Communication method and related apparatus

Abstract

A communication method and a related apparatus. In the method, a first communication apparatus can determine, on the basis of similarity information between an additional condition of input data and an additional condition of N pieces of training data, K models from amongst M models obtained by means of training based on the N pieces of training data, and process the input data on the basis of the K models. Thus, the first communication apparatus can process input data on the basis of models corresponding to training data having an additional condition similar to that of the input data, thus improving the consistency between model training data and model input data, and further improving data processing efficiency.

Description

A communication method and related apparatus

[0001] This application claims priority to Chinese Patent Application No. 202410924418.5, filed on July 10, 2024, entitled "A Communication Method and Related Device", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communications, and more particularly to a communication method and related apparatus. Background Technology

[0003] With the development of communication technology, communication equipment in communication systems can now perform not only traditional communication services but also other new types of services, such as artificial intelligence (AI) services. Generally, a communication system capable of handling AI services can also be called an AI system.

[0004] Currently, communication devices can serve as participating nodes in AI systems, applying their computing power to a specific aspect of the AI ​​system. Generally, AI functions introduced into communication networks rely on models for implementation. For example, communication devices can process input data using models to obtain output data.

[0005] However, how to improve data processing efficiency during the aforementioned data processing process is a technical problem that urgently needs to be solved. Summary of the Invention

[0006] This application provides a communication method and related apparatus for improving data processing efficiency.

[0007] The first aspect of this application provides a communication method, which is executed by a first communication device. The first communication device may be a communication device (such as a terminal device or a network device), or the first communication device may be a component of the communication device (such as a circuit or chip responsible for communication functions (such as a modem chip (also known as a baseband chip), a system-on-chip (SoC) chip, such as an SoC chip containing a modem core, or a system-in-package (SIP) chip), or the first communication device may also be a logic module or software that can implement all or part of the functions of the communication device. In this method, a first communication device receives first information indicating input data; the first communication device receives second information indicating N similarity information corresponding to the additional conditions of the input data and the additional conditions of N training data, where N is a positive integer; wherein, the N training data are used to train M models through model training, where M is a positive integer; the second information is used to determine K models from the M models, where K is a positive integer less than or equal to M; the first communication device processes the input data based on the K models to obtain K output data.

[0008] Based on the above scheme, the second information received by the first communication device indicates N similarity information corresponding to the additional conditions of the input data and the additional conditions of the N training data. Subsequently, the first communication device can determine K models from M models based on the second information, and process the input data indicated by the first information based on these K models to obtain K output data. In this way, the first communication device can determine K models from the M models trained on the N training data based on the similarity information between the additional conditions of the input data and the additional conditions of the N training data, and process the input data based on these K models. Therefore, the first communication device can process the input data based on models corresponding to training data that are similar to the additional conditions of the input data, improving the consistency between the model training data and the model input data, thereby improving data processing efficiency.

[0009] In this application, the model may include an AI model, a neural network model, an AI neural network model, a machine learning model, or an AI processing model, etc.

[0010] In this application, during the process of the communication device processing input data based on a model to obtain output data, the processing may include one or more of the following: reasoning, prediction, derivation, recognition, and decision-making. For example, the input data may be reasoning data, and the output data may be reasoning output data. Exemplarily, in the above process, the first communication device may perform one or more of the following processing on the input data based on K sub-models: reasoning, prediction, derivation, recognition, and decision-making, to obtain output data.

[0011] It should be understood that additional conditions for certain data can indicate relevant conditional information for at least one of the processes in which the data is configured, collected, generated, or acquired. For example, such additional conditions may indicate at least one of the following: spatial filter information, beam information, antenna array information, power information, or application scenario information.

[0012] It should be understood that the similarity information involved in this application includes absolute difference, relative difference, similarity probability, or other information used to characterize similarity. This similarity information can be implemented in various ways; for example, it may include at least one or more of the following:

[0013] The first field indicates whether the similarity (e.g., absolute difference, relative difference, similarity probability) between the additional conditions of a training data point and the additional conditions of the input data is 100%, or whether the additional conditions of a training data point are the same as the additional conditions of the input data. For example, the first field corresponds to a single bit. When the bit is 0, it means that the additional conditions of a training data point are the same as the additional conditions of the input data; when the bit is 1, it means that the additional conditions of a training data point are different from the additional conditions of the input data; or when the bit is 1, it means that the additional conditions of a training data point are the same as the additional conditions of the input data; when the bit is 0, it means that the additional conditions of a training data point are different from the additional conditions of the input data.

[0014] The second field indicates whether the similarity (e.g., absolute difference, relative difference, similarity probability) between the additional conditions of a training data set and the additional conditions of the input data set is 0%, or whether the additional conditions of a training data set are completely different from the additional conditions of the input data set.

[0015] The third field indicates the value of the similarity (e.g., absolute difference, relative difference, similarity probability) between the additional conditions of a training data set and the additional conditions of the input data set.

[0016] Optionally, if the similarity information includes the first field mentioned above, the second information may indicate whether the additional conditions of the input data are the same as the additional conditions of the N training data.

[0017] Optionally, if the similarity information includes the second field mentioned above, the second information may indicate whether the additional conditions of the input data are different from or similar to the additional conditions of the N training data.

[0018] Optionally, the first and second information can be carried in the same message / information / signaling or in different messages / information / signaling; this is not limited here.

[0019] It should be understood that the N similarity information indicated by the second information refers to the similarity information between the additional conditions of the input data and the additional conditions of the N training data. For example, the N similarity information corresponds one-to-one with the additional conditions of the N training data, or the i-th similarity information among the N similarity information is the similarity information between the additional conditions of the input data and the additional conditions of the i-th training data among the N training data.

[0020] In one possible implementation of the first aspect, the first communication device sends third information to determine whether the input data is consistent with the training data corresponding to the K models; wherein the third information is determined based on the K output data.

[0021] Based on the above scheme, the first communication device can also determine and send third information based on the K output data obtained by processing the input data using K models. This allows the recipient of the third information to determine whether the input data is consistent with the training data corresponding to the K models. In this way, the performance of the K models of the first communication device can be supervised, so that the recipient of the third information can perform model management on the models of the first communication device (e.g., model scheduling, model updating, model switching, or function rollback, etc.).

[0022] Optionally, the third information includes at least one of the following:

[0023] The first indication information indicates whether the input data is consistent with the training data corresponding to the K models;

[0024] The second indication information indicates the performance corresponding to the K output data;

[0025] The third indication information indicates the baseline truth corresponding to the K output data.

[0026] In one possible implementation of the first aspect, the additional conditions of the input data include P conditions, and the additional conditions of the i-th training data of the N training data include Q conditions, where P and Q are both positive integers and i takes values ​​from 1 to N; wherein the i-th similarity information among the N similarity information is determined based on any one of the following: the similarity between the p-th condition among the P conditions and the q-th condition among the Q conditions, where p takes values ​​from 1 to P and q takes values ​​from 1 to Q; or, the similarity between the p-th condition among the P conditions and the q-th condition among the Q conditions, and at least one of the importance of the p-th condition among the P conditions and the importance of the q-th condition among the Q conditions.

[0027] Based on the above scheme, the similarity information indicated by the second information can be determined by the similarity and / or importance of the additional conditions of the input data and the additional conditions of the training data. In this way, the second information can indicate the similarity information based on the configured or pre-configured rules.

[0028] In one possible implementation of the first aspect, the additional conditions of the input data include P conditions, and the additional conditions of the i-th training data of the N training data include Q conditions, where P and Q are both positive integers and i takes values ​​from 1 to N; wherein the i-th similarity information among the N similarity information is used to indicate at least one of the following: the overall similarity between the P conditions and the Q conditions, where p takes values ​​from 1 to P and q takes values ​​from 1 to Q; or, the similarity between the p-th condition among the P conditions and the q-th condition among the Q conditions.

[0029] Based on the above scheme, the similarity information indicated by the second information can indicate the overall similarity between the additional conditions of the input data and the additional conditions of the training data and / or the corresponding similarity of each condition, so as to improve the flexibility of the scheme implementation.

[0030] In one possible implementation of the first aspect, the N similarity information is used to determine K models among the M models, including: the N similarity information is used to determine the M similarities corresponding to the M models; wherein, among the M models, the K similarities corresponding to the K models are greater than or equal to the MK similarities corresponding to the other MK models.

[0031] Based on the above scheme, the first communication device can determine the M similarities corresponding to the M models based on the N similarity information indicated by the second information. Furthermore, the first communication device can determine the models corresponding to the K similarities with high similarity as the K models for processing the input data. This enables the first communication device to process the input data based on the K models obtained from the training data corresponding to the additional conditions with high similarity, thereby improving the consistency between the model training data and the model input data and thus improving the data processing efficiency.

[0032] In one possible implementation of the first aspect, the N similarity information is used to determine resource information, the resources indicated by the resource information include the transmission resources of the third information and / or the reception resources of the measurement signal corresponding to the third information, the resource information including one or more of the following: start time domain position, duration, end time domain position, and frequency domain resources.

[0033] Based on the above scheme, the N similarity information indicated by the second information can be used to determine resource information. The resource information indicates that the resource is used to carry the third information and / or the measurement signal corresponding to the third information. In this way, the first communication device can quickly determine the transmission resources of the third information and / or the measurement signal corresponding to the third information, which can further improve communication efficiency.

[0034] In one possible implementation of the first aspect, the method further includes: the first communication device receiving fourth information, the fourth information indicating one or more of the starting time-domain position, duration, and ending time-domain position of resource information associated with L similarity information, and frequency-domain resources; wherein the fourth information and the N similarity information are used to determine the resource information, the L similarity information includes the N similarity information, and L is greater than or equal to N.

[0035] Based on the above scheme, the fourth information received by the first communication device can indicate resource information related to L similarity information, the L similarity information including the N similarity information, so that the first communication device can determine the transmission resources of the third information and / or the measurement signal corresponding to the third information based on the fourth information and the N similarity information.

[0036] Optionally, the fourth piece of information can be pre-configured to reduce transmission overhead.

[0037] A second aspect of this application provides a communication method executed by a second communication device. The second communication device can be a communication equipment (such as a terminal device or network device), or it can be a component of the communication equipment (e.g., a circuit or chip responsible for communication functions, such as a modem chip (also known as a baseband chip), a SoC chip, such as an SoC chip containing a modem core, or a SIP chip, etc.), or it can be a logic module or software capable of implementing all or part of the functions of the communication equipment. In this method, the second communication device sends first information indicating input data; the second communication device sends second information indicating N similarity information corresponding to additional conditions of the input data and additional conditions of N training data, where N is a positive integer; wherein the N training data are used to train M models, where M is a positive integer; the second information is used to determine K models from the M models, and the K models are used to process the input data to obtain K output data, where K is a positive integer less than or equal to M.

[0038] Based on the above scheme, the second communication device sends a second message to the first communication device indicating the N similarity information corresponding to the additional conditions of the input data and the additional conditions of the N training data. Subsequently, the first communication device can determine K models from M models based on the second message, and process the input data indicated by the first message based on these K models to obtain K output data. In this way, the first communication device can determine K models from the M models trained on the N training data based on the similarity information between the additional conditions of the input data and the additional conditions of the N training data, and process the input data based on these K models. Therefore, the first communication device can process the input data based on models corresponding to training data that are similar to the additional conditions of the input data, improving the consistency between the model training data and the model input data, thereby improving data processing efficiency.

[0039] In one possible implementation of the second aspect, the method further includes: the second communication device receiving third information, the third information being used to determine whether the input data is consistent with the training data corresponding to the K models; wherein the third information is determined based on the K output data.

[0040] Based on the above scheme, the first communication device can also determine and send third information based on the K output data obtained by processing the input data using K models, so that the second communication device can determine whether the input data is consistent with the training data corresponding to the K models based on the third information. In this way, the model performance of the K models of the first communication device can be supervised, so that the recipient of the third information can perform model management on the model of the first communication device (e.g., model scheduling, model update, model switching, or function rollback, etc.).

[0041] Optionally, the third information includes at least one of the following:

[0042] The first indication information indicates whether the input data is consistent with the training data corresponding to the K models;

[0043] The second indication information indicates the performance corresponding to the K output data;

[0044] The third indication information indicates the baseline truth corresponding to the K output data.

[0045] In one possible implementation of the second aspect, the additional conditions of the input data include P conditions, and the additional conditions of the i-th training data of the N training data include Q conditions, where P and Q are both positive integers and i takes values ​​from 1 to N; wherein the i-th similarity information among the N similarity information is determined based on any one of the following: the similarity between the p-th condition among the P conditions and the q-th condition among the Q conditions, where p takes values ​​from 1 to P and q takes values ​​from 1 to Q; or, the similarity between the p-th condition among the P conditions and the q-th condition among the Q conditions, and at least one of the importance of the p-th condition among the P conditions and the importance of the q-th condition among the Q conditions.

[0046] Based on the above scheme, the similarity information indicated by the second information can be determined by the similarity and / or importance of the additional conditions of the input data and the additional conditions of the training data. In this way, the second information can indicate the similarity information based on the configured or pre-configured rules.

[0047] In one possible implementation of the second aspect, the additional conditions of the input data include P conditions, and the additional conditions of the i-th training data of the N training data include Q conditions, where P and Q are both positive integers and i takes values ​​from 1 to N; wherein, the i-th similarity information among the N similarity information is used to indicate at least one of the following: the overall similarity between the P conditions and the Q conditions, where p takes values ​​from 1 to P and q takes values ​​from 1 to Q; or, the similarity between the p-th condition among the P conditions and the q-th condition among the Q conditions.

[0048] Based on the above scheme, the similarity information indicated by the second information can indicate the overall similarity between the additional conditions of the input data and the additional conditions of the training data and / or the corresponding similarity of each condition, so as to improve the flexibility of the scheme implementation.

[0049] In one possible implementation of the second aspect, the N similarity information is used to determine K models among the M models, including: the N similarity information is used to determine the M similarities corresponding to the M models; wherein, among the M models, the K similarities corresponding to the K models are greater than or equal to the MK similarities corresponding to the other MK models.

[0050] Based on the above scheme, the first communication device can determine the M similarities corresponding to the M models based on the N similarity information indicated by the second information. Furthermore, the first communication device can determine the models corresponding to the K similarities with high similarity as the K models for processing the input data. This enables the first communication device to process the input data based on the K models obtained from the training data corresponding to the additional conditions with high similarity, thereby improving the consistency between the model training data and the model input data and thus improving the data processing efficiency.

[0051] In one possible implementation of the second aspect, the N similarity information is used to determine resource information, the resources indicated by the resource information include the transmission resources of the third information and / or the reception resources of the measurement signal corresponding to the third information, the resource information includes one or more of the following: start time domain position, duration, end time domain position, and frequency domain resources.

[0052] Based on the above scheme, the N similarity information indicated by the second information can be used to determine resource information. The resource information indicates that the resource is used to carry the third information and / or the measurement signal corresponding to the third information. In this way, the first communication device can quickly determine the transmission resources of the third information and / or the measurement signal corresponding to the third information, which can further improve communication efficiency.

[0053] In one possible implementation of the second aspect, the method further includes: the second communication device sending fourth information, the fourth information indicating one or more of the starting time-domain position, duration, and ending time-domain position of resource information associated with L similarity information, and frequency-domain resources; wherein the fourth information and the N similarity information are used to determine the resource information, the L similarity information includes the N similarity information, and L is greater than or equal to N.

[0054] Based on the above scheme, the fourth information received by the first communication device can indicate resource information related to L similarity information, the L similarity information including the N similarity information, so that the first communication device can determine the transmission resources of the third information and / or the measurement signal corresponding to the third information based on the fourth information and the N similarity information.

[0055] Optionally, the fourth piece of information can be pre-configured to reduce transmission overhead.

[0056] A third aspect of this application provides a communication device, which is a first communication device, comprising a transceiver unit and a processing unit. The transceiver unit is used to receive first information indicating input data. The transceiver unit is also used to receive second information indicating N similarity information corresponding to the additional conditions of the input data and the additional conditions of N training data, where N is a positive integer. The N training data are used to train M models, where M is a positive integer. The second information is used to determine K models from the M models, where K is a positive integer less than or equal to M. The processing unit is used to process the input data based on the K models to obtain K output data.

[0057] In the third aspect of this application, the constituent modules of the communication device can also be used to execute the steps performed in various possible implementations of the first aspect and achieve the corresponding technical effects. For details, please refer to the first aspect, which will not be repeated here.

[0058] A fourth aspect of this application provides a communication device, which is a second communication device. The device includes a transceiver unit and a processing unit. The processing unit is used to determine first information and second information. The transceiver unit is used to send the first information, which indicates input data. The transceiver unit is also used to send the second information, which indicates N similarity information corresponding to the additional conditions of the input data and the additional conditions of N training data, respectively, where N is a positive integer. The N training data are used to train M models through model training, where M is a positive integer. The second information is used to determine K models from the M models. The K models are used to process the input data to obtain K output data, where K is a positive integer less than or equal to M.

[0059] In the fourth aspect of this application, the constituent modules of the communication device can also be used to perform the steps executed in various possible implementations of the second aspect and achieve the corresponding technical effects. For details, please refer to the second aspect, which will not be repeated here.

[0060] A fifth aspect of this application provides a communication device including at least one processor coupled to a memory; the memory is used to store a program or instructions; the at least one processor is used to execute the program or instructions to cause the device to implement the method described in any possible implementation of any of the first to second aspects. Optionally, the communication device may include the memory.

[0061] The sixth aspect of this application provides a communication device including at least one logic circuit and an input / output interface; the logic circuit is used to perform the method as described in any one of the possible implementations of the first to second aspects described above.

[0062] The seventh aspect of this application provides a communication system, which includes the first communication device and the second communication device described above.

[0063] An eighth aspect of this application provides a computer-readable storage medium for storing one or more computer-executable instructions, which, when executed by a processor, perform the method as described in any possible implementation of any of the first to second aspects described above.

[0064] The ninth aspect of this application provides a computer program product (or computer program) that, when executed by a processor, performs the method described in any possible implementation of any of the first to second aspects described above.

[0065] The tenth aspect of this application provides a chip or chip system including at least one processor for supporting a communication device in implementing the methods described in any possible implementation of any of the first to second aspects. For example, the chip may be a baseband chip, a modem chip, a SoC chip (such as an SoC chip containing a modem core), a SIP chip, or a communication module, etc.

[0066] In one possible design, the chip or chip system may further include a memory for storing program instructions and data necessary for the communication device. The chip system may be composed of chips or may include chips and other discrete devices. Optionally, the chip system may also include interface circuitry that provides program instructions and / or data to the at least one processor.

[0067] The technical effects of any of the design methods in aspects three through ten can be found in the technical effects of the different design methods in aspects one through two above, and will not be repeated here. Attached Figure Description

[0068] Figures 1a to 1c are schematic diagrams of the communication system provided in this application;

[0069] Figures 2a to 2g are schematic diagrams of the AI ​​processing involved in this application;

[0070] Figure 3 is an interactive schematic diagram of the communication method provided in this application;

[0071] Figures 4a and 4b are some schematic diagrams of the model provided in this application;

[0072] Figure 4c is an interactive schematic diagram of the communication method provided in this application;

[0073] Figures 5 to 9 are schematic diagrams of the communication device provided in this application. Detailed Implementation

[0074] First, some terms used in the embodiments of this application will be explained to facilitate understanding by those skilled in the art.

[0075] (1) Terminal device: can be a wireless terminal device that can receive network device scheduling and instruction information. The wireless terminal device can be a device that provides voice and / or data connectivity to the user, or a handheld device with wireless connection function, or other processing device connected to a wireless modem.

[0076] Terminal devices can communicate with one or more core networks or the Internet via a radio access network (RAN). Terminal devices can be mobile terminal devices, such as mobile phones (or "cellular" phones), computers, and data cards. For example, they can be portable, pocket-sized, handheld, computer-embedded, or vehicle-mounted mobile devices that exchange voice and / or data with the RAN. Examples include personal communication service (PCS) phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), tablets, and computers with wireless transceiver capabilities. Wireless terminal equipment can also be referred to as a system, subscriber unit, subscriber station, mobile station (MS), remote station, access point (AP), remote terminal, access terminal, user terminal, user agent, subscriber station (SS), customer premises equipment (CPE), terminal, user equipment (UE), mobile terminal (MT), etc.

[0077] By way of example and not limitation, in this embodiment, the terminal device can also be a wearable device. Wearable devices, also known as wearable smart devices or smart wearable devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are feature-rich, large in size, and can achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those that focus on a specific type of application function and require the use of other devices such as smartphones, such as various smart bracelets, smart helmets, and smart jewelry for vital sign monitoring.

[0078] Terminals can also be drones, robots, devices in device-to-device (D2D) communication, vehicles to everything (V2X) communication, virtual reality (VR) terminal devices, augmented reality (AR) terminal devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in telemedicine or telehealth services, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, etc.

[0079] Furthermore, the terminal device can also be a terminal device for a communication system evolved from the fifth generation (5G) communication system (such as 5G Advanced or future communication systems). For example, the form and function of the communication terminal can be further expanded, including but not limited to vehicles, cellular network terminals (integrating satellite terminal functions), drones, and Internet of Things (IoT) devices.

[0080] In this embodiment, the terminal device can also obtain artificial intelligence (AI) services provided by the network device. Optionally, the terminal device can also have AI processing capabilities.

[0081] (2) Network equipment: This can be equipment within a wireless network. For example, network equipment can be a RAN node (or device) that connects terminal devices to the wireless network, and can also be called a base station. Currently, some examples of RAN equipment include: base station, evolved NodeB (eNodeB), gNB (gNodeB) in 5G communication systems, transmission reception point (TRP), evolved Node B (eNB), radio network controller (RNC), Node B (NB), home base station (e.g., home evolved Node B, or home Node B, HNB), base band unit (BBU), or wireless fidelity (Wi-Fi) access point (AP), etc. In addition, in a network architecture, network equipment can include central unit (CU) nodes, distributed unit (DU) nodes, or RAN equipment including both CU and DU nodes.

[0082] Optionally, RAN nodes can also be macro base stations, micro base stations, indoor stations, relay nodes, donor nodes, or radio controllers in cloud radio access network (CRAN) scenarios. RAN nodes can also be servers, wearable devices, vehicles, or in-vehicle equipment. For example, the access network equipment in vehicle-to-everything (V2X) technology can be a roadside unit (RSU).

[0083] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, with different RAN nodes each implementing some of the base station's functions. For example, RAN nodes can be CUs, DUs, CUs (control plane, CP), CUs (user plane, UP), or radio units (RUs). CUs and DUs can be configured separately or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio equipment or radio units, such as remote radio units (RRUs), active antenna units (AAUs), radio heads (RHs), or remote radio heads (RRHs).

[0084] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an open access network (open RAN, O-RAN, or ORAN) system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0085] Communication between access network devices and terminal devices follows a specific protocol layer structure. This protocol layer may include a control plane protocol layer and a user plane protocol layer. The control plane protocol layer may include at least one of the following: radio resource control (RRC) layer, packet data convergence protocol (PDCP) layer, radio link control (RLC) layer, media access control (MAC) layer, or physical (PHY) layer, etc. The user plane protocol layer may include at least one of the following: service data adaptation protocol (SDAP) layer, PDCP layer, RLC layer, MAC layer, or physical layer, etc.

[0086] The correspondence between network elements and their achievable protocol layer functions in the ORAN system can be found in Table 1 below.

[0087] Table 1

[0088] Network devices can be other devices that provide wireless communication functions for terminal devices. The embodiments of this application do not limit the specific technology or form of the network device. For ease of description, the embodiments of this application are not limited.

[0089] Network equipment may also include core network equipment, such as the Mobility Management Entity (MME), Home Subscriber Server (HSS), Serving Gateway (S-GW), Policy and Charging Rules Function (PCRF), and Public Data Network Gateway (PDN gateway or P-GW) in 4th generation (4G) networks; and access and mobility management function (AMF), user plane function (UPF), or session management function (SMF) in 5G networks. Furthermore, this core network equipment may also include other core network equipment in 5G networks and next-generation networks of 5G networks.

[0090] In this embodiment of the application, the network device may also have network nodes with AI capabilities, which can provide AI services to terminals or other network devices. For example, it may be an AI node, computing node, RAN node with AI capabilities, or core network element with AI capabilities on the network side (access network or core network).

[0091] In this application embodiment, the device for implementing the function of the network device can be the network device itself, or it can be a device capable of supporting the network device in implementing the function, such as a chip system. This device can be disposed within the network device. In the technical solutions provided in this application embodiment, the example of a network device being used to implement the function of the network device is used to describe the technical solutions provided in this application embodiment.

[0092] (3) Configuration and Pre-configuration: In this application, both configuration and pre-configuration are used. Configuration refers to the network device / server sending configuration information or parameter values ​​to the terminal via messages or signaling, so that the terminal can determine communication parameters or resources for transmission based on these values ​​or information. Pre-configuration is similar to configuration; it can be parameter information or parameter values ​​pre-negotiated between the network device / server and the terminal device, parameter information or parameter values ​​specified by standard protocols for use by the base station / network device or terminal device, or parameter information or parameter values ​​pre-stored in the base station / server or terminal device. This application does not limit this.

[0093] Furthermore, these values ​​and parameters can be changed or updated.

[0094] (4) The terms "system" and "network" in the embodiments of this application can be used interchangeably. "Multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, or B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the related objects before and after are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, "at least one of A, B and C" includes A, B, C, AB, AC, BC or ABC. And, unless otherwise specified, the ordinal numbers such as "first" and "second" mentioned in the embodiments of this application are used to distinguish multiple objects and are not used to limit the order, sequence, priority or importance of multiple objects.

[0095] (5) In the embodiments of this application, "send" and "receive" indicate the direction of signal transmission. For example, "send information to XX" can be understood as the destination of the information being XX, which may include sending directly through the air interface or sending indirectly through the air interface by other units or modules. "Receive information from YY" can be understood as the source of the information being YY, which may include receiving directly from YY through the air interface or receiving indirectly from YY through the air interface by other units or modules. "Send" can also be understood as the "output" of the chip interface, and "receive" can also be understood as the "input" of the chip interface.

[0096] In other words, sending and receiving can occur between devices, such as between network devices and terminal devices, or within a device, such as between components, modules, chips, software modules, or hardware modules within the device via buses, wiring, or interfaces.

[0097] It is understandable that information may undergo necessary processing, such as encoding and modulation, between the source and destination, but the destination can understand the valid information from the source. Similar statements in this application can be interpreted in a similar way and will not be elaborated further.

[0098] (6) In the embodiments of this application, "instruction" may include direct instruction and indirect instruction, as well as explicit instruction and implicit instruction. The information indicated by a certain piece of information (as described below, the instruction information) is called the information to be instructed. In the specific implementation process, there are many ways to indicate the information to be instructed, such as, but not limited to, directly indicating the information to be instructed, such as the information to be instructed itself or its index. It can also indirectly indicate the information to be instructed by indicating other information, where there is an association between the other information and the information to be instructed; or it can only indicate a part of the information to be instructed, while the other parts of the information to be instructed are known or pre-agreed upon. For example, the instruction can be implemented by using a pre-agreed (e.g., protocol predefined) arrangement order of various information, thereby reducing the instruction overhead to a certain extent. This application does not limit the specific method of instruction. It is understood that for the sender of the instruction information, the instruction information can be used to indicate the information to be instructed, and for the receiver of the instruction information, the instruction information can be used to determine the information to be instructed.

[0099] In this application, unless otherwise specified, the same or similar parts between the various embodiments can be referred to each other. In the various embodiments of this application, and the various methods / designs / implementations within each embodiment, unless otherwise specified or logically conflicting, the terminology and / or descriptions between different embodiments and between the various methods / designs / implementations within each embodiment are consistent and can be mutually referenced. The technical features in different embodiments and the various methods / designs / implementations within each embodiment can be combined to form new embodiments, methods, or implementations based on their inherent logical relationships. The following descriptions of the embodiments of this application do not constitute a limitation on the scope of protection of this application.

[0100] This application can be applied to long-term evolution (LTE) systems, new radio (NR) systems, or future communication systems beyond 5G. These communication systems include at least one network device and / or at least one terminal device.

[0101] Please refer to Figure 1a, which is a schematic diagram of a communication system according to this application. Figure 1a exemplarily shows one network device and six terminal devices, namely terminal device 1, terminal device 2, terminal device 3, terminal device 4, terminal device 5, and terminal device 6. In the example shown in Figure 1a, terminal device 1 is a smart teacup, terminal device 2 is a smart air conditioner, terminal device 3 is a smart gas pump, terminal device 4 is a vehicle, terminal device 5 is a mobile phone, and terminal device 6 is a printer.

[0102] As shown in Figure 1a, the entity sending the AI ​​configuration information can be a network device. The entity receiving the AI ​​configuration information can be terminal devices 1-6. In this case, the network device and terminal devices 1-6 form a communication system. In this communication system, terminal devices 1-6 can send data to the network device, and the network device can receive the data sent by terminal devices 1-6. The network device can also send configuration information to terminal devices 1-6.

[0103] For example, in Figure 1a, terminal devices 4 and 6 can also form a communication system. Terminal device 5 acts as a network device, i.e., the entity sending AI configuration information; terminal devices 4 and 6 act as terminal devices, i.e., the entities receiving AI configuration information. For instance, in a vehicle-to-everything (V2X) system, terminal device 5 sends AI configuration information to terminal devices 4 and 6 respectively, and receives data sent by terminal devices 4 and 6; correspondingly, terminal devices 4 and 6 receive the AI ​​configuration information sent by terminal device 5 and send data back to terminal device 5.

[0104] Taking the communication system shown in Figure 1a as an example, in addition to performing communication-related services, different devices (including network devices and network devices, network devices and terminal devices, and / or terminal devices and terminal devices) may also perform AI-related services.

[0105] As shown in Figure 1b, taking a network device as a base station as an example, the base station can perform communication-related services and AI-related services with one or more terminal devices, and different terminal devices can also perform communication-related services and AI-related services.

[0106] As shown in Figure 1c, taking terminal devices including televisions and mobile phones as an example, communication-related services and AI-related services can also be performed between televisions and mobile phones.

[0107] The technical solutions provided in this application can be applied to wireless communication systems (such as the systems shown in Figures 1a, 1b, or 1c). For example, AI network elements can be introduced into the communication system provided in this application to realize some or all AI-related operations. AI network elements can also be called AI nodes, AI devices, AI entities, AI modules, AI models, or AI units, etc. The AI ​​network element can be built into a network element within the communication system. For example, the AI ​​network element can be an AI module built into: access network equipment, core network equipment, cloud server, or operation, administration, and maintenance (OAM) to realize AI-related functions. The OAM can act as the network management system for the core network equipment and / or the access network equipment. Alternatively, the AI ​​network element can also be an independently set network element in the communication system. Optionally, the terminal or its built-in chip can also include an AI entity to realize AI-related functions.

[0108] Optionally, in communication systems, AI application cases may include, but are not limited to: channel state information (CSI) feedback enhancement, beam management enhancement, positioning accuracy enhancement, network energy saving, load balancing, and mobility optimization. These will be explained below.

[0109] 1. Enhanced CSI feedback

[0110] Channel quality information (CSI) is the channel attribute of a communication link, reported by the terminal device to the network device. By reporting this information, the terminal device can select an appropriate modulation and coding scheme (MCS) to adapt to changing wireless channels. For example, the terminal device might perform channel estimation based on the received channel state information-reference signal (CSI-RS) and then feed back the CSI-RS to the network device. This information serves as input to the network device's model, enabling AI model training. Applying AI to CSI feedback enhancement can reduce overhead, improve accuracy, and enhance predictive capabilities.

[0111] CSI-RS feedback enhancement may include at least one sub-function, such as: CSI compression, CSI prediction, and CSI-RS configuration signaling reduction. CSI compression may further include CSI compression in at least one domain: spatial, time, and frequency.

[0112] 2. Enhanced Beam Management

[0113] Enhanced beam management primarily aims to discover the strongest transmit / receive beam pairs. AI-based sparse beam prediction can improve accuracy. This can be achieved through both network-side and terminal-side AI sparse beam prediction, based on AI training and inference. Taking terminal-side AI sparse beam prediction as an example, the pre-trained AI model on the terminal device can be provided by the network or pre-stored on the terminal device. During training, the network device scans all possible beams and then reports the transmit beam pattern to the terminal device. Once training is complete, the network device only needs to scan a small subset of beams, and the terminal device then feeds back the inference results. AI-based beam management can achieve beam prediction in, for example, the temporal and / or spatial domains, reducing overhead and latency and improving beam selection accuracy.

[0114] Beam management enhancements may include at least one sub-function, such as: beam scan matrix prediction and optimal beam prediction.

[0115] 3. Enhanced positioning accuracy

[0116] In line-of-sight (LOS) or non-line-of-sight (NLOS) scenarios, AI-based positioning can improve positioning accuracy with a smaller number of TRP antennas. Positioning enhancement can include at least one sub-function, such as: positioning enhancement based on access network devices, positioning enhancement based on positioning management function network elements, and positioning enhancement based on terminal devices.

[0117] 4. Network energy saving

[0118] Network energy conservation can be achieved through cell activation / deactivation, load reduction, coverage improvement, or other RAN setting adjustments. AI technology can be used to optimize energy-saving decisions by leveraging data collected within the RAN network. AI algorithms can predict energy efficiency and load status for the next cycle, which can be used to assist in cell activation / deactivation decisions to save energy. Based on the predicted load, the system can dynamically configure energy-saving strategies to maintain a balance between system performance and energy efficiency, and reduce energy consumption.

[0119] 5. Load balancing

[0120] Load balancing can distribute the load evenly between cells and across different areas within a cell, or transfer some traffic from congested cells, or offload users across a single cell, carrier, or access standard, thereby improving network performance. Using AI models to enhance load balancing performance—such as inputting various measurements and feedback from terminal devices and network nodes, as well as historical data—can provide a higher quality user experience and increase system capacity.

[0121] 6. Mobility Management

[0122] Mobility management is a solution that ensures service continuity for mobile devices by minimizing dropped calls, radio link failures (RLFs), unnecessary handovers, and ping-pong effects. AI can enhance mobility management by, for example, reducing the probability of unexpected events, predicting device location / mobility / performance, and routing traffic.

[0123] It should be understood that the definitions of the above technical terms are merely illustrative. For example, as technology continues to develop, the scope of the above definitions may also change, and the embodiments of this application are not intended to limit the scope.

[0124] For example, an AI function may include multiple AI sub-functions.

[0125] Optionally, AI application cases are also called AI application scenarios or AI functions.

[0126] As described above regarding AI application examples, AI can be widely used to improve network performance in areas such as CSI feedback enhancement, beam management, positioning accuracy enhancement, energy saving, mobility enhancement, and load balancing. AI models can typically be deployed on the network side and / or the terminal device side. The training of AI models relies on the collection of training data, which can come from measurements and feedback from the terminal devices.

[0127] The following is a brief introduction to the concepts that may be involved in this application.

[0128] AI can endow machines with human-like intelligence, for example, allowing them to use computer hardware and software to simulate certain intelligent human behaviors. To achieve artificial intelligence, machine learning methods can be employed. In machine learning, machines learn (or train) a model using training data. This model represents the mapping between inputs and outputs. The learned model can be used for reasoning (or prediction), that is, it can be used to predict the output corresponding to a given input. This output can also be called the reasoning result (or prediction result).

[0129] Machine learning can include supervised learning, unsupervised learning, and reinforcement learning. Unsupervised learning can also be called learning without supervision.

[0130] Supervised learning, based on collected sample values ​​and labels, uses machine learning algorithms to learn the mapping relationship between sample values ​​and labels, and then expresses this learned mapping relationship using an AI model. The process of training the machine learning model is the process of learning this mapping relationship. During training, sample values ​​are input into the model to obtain the model's predicted values, and the model parameters are optimized by calculating the error between the model's predicted values ​​and the sample labels (ideal values). After the mapping relationship is learned, it can be used to predict new sample labels. The mapping relationship learned in supervised learning can include linear or non-linear mappings. Based on the type of label, the learning task can be divided into classification tasks and regression tasks.

[0131] Unsupervised learning relies on collected sample values ​​to discover inherent patterns within the samples themselves. One type of unsupervised learning algorithm uses the samples themselves as supervisory signals, meaning the model learns the mapping relationship from sample to sample; this is called self-supervised learning. During training, model parameters are optimized by calculating the error between the model's predictions and the samples themselves. Self-supervised learning can be used for signal compression and decompression recovery applications; common algorithms include autoencoders and generative adversarial networks.

[0132] Reinforcement learning, unlike supervised learning, is a type of algorithm that learns problem-solving strategies through interaction with the environment. Unlike supervised and unsupervised learning, reinforcement learning problems do not have explicit "correct" action labels. The algorithm needs to interact with the environment to obtain reward signals from the environment, and then adjust its decision actions to obtain a larger reward signal value. For example, in downlink power control, the reinforcement learning model adjusts the downlink transmission power of each user based on the total system throughput feedback from the wireless network, aiming to achieve a higher system throughput. The goal of reinforcement learning is also to learn the mapping relationship between the environment state and a better (e.g., optimal) decision action. However, because the label of the "correct action" cannot be obtained in advance, the network cannot be optimized by calculating the error between the action and the "correct action." Reinforcement learning training is achieved through iterative interaction with the environment.

[0133] Neural networks (NNs) are a specific model in machine learning techniques. According to the general approximation theorem, neural networks can theoretically approximate any continuous function, thus enabling them to learn arbitrary mappings. Traditional communication systems rely on extensive expert knowledge to design communication modules, while deep learning communication systems based on neural networks can automatically discover hidden pattern structures from large datasets, establish mapping relationships between data, and achieve performance superior to traditional modeling methods.

[0134] The idea behind neural networks comes from the neuronal structure of the brain. For example, each neuron performs a weighted summation of its input values ​​and outputs the result through an activation function.

[0135] Figure 2a shows a schematic diagram of a neuron structure. Assume the input to the neuron is x = [x0, x1, ..., x...]. n The weights corresponding to each input are w = [w0, w1, ..., w] n ], where n is a positive integer, w i and x i It can be any possible type, such as a decimal, an integer (e.g., 0, a positive integer, or a negative integer), or a complex number. i As x i The weights are used to assign weights to x. i Weighting is applied. The bias for the weighted sum of the input values ​​is, for example, b. Activation functions can take many forms. Suppose the activation function of a neuron is: y = f(z) = max(0, z), then the output of that neuron is: For example, if the activation function of a neuron is y = f(z) = z, then the output of that neuron is: Here, b can be any possible type, such as a decimal, an integer (e.g., 0, a positive integer, or a negative integer), or a complex number. The activation functions of different neurons in a neural network can be the same or different.

[0136] Furthermore, neural networks generally consist of multiple layers, each of which may include one or more neurons. Increasing the depth and / or width of a neural network can improve its expressive power, providing more powerful information extraction and abstract modeling capabilities for complex systems. The depth of a neural network can refer to the number of layers it includes, and the number of neurons in each layer can be called the width of that layer. In one implementation, a neural network includes an input layer and an output layer. The input layer processes the received input information through neurons and passes the processing result to the output layer, which then obtains the output of the neural network. In another implementation, a neural network includes an input layer, hidden layers, and an output layer. The input layer processes the received input information through neurons and passes the processing result to the hidden layer. The hidden layer calculates the received processing result and passes the calculation result to the output layer or the next adjacent hidden layer, ultimately obtaining the output of the neural network. A neural network may include one hidden layer or multiple sequentially connected hidden layers, without limitation.

[0137] Neural networks, for example, are deep neural networks (DNNs). Depending on how the network is constructed, DNNs can include feedforward neural networks (FNNs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs).

[0138] Figure 2b is a schematic diagram of an FNN network. A characteristic of FNN networks is that neurons in adjacent layers are completely connected pairwise. This characteristic makes FNNs typically require a large amount of storage space, leading to high computational complexity.

[0139] CNNs are neural networks specifically designed to process data with a grid-like structure. For example, time-series data (e.g., discrete sampling along a time axis) and image data (e.g., two-dimensional discrete sampling) can both be considered grid-like data. CNNs do not use all the input information at once for computation; instead, they use a fixed-size window to extract a portion of the information for convolution operations, which significantly reduces the computational cost of model parameters. Furthermore, depending on the type of information extracted by the window (e.g., people and objects in an image represent different types of information), each window can use different convolution kernels, allowing CNNs to better extract features from the input data.

[0140] Recurrent Neural Networks (RNNs) are a type of neural network that utilizes feedback time-series information. The input to an RNN includes the current input value and its own output value from the previous time step. RNNs are suitable for acquiring temporally correlated sequence features, and are applicable to applications such as speech recognition and channel coding / decoding.

[0141] In the model training process described above, a loss function can be defined. The loss function describes the difference between the model's output value and the ideal target value. The loss function can be expressed in various forms, and there are no restrictions on its specific form. The model training process can be viewed as follows: by adjusting some or all of the model's parameters, the value of the loss function is made to be less than a threshold or to meet the target requirement.

[0142] A model can also be called an AI model, a rule, or other names. An AI model can be considered a specific method for implementing AI functions. An AI model represents the mapping relationship or function between the model's input and output. AI functions can include one or more of the following: data collection, model training (or model learning), model information dissemination, model inference (or model reasoning, inference, or prediction, etc.), model monitoring or model validation, or inference result publication, etc. AI functions can also be called AI (related) operations or AI-related functions.

[0143] The implementation process of the neural network will be described below with reference to the accompanying drawings.

[0144] 1. Fully connected neural network, also known as multilayer perceptron (MLP).

[0145] As shown in Figure 2c, an MLP consists of an input layer (left side), an output layer (right side), and multiple hidden layers (middle). Each layer of an MLP contains several nodes, called neurons. Neurons in adjacent layers are connected pairwise.

[0146] Optionally, considering neurons in two adjacent layers, the output h of the next layer's neurons is the weighted sum of all neurons x in the previous layer connected to it, processed by an activation function, and can be expressed as: h = f(wx + b).

[0147] Where w is the weight matrix, b is the bias vector, and f is the activation function.

[0148] Alternatively, the output of the neural network can be recursively expressed as: y = f z (w z f z-1 (…)+b z ).

[0149] Where z is the index of the neural network layer, z is greater than or equal to 1 and z is less than or equal to Z, where Z is the total number of layers in the neural network.

[0150] In other words, a neural network can be understood as a mapping from an input data set to an output data set. Neural networks are typically initialized randomly; the process of obtaining this mapping from random values ​​w and b using existing data is called training the neural network.

[0151] Optionally, the training method involves using a loss function to evaluate the output of the neural network.

[0152] As shown in Figure 2d, the error can be backpropagated, and the neural network parameters (including w and b) can be iteratively optimized using gradient descent until the output of the loss function reaches its minimum value, which is the "better point (e.g., the optimal point)" in Figure 2d. It can be understood that the neural network parameters corresponding to the "better point (e.g., the optimal point)" in Figure 2d can be used as the neural network parameters in the trained AI model information.

[0153] Alternatively, the gradient descent process can be represented as:

[0154] Where θ represents the parameters to be optimized (including w and b), L is the loss function, and η is the learning rate, controlling the step size of gradient descent. This represents the differentiation operation. This indicates taking the derivative of θ with respect to L.

[0155] Alternatively, the backpropagation process can utilize the chain rule for partial derivatives.

[0156] As shown in Figure 2e, the gradient of the parameters in the previous layer can be recursively calculated from the gradient of the parameters in the next layer, and can be expressed as:

[0157] Among them, w ij Let s be the weight of the connection between node j and node i. i The weighted sum of the inputs at node i.

[0158] 2. Federated learning (FL).

[0159] The concept of federated learning effectively addresses the current challenges in the development of artificial intelligence. While fully protecting user data privacy and security, it enables various edge devices and central servers to collaborate efficiently to complete the model's learning task.

[0160] As shown in Figure 2f, the FL architecture is the most widely used training architecture in the current FL field, and the FedAvg algorithm is the basic algorithm of FL. The FedAvg algorithm flow is roughly as follows:

[0161] (1) Initialize the model to be trained at the center end. And broadcast it to all clients.

[0162] (2) In the t∈[1,T] round, the client k∈[1,K] is based on the local dataset. For the received global model Perform E epochs of training to obtain the local training results. This is then reported to the central node. In the example shown in Figure 2f, the local training results sent by distributed nodes n, k, and m are denoted as G, respectively. n G k G m .

[0163] (3) The central node collects local training results from all (or some) clients. Assume the set of clients uploading local models in round t is... The central server will use the number of samples from the corresponding client as weights to calculate the new global model. The specific update rule is as follows: Then the central end will send the latest version of the global model. The broadcast is sent to all clients for a new round of training.

[0164] (4) Repeat steps (2) and (3) until the model finally converges or the number of training rounds reaches the upper limit.

[0165] Optionally, in addition to reporting the local model, the client can also... It can also train local gradients The central node averages the local gradients reported by all clients and updates the global model based on this average gradient.

[0166] As can be seen in the FL framework, the dataset resides on distributed nodes (such as clients). These distributed nodes collect their local datasets, perform local training, and report the local results (model or gradients) to the central node. The central node itself may not have a dataset; it can be responsible for fusing the training results from the distributed nodes to obtain a global model, which is then distributed back to the distributed nodes.

[0167] 3. Decentralized learning.

[0168] Figure 2g illustrates a fully distributed system without a central node. The design goal f(x) of a decentralized learning system is generally the goal f of each node. i The mean of (x), i.e. Where n is the number of distributed nodes, and x is the parameter to be optimized; in machine learning, x is the parameter of the machine learning model (such as a neural network). Each node utilizes local data and its local target f. i (x) Calculate the local gradient Then it is sent to its communicatively reachable neighboring nodes. Upon receiving the gradient information from its neighbor, any node can update the parameters x of its local model according to the following formula:

[0169] in, This represents the parameters of the local model after the (k+1)th update (k is a natural number) in the i-th node. This represents the parameters of the local model for the i-th node after the k-th update (if k is 0, then it represents...). (where α is the parameter of the local model of the i-th node that is not involved in the update) k N represents the tuning coefficient. i It is the set of neighboring nodes of node i, |N i | represents the number of elements in the set of neighboring nodes of node i, that is, the number of neighboring nodes of node i. Through information interaction between nodes, the decentralized learning system will eventually learn a unified model.

[0170] The technical solution provided in this application can be applied to communication systems (such as the systems shown in Figure 1a, 1b, or 1c). In a communication system, communication nodes generally possess signal transmission and reception capabilities as well as computing capabilities. Taking a network device with computing capabilities as an example, the computing capabilities of the network device mainly provide computational support for the signal transmission and reception capabilities (e.g., processing the transmission and reception of signals) to realize the communication tasks between the network device and other communication nodes.

[0171] With the development of communication technology, communication equipment in communication systems can now perform not only traditional communication services but also other new types of services, such as artificial intelligence (AI) services. Generally, systems capable of handling AI services, such as communication systems, can also be called AI systems.

[0172] Currently, communication devices can serve as participating nodes in AI systems, applying their computing power to a specific aspect of the AI ​​system. Generally, AI functions introduced into communication networks rely on models for implementation; communication devices can process input data through these models to obtain output data.

[0173] However, how to improve data processing efficiency during the aforementioned data processing process is a technical problem that urgently needs to be solved.

[0174] In one possible implementation, when communication devices are trained based on general data, there is a possibility that the model may become overfitted, becoming too closely matched to the training dataset. This reduces the model's generalization ability during inference, meaning the model cannot adapt to real-world scenarios and / or tasks during reasoning. To address this, an effective approach is to provide the model with training data similar to the inference data, thereby improving its inference performance.

[0175] As an example, the similarity between training data and inference data can be measured by their corresponding additional conditions. For instance, additional conditions for a given piece of data can indicate relevant conditional information regarding at least one process in the configuration, collection, generation, or acquisition of that data. Taking the example of a network device providing training and inference data to a terminal device, the network device can indicate one or more training data sets and an associated ID for each training data set to the terminal device. The additional conditions indicated by the same associated ID for the training data and the inference data are the same. The terminal device can train a model based on the received training data to obtain several models. Subsequently, the network device can indicate a specific inference data set and its associated ID to the terminal device, enabling the terminal device to process the model trained on the training data with the same associated ID, thereby obtaining the corresponding output data for the inference data.

[0176] However, the above process still has some problems and has failed to effectively improve data processing efficiency (such as problems 1 and 2 below).

[0177] Problem 1: There may be one or more additional conditions corresponding to the training data or inference data. When there are multiple additional conditions, the number of combinations of different additional conditions will increase significantly. This leads to the need to allocate a large number of additional condition identifiers, and the communication device needs to maintain these large number of additional condition identifiers, resulting in a decrease in data processing efficiency.

[0178] Question 2: Communication devices can train one or more models based on a certain training data. When there are multiple models, the communication devices will use additional conditions to identify which model to process the inference data and obtain the output data. This makes it impossible for different communication devices to align the models that process the inference data, thus affecting the data processing efficiency.

[0179] To address the aforementioned problems, this application provides a communication method and related apparatus, which will be described in detail below with reference to the accompanying drawings.

[0180] Please refer to Figure 3, which is a schematic diagram of an implementation of the communication method provided in this application. The method includes the following steps.

[0181] It should be noted that, in the following text, Figure 3 uses the first communication device and other communication devices (such as the second communication device) as examples to illustrate the method in this interactive illustration, but this application does not limit the execution subject of this interactive illustration. For example, the communication device can be a communication device (such as a terminal device or a network device), or a chip, baseband chip, modem chip, SoC chip (such as an SoC chip containing a modem core), SIP chip, communication module, chip system, processor, logic module, or software in the communication device.

[0182] As an example, the first communication device can be a terminal device and the second communication device can be a network device.

[0183] As another example, the first communication device can be a network device, and the second communication device can be a terminal device.

[0184] As another example, both the first and second communication devices are terminal devices, meaning that the scheme shown in Figure 3 can be applied to side link communication scenarios.

[0185] S301. The second communication device sends first information, and correspondingly, the first communication device receives the first information. The first information indicates input data.

[0186] S302. The second communication device sends second information, and correspondingly, the first communication device receives the second information. The second information indicates N similarity information corresponding to the additional conditions of the input data and the additional conditions of the N training data, where N is a positive integer. The N training data are used to train M models, where M is a positive integer; the second information is used to determine K models from the M models, where K is a positive integer less than or equal to M.

[0187] S303. The first communication device processes the input data based on the K models to obtain K output data.

[0188] In this application, the model may include an AI model, a neural network model, an AI neural network model, a machine learning model, or an AI processing model, etc.

[0189] In this application, during the process of the communication device processing input data based on a model to obtain output data, the processing may include one or more of the following: reasoning, prediction, derivation, recognition, and decision-making. For example, the input data may be reasoning data, and the output data may be reasoning output data. Exemplarily, in the above process, the first communication device may perform one or more of the following processing on the input data based on K sub-models: reasoning, prediction, derivation, recognition, and decision-making, to obtain output data.

[0190] It should be understood that additional conditions for certain data can indicate relevant conditional information for at least one of the processes in which the data is configured, collected, generated, or acquired. For example, such additional conditions may indicate at least one of the following: spatial filter information, beam information, antenna array information, power information, or application scenarios information.

[0191] For example, spatial filter information can indicate at least one of the following: 3dB beamwidth, beam boresight directions, beam shape, transmit beam angle (Tx), and beam index.

[0192] For example, antenna array information can indicate at least one of the following: number of antennas, antenna arrangement, antenna height, and down tilt.

[0193] For example, power information can indicate at least one of transmission power and reception power.

[0194] For example, application scenario information can indicate at least one of the following: inter-station distance (ISD), urban microcell (Umi), and urban macrocell (Uma).

[0195] It should be understood that the similarity information involved in this application includes absolute difference, relative difference, similarity probability, or other information used to characterize similarity. This similarity information can be implemented in various ways; for example, it may include at least one or more of the following:

[0196] The first field indicates whether the similarity (e.g., absolute difference, relative difference, similarity probability) between the additional conditions of a training data point and the additional conditions of the input data is 100%, or whether the additional conditions of a training data point are the same as the additional conditions of the input data. For example, the first field corresponds to a single bit. When the bit is 0, it means that the additional conditions of a training data point are the same as the additional conditions of the input data; when the bit is 1, it means that the additional conditions of a training data point are different from the additional conditions of the input data; or when the bit is 1, it means that the additional conditions of a training data point are the same as the additional conditions of the input data; when the bit is 0, it means that the additional conditions of a training data point are different from the additional conditions of the input data.

[0197] The second field indicates whether the similarity (e.g., absolute difference, relative difference, similarity probability) between the additional conditions of a training data set and the additional conditions of the input data set is 0%, or whether the additional conditions of a training data set are completely different from the additional conditions of the input data set.

[0198] The third field indicates the value of the similarity (e.g., absolute difference, relative difference, similarity probability) between the additional conditions of a training data set and the additional conditions of the input data set.

[0199] Optionally, if the similarity information includes the first field mentioned above, the second information may indicate whether the additional conditions of the input data are the same as the additional conditions of the N training data.

[0200] Optionally, if the similarity information includes the second field mentioned above, the second information may indicate whether the additional conditions of the input data are different from or similar to the additional conditions of the N training data.

[0201] Optionally, the first and second information can be carried in the same message / information / signaling or in different messages / information / signaling; this is not limited here.

[0202] It should be understood that the N similarity information indicated by the second information refers to the similarity information between the additional conditions of the input data and the additional conditions of the N training data. For example, the N similarity information corresponds one-to-one with the additional conditions of the N training data, or the i-th similarity information among the N similarity information is the similarity information between the additional conditions of the input data and the additional conditions of the i-th training data among the N training data.

[0203] Based on the scheme shown in Figure 3, the second information received by the first communication device in step S302 indicates N similarity information corresponding to the additional conditions of the input data and the additional conditions of the N training data, respectively. Subsequently, the first communication device can determine K models from M models based on the second information, and in step S303, process the input data indicated by the first information based on the K models to obtain K output data. In this way, the first communication device can determine K models from the M models trained on the N training data based on the similarity information between the additional conditions of the input data and the additional conditions of the N training data, and process the input data based on the K models. Therefore, the first communication device can process the input data based on the models corresponding to the training data that are similar to the additional conditions of the input data, which can improve the consistency between the model training data and the model input data, thereby improving data processing efficiency.

[0204] In one possible implementation of the method shown in Figure 3, the additional conditions of the input data indicated by the first information in step S301 include P conditions, and the additional conditions of the i-th training data of N training data include Q conditions, where P and Q are both positive integers, and i takes values ​​from 1 to N. The following will provide an exemplary description with some examples.

[0205] In Method 1, among the N similarity information indicated by the second information, the i-th similarity information is used to indicate the overall similarity between the P conditions and the Q conditions, where p takes values ​​from 1 to P and q takes values ​​from 1 to Q.

[0206] Method 2: In the N similarity information indicated by the second information, the i-th similarity information is used to indicate the similarity between the p-th condition among the P conditions and the q-th condition among the Q conditions, where p takes values ​​from 1 to P and q takes values ​​from 1 to Q.

[0207] It should be noted that p and q may have multiple different implementations. Similarly, in method two, the i-th similarity information can also have multiple implementations. More examples will be used to illustrate this below.

[0208] Example 1: p and q are equal. In this case, Method 2 can be understood as follows: the i-th similarity information is used to indicate the similarity between the j-th condition among P conditions and the j-th condition among Q conditions, where j takes values ​​from 1 to P or from 1 to Q.

[0209] In Example 1, if P equals Q, then, taking the case where both P and Q are greater than 1, the i-th similarity information can indicate the similarity between the first condition in P conditions and the first condition in Q conditions, ..., the similarity between the j-th condition in P conditions and the j-th condition in Q conditions, ..., the similarity between the P-th condition in P conditions and the P-th condition in Q conditions; that is, the i-th similarity information can indicate P similarities.

[0210] In Example 1, if P is greater than Q, then, taking the case where both P and Q are greater than 1, the i-th similarity information can indicate the similarity between the first condition in P conditions and the first condition in Q conditions, ..., the similarity between the j-th condition in P conditions and the j-th condition in Q conditions, ..., the similarity between the Q-th condition in P conditions and the Q-th condition in Q conditions; that is, the i-th similarity information can indicate Q similarities.

[0211] In Example 1, if P is less than Q, then, taking the case where both P and Q are greater than 1, the i-th similarity information can indicate the similarity between the first condition in P conditions and the first condition in Q conditions, ..., the similarity between the j-th condition in P conditions and the j-th condition in Q conditions, ..., the similarity between the P-th condition in P conditions and the P-th condition in Q conditions; that is, the i-th similarity information can indicate P similarities.

[0212] Example 2: The relationship between p and q is not limited. In this case, Method 2 can be understood as follows: the i-th similarity information is used to indicate the similarity between the p-th condition out of P conditions and the q-th condition out of Q conditions, for a total of P*Q similarities. In other words, the i-th similarity information is used to indicate the Q similarities between the 1-th condition out of P conditions and the Q conditions, ..., the Q similarities between the p-th condition out of P conditions and the Q conditions, ..., the Q similarities between the p-th condition out of P conditions and the Q conditions, for a total of P*Q similarities.

[0213] Based on Method 1 and / or Method 2, the similarity information indicated by the second information can indicate the overall similarity between the additional conditions of the input data and the additional conditions of the training data, and / or the corresponding similarity of each condition, so as to improve the flexibility of the scheme implementation.

[0214] Optionally, the N similarity information indicated by the second information is used to determine K models among the M models, including: the N similarity information is used to determine the M similarities corresponding to the M models; wherein, among the M models, the K similarities corresponding to the K models are greater than or equal to the MK similarities corresponding to the other MK models. Specifically, the first communication device can determine the M similarities corresponding to the M models based on the N similarity information indicated by the second information, and the first communication device can determine the models corresponding to the K similarities with higher similarity as the K models for processing the input data, so that the first communication device can process the input data based on the K models obtained from the training data corresponding to the additional conditions with higher similarity, which can improve the consistency between the model training data and the model input data, thereby improving data processing efficiency.

[0215] It should be understood that in Method 1 and Method 2, among the N similarity information indicated by the second information, each similarity information may include the aforementioned third field to indicate the overall similarity and / or the corresponding similarity of each condition.

[0216] In Method A, among the N similarity information indicated by the second information, the determining factors of the i-th similarity information include: the similarity between the p-th condition among the P conditions and the q-th condition among the Q conditions, where p takes values ​​from 1 to P and q takes values ​​from 1 to Q.

[0217] Method B, among the N similarity information indicated by the second information, the determining factors of the i-th similarity information include: the similarity between the p-th condition among the P conditions and the q-th condition among the Q conditions, and the importance of the p-th condition among the P conditions, or the importance of the q-th condition among the Q conditions, where p takes values ​​from 1 to P and q takes values ​​from 1 to Q.

[0218] It should be noted that the degree of importance between any two conditions can be indicated or confirmed by an importance value. For example, the smaller the importance value, the higher the importance; conversely, the larger the importance value, the lower the importance. Similarly, the larger the importance value, the higher the importance; conversely, the smaller the importance value, the lower the importance.

[0219] Based on method A or method B, the similarity information indicated by the second information can be determined by the similarity between the additional conditions of the input data and the additional conditions of the training data. In this way, the second information can indicate the similarity information based on the configured or pre-configured rules, and the similarity of each additional condition can be reflected from the value of the similarity information.

[0220] Based on method B, the similarity information indicated by the second information can be determined by the importance of the additional conditions of the input data and the additional conditions of the training data. In this way, the second information can indicate the similarity information based on the configured or pre-configured rules, and the importance of each additional condition can be reflected from the value of the similarity information to meet the importance requirements of different conditions.

[0221] To facilitate understanding of the above process, some implementation examples will be provided below, taking the similarity information indicating the similarity value as an example.

[0222] As an example, as shown in Figure 4a, let's take an example where both the number of additional conditions for the input data and the number of additional conditions for the training data are 3 (Q = P = 3). As mentioned earlier, the following three conditions can be implemented in various ways, such as spatial filter information, beam information (e.g., at least one of beam angle, beamwidth, beam index, etc.), antenna array information, power information, or application scenario information.

[0223] For the training data corresponding to the associated identifier 1 (denoted as training data 1), the similarity between condition 1 of the input data and condition 1 of training data 1 is 90%, the similarity between condition 2 of the input data and condition 2 of training data 1 is 80%, and the similarity between condition 3 of the input data and condition 3 of training data 1 is 70%.

[0224] For the training data corresponding to the associated identifier 2 (denoted as training data 2), the similarity between condition 1 of the input data and condition 1 of training data 2 is 90%, the similarity between condition 2 of the input data and condition 2 of training data 2 is 95%, and the similarity between condition 3 of the input data and condition 3 of training data 2 is 98%.

[0225] For the training data corresponding to the associated identifier 3 (denoted as training data 3), the similarity between condition 1 of the input data and condition 1 of training data 3 is 95%, the similarity between condition 2 of the input data and condition 2 of training data 3 is 80%, and the similarity between condition 3 of the input data and condition 3 of training data 3 is 85%.

[0226] In the example shown in Figure 4a, based on Method 1, three similarity information points corresponding to the three training data points can be determined, namely:

[0227] The first similarity information indicates the overall similarity between the 3 conditions (P=3) corresponding to the input data and the 3 conditions (Q=3) corresponding to training data 1. For example, this overall similarity can be the average of multiple conditions, i.e., (90% + 80% + 70%) / 3 = 80%. Alternatively, this overall similarity can be a weighted average of multiple conditions; for example, with weighting coefficients of 0.3, 0.2, and 0.5 for the three conditions, the result would be 90% * 0.3 + 80% * 0.2 + 70% * 0.5 = 78%.

[0228] The second similarity information indicates the overall similarity between the 3 conditions (P=3) corresponding to the input data and the 3 conditions (Q=3) corresponding to the training data 2. For example, this overall similarity can be the average of multiple conditions, i.e., (90% + 95% + 98%) / 3 = 94%. Alternatively, this overall similarity can be a weighted average of multiple conditions; for example, with weighting coefficients of 0.3, 0.2, and 0.5 for the three conditions, it would be 90% * 0.3 + 95% * 0.2 + 98% * 0.5 = 95%.

[0229] The third similarity information indicates the overall similarity between the 3 (P=3) conditions corresponding to the input data and the 3 (Q=3) conditions corresponding to training data 1. For example, this overall similarity can be the average of multiple conditions, i.e., (95% + 80% + 85%) / 3 = 86%. Alternatively, this overall similarity can be a weighted average of multiple conditions; for example, with weighting coefficients of 0.3, 0.2, and 0.5 for the three conditions, it would be 95% * 0.3 + 80% * 0.2 + 85% * 0.5 = 87%.

[0230] The following example will use the overall similarity indicated by the three similarity information points mentioned above as a weighted average.

[0231] As can be seen from the combined methods 1 and 8, the overall similarity corresponding to the three similarity information is 78%, 95%, and 87%, respectively. Correspondingly, the second piece of information can be achieved in several ways:

[0232] For example, the second information can indicate the similarity information corresponding to the highest similarity (i.e., the similarity information corresponding to training data 2 with an overall similarity of 95%, N=1), and the first communication device can then process the input data based on the model trained by training data 2 in step S303.

[0233] For example, the second information can indicate the similarity information corresponding to each similarity (i.e., the similarity information corresponding to training data 1 with an overall similarity of 78%, training data 2 with an overall similarity of 95%, and training data 3 with an overall similarity of 87%, N=1). Subsequently, the first communication device can select a model trained on the training data corresponding to several higher similarity information (e.g., 1, 2, or 3) based on the three similarity information to process the input data. Taking the first communication device selecting two higher similarity information as an example, in step S303, the first communication device can process the input data based on the model trained on training data 2 and training data 3.

[0234] Combining Method 1 and Method B, we can see that the overall similarity corresponding to the three similarity information is 78%, 95%, and 87%, respectively. Assuming the importance values ​​corresponding to the above three conditions are 1, 2, and 3 (the smaller the importance value, the higher the importance), then condition 1 is more important than condition 2, and condition 2 is more important than condition 3. Correspondingly, the second piece of information can be achieved in several ways:

[0235] For example, the second information can indicate the similarity information corresponding to the highest similarity, and the first communication device can process the input data in step S303 based on the model trained on the training data corresponding to the highest similarity.

[0236] For example, prioritizing importance, the similarity of additional conditions is determined sequentially from highest to lowest importance to see if it exceeds a similarity threshold. The training data corresponding to the first feature exceeding the similarity threshold is the training data with the highest similarity. From the above, we know that the importance from highest to lowest is condition 1, condition 2, and condition 3; among these three training data, the training data with the highest similarity corresponding to these three conditions satisfies:

[0237] For condition 1, the similarity between the three training data and the input data under condition 1 is 90%, 90%, and 95%, respectively. Therefore, the training data with the highest similarity to the input data under condition 1 is training data 3, with a similarity of 95%.

[0238] For condition 2, the similarity between the three training data and the input data under condition 2 is 80%, 95%, and 80%, respectively. Therefore, the training data with the highest similarity to the input data under condition 2 is training data 2, with a similarity of 95%.

[0239] For condition 3, the similarity between the three training data and the input data for condition 3 is 70%, 98%, and 85%, respectively. Therefore, the training data with the highest similarity to the input data for condition 3 is training data 2, with a similarity of 98%.

[0240] Assuming the similarity threshold is 97%, the similarity of training data 2 is greater than the threshold. Therefore, the training data with the highest similarity to the input data is 2. That is, the second information can indicate that the similarity of training data 2 is the highest (i.e., N=1). Subsequently, the first communication device can process the input data based on the model trained on training data 2 in step S303.

[0241] For example, prioritizing similarity, the importance of additional conditions is determined sequentially from highest to lowest similarity, checking if they fall below an importance threshold. The training data corresponding to the first feature above the importance threshold is the training data with the highest similarity. From the above, we know that the importance from highest to lowest is condition 1, condition 2, and condition 3; in the above three training data sets, the order of similarity satisfies:

[0242] ①. The similarity between condition 3 of training data 2 and condition 3 of input data is 98%.

[0243] ②. The similarity between condition 2 of training data 2 and condition 2 of input data, and the similarity between condition 1 of training data 3 and condition 1 of input data, i.e., 95%.

[0244] ③. The similarity between condition 1 of training data 1 and condition 1 of input data, and the similarity between condition 1 of training data 2 and condition 1 of input data, i.e., 90%.

[0245] ④. The similarity between condition 3 of training data 3 and condition 3 of input data, i.e., 85%.

[0246] ⑤. The similarity between condition 2 of training data 1 and condition 2 of input data, and the similarity between condition 2 of training data 3 and condition 2 of input data, i.e., 80%.

[0247] ⑥. The similarity between condition 3 of training data 1 and condition 3 of input data, i.e., 70%.

[0248] Assuming the similarity threshold is 97% and the importance threshold is 3, the similarity corresponding to condition 3 in training data 2 is greater than the threshold, and condition 3 in training data 2 also satisfies the importance threshold. Therefore, the training data with the highest similarity to the input data is 2. That is, the second information can indicate that the similarity corresponding to training data 2 is the highest (i.e., N=1). Subsequently, the first communication device can process the input data based on the model trained on training data 2 in step S303.

[0249] As can be seen from the above process, the second information can indicate the similarity information between the additional conditions of one or more training data and the additional conditions of the input data, so that the first communication device can use the model trained by the training data with high similarity to process the input data based on the similarity information, which can improve the consistency between the model training data and the model input data, thereby improving the data processing efficiency.

[0250] In the above example, the implementation process of the second information through method one is taken as an example (i.e., the similarity information indicates the overall similarity). As described above, the second information can be implemented through method two, or the second information can also be implemented through a combination of method one and method two. In the latter two implementation processes, the first communication device can compare the similarity corresponding to each additional condition one by one to obtain the comparison result, or it can determine the overall similarity based on the similarity corresponding to each additional condition and then use the overall similarity as the comparison result. After that, the first communication device can determine several models for processing the input data based on the comparison result. The specific implementation can refer to the above process.

[0251] As another example, as shown in Figure 4b, let's take the case where the number of additional conditions for the input data and the number of additional conditions for the training data are both 1 (Q = P = 1). As mentioned above, the following one condition can be achieved in multiple ways, such as spatial filter information, beam information (e.g., at least one of beam angle, beamwidth, beam index, etc.), antenna array information, power information, or application scenario information.

[0252] In Figure 4b, based on 3 (N=3) training data, the following 2 (M=2) models can be obtained:

[0253] Model 1 is obtained based on training data 1 and training data 2;

[0254] Model 2 is obtained based on training data 2 and training data 3.

[0255] Subsequently, assuming that the similarity information indicated by the second information received by the first communication device in step S302 includes:

[0256] For the training data corresponding to the associated identifier 1 (denoted as training data 1), the additional conditions of the input data have a similarity of 95% with the additional conditions of training data 1.

[0257] For the training data corresponding to the associated identifier 2 (denoted as training data 2), the additional conditions of the input data have a similarity of 98% with the additional conditions of training data 2.

[0258] For the training data corresponding to the associated identifier 3 (denoted as training data 3), the additional conditions of the input data have a similarity of 90% with the additional conditions of training data 3.

[0259] Therefore, the first communication device can select K models from 2 (M=2) models to process the input data based on the similarity information indicated by the second information. It can be seen that in the example shown in Figure 4b, the training data 2 has the highest similarity to the input data. Accordingly, after receiving the second information, the first communication device can determine the similarity between the two models based on the similarity information indicated by the second information, including:

[0260] The similarity score corresponding to Model 1. For example, the similarity score of Model 1 can be the average of the similarities between different training data and input data corresponding to Model 1, i.e., (95% + 98%) / 2 = 96.5%. Alternatively, the similarity score of Model 1 can be the weighted average of the similarities between different training data and input data corresponding to Model 1. Taking two training data points with weighting coefficients of 0.4 and 0.6 as an example, the score would be 95% * 0.4 + 98% * 0.6 = 96.8%.

[0261] The similarity to Model 2. For example, the similarity to Model 2 can be the average of the similarities between different training data and the input data, i.e., (98% + 90%) / 2 = 94%. Alternatively, the similarity to Model 2 can be the weighted average of the similarities between different training data and the input data. Taking two training data points with weighting coefficients of 0.4 and 0.6 as an example, the similarity would be 98% * 0.4 + 90% * 0.6 = 93.2%.

[0262] Subsequently, taking the above-mentioned weighted average implementation process as an example, the first communication device can determine that the similarity of model 1 is 96.8% based on the similarity information indicated by the second information, and determine that the similarity of model 1 is 93.2%.

[0263] When K is 2, in step S303, the first communication device can process the input data based on model 1 and model 2 to obtain the output data of model 1 and the output data of model 2, for a total of 2 (K=2) output data.

[0264] When K is 1, in step S303, the first communication device can process the input data based on the model with higher similarity among the two models (i.e., model 1) to obtain the output data of model 1, for a total of 1 (K=1) output data.

[0265] Optionally, the value of K can be pre-configured or indicated by the network device.

[0266] As can be seen from the above process, the second information can indicate the similarity information between the additional conditions of one or more training data and the additional conditions of the input data. This allows the first communication device to process the input data using some or all of the models trained on the highly similar training data, thereby improving the consistency between the model training data and the model input data and thus improving data processing efficiency. Furthermore, the first communication device can also select some or all of the models corresponding to the same training data for data processing based on the similarity information. When the first communication device selects some models for data processing, it does not need to process data based on other models, which can reduce data processing latency and lower power consumption and computing power consumption.

[0267] In one possible implementation, as shown in Figure 4c, the method shown in Figure 3 further includes:

[0268] S304. The first communication device sends third information, and correspondingly, the second communication device receives the third information, which is used to determine whether the input data is consistent with the training data corresponding to the K models; wherein, the third information is determined based on the K output data. In other words, the first communication device can also determine and send the third information based on the K output data obtained by processing the input data using the K models, so that the receiver of the third information can determine whether the input data is consistent with the training data corresponding to the K models. In this way, the model performance of the K models of the first communication device can be supervised, so that the receiver of the third information can perform model management on the models of the first communication device (e.g., model scheduling, model update, model switching, or function rollback, etc.).

[0269] Optionally, the third information includes at least one of the following:

[0270] The first indication information indicates whether the input data is consistent with the training data corresponding to the K models;

[0271] The second indication information indicates the performance corresponding to the K output data;

[0272] The third indication information indicates the baseline truth corresponding to the K output data.

[0273] Optionally, the above performance can indicate one or more of the following: system performance, link performance, or model accuracy.

[0274] For example, if the third information includes the second indication information and the performance of the K output data indicated by the second indication information is lower than a threshold, the third information may also include request information for requesting function rollback (e.g., requesting rollback to non-AI mode) and / or requesting model updates (e.g., requesting retraining of some or all of the K models).

[0275] For example, if the third information includes the second indication information and the performance of the K output data indicated by the second indication information is higher than the threshold, the second communication device can determine that the current input data (denoted as input data 1) is consistent with the training data. Accordingly, the second communication device can subsequently indicate the additional conditions corresponding to other input data (denoted as input data 2) that are the same or similar to the additional conditions of input data 1. The additional conditions corresponding to the training data are the same. For example, the second communication device indicates through the first field mentioned above that the similarity (e.g., absolute difference, relative difference, similarity probability) between the additional conditions of the training data and the additional conditions of input data 2 is 100%, or indicates whether the additional conditions of the training data are the same as the additional conditions of input data 2.

[0276] In one possible implementation, the N similarity information pieces are used to determine resource information. The resources indicated by this resource information include the transmission resources of the third information and / or the reception resources of the measurement signal corresponding to the third information. This resource information includes one or more of the following: start time-domain position, duration, end time-domain position, and frequency-domain resources. Specifically, the N similarity information pieces indicated by the second information can be used to determine resource information. The resources indicated by this resource information are used to carry the third information and / or the measurement signal corresponding to the third information. In this way, the first communication device can quickly determine the transmission resources of the third information and / or the measurement signal corresponding to the third information, further improving communication efficiency.

[0277] Optionally, as shown in Figure 4c, the method shown in Figure 3 also includes:

[0278] S305. The second communication device sends fourth information, and the first communication device receives the fourth information. This fourth information indicates one or more of the following: the start time-domain position, duration, and end time-domain position of resource information associated with L similarity information, and frequency-domain resources. The fourth information and the N similarity information are used to determine the resource information, and the L similarity information includes the N similarity information, where L is greater than or equal to N. This enables the first communication device to determine the transmission resources of the third information and / or the measurement signal corresponding to the third information based on the fourth information and the N similarity information.

[0279] Optionally, the fourth piece of information can be pre-configured to reduce transmission overhead.

[0280] Optionally, the aforementioned starting time-domain position can be determined by the time-domain offset length and the starting time. In this case, the aforementioned resource information may include the time-domain offset length (or an index or identifier of the time-domain offset length), etc., so that the first communication device and the second communication device can determine the starting time-domain position for transmitting the third information and / or the starting time-domain position for the measurement signal corresponding to the transmission of the third information based on the resource information.

[0281] For example, the start time could be the time when the first communication device receives or parses the first information in step S301, the time when the first communication device receives or parses the second information in step S302, the start time when the first communication device processes the input data in step S303, the time when the first communication device obtains K output data in step S303, the time when the first communication device sends the third information in step S304, or the time when the first communication device sends or receives the measurement signal corresponding to the third information in step S304. No limitation is made here.

[0282] It should be noted that the aforementioned third information and / or the measurement signal corresponding to the third information can be used to determine the model performance of K models, thereby enabling model management of the K models. Taking model management including model performance monitoring as an example, the transmission time of the third information and / or the measurement signal corresponding to the third information can be understood as the model performance monitoring time (or supervision time). As can be seen from the above process, this supervision time can be determined based on the time-domain bias length, and the similarity indicated by the aforementioned similarity information can be correlated with this time-domain bias length. For example, the level of similarity indicated by any of the L or N similarity information pieces is negatively correlated with the length of the time-domain bias length corresponding to that similarity.

[0283] As an example, if the additional conditions of the input data are not very similar to the additional conditions of a certain training data, the output data obtained by the model trained on that training data may be poor (or the model trained on that training data may not be able to process the input data, resulting in no output data). In this case, more frequent model performance monitoring may be required. Accordingly, the time-domain bias length corresponding to this similarity is shorter, so that model management can be achieved through more frequent model performance monitoring, thereby improving data processing performance.

[0284] As another example, if the additional conditions of the input data are highly similar to the additional conditions of a certain training data, the output data obtained by the model trained on that training data may have better performance. In this case, more frequent model performance monitoring may not be required. Correspondingly, the time-domain bias length corresponding to this similarity is longer, so that model management can be achieved through sparser (or less frequent) model performance monitoring to reduce overhead.

[0285] Referring to Figure 5, this application embodiment provides a communication device 500. This communication device 500 can implement the functions of the first communication device (or second communication device) in the above method embodiments, and therefore can also achieve the beneficial effects of the above method embodiments. In this application embodiment, the communication device 500 can be the first communication device (or the second communication device), or it can be an integrated circuit or component inside the first communication device (or the second communication device), such as a chip, baseband chip, modem chip, SoC chip (e.g., an SoC chip containing a modem core), SIP chip, communication module, chip system, processor, etc.

[0286] It should be noted that the transceiver unit 502 may include a transmitting unit and a receiving unit, which are used to perform transmitting and receiving respectively.

[0287] In one possible implementation, when the device 500 is used to execute the method performed by the first communication device in FIG3 and related embodiments, the device 500 includes a processing unit 501 and a transceiver unit 502; the transceiver unit 502 is used to receive first information, which indicates input data; the transceiver unit 502 is also used to receive second information, which indicates N similarity information corresponding to the additional conditions of the input data and the additional conditions of N training data, respectively, where N is a positive integer; wherein, the N training data are used to train M models through model training, where M is a positive integer; the second information is used to determine K models from the M models, where K is a positive integer less than or equal to M; the processing unit 501 is used to process the input data based on the K models to obtain K output data.

[0288] In one possible implementation, when the device 500 is used to execute the method performed by the second communication device in FIG3 and related embodiments, the device 500 includes a processing unit 501 and a transceiver unit 502; the processing unit 501 is used to determine first information and second information, and the transceiver unit 502 is used to send the first information, which indicates input data; the transceiver unit 502 is also used to send the second information, which indicates N similarity information corresponding to the additional conditions of the input data and the additional conditions of N training data, respectively, where N is a positive integer; wherein, the N training data are used to train M models through model training, where M is a positive integer; the second information is used to determine K models from the M models, and the K models are used to process the input data to obtain K output data, where K is a positive integer less than or equal to M.

[0289] In one possible design, when the communication device 500 is a terminal device or a communication module within a terminal, the functionality of the processing unit 501 can be implemented by one or more processors. Specifically, the processor may include a modem chip, a SoC chip (such as a SoC chip containing a modem core), or a SIP chip. The functionality of the transceiver unit 502 can be implemented by transceiver circuitry.

[0290] In one possible design, when the communication device 500 is a circuit or chip in a terminal responsible for communication functions, such as a modem chip, a SoC chip, or a SoC chip or SIP chip containing a modem core, the function of the processing unit 501 can be implemented by a circuit system in the aforementioned chip that includes one or more processors or processor cores. The function of the transceiver unit 502 can be implemented by the interface circuitry or data transceiver circuitry on the aforementioned chip.

[0291] It should be noted that the information execution process of the unit of the above-mentioned communication device 500 can be specifically described in the method embodiment shown above in this application, and will not be repeated here.

[0292] Please refer to Figure 6, which is another schematic structural diagram of the communication device 600 provided in this application. The communication device 600 includes a logic circuit 601 and an input / output interface 602. The communication device 600 can be a chip or an integrated circuit.

[0293] In Figure 5, the transceiver unit 502 can be a communication interface, which can be the input / output interface 602 in Figure 6, and the input / output interface 602 can include an input interface and an output interface. Alternatively, the communication interface can also be a transceiver circuit, which can include an input interface circuit and an output interface circuit.

[0294] In one possible implementation, when the device 600 is used to execute the method performed by the first communication device in FIG3 and related embodiments, the input / output interface 602 is used to receive first information, which indicates input data; the input / output interface 602 is also used to receive second information, which indicates N similarity information corresponding to the additional conditions of the input data and the additional conditions of N training data, respectively, where N is a positive integer; wherein, the N training data are used to train M models through model training, where M is a positive integer; the second information is used to determine K models from the M models, where K is a positive integer less than or equal to M; the logic circuit 601 is used to process the input data based on the K models to obtain K output data.

[0295] In one possible implementation, when the device 600 is used to execute the method performed by the second communication device in FIG3 and related embodiments, the logic circuit 601 is used to determine the first information and the second information, and the input / output interface 602 is used to send the first information, which indicates the input data; the input / output interface 602 is also used to send the second information, which indicates the N similarity information corresponding to the additional conditions of the input data and the additional conditions of the N training data, respectively, where N is a positive integer; wherein, the N training data are used to train the model to obtain M models, where M is a positive integer; the second information is used to determine K models from the M models, and the K models are used to process the input data to obtain K output data, where K is a positive integer less than or equal to M.

[0296] The logic circuit 601 and the input / output interface 602 can also perform other steps performed by the first or second communication device in any embodiment and achieve corresponding beneficial effects, which will not be elaborated here.

[0297] In one possible implementation, the processing unit 501 shown in FIG5 can be the logic circuit 601 in FIG6.

[0298] Optionally, the logic circuit 601 can be a processing device, the functions of which can be partially or entirely implemented in software.

[0299] Optionally, the processing apparatus may include a memory and a processor, wherein the memory is used to store a computer program, and the processor reads and executes the computer program stored in the memory to perform the corresponding processing and / or steps in any of the method embodiments.

[0300] Optionally, the processing device may consist of only a processor. A memory for storing computer programs is located outside the processing device, and the processor is connected to the memory via circuitry / wires to read and execute the computer programs stored in the memory. The memory and processor may be integrated together or physically independent of each other.

[0301] Optionally, the processing device may be one or more chips, or one or more integrated circuits. For example, the processing device may be one or more field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), system-on-chips (SoCs), central processing units (CPUs), network processors (NPs), digital signal processors (DSPs), microcontroller units (MCUs), programmable logic controllers (PLDs), or other integrated chips, or any combination of the above chips or processors.

[0302] Please refer to Figure 7, which shows the communication device 700 involved in the above embodiments provided in the embodiments of this application. Specifically, the communication device 700 can be the communication device as a terminal device in the above embodiments. The example shown in Figure 7 is that the terminal device is implemented through the terminal device (or the components in the terminal device).

[0303] The present invention provides a possible logical structure diagram of the communication device 700, which may include, but is not limited to, at least one processor 701 and a communication port 702.

[0304] In Figure 5, the transceiver unit 502 can be a communication interface, which can be the communication port 702 in Figure 7. The communication port 702 can include an input interface and an output interface. Alternatively, the communication port 702 can also be a transceiver circuit, which can include an input interface circuit and an output interface circuit.

[0305] Further optionally, the device may also include at least one of a memory 703 and a bus 704. In the embodiments of this application, the at least one processor 701 is used to control the operation of the communication device 700.

[0306] Furthermore, the processor 701 can be a central processing unit, a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a digital signal processor and a microprocessor, etc. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0307] It should be noted that the communication device 700 shown in Figure 7 can be used to implement the steps implemented by the terminal device in the aforementioned method embodiments and to achieve the corresponding technical effects of the terminal device. The specific implementation of the communication device shown in Figure 7 can be referred to the description in the aforementioned method embodiments, and will not be repeated here.

[0308] Please refer to Figure 8, which is a structural schematic diagram of the communication device 800 involved in the above embodiments provided in the embodiments of this application. Specifically, the communication device 800 can be a communication device as a network device in the above embodiments. The example shown in Figure 8 is that the network device is implemented through a network device (or a component in the network device). The structure of the communication device can be referred to the structure shown in Figure 8.

[0309] The communication device 800 includes at least one processor 811 and at least one network interface 814. Optionally, the communication device further includes at least one memory 812, at least one transceiver 813, and one or more antennas 815. The processor 811, memory 812, transceiver 813, and network interface 814 are connected, for example, via a bus. In this embodiment, the connection may include various interfaces, transmission lines, or buses, etc., and this embodiment is not limited thereto. The antenna 815 is connected to the transceiver 813. The network interface 814 enables the communication device to communicate with other communication devices through a communication link. For example, the network interface 814 may include a network interface between the communication device and core network equipment, such as an S1 interface, or a network interface between the communication device and other communication devices (e.g., other network devices or core network equipment), such as an X2 or Xn interface.

[0310] In Figure 5, the transceiver unit 502 can be a communication interface, which can be the network interface 814 in Figure 8. The network interface 814 can include an input interface and an output interface. Alternatively, the network interface 814 can also be a transceiver circuit, which can include an input interface circuit and an output interface circuit.

[0311] The processor 811 is primarily used to process communication protocols and communication data, control the entire communication device, execute software programs, and process data from these programs, for example, to support the actions described in the embodiments of the communication device. The communication device may include a baseband processor and a central processing unit (CPU). The baseband processor is primarily used to process communication protocols and communication data, while the CPU is primarily used to control the entire terminal device, execute software programs, and process data from these programs. The processor 811 in Figure 8 can integrate the functions of both a baseband processor and a CPU. Those skilled in the art will understand that the baseband processor and CPU can also be independent processors interconnected via technologies such as buses. Those skilled in the art will understand that a terminal device may include multiple baseband processors to adapt to different network standards, and multiple CPUs to enhance its processing capabilities. The various components of the terminal device can be connected via various buses. The baseband processor can also be described as a baseband processing circuit or a baseband processing chip. The CPU can also be described as a central processing circuit or a central processing chip. The function of processing communication protocols and communication data can be built into the processor or stored in memory as a software program, which is then executed by the processor to implement the baseband processing function.

[0312] The memory is primarily used to store software programs and data. The memory 812 can exist independently or be connected to the processor 811. Optionally, the memory 812 can be integrated with the processor 811, for example, integrated into a single chip. The memory 812 can store program code that executes the technical solutions of the embodiments of this application, and its execution is controlled by the processor 811. The various types of computer program code being executed can also be considered as drivers for the processor 811.

[0313] Figure 8 shows only one memory and one processor. In actual terminal devices, there may be multiple processors and multiple memories. Memory can also be called storage medium or storage device, etc. Memory can be a storage element on the same chip as the processor, i.e., an on-chip storage element, or it can be a separate storage element; this application does not limit this.

[0314] Transceiver 813 can be used to support the reception or transmission of radio frequency (RF) signals between a communication device and a terminal. Transceiver 813 can be connected to antenna 815. Transceiver 813 includes a transmitter Tx and a receiver Rx. Specifically, one or more antennas 815 can receive RF signals. The receiver Rx of transceiver 813 receives the RF signals from the antennas, converts the RF signals into digital baseband signals or digital intermediate frequency (IF) signals, and provides the digital baseband signals or IF signals to processor 811 so that processor 811 can perform further processing on the digital baseband signals or IF signals, such as demodulation and decoding. Furthermore, the transmitter Tx in transceiver 813 is also used to receive modulated digital baseband signals or IF signals from processor 811, convert the modulated digital baseband signals or IF signals into RF signals, and transmit the RF signals through one or more antennas 815. Specifically, the receiver Rx can selectively perform one or more stages of downmixing and analog-to-digital conversion on the radio frequency signal to obtain a digital baseband signal or a digital intermediate frequency (IF) signal. The order of these downmixing and IF conversion processes is adjustable. The transmitter Tx can selectively perform one or more stages of upmixing and digital-to-analog conversion on the modulated digital baseband signal or digital IF signal to obtain a radio frequency signal. The order of these upmixing and IF conversion processes is also adjustable. The digital baseband signal and the digital IF signal can be collectively referred to as digital signals.

[0315] The transceiver 813 can also be called a transceiver unit, transceiver, transceiver device, etc. Optionally, the device in the transceiver unit that performs the receiving function can be regarded as the receiving unit, and the device in the transceiver unit that performs the transmitting function can be regarded as the transmitting unit. That is, the transceiver unit includes a receiving unit and a transmitting unit. The receiving unit can also be called a receiver, input port, receiving circuit, etc., and the transmitting unit can be called a transmitter, transmitter, or transmitting circuit, etc.

[0316] It should be noted that the communication device 800 shown in Figure 8 can be used to implement the steps implemented by the network device in the aforementioned method embodiments and achieve the corresponding technical effects of the network device. The specific implementation of the communication device 800 shown in Figure 8 can be referred to the description in the aforementioned method embodiments, and will not be repeated here.

[0317] Please refer to Figure 9, which is a schematic diagram of the structure of the communication device involved in the above embodiments provided in the embodiments of this application.

[0318] It is understood that the communication device 900 includes, for example, modules, units, elements, circuits, or interfaces, which are appropriately configured together to execute the technical solutions provided in this application. The communication device 900 may be the terminal device or network device described above, or a component (e.g., a chip) within these devices, used to implement the methods described in the following method embodiments. The communication device 900 includes one or more processors 901. The processor 901 may be a general-purpose processor or a dedicated processor, for example, a baseband processor or a central processing unit. The baseband processor can be used to process communication protocols and communication data, and the central processing unit can be used to control the communication device (e.g., a RAN node, terminal, or chip), execute software programs, and process data from the software programs.

[0319] Optionally, in one design, processor 901 may include program 903 (sometimes also referred to as code or instructions), which may be executed on processor 901 to cause communication device 900 to perform the methods described in the embodiments below. In yet another possible design, communication device 900 includes circuitry (not shown in FIG9).

[0320] Optionally, the communication device 900 may include one or more memories 902 storing a program 904 (sometimes referred to as code or instructions), which can be run on the processor 901 to cause the communication device 900 to perform the methods described in the above method embodiments.

[0321] Optionally, the processor 901 and / or memory 902 may include AI modules 907 and 908, which are used to implement AI-related functions. The AI ​​modules can be implemented through software, hardware, or a combination of both. For example, the AI ​​module may include a radio intelligence control (RIC) module. For example, the AI ​​module may be a near real-time RIC or a non-real-time RIC.

[0322] Optionally, the processor 901 and / or memory 902 may also store data. The processor and memory may be configured separately or integrated together.

[0323] Optionally, the communication device 900 may further include a transceiver 905 and / or an antenna 906. The processor 901, sometimes referred to as a processing unit, controls the communication device (e.g., a RAN node or terminal). The transceiver 905, sometimes referred to as a transceiver unit, transceiver, transceiver circuit, or transceiver, is used to implement the transmission and reception functions of the communication device via the antenna 906.

[0324] In Figure 5, the processing unit 501 can be a processor 901. The transceiver unit 502 shown in Figure 5 can be a communication interface, which can be the transceiver 905 in Figure 9. The transceiver 905 can include an input interface and an output interface. Alternatively, the transceiver 905 can also be a transceiver circuit, which can include an input interface circuit and an output interface circuit.

[0325] This application also provides a computer-readable storage medium for storing one or more computer-executable instructions. When the computer-executable instructions are executed by a processor, the processor performs the method described in the possible implementations of the first or second communication device in the foregoing embodiments.

[0326] This application also provides a computer program product (or computer program) that, when executed by a processor, executes the method described above for the possible implementation of the first or second communication device.

[0327] This application also provides a chip system including at least one processor for supporting a communication device in implementing the functions involved in the possible implementations of the communication device described above. Optionally, the chip system further includes an interface circuit that provides program instructions and / or data to the at least one processor. In one possible design, the chip system may also include a memory for storing the program instructions and data necessary for the communication device. The chip system may be composed of chips or may include chips and other discrete devices, wherein the communication device may specifically be the first communication device or the second communication device in the aforementioned method embodiments.

[0328] This application also provides a communication system, which includes the first communication device in any of the above embodiments.

[0329] Optionally, the communication system may also include a second communication device.

[0330] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms. Whether a function is implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0331] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0332] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A communication method, characterized in that, include: Receive first information, which indicates input data; Receive second information, which indicates N similarity information corresponding to the additional conditions of the input data and the additional conditions of N training data, where N is a positive integer; wherein, the N training data are used to train M models through the model, where M is a positive integer; the second information is used to determine K models from the M models, where K is a positive integer less than or equal to M; The input data is processed based on the K models to obtain K output data.

2. The method according to claim 1, characterized in that, The method further includes: A third message is sent, which is used to determine whether the input data is consistent with the training data corresponding to the K models; wherein the third message is determined based on the K output data.

3. The method according to claim 2, characterized in that, The third information includes at least one of the following: The first indication information indicates whether the input data is consistent with the training data corresponding to the K models; The second indication information indicates the performance corresponding to the K output data; The third indication information indicates the baseline truth corresponding to the K output data.

4. The method according to any one of claims 1 to 3, characterized in that, The additional conditions for the input data include P conditions, and the additional conditions for the i-th training data of the N training data include Q conditions, where P and Q are both positive integers, and i takes values ​​from 1 to N; The i-th similarity information among the N similarity information is determined based on any one of the following: The similarity between the p-th condition out of the P conditions and the q-th condition out of the Q conditions, where p ranges from 1 to P and q ranges from 1 to Q; or, The similarity between the p-th condition among the P conditions and the q-th condition among the Q conditions, and at least one of the importance of the p-th condition among the P conditions and the importance of the q-th condition among the Q conditions.

5. The method according to any one of claims 1 to 4, characterized in that, The additional conditions for the input data include P conditions, and the additional conditions for the i-th training data of the N training data include Q conditions, where P and Q are both positive integers, and i takes values ​​from 1 to N; The i-th similarity information among the N similarity information is used to indicate at least one of the following: The overall similarity between the P conditions and the Q conditions, where p ranges from 1 to P and q ranges from 1 to Q; or... The similarity between the p-th condition among the P conditions and the q-th condition among the Q conditions.

6. The method according to any one of claims 1 to 5, characterized in that, The N similarity information is used to determine K models from the M models, including: The N similarity information is used to determine the M similarities corresponding to the M models; wherein, among the M models, the K similarities corresponding to the K models are greater than or equal to the MK similarities corresponding to the other MK models.

7. The method according to any one of claims 1 to 6, characterized in that, The N similarity information is used to determine resource information. The resources indicated by the resource information include the transmission resources of the third information and / or the reception resources of the measurement signal corresponding to the third information. The resource information includes one or more of the following: start time domain position, duration, end time domain position, and frequency domain resources.

8. The method according to claim 7, characterized in that, The method further includes: Receive fourth information, which indicates the start time domain position, duration, and end time domain position of resource information associated with L similarity information, and one or more of the frequency domain resources; wherein, the fourth information and the N similarity information are used to determine the resource information, and the L similarity information includes the N similarity information, where L is greater than or equal to N.

9. The method according to any one of claims 1 to 8, characterized in that, The similarity information includes absolute difference, relative difference, or similarity probability.

10. The method according to any one of claims 1 to 9, characterized in that, The additional condition is used to indicate at least one of the following: Space filter information, beam information, antenna array information, power information, or application scenario information.

11. A communication method, characterized in that, include: Send a first message, which indicates the input data; Send a second message, which indicates N similarity information corresponding to the additional conditions of the input data and the additional conditions of the N training data, where N is a positive integer; wherein, the N training data are used to train M models through the model, where M is a positive integer; the second message is used to determine K models from the M models, and the K models are used to process the input data to obtain K output data, where K is a positive integer less than or equal to M.

12. The method according to claim 11, characterized in that, The method further includes: Receive third information, which is used to determine whether the input data is consistent with the training data corresponding to the K models; wherein the third information is determined based on the K output data.

13. The method according to claim 12, characterized in that, The third information includes at least one of the following: The first indication information indicates whether the input data is consistent with the training data corresponding to the K models; The second indication information indicates the performance corresponding to the K output data; The third indication information indicates the baseline truth corresponding to the K output data.

14. The method according to any one of claims 11 to 13, characterized in that, The additional conditions for the input data include P conditions, and the additional conditions for the i-th training data of the N training data include Q conditions, where P and Q are both positive integers, and i takes values ​​from 1 to N; The i-th similarity information among the N similarity information is determined based on any one of the following: The similarity between the p-th condition among the P conditions and the q-th condition among the Q conditions, where p ranges from 1 to P and q ranges from 1 to Q; The similarity between the p-th condition among the P conditions and the q-th condition among the Q conditions, and at least one of the importance of the p-th condition among the P conditions and the importance of the q-th condition among the Q conditions.

15. The method according to any one of claims 11 to 14, characterized in that, The additional conditions for the input data include P conditions, and the additional conditions for the i-th training data of the N training data include Q conditions, where P and Q are both positive integers, and i takes values ​​from 1 to N; The i-th similarity information among the N similarity information is used to indicate at least one of the following: The overall similarity between the P conditions and the Q conditions, where p ranges from 1 to P and q ranges from 1 to Q; or... The similarity between the p-th condition among the P conditions and the q-th condition among the Q conditions.

16. The method according to any one of claims 11 to 15, characterized in that, The N similarity information is used to determine K models from the M models, including: The N similarity information is used to determine the M similarities corresponding to the M models; wherein, among the M models, the K similarities corresponding to the K models are greater than or equal to the MK similarities corresponding to the other MK models.

17. The method according to any one of claims 11 to 16, characterized in that, The N similarity information is used to determine resource information. The resources indicated by the resource information include the transmission resources of the third information and / or the reception resources of the measurement signal corresponding to the third information. The resource information includes one or more of the following: start time domain position, duration, end time domain position, and frequency domain resources.

18. The method according to claim 17, characterized in that, The method further includes: Send a fourth message, which indicates the start time domain position, duration, and end time domain position of the resource information associated with L similarity information, and one or more of the frequency domain resources; wherein, the fourth message and the N similarity information are used to determine the resource information, and the L similarity information includes the N similarity information, where L is greater than or equal to N.

19. The method according to any one of claims 11 to 18, characterized in that, The similarity information includes absolute difference, relative difference, or similarity probability.

20. The method according to any one of claims 11 to 19, characterized in that, The additional condition is used to indicate at least one of the following: Space filter information, beam information, antenna array information, power information, or application scenario information.

21. A communication device, characterized in that, It includes a module for performing the method as described in any one of claims 1 to 10, or includes a module for performing the method as described in any one of claims 11 to 20.

22. A communication device, characterized in that, It includes at least one processor, said at least one processor being configured to perform the method as described in any one of claims 1 to 10, or said at least one processor being configured to perform the method as described in any one of claims 11 to 20.

23. The communication device according to claim 22, characterized in that, It also includes a memory that stores computer programs or instructions.

24. The communication device according to claim 22, characterized in that, The communication device is a chip or chip system.

25. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer programs or instructions, which, when executed by a communication device,... Implement the method as described in any one of claims 1 to 10; or, Implement the method as described in any one of claims 11 to 20.

26. A computer program product, characterized in that, This includes computer programs or instructions that, when executed by a computer, Implement the method as described in any one of claims 1 to 10; or, Implement the method as described in any one of claims 11 to 20.

Images