.

[0245] Optionally, the type of the model input data includes at least one of the following:

[0246] Time domain channel impulse response; delay power spectrum; delay spectrum; RSRP.

[0247] Optionally, the type of the model output data includes at least one of the following:

[0248] Arrival time TOA; reference signal time difference RSTD; first indication information; angle of arrival AOA; angle of departure AOD; position coordinates; the first indication information is used to indicate that the first device and the second device are in line-of-sight LOS or non-line-of-sight NLOS.

[0249] Optionally, the PRS configuration information includes at least one of the following:

[0250] Signal bandwidth; comb structure, time domain multipath resolution.

[0251] Optionally, the reasoning accuracy includes at least one of the following:

[0252] The highest inference accuracy corresponding to each of the different types of model output data;

[0253] For any type of the model output data, the highest inference accuracy corresponding to each of the different types of model input data.

[0254] Optionally, the AI ​​function includes at least one AI model.

[0255] Optionally, the first information is reported through the capability of the first device.

[0256] Optionally, the first information also includes: a prerequisite feature group that supports the AI ​​function.

[0257] Optionally, the first information further includes: a feature group serial number corresponding to a feature group supporting the capability of the first device.

[0258] Optionally, the first information is represented by information of a preset length obtained by encoding, and information at different positions in the information of the preset length is used to represent different parameters in the first information.

[0259] Optionally, the sending module 110 is further configured to:

[0260] After the first device sends first information of the first AI model to the second device, if the first information of the second AI model has at least one parameter identical to that of the first AI model, the first information of the second AI model is sent to the second device, where the first information of the second AI model includes at least one of the following: difference information between the second AI model and the first AI model, and association information between the first AI model and the second AI model.

[0261] Optionally, when the first information includes information of multiple AI models, and the information of the multiple AI models has the same parameters, the first information includes:

[0262] The AI ​​model identifier corresponding to the same parameters.

[0263] Optionally, for the first parameter in the first information reported through the capability of the first device, the first information further includes: a prerequisite feature group that supports the first parameter.

[0264] Optionally, for the first information reported through the capability of the first device, the first information further includes: a feature group serial number corresponding to a feature group supporting the capability of the first device.

[0265] Optionally, the second information is reported through the capability of the first device, and the third information is carried by the second information through radio resource control RRC signaling or media access control MAC-control element CE or long term evolution positioning protocol LPP signaling.

[0266] Optionally, the device capability information of the first device related to at least one of the AI ​​function and the AI ​​model includes at least one of the following:

[0267] Support for model deployment;

[0268] The ability to measure model input data;

[0269] The support capabilities for model deployment include at least one of the following:

[0270] The maximum supported model computational complexity;

[0271] The maximum number of model parameters supported;

[0272] The maximum number of models supported;

[0273] Model storage capabilities;

[0274] Computing ability;

[0275] whether to support receiving the model from the second device;

[0276] Whether to support deployment of the model from the second device;

[0277] Ability to compile AI models;

[0278] The ability to measure model input data includes at least one of the following:

[0279] The data types supported for measurement;

[0280] The maximum number of paths supported for measurement;

[0281] The maximum number of additional paths supported for measurement;

[0282] Maximum number of channel taps supported for measurement;

[0283] The maximum number of TRPs supported for measurement;

[0284] The PRS that supports the maximum number of TRPs measured within the preset measurement time window;

[0285] Supported preprocessing methods for model input data.

[0286] Optionally, the preprocessing method of the model input data includes at least one of the following: truncation processing, fast Fourier transform FFT and normalization.

[0287] The device of this embodiment can be used to execute the method of any embodiment in the aforementioned first device-side method embodiment. Its specific implementation process and technical effects are similar to those in the first device-side method embodiment. For details, please refer to the detailed introduction in the first device-side method embodiment, which will not be repeated here.

[0288] FIG6 is a second structural diagram of an information reporting apparatus provided in an embodiment of the present application. As shown in FIG6 , the information reporting apparatus is applied to a second device and includes:

[0289] The receiving module 210 is used to receive first information sent by the first device, where the first information is used to indicate at least one of the following types of information: information related to the AI ​​function; information related to the AI ​​model; and device capability information related to the first device and at least one of the AI ​​function and the AI ​​model.

[0290] Optionally, the first information includes at least one of the following:

[0291] AI function identifier, dataset identifier included in the AI ​​function, model input data type supported by the AI ​​function, model output data type supported by the AI ​​function, downlink positioning reference signal PRS identifier supported by the AI ​​function, PRS configuration information supported by the AI ​​function, inference delay range supported by the AI ​​function, reference signal received power RSRP range supported by the AI ​​function, RSRP distribution supported by the AI ​​function, signal-to-interference and noise ratio SINR range supported by the AI ​​function, SINR distribution supported by the AI ​​function, implicit feature distribution supported by the AI ​​function, implicit feature acquisition method supported by the AI ​​function, area identifier supported by the AI ​​function, transmission receiving point TRP identifier supported by the AI ​​function, cell identifier supported by the AI ​​function, number of TRPs supported by the AI ​​function, number of cells supported by the AI ​​function, inference accuracy supported by the AI ​​function.

[0292] Optionally, the first information includes at least one of the following:

[0293] AI model identifier, dataset identifier associated with the AI ​​model, model input data type supported by the AI ​​model, model output data type supported by the AI ​​model, downlink positioning reference signal PRS identifier of the AI ​​model, PRS configuration information of the AI ​​model, inference delay range of the AI ​​model, RSRP range applicable to the AI ​​model, RSRP distribution applicable to the AI ​​model, SINR range applicable to the AI ​​model, SINR distribution applicable to the AI ​​model, implicit feature distribution applicable to the AI ​​model, implicit feature acquisition method applicable to the AI ​​model, area identifier applicable to the AI ​​model, transmission reception point TRP identifier applicable to the AI ​​model, cell identifier applicable to the AI ​​model, number of TRPs supported by the AI ​​model, number of cells supported by the AI ​​model, and inference accuracy of the AI ​​model.

[0294] Optionally, the first information includes at least one of the following: second information and third information, wherein the second information is used to indicate AI function-related information, and the third information is used to indicate AI model-related information;

[0295] The second information includes at least one of the following:

[0296] AI function identifier, model input data type supported by the AI ​​function, model output data type supported by the AI ​​function, and inference latency range supported by the AI ​​function;

[0297] The third information includes at least one of the following:

[0298] AI model identifier, dataset identifier associated with the AI ​​model, downlink positioning reference signal (PRS) identifier of the AI ​​model, PRS configuration information of the AI ​​model, RSRP range applicable to the AI ​​model, RSRP distribution applicable to the AI ​​model, SINR range applicable to the AI ​​model, SINR distribution applicable to the AI ​​model, implicit feature distribution applicable to the AI ​​model, implicit feature acquisition method applicable to the AI ​​model, area identifier applicable to the AI ​​model, transmission receiving point (TRP) identifier applicable to the AI ​​model, cell identifier applicable to the AI ​​model, number of TRPs supported by the AI ​​model, number of cells supported by the AI ​​model, and inference accuracy of the AI ​​model.

[0299] Optionally, the type of the model input data includes at least one of the following:

[0300] Time domain channel impulse response; delay power spectrum; delay spectrum; RSRP.

[0301] Optionally, the type of the model output data includes at least one of the following:

[0302] Arrival time TOA; reference signal time difference RSTD; first indication information; angle of arrival AOA; angle of departure AOD; position coordinates; the first indication information is used to indicate that the first device and the second device are in line-of-sight LOS or non-line-of-sight NLOS.

[0303] Optionally, the PRS configuration information includes at least one of the following:

[0304] Signal bandwidth; comb structure, time domain multipath resolution.

[0305] Optionally, the reasoning accuracy includes at least one of the following:

[0306] The highest inference accuracy corresponding to each of the different types of model output data;

[0307] For any type of the model output data, the highest inference accuracy corresponding to each of the different types of model input data.

[0308] Optionally, the AI ​​function includes at least one AI model.

[0309] Optionally, the first information is reported through the capability of the first device.

[0310] Optionally, the first information also includes: a prerequisite feature group that supports the AI ​​function.

[0311] Optionally, the first information further includes: a feature group serial number corresponding to a feature group supporting the capability of the first device.

[0312] Optionally, the first information is represented by information of a preset length obtained by encoding, and information at different positions in the information of the preset length is used to represent different parameters in the first information.

[0313] Optionally, the receiving module 210 is further configured to:

[0314] After the second device receives the first information of the first AI model sent by the first device, if the first information of the second AI model has at least one parameter identical to that of the first AI model, the second device receives the first information of the second AI model sent by the first device, where the first information of the second AI model includes at least one of the following: difference information between the second AI model and the first AI model, and association information between the first AI model and the second AI model.

[0315] Optionally, when the first information includes information of multiple AI models, and the information of the multiple AI models has the same parameters, the first information includes:

[0316] The AI ​​model identifier corresponding to the same parameters.

[0317] Optionally, for the first parameter in the first information reported through the capability of the first device, the first information further includes: a prerequisite feature group that supports the first parameter.

[0318] Optionally, for the first information reported through the capability of the first device, the first information further includes: a feature group serial number corresponding to a feature group supporting the capability of the first device.

[0319] Optionally, the second information is reported through the capability of the first device, and the third information is carried by the second information through radio resource control RRC signaling or media access control MAC-control element CE or long term evolution positioning protocol LPP signaling.

[0320] Optionally, the device capability information of the first device related to at least one of the AI ​​function and the AI ​​model includes at least one of the following:

[0321] Support for model deployment;

[0322] The ability to measure model input data;

[0323] The support capabilities for model deployment include at least one of the following:

[0324] The maximum supported model computational complexity;

[0325] The maximum number of model parameters supported;

[0326] The maximum number of models supported;

[0327] Model storage capabilities;

[0328] Computing ability;

[0329] whether to support receiving the model from the second device;

[0330] Whether to support deployment of the model from the second device;

[0331] Ability to compile AI models;

[0332] The ability to measure model input data includes at least one of the following:

[0333] The data types supported for measurement;

[0334] The maximum number of paths supported for measurement;

[0335] The maximum number of additional paths supported for measurement;

[0336] Maximum number of channel taps supported for measurement;

[0337] The maximum number of TRPs supported for measurement;

[0338] The PRS that supports the maximum number of TRPs measured within the preset measurement time window;

[0339] Supported preprocessing methods for model input data.

[0340] Optionally, the preprocessing method of the model input data includes at least one of the following: truncation processing, fast Fourier transform FFT and normalization.

[0341] The device of this embodiment can be used to execute the method of any embodiment of the aforementioned second device side method embodiment. Its specific implementation process and technical effects are similar to those in the second device side method embodiment. For details, please refer to the detailed introduction in the second device side method embodiment, which will not be repeated here.

[0342] The information reporting device in the embodiments of the present application can be an electronic device, such as an electronic device with an operating system, or a component in an electronic device, such as an integrated circuit or chip. The electronic device can be a terminal, or it can be other devices other than a terminal. For example, the terminal can include but is not limited to the types of terminal 11 listed above, and other devices can be servers, network attached storage (NAS), etc., which are not specifically limited in the embodiments of the present application.

[0343] The information reporting device provided in the embodiment of the present application can implement the various processes implemented in the method embodiments of Figures 2 to 4 and achieve the same technical effects. To avoid repetition, they will not be described here.

[0344] As shown in Figure 7, an embodiment of the present application further provides a communication device 700, including a processor 701 and a memory 702. The memory 702 stores a program or instruction that can be run on the processor 701. For example, when the communication device 700 is a terminal, the program or instruction, when executed by the processor 701, implements the various steps of the above-mentioned information reporting method embodiment and can achieve the same technical effect. When the communication device 700 is a network-side device, the program or instruction, when executed by the processor 701, implements the various steps of the above-mentioned information reporting method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0345] An embodiment of the present application also provides a terminal, including 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 steps in the method embodiment shown in Figure 2. This terminal embodiment corresponds to the above-mentioned terminal-side method embodiment, and each implementation process and implementation method of the above-mentioned method embodiment can be applied to this terminal embodiment and can achieve the same technical effect. Specifically, Figure 8 is a schematic diagram of the hardware structure of a terminal that implements an embodiment of the present application. The terminal 800 includes but is not limited to: a radio frequency unit 801, a network module 802, an audio output unit 803, an input unit 804, a sensor 805, a display unit 806, a user input unit 807, an interface unit 808, a memory 809, and at least some of the components of the processor 810.

[0346] Those skilled in the art will appreciate that the terminal 800 may also include a power supply (such as a battery) to power various components. The power supply may be logically connected to the processor 810 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The terminal structure shown in FIG8 does not limit the terminal. The terminal may include more or fewer components than shown, or may combine certain components, or have different component arrangements, which will not be described in detail here.

[0347] It should be understood that in an embodiment of the present application, the input unit 804 may include a graphics processing unit (GPU) 8041 and a microphone 8042, and the graphics processor 8041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 806 may include a display panel 8061, and the display panel 8061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 807 includes a touch panel 8071 and at least one of other input devices 8072. The touch panel 8071 is also called a touch screen. The touch panel 8071 may include two parts: a touch detection device and a touch controller. Other input devices 8072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and an operating stick, which will not be repeated here.

[0348] In the embodiment of the present application, after receiving downlink data from a network-side device, the radio frequency unit 801 may transmit the data to the processor 810 for processing. Furthermore, the radio frequency unit 801 may send uplink data to the network-side device. Typically, the radio frequency unit 801 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low-noise amplifier, a duplexer, and the like.

[0349] The memory 809 can be used to store software programs or instructions and various data. The memory 809 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, applications or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory 809 may include a volatile memory or a non-volatile memory. Among them, 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 random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DRRAM). The memory 809 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0350] Processor 810 may include one or more processing units. Optionally, processor 810 integrates an application processor and a modem processor. The application processor primarily handles operations related to the operating system, user interface, and application programs, while the modem processor primarily processes wireless communication signals, such as a baseband processor. It is understood that the modem processor may not be integrated into processor 810.

[0351] Among them, the radio frequency unit 801 is used to send first information to the second device, where the first information is used to indicate at least one of the following types of information: AI function-related information; AI model-related information; and device capability information related to the terminal and at least one of the AI ​​function and AI model.

[0352] Optionally, the first information includes at least one of the following:

[0353] AI function identifier, dataset identifier included in the AI ​​function, model input data type supported by the AI ​​function, model output data type supported by the AI ​​function, downlink positioning reference signal PRS identifier supported by the AI ​​function, PRS configuration information supported by the AI ​​function, inference delay range supported by the AI ​​function, reference signal received power RSRP range supported by the AI ​​function, RSRP distribution supported by the AI ​​function, signal-to-interference and noise ratio SINR range supported by the AI ​​function, SINR distribution supported by the AI ​​function, implicit feature distribution supported by the AI ​​function, implicit feature acquisition method supported by the AI ​​function, area identifier supported by the AI ​​function, transmission receiving point TRP identifier supported by the AI ​​function, cell identifier supported by the AI ​​function, number of TRPs supported by the AI ​​function, number of cells supported by the AI ​​function, inference accuracy supported by the AI ​​function.

[0354] Optionally, the first information includes at least one of the following:

[0355] AI model identifier, dataset identifier associated with the AI ​​model, model input data type supported by the AI ​​model, model output data type supported by the AI ​​model, downlink positioning reference signal PRS identifier of the AI ​​model, PRS configuration information of the AI ​​model, inference delay range of the AI ​​model, RSRP range applicable to the AI ​​model, RSRP distribution applicable to the AI ​​model, SINR range applicable to the AI ​​model, SINR distribution applicable to the AI ​​model, implicit feature distribution applicable to the AI ​​model, implicit feature acquisition method applicable to the AI ​​model, area identifier applicable to the AI ​​model, transmission reception point TRP identifier applicable to the AI ​​model, cell identifier applicable to the AI ​​model, number of TRPs supported by the AI ​​model, number of cells supported by the AI ​​model, and inference accuracy of the AI ​​model.

[0356] Optionally, the first information includes at least one of the following: second information and third information, wherein the second information is used to indicate AI function-related information, and the third information is used to indicate AI model-related information;

[0357] The second information includes at least one of the following:

[0358] AI function identifier, model input data type supported by the AI ​​function, model output data type supported by the AI ​​function, and inference latency range supported by the AI ​​function;

[0359] The third information includes at least one of the following:

[0360] AI model identifier, dataset identifier associated with the AI ​​model, downlink positioning reference signal (PRS) identifier of the AI ​​model, PRS configuration information of the AI ​​model, RSRP range applicable to the AI ​​model, RSRP distribution applicable to the AI ​​model, SINR range applicable to the AI ​​model, SINR distribution applicable to the AI ​​model, implicit feature distribution applicable to the AI ​​model, implicit feature acquisition method applicable to the AI ​​model, area identifier applicable to the AI ​​model, transmission receiving point (TRP) identifier applicable to the AI ​​model, cell identifier applicable to the AI ​​model, number of TRPs supported by the AI ​​model, number of cells supported by the AI ​​model, and inference accuracy of the AI ​​model.

[0361] Optionally, the type of the model input data includes at least one of the following:

[0362] Time domain channel impulse response; delay power spectrum; delay spectrum; RSRP.

[0363] Optionally, the type of the model output data includes at least one of the following:

[0364] Arrival time TOA; reference signal time difference RSTD; first indication information; angle of arrival AOA; angle of departure AOD; position coordinates; the first indication information is used to indicate that the first device and the second device are in line-of-sight LOS or non-line-of-sight NLOS.

[0365] Optionally, the PRS configuration information includes at least one of the following:

[0366] Signal bandwidth; comb structure, time domain multipath resolution.

[0367] Optionally, the reasoning accuracy includes at least one of the following:

[0368] The highest inference accuracy corresponding to each of the different types of model output data;

[0369] For any type of the model output data, the highest inference accuracy corresponding to each of the different types of model input data.

[0370] Optionally, the AI ​​function includes at least one AI model.

[0371] Optionally, the first information is reported through the capability of the first device.

[0372] Optionally, the first information also includes: a prerequisite feature group that supports the AI ​​function.

[0373] Optionally, the first information further includes: a feature group serial number corresponding to a feature group supporting the capability of the first device.

[0374] Optionally, the first information is represented by information of a preset length obtained by encoding, and information at different positions in the information of the preset length is used to represent different parameters in the first information.

[0375] Optionally, the radio frequency unit 801 is further configured to:

[0376] After sending the first information of the first AI model to the second device, if the first information of the second AI model has at least one parameter identical to that of the first AI model, the first information of the second AI model is sent to the second device, where the first information of the second AI model includes at least one of the following: difference information between the second AI model and the first AI model, and association information between the first AI model and the second AI model.

[0377] Optionally, when the first information includes information of multiple AI models, and the information of the multiple AI models has the same parameters, the first information includes:

[0378] The AI ​​model identifier corresponding to the same parameters.

[0379] Optionally, for the first parameter in the first information reported through the capability of the first device, the first information further includes: a prerequisite feature group that supports the first parameter.

[0380] Optionally, for the first information reported through the capability of the first device, the first information further includes: a feature group serial number corresponding to a feature group supporting the capability of the first device.

[0381] Optionally, the second information is reported through the capability of the first device, and the third information is carried by the second information through radio resource control RRC signaling or media access control MAC-control element CE or long term evolution positioning protocol LPP signaling.

[0382] Optionally, the device capability information of the first device related to at least one of the AI ​​function and the AI ​​model includes at least one of the following:

[0383] Support for model deployment;

[0384] The ability to measure model input data;

[0385] The support capabilities for model deployment include at least one of the following:

[0386] The maximum supported model computational complexity;

[0387] The maximum number of model parameters supported;

[0388] The maximum number of models supported;

[0389] Model storage capabilities;

[0390] Computing ability;

[0391] whether to support receiving the model from the second device;

[0392] Whether to support deployment of the model from the second device;

[0393] Ability to compile AI models;

[0394] The ability to measure model input data includes at least one of the following:

[0395] The data types supported for measurement;

[0396] The maximum number of paths supported for measurement;

[0397] The maximum number of additional paths supported for measurement;

[0398] Maximum number of channel taps supported for measurement;

[0399] The maximum number of TRPs supported for measurement;

[0400] The PRS that supports the maximum number of TRPs measured within the preset measurement time window;

[0401] Supported preprocessing methods for model input data.

[0402] Optionally, the preprocessing method of the model input data includes at least one of the following: truncation processing, fast Fourier transform FFT and normalization.

[0403] It can be understood that the implementation process of each implementation method mentioned in this embodiment can refer to the relevant description of the method embodiment shown in Figure 2, and achieve the same or corresponding technical effects. To avoid repetition, it will not be repeated here.

[0404] The present application also provides a network-side device, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to execute a program or instruction to implement the steps of the method embodiment shown in Figure 2 or Figure 4. This network-side device embodiment corresponds to the aforementioned network-side device method embodiment, and each implementation process and implementation method of the aforementioned method embodiment is applicable to this network-side device embodiment and can achieve the same technical effects.

[0405] Specifically, embodiments of the present application also provide a network-side device. As shown in Figure 9, the network-side device 900 includes an antenna 91, a radio frequency device 92, a baseband device 93, a processor 94, and a memory 95. Antenna 91 is connected to radio frequency device 92. In the uplink direction, radio frequency device 92 receives information via antenna 91 and sends the received information to baseband device 93 for processing. In the downlink direction, baseband device 93 processes the information to be transmitted and sends it to radio frequency device 92. Radio frequency device 92 processes the received information and then sends it through antenna 91.

[0406] The method executed by the network-side device in the above embodiment may be implemented in the baseband device 93 , which includes a baseband processor.

[0407] The baseband device 93 may include, for example, at least one baseband board, on which multiple chips are arranged, as shown in Figure 9, one of the chips is, for example, a baseband processor, which is connected to the memory 95 through a bus interface to call the program in the memory 95 and execute the network device operations shown in the above method embodiment.

[0408] The network side device may further include a network interface 96, which is, for example, a Common Public Radio Interface (CPRI).

[0409] Specifically, the network side device 900 of the embodiment of the present application also includes: instructions or programs stored in the memory 95 and can be run on the processor 94. The processor 94 calls the instructions or programs in the memory 95 to execute the methods executed by each module shown in Figure 5 and achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0410] Specifically, the embodiment of the present application further provides a network side device. As shown in FIG10 , the network side device 1000 includes: a processor 1001, a network interface 1002, and a memory 1003. The network interface 1002 is, for example, a common public radio interface (CPRI).

[0411] Specifically, the network side device 1000 of the embodiment of the present application also includes: instructions or programs stored in the memory 1003 and executable on the processor 1001. The processor 1001 calls the instructions or programs in the memory 1003 to execute the method of execution of each module shown in Figure 6 and achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0412] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the above-mentioned information reporting method embodiment are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0413] The processor is the processor in the terminal 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. In some examples, the readable storage medium may be a non-transitory readable storage medium.

[0414] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned information reporting method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0415] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0416] An embodiment of the present application further provides a computer program / program product, which is stored in a storage medium. The computer program / program product is executed by at least one processor to implement the various processes of the above-mentioned information reporting method embodiment and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0417] An embodiment of the present application also provides a communication system, including: a first device and a second device, wherein the first device can be used to execute the steps of the information reporting method described above, and the second device can be used to execute the steps of the information reporting method described above.

[0418] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0419] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of a computer software product plus a necessary general-purpose hardware platform, or of course, by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes a number of instructions for enabling a terminal or network-side device to execute the methods described in each embodiment of the present application.

[0420] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms of implementation methods without departing from the purpose of this application and the scope of protection of the claims. These implementation methods are all within the protection of this application.

Claims

1. An information reporting method, comprising: The first device sends first information to the second device, where the first information is used to indicate at least one of the following types of information: information related to an AI function; information related to an AI model; and device capability information of the first device related to at least one of the AI ​​function and the AI ​​model.

2. The method according to claim 1, wherein: The first information includes at least one of the following: AI function identifier, data set identifier included in the AI ​​function, type of model input data supported by the AI ​​function, type of model output data supported by the AI ​​function, downlink positioning reference signal PRS identifier supported by the AI ​​function, configuration information of PRS supported by the AI ​​function, inference delay range supported by the AI ​​function, reference signal received power RSRP range supported by the AI ​​function, RSRP distribution supported by the AI ​​function, signal to interference and noise ratio SINR range supported by the AI ​​function, SINR distribution supported by the AI ​​function, implicit feature distribution supported by the AI ​​function, implicit feature acquisition method supported by the AI ​​function, area identifier supported by the AI ​​function, transmission receiving point TRP identifier supported by the AI ​​function, cell identifier supported by the AI ​​function, number of TRPs supported by the AI ​​function, number of cells supported by the AI ​​function, inference accuracy supported by the AI ​​function.

3. The method according to claim 1, wherein: The first information includes at least one of the following: AI model identifier, dataset identifier associated with the AI ​​model, type of model input data supported by the AI ​​model, type of model output data supported by the AI ​​model, downlink positioning reference signal PRS identifier of the AI ​​model, configuration information of the PRS of the AI ​​model, inference delay range of the AI ​​model, RSRP range applicable to the AI ​​model, RSRP distribution applicable to the AI ​​model, SINR range applicable to the AI ​​model, SINR distribution applicable to the AI ​​model, implicit feature distribution applicable to the AI ​​model, implicit feature acquisition method applicable to the AI ​​model, area identifier applicable to the AI ​​model, transmission receiving point TRP identifier applicable to the AI ​​model, cell identifier applicable to the AI ​​model, number of TRPs supported by the AI ​​model, number of cells supported by the AI ​​model, inference accuracy of the AI ​​model.

4. The method according to claim 1, wherein: The first information includes at least one of the following: second information and third information, the second information is used to indicate AI function related information, and the third information is used to indicate AI model related information; The second information includes at least one of the following: AI function identification, model input data types supported by the AI ​​function, model output data types supported by the AI ​​function, and inference latency range supported by the AI ​​function; The third information includes at least one of the following: AI model identifier, dataset identifier associated with the AI ​​model, downlink positioning reference signal PRS identifier of the AI ​​model, configuration information of the PRS of the AI ​​model, RSRP range applicable to the AI ​​model, RSRP distribution applicable to the AI ​​model, SINR range applicable to the AI ​​model, SINR distribution applicable to the AI ​​model, implicit feature distribution applicable to the AI ​​model, implicit feature acquisition method applicable to the AI ​​model, area identifier applicable to the AI ​​model, transmission receiving point TRP identifier applicable to the AI ​​model, cell identifier applicable to the AI ​​model, number of TRPs supported by the AI ​​model, number of cells supported by the AI ​​model, and inference accuracy of the AI ​​model.

5. The method according to any one of claims 2 to 4, wherein: The type of the model input data includes at least one of the following: Time domain channel impulse response; delay power spectrum; delay spectrum; RSRP.

6. The method according to any one of claims 2 to 4, wherein: The type of the model output data includes at least one of the following: Time of arrival TOA; Reference signal time difference RSTD; First indication information; Angle of arrival AOA; Angle of departure AOD; Position coordinates; the first indication information is used to indicate that the first device and the second device are in line-of-sight LOS or non-line-of-sight NLOS.

7. The method according to any one of claims 2 to 4, wherein: The PRS configuration information includes at least one of the following: Signal bandwidth; comb structure, time domain multipath resolution.

8. The method according to any one of claims 2 to 4, wherein: The reasoning accuracy includes at least one of the following: The highest inference accuracy corresponding to different types of model output data; For any type of model output data, the highest inference accuracy corresponding to different types of model input data.

9. The method according to any one of claims 1 to 8, wherein: The AI ​​function includes at least one AI model.

10. The method according to any one of claims 2 or 5-8, wherein: The first information is reported through the capability of the first device.

11. The method according to claim 10, wherein: The first information also includes: a prerequisite feature group supporting the AI ​​function.

12. The method according to claim 10, wherein: The first information also includes: a feature group serial number corresponding to the feature group supporting the capability of the first device.

13. The method according to any one of claims 3 or 5-8, wherein: The first information is represented by information of a preset length obtained by encoding, and information at different positions in the information of the preset length is used to represent different parameters in the first information.

14. The method according to any one of claims 3 or 5-8, wherein: After the first device sends the first information of the first AI model to the second device, the method further includes: If the first information of the second AI model has at least one parameter that is the same as that of the first AI model, the first device sends the first information of the second AI model to the second device, and the first information of the second AI model includes at least one of the following: difference information between the second AI model and the first AI model, and association information between the first AI model and the second AI model.

15. The method according to any one of claims 3 or 5-8, wherein: In a case where the first information includes information of multiple AI models, and the information of the multiple AI models has the same parameters, the first information includes: The AI ​​model identifier corresponding to the same parameters.

16. The method according to any one of claims 3, 5-8 or 13-15, wherein: For the first parameter in the first information reported through the capability of the first device, the first information further includes: a prerequisite feature group supporting the first parameter.

17. The method according to any one of claims 3, 5-8 or 13-15, wherein: For the first information reported through the capability of the first device, the first information further includes: a feature group serial number corresponding to a feature group supporting the capability of the first device.

18. The method according to claim 4, wherein: The second information is reported through the capability of the first device, and the third information is carried through the second information through radio resource control RRC signaling or media access control MAC-control element CE or long term evolution positioning protocol LPP signaling.

19. The method according to any one of claims 1 to 18, wherein: The device capability information of the first device related to at least one of the AI ​​function and the AI ​​model includes at least one of the following: Ability to support model deployment; The ability to measure model input data; The support capability for model deployment includes at least one of the following: The maximum supported model computational complexity; The maximum number of model parameters supported; The maximum number of models supported; Model storage capabilities; Computational capacity; whether to support receiving the model from the second device; whether to support deployment of the model from the second device; Ability to compile AI models; The ability to measure model input data includes at least one of the following: The data types supported for measurement; The maximum number of paths supported for measurement; The maximum number of additional paths supported for measurement; Maximum number of channel taps supported for measurement; The maximum number of TRPs supported for measurement; A PRS that supports the maximum number of TRPs measured within a preset measurement time window; Supported preprocessing methods for model input data.

20. The method according to claim 19, wherein: The preprocessing method of the model input data includes at least one of the following: truncation processing, fast Fourier transform FFT and normalization.

21. A method for receiving information, comprising: The second device receives first information sent by the first device, where the first information is used to indicate at least one of the following types of information: information related to the AI ​​function; information related to the AI ​​model; and device capability information of the first device related to at least one of the AI ​​function and the AI ​​model.

22. The method according to claim 21, wherein: The first information includes at least one of the following: AI function identifier, data set identifier included in the AI ​​function, type of model input data supported by the AI ​​function, type of model output data supported by the AI ​​function, downlink positioning reference signal PRS identifier supported by the AI ​​function, configuration information of PRS supported by the AI ​​function, inference delay range supported by the AI ​​function, reference signal received power RSRP range supported by the AI ​​function, RSRP distribution supported by the AI ​​function, signal to interference and noise ratio SINR range supported by the AI ​​function, SINR distribution supported by the AI ​​function, implicit feature distribution supported by the AI ​​function, implicit feature acquisition method supported by the AI ​​function, area identifier supported by the AI ​​function, transmission receiving point TRP identifier supported by the AI ​​function, cell identifier supported by the AI ​​function, number of TRPs supported by the AI ​​function, number of cells supported by the AI ​​function, inference accuracy supported by the AI ​​function.

23. The method according to claim 21, wherein: The first information includes at least one of the following: AI model identifier, dataset identifier associated with the AI ​​model, type of model input data supported by the AI ​​model, type of model output data supported by the AI ​​model, downlink positioning reference signal PRS identifier of the AI ​​model, configuration information of the PRS of the AI ​​model, inference delay range of the AI ​​model, RSRP range applicable to the AI ​​model, RSRP distribution applicable to the AI ​​model, SINR range applicable to the AI ​​model, SINR distribution applicable to the AI ​​model, implicit feature distribution applicable to the AI ​​model, implicit feature acquisition method applicable to the AI ​​model, area identifier applicable to the AI ​​model, transmission receiving point TRP identifier applicable to the AI ​​model, cell identifier applicable to the AI ​​model, number of TRPs supported by the AI ​​model, number of cells supported by the AI ​​model, inference accuracy of the AI ​​model.

24. The method according to claim 21, wherein: The first information includes at least one of the following: second information and third information, the second information is used to indicate AI function related information, and the third information is used to indicate AI model related information; The second information includes at least one of the following: AI function identification, model input data types supported by the AI ​​function, model output data types supported by the AI ​​function, and inference latency range supported by the AI ​​function; The third information includes at least one of the following: AI model identifier, dataset identifier associated with the AI ​​model, downlink positioning reference signal PRS identifier of the AI ​​model, configuration information of the PRS of the AI ​​model, RSRP range applicable to the AI ​​model, RSRP distribution applicable to the AI ​​model, SINR range applicable to the AI ​​model, SINR distribution applicable to the AI ​​model, implicit feature distribution applicable to the AI ​​model, implicit feature acquisition method applicable to the AI ​​model, area identifier applicable to the AI ​​model, transmission receiving point TRP identifier applicable to the AI ​​model, cell identifier applicable to the AI ​​model, number of TRPs supported by the AI ​​model, number of cells supported by the AI ​​model, and inference accuracy of the AI ​​model.

25. The method according to any one of claims 22 to 24, wherein: The type of the model input data includes at least one of the following: Time domain channel impulse response; delay power spectrum; delay spectrum; RSRP.

26. The method according to any one of claims 22 to 24, wherein: The type of the model output data includes at least one of the following: Time of arrival TOA; Reference signal time difference RSTD; First indication information; Angle of arrival AOA; Angle of departure AOD; The first indication information is used to indicate the position coordinates between the first device and the second device. In line-of-sight (LOS) or non-line-of-sight (NLOS).

27. The method according to any one of claims 22 to 24, wherein: The PRS configuration information includes at least one of the following: Signal bandwidth; comb structure, time domain multipath resolution.

28. The method according to any one of claims 22 to 24, wherein: The reasoning accuracy includes at least one of the following: The highest inference accuracy corresponding to different types of model output data; For any type of model output data, the highest inference accuracy corresponding to different types of model input data.

29. The method according to any one of claims 21 to 28, wherein: The AI ​​function includes at least one AI model.

30. The method according to any one of claims 22 or 25-28, wherein: The first information is reported through the capability of the first device.

31. The method according to claim 30, wherein: The first information also includes: a prerequisite feature group supporting the AI ​​function.

32. The method of claim 30, wherein: The first information also includes: a feature group serial number corresponding to the feature group supporting the capability of the first device.

33. The method according to any one of claims 23 or 25-28, wherein: The first information is represented by information of a preset length obtained by encoding, and information at different positions in the information of the preset length is used to represent different parameters in the first information.

34. The method according to any one of claims 23 or 25-28, wherein: After the second device receives the first information of the first AI model sent by the first device, the method further includes: If the first information of the second AI model has at least one parameter that is the same as that of the first AI model, the second device receives the first information of the second AI model sent by the first device, and the first information of the second AI model includes at least one of the following: difference information between the second AI model and the first AI model, and association information between the first AI model and the second AI model.

35. The method according to any one of claims 23 or 25-28, wherein: In a case where the first information includes information of multiple AI models, and the information of the multiple AI models has the same parameters, the first information includes: The AI ​​model identifier corresponding to the same parameters.

36. The method according to any one of claims 23, 25-28 or 3-35, wherein: For the first parameter in the first information reported through the capability of the first device, the first information further includes: a prerequisite feature group supporting the first parameter.

37. The method according to any one of claims 23, 25-28 or 3-35, wherein: For the first information reported through the capability of the first device, the first information further includes: a feature group serial number corresponding to a feature group supporting the capability of the first device.

38. The method of claim 24, wherein: The second information is reported through the capability of the first device, and the third information is carried through the second information through radio resource control RRC signaling or media access control MAC-control element CE or long term evolution positioning protocol LPP signaling.

39. The method according to any one of claims 21 to 38, wherein: The device capability information of the first device related to at least one of the AI ​​function and the AI ​​model includes at least one of the following: Ability to support model deployment; The ability to measure model input data; The support capability for model deployment includes at least one of the following: The maximum supported model computational complexity; The maximum number of model parameters supported; The maximum number of models supported; Model storage capabilities; Computational capacity; whether to support receiving the model from the second device; whether to support deployment of the model from the second device; Ability to compile AI models; The ability to measure model input data includes at least one of the following: The data types supported for measurement; The maximum number of paths supported for measurement; The maximum number of additional paths supported for measurement; Maximum number of channel taps supported for measurement; The maximum number of TRPs supported for measurement; Supported preprocessing methods for model input data.

40. The method of claim 39, wherein: The preprocessing method of the model input data includes at least one of the following: truncation processing, fast Fourier transform FFT and normalization.

41. An information reporting device, comprising: A sending module is used to send first information to a second device, where the first information is used to indicate at least one of the following types of information: information related to the AI ​​function; information related to the AI ​​model; and device capability information related to the first device and at least one of the AI ​​function and the AI ​​model.

42. An information receiving device, comprising: A receiving module is used to receive first information sent by a first device, where the first information is used to indicate at least one of the following types of information: information related to an AI function; information related to an AI model; and device capability information related to the first device and at least one of the AI ​​function and the AI ​​model.

43. A first device, comprising a processor and a memory, wherein the memory stores programs or instructions that can be executed on the processor, and when the program or instructions are executed by the processor, the steps of the information reporting method as described in any one of claims 1 to 20 are implemented.

44. A second device, comprising 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 information receiving method as described in any one of claims 21 to 40 are implemented.

45. A readable storage medium storing a program or instruction, wherein the program or instruction, when executed by a processor, implements the information reporting method as described in any one of claims 1 to 20, or implements the steps of the information receiving method as described in any one of claims 21 to 40.

Images