Communication method and related equipment

Abstract

A communication method and related device, the method comprising: generating or receiving first information, the first information being used for indicating similarity between a first data set and a second data set, the first data set being used for training a model, the second data set being data acquired by a first communication device; obtaining a judgment result, the judgment result being determined based on the first information, the judgment result being used for indicating whether the model is suitable for the first communication device, so as to judge whether the model is suitable for the first communication device based on the similarity between the first data set and the second data set, thereby avoiding sending an improper model to the first communication device; and the calculation overhead caused by model training is also reduced.

Description

Technical Field

[0001] This application relates to the field of communication technology, and in particular to a communication method and related equipment. Background Technology

[0002] With the development of communication technology and the increasing maturity of artificial intelligence (AI) technology, AI has gradually become an indispensable part of wireless communication systems, and many communication functions can be implemented based on AI technology. For example, AI-based location prediction involves communication devices using AI models to predict their future location. Another example is AI-based channel compression, where communication devices use AI models to compress channel measurement results before reporting them to another communication device.

[0003] In wireless communication systems, it's often necessary to determine model availability. This means determining whether a model trained on data from device A can be applied to device B. For example, a network management system trains a model based on data from base station 1. It needs to determine if this model can be applied to other base stations besides base station 1. A common method is trial and error: directly applying the model to dataset B and monitoring its performance. If the performance is good, the model is used; otherwise, it is not. For instance, a network management system trains a model (used to predict terminal device locations) based on terminal device location data collected from base station 1. This model is then applied to base station 2, and its performance on base station 2 is analyzed after a period of time. If the performance is good, the model is used on base station 2; otherwise, it is not.

[0004] However, this method has a large latency, requiring additional time for model performance monitoring and evaluation, resulting in significant resource overhead. Summary of the Invention

[0005] This application provides a communication method and related device that can determine whether a model is suitable for a first communication device based on the similarity between a first dataset and a second dataset, thereby avoiding sending an unsuitable model to the first communication device and reducing the computational overhead caused by model training.

[0006] This application provides a communication method, which can be executed by a first communication device, or by a component of the first communication device, such as a processor, circuit, chip, or chip system, or by a logic module or software capable of implementing all or part of the first communication device. Taking the application of this method to a first communication device as an example, the method includes: the first communication device generating or receiving first information, which is used to indicate the similarity between a first dataset and a second dataset, the first dataset being used to train a model, and the second dataset being data acquired by the first communication device; the first communication device acquiring a judgment result, which is determined based on the first information, and the judgment result being used to indicate whether the model is suitable for the first communication device.

[0007] Based on the above technical solution, the first communication device determines the usability of the model based on the similarity between the first dataset and the second dataset, that is, it determines whether the model trained on the first dataset of the second communication device is suitable for the second communication device, without having to train a new model for the first communication device. This reduces the computational overhead of model training, lowers the latency of model deployment, and improves the accuracy and flexibility of model deployment.

[0008] In this application, the terms "model", "AI model", "neural network model", "AI neural network model", "machine learning model", and "AI processing model" can be used interchangeably.

[0009] In one possible implementation of the first aspect, the second dataset is data collected by the first communication device locally or from an external source.

[0010] In one possible implementation of the first aspect, receiving the first information includes:

[0011] The first communication device receives the first information from the second communication device.

[0012] It is understood that the first information can be generated by either the first communication device or the second communication device. Based on the above technical solution, the second communication device is responsible for generating the first information, and the first communication device receives the first information from the second communication device.

[0013] It is understandable that the first communication device and the second communication device can be implemented in multiple ways.

[0014] For example, the first communication device can be a base station, a central unit (CU), a distributed unit (DU), a radio intelligent unit (RIU), a base station, a core network, a server, or a terminal device, and the second communication device can also be a base station, a CU, a DU, an RIU, a base station, a core network, a server, or a terminal device.

[0015] In this application, the first communication device can be understood as a model user, i.e., a device that needs to use the AI ​​model. The second communication device can be understood as a model manager, i.e., a device with AI model management functions.

[0016] In one possible implementation of the first aspect, before the first communication device receives the first information, the method further includes:

[0017] The first communication device receives second information from the second communication device, and the second information is used to obtain a second dataset.

[0018] Based on the above technical solution, in the scenario where the second communication device generates the first information and the first communication device receives the first information, since the second communication device needs to generate the first information based on the similarity between the first dataset and the second dataset, and the second dataset is the data obtained by the first communication device, the second communication device needs to send the second information to the first communication device before generating the first information, so that after the first communication device receives the second information sent by the second communication device for obtaining the second dataset, it sends the second dataset to the second communication device.

[0019] In one possible implementation of the first aspect, generating the first information includes:

[0020] The first communication device generates the first information.

[0021] It is understandable that the first information can be generated by either the first communication device or the second communication device. Based on the above technical solution, the first communication device is responsible for generating the first information.

[0022] In one possible implementation of the first aspect, the judgment result includes a first judgment result, and before the first communication device generates the first information, the method further includes:

[0023] The first communication device receives third information from the second communication device. The third information is used to obtain the first judgment result, or the third information is used to obtain the first information.

[0024] Based on the above technical solution, there are two scenarios when the first communication device generates the first information. First, after generating the first information, the first communication device sends the first information to the second communication device, enabling the second communication device to determine a judgment result based on the first information. In this case, the third information received by the first communication device is used to acquire the first information. Second, after generating the first information, the first communication device continues to generate a first judgment result based on the first information and sends the first judgment result to the second communication device, enabling the second communication device to receive and judge the first judgment result. In this case, the third information received by the first communication device is used to acquire the first judgment result.

[0025] In one possible implementation of the first aspect, after the first communication device generates the first information, the method further includes:

[0026] The first communication device sends the first information to the second communication device.

[0027] In one possible implementation of the first aspect, the judgment result includes a first judgment result, and obtaining the judgment result includes:

[0028] The first communication device generates a first judgment result based on the first information.

[0029] It is understood that the first judgment result can be generated by either the first communication device or the second communication device. Based on the above technical solution, the first communication device is responsible for generating the first judgment result based on the first information generated by either the first communication device or the second communication device.

[0030] In one possible implementation of the first aspect, after the first communication device generates the first judgment result based on the first information, the method further includes:

[0031] The first communication device sends the first judgment result to the second communication device.

[0032] Understandably, the first communication device can be understood as the model user, i.e., the device that needs to use the AI ​​model. The second communication device can be understood as the model manager, i.e., the device with AI model management capabilities. Therefore, after the first communication device generates the first judgment result, it needs to send the first judgment result to the second communication device so that the second communication device can determine whether the model is suitable for the first communication device based on the first judgment result.

[0033] In one possible implementation of the first aspect, the judgment result includes a second judgment result, and obtaining the judgment result includes:

[0034] The first communication device receives a second judgment result from the second communication device, and the second judgment result is determined based on the first judgment result.

[0035] Based on the above technical solution, after the first communication device generates first information and sends the first information to the second communication device, the second communication device generates a first judgment result based on the first information, then determines a second judgment result based on the first judgment result, and sends the second judgment result to the first communication device.

[0036] In one possible implementation of the first aspect, before the second communication device sends the second judgment result to the first communication device, the method further includes:

[0037] The first communication device sends a fourth message to the second communication device, which is used to obtain the model.

[0038] Based on the above technical solution, the first communication device can actively send fourth information to the second communication device when the model needs to be used, so as to trigger the second communication device to generate a second judgment result.

[0039] A second aspect of this application provides a communication method. This method can be executed by a second communication device, or by a component of the second communication device, such as a processor, circuit, chip, or chip system. It can also be implemented by a logic module or software capable of implementing all or part of the second communication device. Taking the application of this method to a second communication device as an example, the method includes: the second communication device generating or receiving first information, which indicates the similarity between a first dataset and a second dataset, the first dataset being used to train a model, and the second dataset being data acquired by the first communication device; the second communication device acquiring a judgment result, which is determined based on the first information, and the judgment result indicating whether the model is suitable for the first communication device.

[0040] Based on the above technical solution, the second communication device determines the usability of the model based on the similarity between the first dataset and the second dataset. That is, it determines whether the model trained on the first dataset of the second communication device is suitable for the second communication device, without having to train a new model for the first communication device. This reduces the computational overhead of model training, lowers the latency of model deployment, and improves the accuracy and flexibility of model deployment.

[0041] In this application, the terms "model", "AI model", "neural network model", "AI neural network model", "machine learning model", and "AI processing model" can be used interchangeably.

[0042] In one possible implementation of the second aspect, generating the first information includes:

[0043] The second communication device generates the first information.

[0044] It is understandable that the first information can be generated by either the first communication device or the second communication device. Based on the above technical solution, the second communication device is responsible for generating the first information.

[0045] In one possible implementation of the second aspect, before the second communication device generates the first information, the method further includes:

[0046] The second communication device sends second information to the first communication device, and the second information is used to obtain the second dataset.

[0047] Based on the above technical solution, in the scenario where the second communication device generates the first information and the first communication device receives the first information, since the second communication device needs to generate the first information based on the similarity between the first dataset and the second dataset, and the second dataset is the data obtained by the first communication device, the second communication device needs to send the second information to the first communication device before generating the first information.

[0048] In one possible implementation of the second aspect, receiving the first information includes:

[0049] The second communication device receives the first information from the first communication device.

[0050] It is understood that the first information can be generated by either the first communication device or the second communication device. Based on the above technical solution, the first communication device is responsible for generating the first information, and the second communication device receives the first information from the first communication device.

[0051] In one possible implementation of the second aspect, the judgment result includes a first judgment result, and before the second communication device receives the first information from the first communication device, the method further includes:

[0052] The second communication device sends third information to the first communication device. The third information is used to obtain the first judgment result, or the third information is used to obtain the first information.

[0053] Based on the above technical solution, there are two scenarios when the first communication device generates the first information. First, after generating the first information, the first communication device sends the first information to the second communication device, enabling the second communication device to determine a judgment result based on the first information. In this case, the third information received by the first communication device is used to acquire the first information. Second, after generating the first information, the first communication device continues to generate a first judgment result based on the first information and sends the first judgment result to the second communication device, enabling the second communication device to receive and judge the first judgment result. In this case, the third information received by the first communication device is used to acquire the first judgment result.

[0054] In one possible implementation of the second aspect, the judgment result includes a first judgment result, and obtaining the judgment result includes:

[0055] The second communication device generates a first judgment result based on the first information.

[0056] It is understood that the first judgment result can be generated by either the first communication device or the second communication device. Based on the above technical solution, the second communication device is responsible for generating the first judgment result based on the first information generated by either the first or second communication device.

[0057] In one possible implementation of the second aspect, the judgment result further includes a second judgment result. After the second communication device generates the first judgment result based on the first information, the method further includes:

[0058] The second communication device sends a second judgment result to the first communication device, and the second judgment result is determined based on the first judgment result.

[0059] Based on the above technical solution, after the second communication device generates a first judgment result based on the first information, the second communication device can determine a second judgment result based on the first judgment result and send the second judgment result to the first communication device.

[0060] In one possible implementation of the second aspect, before the second communication device sends the second judgment result to the first communication device, the method further includes:

[0061] The second communication device receives fourth information from the first communication device, and the fourth information is used to obtain the model.

[0062] Based on the above technical solution, the first communication device can actively send fourth information to the second communication device when the model needs to be used, so as to trigger the second communication device to generate a second judgment result.

[0063] In one possible implementation of the second aspect, after the second communication device generates the first information, the method further includes:

[0064] The second communication device sends the first information to the first communication device.

[0065] In one possible implementation of the second aspect, the judgment result includes a first judgment result, and obtaining the judgment result includes:

[0066] The second communication device receives the first judgment result from the first communication device.

[0067] It is understandable that the first judgment result can be generated by either the first communication device or the second communication device. Based on the above technical solution, the first communication device is responsible for generating the first judgment result based on the first information generated by the second communication device.

[0068] In one possible implementation of the second aspect, the judgment result further includes a second judgment result, and after the second communication device receives the first judgment result from the first communication device, the method further includes:

[0069] The second communication device sends a second judgment result to the first communication device, and the second judgment result is determined based on the first judgment result.

[0070] Based on the above technical solution, after the second communication device receives the first judgment result from the first communication device, the second communication device can determine the second judgment result based on the first judgment result and send the second judgment result to the first communication device.

[0071] A third aspect of this application provides a communication device, which includes a processing unit and a transceiver unit; the processing unit is used to generate or receive first information, the first information being used to indicate the similarity between a first dataset and a second dataset, the first dataset being used to train a model, and the second dataset being data acquired by a first communication device; the transceiver unit is used to obtain a judgment result, the judgment result being determined based on the first information, and the judgment result being used to indicate whether the model is applicable to the first communication device.

[0072] In the third aspect of this application, the constituent modules (or units, or means) of the communication device can also be used to perform the steps executed in various possible implementations of the first or second aspect and achieve the corresponding technical effects. For details, please refer to the first aspect, which will not be repeated here.

[0073] A fourth 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 enable the device to implement any possible implementation of the first or second aspect described above.

[0074] In one possible implementation, the communication device also includes a memory. Optionally, the processor and memory are integrated together.

[0075] The fifth 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 a method as described in any of the possible implementations of the first or second aspect above.

[0076] The sixth aspect of this application provides a computer-readable storage medium storing a computer program or instructions that, when executed by a first communication device or a second communication device, implement a method as described in any of the possible implementations of the first or second aspect above.

[0077] The seventh aspect of this application provides a computer program product (or computer program) including a computer program or instructions, which, when executed by a processor, implements any one of the possible implementations of the first or second aspect described above.

[0078] The eighth aspect of this application provides a chip system including at least one processor for supporting a communication device to implement any possible implementation of the first or second aspect described above.

[0079] In one possible design, the 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 at least one processor.

[0080] The technical effects of any of the design methods in aspects three through eight can be found in the technical effects of different design methods in aspects one or two above, and will not be repeated here. Attached Figure Description

[0081] Figure 1 A schematic diagram of the communication system provided in this application;

[0082] Figures 2a to 2g This is a schematic diagram of the AI ​​processing involved in this application;

[0083] Figure 3 This is a schematic diagram illustrating an implementation of the communication method provided in an embodiment of this application;

[0084] Figure 4a This is a schematic diagram of a wireless network architecture;

[0085] Figure 4b This is a schematic diagram of another wireless network architecture;

[0086] Figure 5 A schematic diagram illustrating another implementation of the communication method provided in the embodiments of this application;

[0087] Figure 6 A schematic diagram illustrating another implementation of the communication method provided in the embodiments of this application;

[0088] Figure 7A schematic diagram illustrating another implementation of the communication method provided in the embodiments of this application;

[0089] Figure 8 A schematic diagram illustrating another implementation of the communication method provided in the embodiments of this application;

[0090] Figures 9 to 11 A schematic diagram of the communication device provided in this application. Detailed Implementation

[0091] First, some terms used in the embodiments of this application will be explained to facilitate understanding by those skilled in the art.

[0092] (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.

[0093] 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, 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.

[0094] 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.

[0095] Terminals can also be drones, robots, devices in device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, virtual reality (VR) terminals, augmented reality (AR) terminals, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical care, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, and wireless terminals in smart homes, etc.

[0096] Furthermore, terminal devices can be terminal devices in future communication networks (such as 6th generation (6G) communication systems) or terminal devices in future evolved public land mobile networks (PLMNs). For example, terminals in future communication networks include, but are not limited to, vehicles, cellular network terminals (integrated with satellite terminal functionality), drones, and Internet of Things (IoT) devices.

[0097] In this embodiment, the terminal device can also obtain AI services provided by the network device. Optionally, the terminal device can also have AI processing capabilities.

[0098] (2) Network equipment: This can be equipment in 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 structure, network equipment can include centralized unit (CU) nodes, distributed unit (DU) nodes, or RAN equipment including CU nodes and DU nodes.

[0099] 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).

[0100] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, with different RAN nodes each implementing a portion of the base station's functions. For example, RAN nodes can be central units (CUs), distributed units (DUs), CU-control plane (CPs), CU-user plane (UPs), or radio units (RUs), etc. CUs and DUs can be set up separately or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs).

[0101] 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.

[0102] 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.

[0103] The correspondence between network elements and their achievable protocol layer functions in the ORAN system can be found in Table 1 below.

[0104] Table 1

[0105] ORAN network elements 3GPP protocol layer functions O-CU-CP RRC+PCDP - Control Plane (PDCP-C) O-CU-UP SDAP+PCDP - User Plane (PDCP-U) O-DU RLC+MAC+PHY-high O-RU PHY-low

[0106] 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.

[0107] 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, 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 used in future communication networks.

[0108] 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).

[0109] 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 that function, such as a chip system, which can be installed in 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.

[0110] (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.

[0111] Furthermore, these values ​​and parameters can be changed or updated.

[0112] (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.

[0113] (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.

[0114] 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.

[0115] 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.

[0116] (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.

[0117] 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.

[0118] This application can be applied to communication systems of long-term evolution (LTE), new radio (NR), or future communication networks (such as Beyond 5G (B5G), 6G, etc.). The communication system includes at least one network device and / or at least one terminal device.

[0119] Please see Figure 1 This is a schematic diagram of the architecture of the communication system 1000 used in an embodiment of this application. Figure 1 As shown, the communication system includes a radio access network (RAN) 100 and a core network 200. Optionally, the communication system 1000 may also include an Internet 300. The RAN 100 includes at least one RAN node (e.g., ...). Figure 1 110a and 110b, collectively referred to as 110, may also include at least one terminal (such as...). Figure 1 RAN100, denoted as RAN100, comprises RAN nodes 120a-120j, collectively referred to as RAN120. RAN100 may also include other RAN nodes, such as wireless relay equipment and / or wireless backhaul equipment. Figure 1 (Not shown in the image). Terminal 120 connects wirelessly to RAN node 110, and RAN node 110 connects wirelessly or via a wired connection to core network 200. The core network equipment in core network 200 and RAN node 110 in RAN 100 can be independent physical devices, or they can be the same physical device integrating the logical functions of core network equipment and RAN nodes. Terminals can connect to each other, and RAN nodes can connect to each other, via wired or wireless connections.

[0120] RAN100 can be an evolved universal terrestrial radio access (E-UTRA) system, a new radio (NR) system, or a future radio access system as defined in the 3rd generation partnership project (3GPP). RAN100 can also include two or more of the above-mentioned different radio access systems. RAN100 can also be an open RAN (O-RAN).

[0121] For ease of description, the following text uses a base station as an example of a RAN node.

[0122] Base stations and terminals can be fixed or mobile. They can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can be deployed on aircraft, balloons, and satellites. The embodiments of this application do not limit the application scenarios of the base stations and terminals.

[0123] The roles of base stations and terminals can be relative, for example, Figure 1 The helicopter or drone 120i can be configured as a mobile base station. For terminals 120j accessing the wireless access network 100 via 120i, terminal 120i is a base station; however, for base station 110a, 120i is a terminal, meaning that 110a and 120i communicate via a wireless air interface protocol. Of course, 110a and 120i can also communicate via a base station-to-base station interface protocol; in this case, 120i is also a base station relative to 110a. Therefore, both base stations and terminals can be collectively referred to as communication devices. Figure 1 The 110a and 110b in the text can be referred to as communication devices with base station functions. Figure 1 The 120a-120j in the text can be referred to as communication devices with terminal functions.

[0124] Communication between base stations and terminals, between base stations, and between terminals can be conducted using licensed spectrum, unlicensed spectrum, or both simultaneously. Communication can be conducted using spectrum below 6 GHz, spectrum above 6 GHz, or both simultaneously. The embodiments of this application do not limit the spectrum resources used for wireless communication.

[0125] In the embodiments of this application, the functions of the base station can be executed by modules (such as chips) within the base station, or by a control subsystem that includes base station functions. This control subsystem, including base station functions, can be a control center in the aforementioned application scenarios such as smart grids, industrial control, intelligent transportation, and smart cities. Similarly, the functions of the terminal can be executed by modules (such as chips or modems) within the terminal, or by a device that includes terminal functions.

[0126] The technical solution provided in this application can be applied to wireless communication systems (e.g.) Figure 1 The system shown, for example, the communication system provided in this application, can incorporate AI network elements to implement 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, an AI network element can be an AI module built into: a terminal device, access network device, core network device, cloud server, or operation, administration and maintenance (OAM) management system, used to implement AI-related functions. The OAM can be the management system for the core network device and / or the management system for the access network device. Alternatively, the AI ​​network element can also be a network element independently set up in the communication system. Optionally, the terminal or its built-in chip can also include an AI entity to implement AI-related functions.

[0127] The following is a brief introduction to the artificial intelligence (AI) that may be involved in this application.

[0128] Artificial intelligence (AI) enables machines to possess human-like intelligence, such as allowing them to use computer hardware and software to simulate certain intelligent human behaviors. To achieve AI, machine learning methods can be employed. In machine learning, machines learn (or train) models using training data. These models represent 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 decision actions. 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] like Figure 2a The diagram shown is a schematic representation of a neuron structure. Assume the neuron's input is x = [x0, x1, ..., x...]. n The weights corresponding to each input are w = [w, w1, ..., w2]. 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 summation of the input values ​​is, for example, b. Activation functions can take many forms. Assuming a neuron's activation function is y = f(z) = max(0, z), then the neuron's output 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 This is a schematic diagram of a Free-Nearest Neural Network (FNN). A key characteristic of FNNs 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 (discrete sampling along the time axis) and image data (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 (such as people and objects in an image representing 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 distributed neural network (DNN) that utilizes feedback time-series information. Their input includes the current input value and their own output value from the previous time step. RNNs are well-suited for acquiring temporally correlated sequence features, and are particularly applicable to applications such as speech recognition and channel coding / decoding.

[0141] In the model training process described above for machine learning, a loss function can be defined. The loss function describes the difference or discrepancy 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 value 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] like Figure 2c As shown, 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 a neuron in the next layer is the weighted sum of all neurons x in the previous layer connected to it, after passing through an activation function, and can be expressed as:

[0147] h = f(wx + b).

[0148] Where w is the weight matrix, b is the bias vector, and f is the activation function.

[0149] Alternatively, the output of the neural network can be recursively expressed as:

[0150] y = f n (w n f n-1 (…)+b n ).

[0151] Where n is the index of the neural network layer, 1 <= n <= N, and N is the total number of layers in the neural network.

[0152] 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.

[0153] Optionally, the training process can be carried out by using a loss function to evaluate the output of the neural network.

[0154] like Figure 2d As shown, the error can be backpropagated, and the neural network parameters (including w and b) can be iteratively optimized using gradient descent until the loss function reaches its minimum. Figure 2d The term "relative advantage (e.g., optimal advantage)" is used. This is understandable. Figure 2d The neural network parameters corresponding to the "better points (e.g., the best points)" in the data can be used as neural network parameters in the trained AI model information.

[0155] Alternatively, the gradient descent process can be represented as:

[0156]

[0157] 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.

[0158] Alternatively, the backpropagation process can utilize the chain rule for partial derivatives.

[0159] like Figure 2e As shown, 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:

[0160]

[0161] 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.

[0162] 2. Federated learning (FL).

[0163] 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.

[0164] like Figure 2f As shown, the FL architecture is a current training architecture in the FL field. For example, the FedAvg algorithm is a fundamental algorithm in FL, and its algorithm flow is roughly as follows:

[0165] (1) Initialize the model to be trained at the center end. And broadcast it to all client devices.

[0166] (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. It is then reported to the central node.

[0167] (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 client devices for a new round of training.

[0168] (4) Repeat steps (2) and (3) until the model finally converges or the number of training rounds reaches the upper limit.

[0169] In addition to reporting the local model It can also train local gradients The central node will report the gradients, average the local gradients, and update the global model based on the direction of the average gradient.

[0170] As can be seen in the FL framework, the dataset resides at distributed nodes. These nodes collect their local datasets, perform local training, and report the local results (model or gradients) to the central node. The central node itself does not have a dataset; it is only responsible for fusing the training results from the distributed nodes to obtain a global model, which is then distributed back to the distributed nodes.

[0171] 3. Decentralized learning. Unlike federated learning, another distributed learning architecture is decentralized learning.

[0172] like Figure 2g As shown, consider 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:

[0173]

[0174] 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 after the k-th update in the i-th node (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.

[0175] In wireless networks, many communication functions can be implemented using AI methods. For example, AI-based location prediction involves the base station using an AI model to predict the future location of terminal devices. Another example is AI-based channel compression, where terminal devices use an AI model to compress channel measurement results before reporting them to the network.

[0176] Typically, devices with AI model management capabilities and devices that need to use AI models are referred to as model managers and model users, respectively. In wireless networks, model managers and model users can be various types of devices. For example, a network management device is a model manager, and a base station is a model user; another example is that base station 1 is a model manager, and base station 2 is a model user; yet another example is that a base station is a model manager, and a terminal device is a model user, and so on.

[0177] In wireless communication systems, it is often necessary to determine the usability of a model. That is, to determine whether a model trained on data from device A can be applied to device B (or, in other words, whether the model can achieve good performance when applied to dataset B). For example, the network management system trains a model based on data from base station 1. At this point, it is necessary to determine whether the model can be applied to other base stations besides base station 1. If so, then it will not be necessary to train a new model for each base station, which can greatly reduce the computational overhead of model training.

[0178] Model usability assessment refers to determining whether a model trained on dataset A can be applied to dataset B. A common current approach is trial and error: directly applying the model to dataset B and then monitoring its performance. If the performance is good, the model is continued to be used; otherwise, it is not. For example, a network management system trains a model based on terminal device location data collected by base station 1. (This model is used to predict the location of terminal devices.) The model is then applied to base station 2, and its performance on base station 2 is analyzed after a period of time. If the performance is good (e.g., the error between the model's predictions and the actual values ​​is small, or the communication rate of the terminal devices is high after resource scheduling based on the model's results), then the model continues to be used on base station 2; otherwise, it is not used on base station 2. This method has several drawbacks: first, it has a large latency, requiring additional time for model performance monitoring and evaluation; second, it has a negative impact on the network, for example, during the model performance monitoring phase, resource scheduling based on the model's results by base station 2 may cause a decrease in the communication rate of terminal devices.

[0179] To address the aforementioned problems, embodiments of this application provide a communication method and related equipment. Please refer to... Figure 3 , Figure 3 This is a schematic diagram of one implementation of the communication method provided in an embodiment of this application. The method includes the following steps.

[0180] S301. Generate or receive first information, the first information being used to indicate the similarity between a first dataset and a second dataset, the first dataset being used to train a model, and the second dataset being data acquired by a first communication device.

[0181] In this application, the terms "model", "AI model", "neural network model", "AI neural network model", "machine learning model", and "AI processing model" can be used interchangeably.

[0182] S302. Obtain the judgment result, which is determined based on the first information, and the judgment result is used to indicate whether the model is suitable for the first communication device.

[0183] It should be noted that, Figure 3 The document does not restrict the entity that can execute the interactive demonstration. For example, in Figure 3 In this method, the executing entity can be a first communication device or a second communication device, or it can be replaced by a chip, chip system, processor, logic module or software in the first communication device or the second communication device.

[0184] In this application, the first communication device can be understood as a model user, i.e., a device that needs to use the AI ​​model. The second communication device can be understood as a model manager, i.e., a device with AI model management functions. Correspondingly, in Figure 3 In this context, the first and second communication devices can be implemented in various ways.

[0185] Please see Figure 4a , Figure 4a The wireless network shown can be understood as a typical wireless network, including base stations, network management, core network, radio intelligent units (RIUs), servers, terminal devices, CUs (Cellular Units) and DUs (Dedicated Units). The RIU is the network element or network function responsible for the intelligent functions of the radio access network (such as model training and inference). The base station can adopt a non-separated architecture or a separated architecture. In a separated architecture, the base station is divided into two parts: the CU and the DU. The CU is responsible for higher-layer radio protocol functions, and the DU is responsible for lower-layer radio protocol functions. (The last sentence appears to be incomplete and possibly refers to a different context.) Figure 4a In the wireless network shown, an example of a model administrator and a model user is as follows:

[0186] The model manager is the network administrator, and the model user is the base station, CU, or DU.

[0187] The model manager is the RIU, and the model user is the base station, CU, or DU.

[0188] The model manager is CU, and the model user is DU.

[0189] The model manager is the base station, and the model user is the terminal device.

[0190] The model manager is base station A, and the model user is base station B.

[0191] The model manager is the core network, and the model users are base stations or terminal equipment.

[0192] The model manager is the server, and the model user is the base station or terminal device.

[0193] Please see Figure 4b , Figure 4b The wireless network shown can be understood as an open radioaccess network (O-RAN), which includes a non-real-time radio access network intelligent controller (Non-RT RIC), a near-real-time radio access network intelligent controller (Near-RTRIC), an open network architecture central unit control plane (O-CU-CP), an open network architecture central unit user plane (O-CU-UP), an open network architecture distributed unit (O-DU), and an open network architecture evolved node B (O-eNB). In such a way... Figure 4b In the wireless network shown, an example of a model administrator and a model user is as follows:

[0194] The model manager is a non-real-time RIC, while the model user is a near-real-time RIC.

[0195] The model manager is a non-real-time RIC, and the model user is an O-CU-CP, O-DU, or O-eNB.

[0196] The model manager is a near real-time RIC, and the model users are O-CU-CP, O-DU, or O-eNB.

[0197] It is understood that the model manager and the model user can be the same device. For example, the model manager and the model user can both be terminal devices, or they can be different devices. This is just an example and is not a limitation.

[0198] For ease of explanation, the first communication device and the second communication device will be used as the execution entities below. Figure 3 The method shown will be explained.

[0199] In one possible implementation, the first communication device generates first information and the first communication device generates a judgment result.

[0200] Understandably, this implementation is suitable for scenarios where the second communication device lacks computing resources while the first communication device has surplus computing resources. Since the first communication device is responsible for generating the first information and the judgment result, it can reduce the computing burden on the second communication device.

[0201] For this implementation method, please refer to Figure 5 , Figure 5 This is a schematic diagram illustrating another implementation of the communication method provided in an embodiment of this application. The method includes the following steps.

[0202] S501. The second communication device acquires the model and the first dataset.

[0203] In this embodiment, the model is associated with and used for a specific use case. For example, use case 1 is for location prediction, where a second communication device deploys a model to predict the future location of the first communication device based on its current location. Use case 2 is for channel compression, where a first communication device deploys a model to compress channel measurement results.

[0204] In one possible implementation, the second communication device trains the model.

[0205] In one possible implementation, the second communication device obtains the model from an external source. For example, the second communication device can obtain the model from an equipment vendor's server.

[0206] In one possible implementation, the data in the first dataset is labeled data. For example, the data used in use case 1 is labeled data, and the data content is {the current location of the first communication device, the future location of the first communication device}, where "the future location of the first communication device" is the label.

[0207] In one possible implementation, the data in the first dataset is unlabeled. For example, the data used in use case 2 is unlabeled data, and the data content is {channel measurement results}, without any labels.

[0208] S502. The second communication device sends third information to the first communication device, the third information being used to obtain the first judgment result.

[0209] Understandably, before sending the model to the first communication device, the second communication device needs to determine whether the model is suitable for the first communication device, that is, whether the first communication device can achieve the predetermined performance target after using the model, so as to avoid sending an unsuitable model to the first communication device.

[0210] In one possible implementation, the judgment result includes a first judgment result, which is used to indicate whether the model is suitable for the first communication device.

[0211] In one possible implementation, the third information includes:

[0212] Information A: First dataset.

[0213] Information B: Information used to indicate the types of data in the first dataset.

[0214] Information C: Information used to indicate the quantity of data in the second dataset.

[0215] Information D: Calculated information used to indicate similarity.

[0216] Information E: Judgment information used to indicate whether the model is applicable.

[0217] Information A is required, while information B, C, D, and E are optional.

[0218] Understandably, compared to pre-configured or pre-defined similarity calculation information and / or model applicability judgment information in communication standards, the second communication device can improve implementation flexibility by indicating similarity calculation information and / or model applicability judgment information through third information. This allows for flexible and autonomous selection of which calculation method or judgment method to use, making it suitable for various application scenarios and enabling more accurate judgment of model applicability.

[0219] The first dataset refers to the dataset used for model training. For example, for use case 1, the data in the first dataset is {the location of the terminal device at time 1, the location of the terminal device at time 2}, and for use case 2, the data in the first dataset is {channel measurement results}. The second dataset refers to data related to the first communication device, which is collected locally or acquired externally by the first communication device. For example, the second dataset is data acquired by the first communication device from other devices.

[0220] Regarding information A, since the first dataset is the data needed for model training and the first communication device is responsible for generating the first information, the second communication device needs to send the first dataset to the first communication device.

[0221] Regarding information B, this information is used to directly or indirectly indicate the type of data in the first dataset.

[0222] For example, in use case 1, the information indicates the type of data as {the location of the first communication device at time 1, the location of the first communication device at time 2}. In use case 2, the information indicates the type of data as {channel measurement results}.

[0223] Indirect methods include, for example, using the information to indicate an index (e.g., "index 1") of the type of data in a first dataset, the type of data corresponding to which the index is pre-configured to the first communication device or predefined in a communication standard. Another example is using the information to indicate an identifier of a model (e.g., "model 1"), the type of data corresponding to which the model is pre-configured to the type of data in the first dataset or predefined in a communication standard. Yet another example is using the information to indicate an identifier of a use case (e.g., "use case 1"), the type of data corresponding to which the use case is pre-configured to the type of data in the first dataset or predefined in a communication standard.

[0224] Regarding information C, this information can be used to indicate the number of data in the second dataset, or it can be used to indicate the minimum number of data contained in the second dataset.

[0225] It should be understood that a certain amount of data is generally required for model training to ensure accuracy. Therefore, the accuracy of model training can be guaranteed by setting a minimum number of data points in the second dataset.

[0226] Information D is used to indicate how to calculate the similarity between the first and second datasets.

[0227] In this application, the method for calculating similarity is not limited. For example, one or more of the following indicators can be used for calculation: cross entropy, relative entropy, Jensen-Shannon divergence, Bhattacharyya distance, and Wasserstein distance. The calculation formulas are shown in Table 1 below.

[0228] The specific format of this information is not limited. For example, it can be an enumeration type, with a value of "Cross Entropy" indicating the use of the cross entropy formula and a value of "Relative Entropy" indicating the use of the relative entropy formula; it can also be an integer type, with a value of "0" indicating the use of the cross entropy formula and a value of "1" indicating the use of the relative entropy formula.

[0229] Table 1 Similarity Calculation Formula

[0230]

[0231]

[0232] Regarding E, this information is used to indicate the method for determining whether the model is suitable for the first communication device. For example, this information includes a similarity threshold. If the calculated similarity is less than this threshold, the model is considered... It can be used in the first communication device. For example, this information indication uses a probabilistic approach, specifically based on the sigmoid function. Calculate the probability value corresponding to the similarity (x is the similarity, y is the probability value), and then generate a random number between 0 and 1. If the value of the random number is less than the probability value y, then the model is considered to be usable for the first communication device.

[0233] S503. The first communication device generates a second dataset based on the third information.

[0234] The first communication device can use the already collected local data to generate the second dataset, or it can re-collect data to generate the second dataset.

[0235] It is understandable that if the third information in S502 indicates the quantity information of the data in the second dataset, the first communication device needs to refer to the quantity information to generate the second dataset.

[0236] S504. The first communication device generates first information based on a first dataset and a second dataset. The first information is used to indicate the similarity between the first dataset and the second dataset.

[0237] It is understood that if the third information in S502 indicates similarity calculation information, the first communication device can generate the first information based on the calculation formula indicated by the calculation information (e.g., the formula in Table 1 above). If the third information in S502 does not indicate similarity calculation information, the first communication device can generate the first information based on a pre-configured formula or a formula predefined in the communication standard.

[0238] It is understandable that the principle of using the similarity between the first and second datasets to approximate the usability of the model is that, in some scenarios, the model performance is approximately positively correlated with the similarity of the datasets. In other words, the greater the similarity between the first and second datasets, the better the performance of the model when applied to the second dataset.

[0239] In one possible implementation, the first piece of information is the specific value of the similarity score. For example, the first piece of information could be a similarity score of 0.6.

[0240] In one possible implementation, the first information is an identifier obtained based on the specific value of the similarity. For example, the first information can be the interval where the similarity lies, with three predefined numerical intervals: [0, 0.5), [0.5, 0.8), and [0.8, 1]. When the similarity is 0.6, the first information is "interval 2".

[0241] S505. The first communication device generates a first judgment result based on the first information.

[0242] The judgment result includes a first judgment result, which is used to indicate whether the model is suitable for the first communication device.

[0243] It is understandable that if the third information in S502 indicates information on whether the model is applicable, the first communication device can make a judgment based on that information. If the third information in S502 does not indicate information on whether the model is applicable, the first communication device can make a judgment based on pre-configured rules or rules predefined in the communication standard. For example, the first communication device can make a judgment based on a pre-set threshold value; if the similarity information is less than the threshold value, the model is deemed applicable to the first communication device. Another example is that the first communication device can make a judgment based on the sigmoid function. Calculate the probability value corresponding to the similarity (x is the similarity, y is the probability value), and then generate a random number between 0 and 1. If the value of the random number is less than the probability value y, then the model is considered to be applicable to the first communication device, and the model is determined to be suitable for the first communication device.

[0244] In one possible implementation, the first judgment result is represented by an enumeration type. For example, a value of "True" indicates that it is available.

[0245] In one possible implementation, the first judgment result is represented by an integer type, for example, a value of "0" indicates availability.

[0246] It is understood that one implementation method for the first communication device to generate the first judgment result based on the third information can be as shown in S503 to S505. In actual implementation or application, the specific method by which the first communication device generates the first judgment result based on the third information is not limited here.

[0247] S506. The first communication device sends the first judgment result to the second communication device.

[0248] Understandably, since the second communication device is a device with AI model management capabilities, and the model is trained based on the first dataset, the second communication device is responsible for determining whether the model is applicable to another device, such as the first communication device. If it is deemed applicable, the second communication device sends the model to the first communication device for use, so that the model trained based on the data of the second communication device can be applied to the first communication device. This eliminates the need to retrain a new model for the first communication device, thereby greatly reducing the computational overhead caused by model training.

[0249] S507. The second communication device determines the second judgment result based on the first judgment result.

[0250] In one possible implementation, the first judgment result is represented by an enumeration type, for example, a value of "True" indicates availability. If the second communication device determines that the first judgment result is "True", then the judgment model is applicable to the first communication device, and the model's information is determined as the second judgment result. If the second communication device determines that the first judgment result is not "True", then the judgment model is not applicable to the first communication device.

[0251] In one possible implementation, the first judgment result is represented by an integer type; for example, a value of "0" indicates availability. If the second communication device determines that the value of the first judgment result is "0", then the judgment model applies to the first communication device, and the information of the model is determined as the second judgment result. If the second communication device determines that the value of the first judgment result is not "0", then the judgment model does not apply to the first communication device.

[0252] In one possible implementation, the second judgment result includes information about the model or information indicating that the model failed to acquire the model.

[0253] If the second communication device determines that the model is applicable to the first communication device, then the second communication device sends the model information to the first communication device so that the first communication device can use the model. If the second communication device determines that the model is not applicable to the first communication device, then the second communication device sends information to the first communication device indicating that the model acquisition failed.

[0254] In one possible implementation, the information used to indicate model failure includes the reason for the failure. For example, the reason could be "the model is not applicable" or "the similarity between the first dataset and the second dataset does not meet the requirements."

[0255] S508. If the second judgment result is yes, then the second communication device sends the model information to the first communication device.

[0256] S509. The first communication device uses the model based on the information from the model.

[0257] II. In one possible implementation, the first communication device generates first information, and the second communication device generates a judgment result.

[0258] Understandably, since the first communication device is responsible for generating the first information, it can reduce the computational burden on the second communication device. Furthermore, since the second communication device is responsible for generating the judgment result, in scenarios where the number of second communication devices is small while the number of first communication devices is large, the workload of parameter configuration can be reduced. That is, only the relevant information regarding the applicability of the judgment model needs to be configured for the small number of second communication devices, without needing to perform the aforementioned configuration for the large number of first communication devices.

[0259] For this implementation method, please refer to Figure 6 , Figure 6 This is a schematic diagram illustrating another implementation of the communication method provided in an embodiment of this application. The method includes the following steps.

[0260] S601. The second communication device acquires the model and the first dataset.

[0261] For detailed information on S601, please refer to [link / reference]. Figure 5 The description of S501 shown will not be repeated here.

[0262] S602. The second communication device sends third information to the first communication device, the third information being used to obtain the first information.

[0263] Understandably, before sending the model to the first communication device, the second communication device needs to determine whether the model is suitable for the first communication device, that is, whether the first communication device can achieve the predetermined performance target after using the model, in order to avoid sending an unsuitable model to the first communication device. Since the first communication device is responsible for generating the first information, while the second communication device is responsible for generating the judgment result, the second communication device needs to obtain the first information from the first communication device.

[0264] In one possible implementation, the third information includes:

[0265] Information A: First dataset.

[0266] Information B: Information used to indicate the types of data in the first dataset.

[0267] Information C: Information used to indicate the quantity of data in the second dataset.

[0268] Information D: Calculated information used to indicate similarity.

[0269] Information A is required, while information B, C, and D are optional.

[0270] Understandably, compared to pre-configured or pre-defined similarity calculation information and / or model applicability judgment information in communication standards, the second communication device can improve implementation flexibility by indicating similarity calculation information and / or model applicability judgment information through third information. This allows for flexible and autonomous selection of which calculation method or judgment method to use, making it suitable for various application scenarios and enabling more accurate judgment of model applicability.

[0271] For detailed explanations of information A through information D, please refer to [link / reference]. Figure 5 The description of S502 shown will not be repeated here.

[0272] It is understandable that, since the second communication device is responsible for generating the judgment result, the second communication device does not need to send judgment information to the first communication device to indicate whether the model is applicable.

[0273] S603. The first communication device generates a second dataset based on the third information.

[0274] S604. The first communication device generates first information based on a first dataset and a second dataset. This first information is used to indicate the similarity between the first dataset and the second dataset.

[0275] For detailed explanations of S603 to S604, please refer to [link / reference]. Figure 5 The descriptions of S503 to S504 shown will not be repeated here.

[0276] It is understood that one implementation method for the first communication device to generate the first information based on the third information can be as shown in S603 to S604. In actual implementation or application, the specific method by which the first communication device generates the first information based on the third information is not limited here.

[0277] S605. The first communication device sends the first information to the second communication device.

[0278] S606. The second communication device generates a first judgment result based on the first information.

[0279] The judgment result includes a first judgment result, which is used to indicate whether the model is suitable for the first communication device.

[0280] Understandably, compared to pre-configured or pre-defined judgment methods in communication standards, the second communication device can directly obtain judgment information indicating whether the model is applicable, either locally or externally. This improves implementation flexibility, allowing for flexible and autonomous selection of calculation or judgment methods, making it suitable for various application scenarios and enabling more accurate judgments about model applicability. If the second communication device does not obtain judgment information indicating model applicability, it can also make a judgment based on pre-configured rules or rules pre-defined in communication standards. For example, the second communication device can make a judgment based on a pre-set threshold value; if the similarity information is less than the threshold value, the model is deemed applicable to the first communication device. Another example is that the second communication device can use the sigmoid function... The probability value corresponding to the similarity is calculated (x is the similarity, y is the probability value), and then a random number between 0 and 1 is generated. If the value of the random number is less than the probability value y, the model is determined to be suitable for the first communication device.

[0281] In one possible implementation, the first judgment result is represented by an enumeration type. For example, a value of "True" indicates that it is available.

[0282] In one possible implementation, the first judgment result is represented by an integer type, for example, a value of "0" indicates availability.

[0283] S607. The second communication device determines the second judgment result based on the first judgment result.

[0284] S608. If the second judgment result is yes, then the second communication device sends the model information to the first communication device.

[0285] S609. The first communication device uses the model based on the information from the model.

[0286] For detailed explanations of S607 to S609, please refer to [link / reference]. Figure 5 The descriptions of S507 to S509 shown will not be repeated here.

[0287] Third, in one possible implementation, the second communication device generates the first information and the second communication device generates the judgment result.

[0288] Understandably, since the second communication device is responsible for generating the first information and the judgment result, compared to the pre-configured or pre-defined similarity calculation method and / or model applicability judgment method in the communication standard, the second communication device can directly obtain the calculation information indicating similarity and / or the judgment information indicating model applicability from local or external sources. This improves the flexibility of implementation, allowing for flexible and autonomous selection of which calculation method or judgment method to use, making it suitable for various application scenarios, and enabling more accurate judgment of model applicability.

[0289] For this implementation method, please refer to Figure 7 , Figure 7 This is a schematic diagram illustrating another implementation of the communication method provided in an embodiment of this application. The method includes the following steps.

[0290] S701. The second communication device acquires the model and the first dataset.

[0291] S702. The second communication device sends second information to the first communication device, the second information being used to obtain a second dataset.

[0292] In one possible implementation, the second information includes:

[0293] Information A: Information used to indicate the types of data in the second dataset.

[0294] Information B: Information used to indicate the quantity of data in the second dataset.

[0295] Information C: Information used to indicate the types of data in the first dataset.

[0296] Information A is used to directly or indirectly indicate the type of data in the second dataset.

[0297] For example, in use case 1, the information indicates the type of data as {the location of the first communication device at time 1, the location of the first communication device at time 2}. In use case 2, the information indicates the type of data as {channel measurement results}.

[0298] Indirect methods include, for example, the information indicating an index of data type (e.g., "index 1"), the type of data corresponding to which the index can be pre-configured to the first communication device or pre-defined in the communication standard. Another example is that the information indicating an identifier of a model (e.g., "model 1"), the type of data corresponding to which the model can be pre-configured to the first communication device or pre-defined in the communication standard. Yet another example is that the information indicating an identifier of a use case (e.g., "use case 1"), the type of data corresponding to which the use case can be pre-configured to the first communication device or pre-defined in the communication standard.

[0299] For a description of information B, please refer to Figure 5 The description of S502 shown will not be repeated here.

[0300] The description of information C is similar to that of information A, and will not be repeated here.

[0301] It should be noted that the following two scenarios exist.

[0302] In the first scenario, when the first communication device needs to use a model, it can proactively send a model request to the second communication device, allowing the second communication device to determine whether the model is suitable for the first communication device. In this scenario, in one possible implementation, the second information includes information A and information C. Furthermore, in another possible implementation, the second information also includes information B. That is, information A and information C are required, while information B is optional.

[0303] The second approach involves the second communication device actively determining whether the model is applicable to the first communication device, rather than relying on a request from the first communication device. In this scenario, in one possible implementation, the second information includes information A. Furthermore, in another possible implementation, the second information also includes information C. That is, information A is mandatory, and information C is optional.

[0304] S703. The first communication device generates a second dataset based on the second information.

[0305] For detailed information on S703, please refer to [link / reference]. Figure 5 The description of S503 shown will not be repeated here.

[0306] S704. The first communication device sends fourth information to the second communication device, the fourth information including the second dataset.

[0307] As described above, there are two scenarios. In the first scenario, the fourth information is used to obtain the model. In this scenario, in one possible implementation, the fourth information includes:

[0308] Information A: Second dataset.

[0309] Information B: Calculated information used to indicate similarity.

[0310] Information C: Judgment information used to indicate whether the model is applicable.

[0311] Information A is required, while information B and information C are optional.

[0312] For descriptions of information A through information C, please refer to... Figure 5 The description of S502 shown will not be repeated here.

[0313] Understandably, in this scenario, the first communication device only initiates a model request when it needs to use the model, triggering the second communication device to determine whether the model is suitable for the first communication device. Therefore, in one possible implementation, the first communication device can send information B and / or information C to the second communication device to suggest which similarity calculation or judgment method the second communication device should use.

[0314] In the second scenario, the fourth information includes a second dataset, which is sent to the first communication device so that the second communication device can calculate similarity information based on the second dataset.

[0315] It is understood that the fourth piece of information may use identifiers, numerical values ​​or other methods to indicate the specific content of the information, and no specific method of indication is limited here.

[0316] S705. The second communication device generates first information based on the first dataset and the second dataset. This first information is used to indicate the similarity between the first dataset and the second dataset.

[0317] It is understood that if the fourth information in S704 indicates similarity calculation information, the second communication device can generate the first information based on the calculation formula indicated by the calculation information (e.g., the formula in Table 1 above). If the fourth information in S704 does not indicate similarity calculation information, the second communication device can generate the first information based on a pre-configured formula or a formula predefined in the communication standard.

[0318] It is understandable that the principle of using the similarity between the first and second datasets to approximate the usability of the model is that, in some scenarios, the model performance is approximately positively correlated with the similarity of the datasets. In other words, the greater the similarity between the first and second datasets, the better the performance of the model when applied to the second dataset.

[0319] In one possible implementation, the first piece of information is the specific value of the similarity score. For example, the first piece of information could be a similarity score of 0.6.

[0320] In one possible implementation, the first information is an identifier obtained based on the specific value of the similarity. For example, the first information can be the interval where the similarity lies, with three predefined numerical intervals: [0, 0.5), [0.5, 0.8), and [0.8, 1]. When the similarity is 0.6, the first information is "interval 2".

[0321] S706. The second communication device generates a first judgment result based on the first information.

[0322] The judgment result includes a first judgment result, which is used to indicate whether the model is suitable for the first communication device.

[0323] Understandably, if the fourth information in S704 indicates information for determining whether the model is applicable, the second communication device can make a judgment based on that information. If the fourth information in S704 does not indicate information for determining whether the model is applicable, the second communication device can make a judgment based on pre-configured rules or rules predefined in the communication standard. For example, the second communication device can make a judgment based on a pre-set threshold value; if the similarity information is less than the threshold value, the model is deemed applicable to the first communication device. Another example is that the second communication device can make a judgment based on the sigmoid function. The probability value corresponding to the similarity is calculated (x is the similarity, y is the probability value), and then a random number between 0 and 1 is generated. If the value of the random number is less than the probability value y, the model is determined to be suitable for the first communication device.

[0324] In one possible implementation, the first judgment result is represented by an enumeration type. For example, a value of "True" indicates that it is available.

[0325] In one possible implementation, the first judgment result is represented by an integer type, for example, a value of "0" indicates availability.

[0326] S707. The second communication device determines the second judgment result based on the first judgment result.

[0327] It is understood that one implementation method for the second communication device to determine the second judgment result based on the fourth information can be as shown in S705 to S707. In actual implementation or application, the specific method by which the second communication device determines the second judgment result based on the fourth information is not limited here.

[0328] S708. If the second judgment result is yes, then the second communication device sends the model information to the first communication device.

[0329] S709. The first communication device uses the model based on the information from the model.

[0330] For detailed explanations of S707 to S709, please refer to [link / reference needed]. Figure 5 The descriptions of S507 to S509 shown will not be repeated here.

[0331] S7010. If the second judgment result is negative, the second communication device sends information to the first communication device to indicate that the model acquisition has failed.

[0332] In one possible implementation, the information used to indicate model failure includes the reason for the failure. For example, the reason could be "the model is not applicable" or "the similarity between the first dataset and the second dataset does not meet the requirements."

[0333] S7011. The first communication device determines whether to send the fourth information to the second communication device again.

[0334] After the second communication device sends information to the first communication device indicating that the model acquisition has failed, the first communication device can take appropriate strategies based on the cause value and determine whether to send a fourth message to the second communication device again.

[0335] For example, if the model acquisition fails due to "model not applicable" or "similarity between the first and second datasets does not meet requirements," the first communication device can continue to collect data and calculate the similarity between the newly collected dataset and the original second dataset. It will only request the model from the second communication device again if the similarity is low (understandably, if the similarity is high, it indicates that the features of the local data have not changed significantly, and the model is still likely unusable; therefore, no further request to acquire the model will be initiated). If the model acquisition fails for other reasons, the first communication device will adopt other strategies.

[0336] For example, if the reason for the failure to acquire the model is "transmission resources are unavailable", it means that the model meets the applicable conditions, but the transmission resources between the first communication device and the second communication device are insufficient to transmit the model. In this case, the first communication device can wait for a period of time and then initiate the request to acquire the model again, that is, send the fourth information to the second communication device. This fourth information is used to acquire the model.

[0337] Understandably, in the first scenario, the first communication device only initiates a model request when it needs to use the model, triggering the second communication device to determine whether the model is suitable for the first communication device. Therefore, when the second communication device determines that the model is not suitable for the first communication device, it can send information indicating that the model acquisition failed. This allows the first communication device to clarify the specific reason for the request failure based on this information and take appropriate strategies based on that specific reason, thereby improving the accuracy of the model suitability judgment and further improving the accuracy and efficiency of model deployment.

[0338] It should be noted that, in addition to the first scenario, when the second communication device determines that the model is not applicable to the first communication device, it can also send information to the first communication device to indicate that the model acquisition has failed. This application does not limit the specific application scenario of this implementation step, but can be set according to actual needs.

[0339] IV. In one possible implementation, the second communication device generates the first information, and the first communication device generates the judgment result.

[0340] Understandably, having the second communication device generate the judgment result avoids sending inappropriate models to the first communication device. Having the first communication device generate the first information reduces the computational burden on the second communication device.

[0341] For this implementation method, please refer to Figure 8 , Figure 8 This is a schematic diagram illustrating another implementation of the communication method provided in an embodiment of this application. The method includes the following steps.

[0342] S801. The second communication device acquires the model and the first dataset.

[0343] S802. The second communication device sends second information to the first communication device, the second information being used to obtain a second dataset.

[0344] In one possible implementation, the second information includes:

[0345] Information A: Information used to indicate the types of data in the second dataset.

[0346] Information B: Information used to indicate the quantity of data in the second dataset.

[0347] Information A is required, while information B is optional.

[0348] For detailed descriptions of information A and information B, please refer to [link / reference]. Figure 7 The description of S702 shown will not be repeated here.

[0349] S803. The first communication device generates a second dataset based on the second information.

[0350] S804. The first communication device sends fourth information to the second communication device, the fourth information including the second dataset.

[0351] For detailed explanations of S803 to S804, please refer to [link / reference]. Figure 7 The descriptions of S703 to S704 shown will not be repeated here. It should be understood that this fourth piece of information applies to the second scenario mentioned in S704.

[0352] S805. The second communication device generates first information based on the first dataset and the second dataset. This first information is used to indicate the similarity between the first dataset and the second dataset.

[0353] For detailed information on S805, please refer to [link / reference]. Figure 7 The description of S705 shown will not be repeated here.

[0354] S806. The second communication device sends the first information to the first communication device.

[0355] S807. The first communication device generates a first judgment result based on the first information.

[0356] S808. The first communication device sends the first judgment result to the second communication device.

[0357] S809. The second communication device determines the second judgment result based on the first judgment result.

[0358] S8010. If the second judgment result is yes, then the second communication device sends the model information to the first communication device.

[0359] S8011. The first communication device uses the model based on the information from the model.

[0360] For detailed explanations of S807 to S8011, please refer to the respective documents. Figure 5 The descriptions of S505 to S509 shown will not be repeated here.

[0361] In one possible implementation, the first to fourth information can be carried in broadcast, unicast, or multicast messages.

[0362] It is understandable that the similarity information between the first dataset used for training the interaction model between the second communication device and the first communication device and the second dataset obtained by the first communication device enables the second communication device to obtain the similarity information and / or the judgment information of model availability. This allows the second communication device to accurately determine whether the model is suitable for the first communication device, thereby avoiding sending an unsuitable model to the first communication device and reducing the computational overhead of model training.

[0363] Please see Figure 9 This application provides a communication device 900, which can realize the functions of the second communication device or the first communication device in the above method embodiments, and thus also achieve the beneficial effects of the above method embodiments. In this application embodiment, the communication device 900 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.

[0364] It should be noted that the transceiver unit 902 may include a transmitting unit and a receiving unit, which are used to perform transmitting and receiving respectively.

[0365] In one possible implementation, when the device 900 is used to perform the method executed by the first communication device in the foregoing embodiments, the device 900 includes a processing unit 901;

[0366] The processing unit 901 is used to generate first information, which is used to indicate the similarity between a first dataset and a second dataset. The first dataset is used to train the model, and the second dataset is data acquired by the first communication device. The processing unit 901 is also used to obtain a judgment result, which is determined based on the first information and is used to indicate whether the model is suitable for the first communication device.

[0367] In one possible implementation, when the device 900 is used to perform the method executed by the first communication device in the foregoing embodiments, the device 900 includes a processing unit 901 and a transceiver unit 902.

[0368] The transceiver unit 902 is used to receive first information, which is used to indicate the similarity between a first dataset and a second dataset. The first dataset is used to train the model, and the second dataset is data acquired by the first communication device. The processing unit 901 is used to obtain a judgment result, which is determined based on the first information and is used to indicate whether the model is suitable for the first communication device.

[0369] It should be noted that the information execution process of the unit of the above-mentioned communication device 900 can be specifically described in the method embodiment shown above in this application, and will not be repeated here.

[0370] Please see Figure 10 This is another schematic structural diagram of the communication device 1000 provided in this application.

[0371] In one possible implementation, the communication device 1000 includes a logic circuit 1001. The communication device 1000 can be a chip or an integrated circuit.

[0372] The logic circuit 1001 is used to generate first information, which is used to indicate the similarity between a first dataset and a second dataset. The first dataset is used to train the model, and the second dataset is data acquired by the first communication device. The logic circuit 1001 is also used to obtain a judgment result, which is determined based on the first information and is used to indicate whether the model is suitable for the first communication device.

[0373] In one possible implementation, the communication device 1000 includes a logic circuit 1001 and an input / output interface 1002. The communication device 1000 can be a chip or an integrated circuit.

[0374] in, Figure 9 The transceiver unit 902 shown can be a communication interface, which can be... Figure 10The input / output interface 1002 may include an input interface and an output interface. Alternatively, the communication interface may also be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0375] The input / output interface 1002 is used to receive first information, which is used to indicate the similarity between a first dataset and a second dataset. The first dataset is used to train the model, and the second dataset is data acquired by the first communication device. The logic circuit 1001 is used to obtain a judgment result, which is determined based on the first information and is used to indicate whether the model is suitable for the first communication device.

[0376] The logic circuit 1001 and the input / output interface 1002 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.

[0377] In one possible implementation, Figure 9 The processing unit 901 shown can be Figure 10 The logic circuit 1001 in the middle.

[0378] Optionally, the logic circuit 1001 can be a processing device, the functions of which can be partially or entirely implemented in software.

[0379] 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.

[0380] Optionally, the processing device may include 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.

[0381] 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 processors (CPUs), network processors (NPs), digital signal processors (DSPs), microcontroller units (MCUs), programmable logic devices (PLDs), or other integrated chips, or any combination of the above chips or processors.

[0382] Please see Figure 11 The above-described embodiments of the communication device provided in this application are schematic diagrams of the structure of the communication device.

[0383] It is understood that the communication device 110 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 110 may be the first or second communication 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 110 includes one or more processors 111. The processor 111 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.

[0384] Optionally, in one design, the processor 111 may include a program 113 (sometimes also referred to as code or instructions), which can be executed on the processor 111 to cause the communication device 110 to perform the methods described in the embodiments below. In yet another possible design, the communication device 110 includes circuitry (…). Figure 11 (Not shown).

[0385] Optionally, the communication device 110 may include one or more memories 112 storing a program 114 (sometimes referred to as code or instructions), which can be run on the processor 111 to cause the communication device 110 to perform the methods described in the above method embodiments.

[0386] Optionally, the processor 111 and / or memory 112 may include an AI module 117, which is used to implement AI-related functions. The AI ​​module 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.

[0387] Optionally, the processor 111 and / or memory 112 may also store data. The processor and memory may be configured separately or integrated together.

[0388] Optionally, the communication device 110 may further include a transceiver 115 and / or an antenna 116. The processor 111, sometimes referred to as a processing unit, controls the communication device (e.g., a RAN node or terminal). The transceiver 115, sometimes referred to as a transceiver unit, transceiver, transceiver circuit, or transceiver, is used to realize the transmission and reception functions of the communication device through the antenna 116.

[0389] in, Figure 9 The processing unit 901 shown may be a processor 111. Figure 9 The transceiver unit 902 shown can be a communication interface, which can be... Figure 11 The transceiver 115 may include an input interface and an output interface. Alternatively, the transceiver 115 may also be a transceiver circuit, which may include an input interface circuit and an output interface circuit.

[0390] This application also 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 of the possible implementations in the foregoing embodiments.

[0391] This application also provides a computer program product (or computer program) that, when executed by a processor, performs any of the methods described above.

[0392] 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 further 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.

[0393] This application also provides a communication system, the network system architecture of which includes a first communication device and a second communication device in any of the above embodiments.

[0394] In the several 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 an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0395] 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.

[0396] 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 by comprising: The method comprises: generating or receiving first information, the first information being used to indicate a similarity between a first data set and a second data set, the first data set being used to train a model, and the second data set being data obtained by a first communication device; obtaining a determination result, the determination result being determined based on the first information, and the determination result being used to indicate whether the model is applicable to the first communication device.

2. The method of claim 1, wherein, The receiving of the first information comprises: The first communication device receives the first information from the second communication device.

3. The method of claim 2, wherein, Before the first communication device receives the first information, the method further comprises: The first communication device receives second information from the second communication device, the second information being used to obtain the second data set.

4. The method of claim 1, wherein, The generating of the first information comprises: The first communication device generates the first information.

5. The method of claim 4, wherein, The determination result comprises a first determination result, and before the first communication device generates the first information, the method further comprises: The first communication device receives third information from the second communication device, the third information being used to obtain the first determination result, or the third information being used to obtain the first information.

6. The method according to claim 4 or 5, characterized in that, After the first communication device generates the first information, the method further comprises: The first communication device sends the first information to the second communication device.

7. The method according to any one of claims 2 to 5, characterized in that, The determination result comprises a first determination result, and the obtaining of the determination result comprises: The first communication device generates the first determination result according to the first information.

8. The method of claim 7, wherein, After the first communication device generates the first determination result according to the first information, the method further comprises: The first communication device sends the first determination result to the second communication device.

9. The method according to any one of claims 4 to 6, characterized in that, The determination result comprises a second determination result, and the obtaining of the determination result comprises: The first communication device receives the second determination result from the second communication device, the second determination result being determined based on the first determination result.

10. The method of claim 9, wherein, Before the first communication device receives the second determination result from the second communication device, the method further comprises: The first communication device sends fourth information to the second communication device, the fourth information being used to obtain the model.

11. The method of claim 1, wherein, The generating of the first information comprises: The second communication device generates the first information.

12. The method of claim 11, wherein, Before the second communication device generates the first information, the method further comprises: The second communication device sends second information to the first communication device, the second information being used to obtain the second data set.

13. The method of claim 1, wherein, The receiving of the first information comprises: The second communication device receives the first information from the first communication device.

14. The method of claim 13, wherein, The determination result comprises a first determination result, and before the second communication device receives the first information from the first communication device, the method further comprises: The second communication device sends third information to the first communication device, the third information being used to obtain the first determination result, or the third information being used to obtain the first information.

15. The method according to any one of claims 11 to 14, characterized in that, The determination result comprises a first determination result, and the obtaining of the determination result comprises: The second communication device generates the first determination result according to the first information.

16. The method of claim 15, wherein, The determination result further comprises a second determination result, and after the second communication device generates the first determination result according to the first information, the method further comprises: The second communication device sends the second determination result to the first communication device, and the second determination result is determined based on the first determination result.

17. The method of claim 16, wherein, Before the second communication device sends the second determination result to the first communication device, the method further comprises: The second communication device receives fourth information from the first communication device, and the fourth information is used to obtain the model.

18. The method of claim 11 or 12, wherein, After the second communication device generates the first information, the method further comprises: The second communication device sends the first information to the first communication device.

19. The method of claim 18, wherein, The determination result comprises a first determination result, and obtaining the determination result comprises: The second communication device receives the first determination result from the first communication device.

20. The method of claim 19, wherein, The determination result further comprises a second determination result, and after the second communication device receives the first determination result from the first communication device, the method further comprises: The second communication device sends the second determination result to the first communication device, and the second determination result is determined based on the first determination result.

21. A communications device, characterized by A module for performing the method of any one of claims 1 to 20.

22. A communications device, characterized by At least one processor coupled with a memory, and the at least one processor is configured to perform the method of any one of claims 1 to 20.

23. The communication apparatus according to claim 22, wherein, The communication device is a chip or a chip system.

24. A readable storage medium characterized by, The storage medium stores a computer program or instructions, and when the computer program or instructions are executed by the communication device, the method of any one of claims 1 to 20 is implemented.

25. A computer program product, characterised in that, A computer program or instructions, when executed by a processor, implement the method of any one of claims 1 to 20.

Images