A communication method, apparatus and system

Through information exchange between terminal devices and network devices, terminal devices can quickly obtain supported AI or ML models, solving the problem that terminal devices cannot preload all models and achieving high-quality wireless communication services.

CN116347356BActive Publication Date: 2026-02-10BAICELLS TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202310403767.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-04-16
Publication Date
2026-02-10
Estimated Expiration
2043-04-16

AI Technical Summary

Technical Problem

Terminal devices cannot preload all AI or ML models, which limits the application of AI or ML in wireless communication networks.

Method used

The terminal device sends information indicating the functions and performance indicators it supports to the network device. Based on this information, the network device sends the corresponding AI or ML model data, enabling the terminal device to quickly obtain the supported models.

Benefits of technology

It enables terminal devices to quickly acquire supported AI or ML models, promotes the application of AI or ML in wireless communication networks, and supports high-quality services such as positioning, beam management, and CSI feedback.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116347356B_ABST
    Figure CN116347356B_ABST
Patent Text Reader

Abstract

The application provides a communication method, device and system. The method comprises: a first communication device sending first information to a second communication device, the first information being used to indicate a first function that the first communication device can use, the first function having one or more models, the model being an artificial intelligence model or a machine learning model, the first function being used for the first communication device to support a first service related to the first function; and the first communication device receiving model data of a first model sent by the second communication device, the first model being determined by the second communication device according to the first information, the first model being a model that the first communication device can use and supports the first service. The communication method of the application can enable a terminal device to quickly obtain an AI model or a ML model that it supports, thereby facilitating the application of AI or ML in a wireless communication network.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

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

[0002] With the rapid development of wireless communication networks, artificial intelligence (AI) or machine learning (ML) is playing an increasingly important role. For example, terminal devices can use AI or ML models to provide a variety of services such as positioning, beam management, and channel state information (CSI) feedback.

[0003] Taking location services as an example, in non-line-of-sight (NLoS) scenarios, where there are obstacles or occlusions, terminal devices can collect, analyze, and process data based on AI or ML models to obtain highly accurate location information. This enables terminal devices to provide accurate location services in various complex environments such as factories, buildings, indoor and outdoor environments.

[0004] Currently, there are numerous types of AI or ML models, and the data volume of these models is enormous. Terminal devices cannot pre-load all of these models, thus limiting their application in wireless communication networks. Therefore, enabling terminal devices to quickly obtain AI or ML models is a pressing technical challenge that needs to be addressed. Summary of the Invention

[0005] This application provides a communication method, apparatus, device, and system that enables terminal devices to quickly obtain their supported AI or ML models, thereby facilitating the application of AI or ML in wireless communication networks.

[0006] In a first aspect, this application provides a communication method applied to a communication system including a first communication device and a second communication device, wherein the first communication device may be a terminal device or a module in a terminal device, and the second communication device may be a network device or a module in a network device.

[0007] In the first aspect, the method is used to implement the functions of the first communication device. For example, the method can be applied to a terminal device or a module in the terminal device. The embodiments of this application do not limit the specific subject executing the method. Optionally, the method can be jointly implemented by multiple functional modules on the terminal device side, and the methods executed by each functional module are also within the protection scope of this application.

[0008] Taking the application of this method to a first communication device as an example, in this method, the first communication device sends first information to a second communication device. The first information is used to indicate a first function that the first communication device can use. The first function has one or more models, which are artificial intelligence models or machine learning models. The first function is used by the first communication device to support a first service related to the first function. The first communication device receives model data of a first model sent by the second communication device. The first model is determined by the second communication device based on the first information. The first model is a model that the first communication device can use and supports the first service.

[0009] Using the method provided in the first aspect, the first communication device sends first information to the second communication device, enabling the second communication device to know a first function with one or more models that the first communication device can use. This first function may be, for example, a positioning function, a beam management function, a CSI feedback function, etc. Based on this first information, the second communication device can send model data of the first model to the first communication device. This model data may be, for example, the model structure and / or model parameters of the first model. This allows the first communication device to quickly obtain its supported AI or ML models, thereby facilitating the application of AI or ML in wireless communication networks.

[0010] In one possible design, the method further includes: a first communication device sending second information to a second communication device, the second information indicating the expected performance indicators of a first service supported by the first communication device, so that the second communication device determines a first model based on the first information and the second information.

[0011] The method provided by this implementation allows the first communication device to quickly obtain a first model that meets and can be used by reporting the expected performance indicators. As a result, the terminal device can use the first model to support a high-quality first service.

[0012] In one possible design, the method further includes: a first communication device receiving third information sent by a second communication device, the third information being determined by the second communication device based on the first information, the third information being used to indicate model data of all models, all models including models that the first communication device can use, or models that the first communication device can use and that meet the expected performance indicators; the first communication device determining a first model based on the third information; and the first communication device sending a first result to the second communication device, the first result being used to indicate the first model.

[0013] According to the method provided in this embodiment, after receiving the third information determined by the second communication device based on the first information, the first communication device determines the first model from all models indicated by the third information, and instructs the second communication device on the first model through the first result, so as to notify the second communication device of the determined first model.

[0014] In one possible design, after the first communication device sends a first result to the second communication device, the method further includes: the first communication device receiving a first notification from the second communication device.

[0015] By using the method provided in this embodiment, the first communication device can determine that the second communication device has received the first result by receiving a first notification from the second communication device through the first communication device.

[0016] In one possible design, the first communication device receives fourth information sent by the second communication device, the fourth information being determined by the second communication device based on the first information, the fourth information including auxiliary information indicating all models, all models including models that the first communication device can use, or models that the first communication device can use and that meet the expected performance indicators; the first communication device determines auxiliary information for the first model based on the fourth information; the first communication device sends a second result to the second communication device, the second result being used to indicate the auxiliary information for the first model.

[0017] The method provided by this embodiment allows the first communication device to receive the fourth information, determine the auxiliary information of the first model, and indicate the auxiliary information of the first model to the second communication device through the second result. This enables the second communication device to send only the model data of the first model corresponding to the auxiliary information, thereby enabling the first communication device to quickly obtain the AI ​​model or ML model it supports, while also saving signaling overhead.

[0018] In one possible design, after the first communication device receives the first model, the method further includes: the first communication device sending a second notification to the second communication device, the second notification being used to indicate that the first communication device has received the second result.

[0019] By using the method provided in this embodiment, a second notification can be sent by a first communication device and a second communication device, enabling the second communication device to promptly determine that the first communication device has received the second result.

[0020] In one possible design, the method further includes: the first communication device sending a third notification to the second communication device, the third notification being used to indicate that the first communication device has received model data of the first model.

[0021] According to the method provided in this embodiment, after the first communication device reports first information to the second communication device, the second communication device determines the first model based on the first information and directly sends the model data of the determined first model to the first communication device, thereby enabling the first communication device to obtain the model data of the first model. Furthermore, after obtaining the model data of the first model, the first communication device can also send a third notification to the second communication device to indicate that the first communication device has received the model data of the first model.

[0022] Secondly, this application provides a communication method applied to a communication system including a first communication device and a second communication device, wherein the first communication device can be a terminal device or a module in a terminal device, and the second communication device can be a network device or a module in a network device.

[0023] In the second aspect, the method is used to implement the functions of the second communication device. For example, the method can be applied to a network device or a module in a network device, and this application does not limit the specific entity executing the method. Optionally, the method can be implemented by multiple functional modules on the second communication device side through interaction, and the methods executed by each functional module are also within the protection scope of this application.

[0024] Taking the application of this method to a second communication device as an example, in this method, the second communication device receives first information from the first communication device; the first information is used to indicate a first function that the first communication device can use, the first function has one or more models, the models are artificial intelligence models or machine learning models, the first function is used by the first communication device to support a first service related to the first function; the second communication device sends model data of the first model to the first communication device, the first model is determined by the second communication device according to the first information, the first model is a model that the first communication device can use and supports the first service.

[0025] The method provided in this embodiment allows the second communication device to determine the model data of the first model to be sent to the first communication device based on the first information from the first communication device, and enables the first communication device to quickly obtain the model data of the first model by sending the model data of the first model. This allows the first communication device to quickly obtain the AI ​​or ML models it supports, thereby facilitating the application of AI or ML in wireless communication networks.

[0026] In one possible design, the method further includes: a second communication device receiving second information, the second information being used to indicate the expected performance indicators of a first service supported by the first communication device; the second communication device sending model data of a first model to the first communication device, including: the second communication device sending model data of the first model to the first communication device, the first model being determined by the first information and the second information.

[0027] Using the method provided in this embodiment, the second communication device can transmit model data of a first model that conforms to the first information and the second information to the first communication device based on the first information and the second information sent by the first communication device.

[0028] In one possible design, the second communication device sends third information to the first communication device. The third information is determined by the second communication device based on the first information. The third information is used to indicate the model data of all models. All models include models that the first communication device can use, or models that the first communication device can use and that meet the expected performance indicators. The second communication device receives a first result sent by the first communication device. The first result is used to indicate the first model.

[0029] The method provided by this embodiment allows the second communication device to send all models that match the first information of the first communication device, or the first information and the second information, to the first communication device, so that the first communication device can determine one or more first models from them, and the second communication device can send the first model indicated by the first result to the first communication device.

[0030] In one possible design, after the second communication device receives the first result sent by the first communication device, the method further includes: the second communication device sending a first notification to the first communication device, the first notification being used to indicate that the second communication device has received the first result.

[0031] According to the method provided by this embodiment, after receiving the first result reported by the first communication device, the second communication device can also send a first notification to the first communication device so that the first communication device can determine that the second communication device has received the first result.

[0032] In one possible design, the second communication device sends a fourth message to the first communication device, the fourth message being determined by the second communication device based on the first message, the fourth message including auxiliary information indicating all models, all models including models that the first communication device can use, or models that the first communication device can use and that meet the expected performance indicators; the second communication device receives a second result from the first communication device, the second result being used to indicate auxiliary information for the first model.

[0033] The method provided by this embodiment allows the second communication device to determine the fourth information based on the first information and send the fourth information, which includes auxiliary information for indicating all models, to the first communication device. This enables the first communication device to quickly obtain the AI ​​or ML models it supports, while also saving overhead.

[0034] In one possible design, after the second communication device sends the first model to the first communication device, the method further includes: the second communication device receiving a second notification from the first communication device, the second notification indicating that the first communication device has received a second result.

[0035] The method provided by this embodiment allows the second communication device to determine that the first communication device has received the second result based on the received second notification.

[0036] In one possible design, the second communication device receives a third notification sent by the first communication device, the third notification indicating that the first communication device has received model data of the first model.

[0037] The method provided by this embodiment enables the second communication device to promptly determine that the first communication device has received the model data of the first model.

[0038] Thirdly, this application provides a communication device including a module for performing the methods as described in the first aspect of this application and any possible design of the first aspect; or, a module for performing the methods as described in the second aspect of this application and any possible design of the second aspect.

[0039] Fourthly, this application provides a communication device, comprising: a processor; the processor being configured to execute a computer-executable program or instructions in a memory, causing the communication device to perform the methods of the first aspect of this application and any possible design of the first aspect; or, causing the communication device to perform the methods of the second aspect of this application and any possible design of the second aspect.

[0040] Fifthly, this application provides a communication system comprising: a communication device for performing the methods as described in the first aspect of this application and any possible design of the first aspect, and a communication device for performing the methods as described in the second aspect of this application and any possible design of the second aspect.

[0041] In a sixth aspect, this application provides a computer-readable storage medium storing a computer-executable program or instructions configured to perform the methods of the first aspect of this application and any possible design of the first aspect; or, the computer-executable program or instructions configured to perform the methods of the second aspect of this application and any possible design of the second aspect.

[0042] In a seventh aspect, this application provides a chip, characterized in that it includes: an interface circuit and a logic circuit, wherein the interface circuit is used to receive signals from other chips outside the chip and transmit them to the logic circuit, or to send signals from the logic circuit to other chips outside the chip, and the logic circuit is used to implement the methods in the first aspect of this application and any possible design of the first aspect; or, the logic circuit is used to implement the methods in the second aspect of this application and any possible design of the second aspect.

[0043] Eighthly, this application provides a computer program product comprising: execution instructions stored in a readable storage medium, at least one processor of an electronic device being able to read the execution instructions from the readable storage medium, and the at least one processor executing the execution instructions causing the electronic device to implement the first aspect and any possible design of the first aspect or the second aspect and any possible design of the second aspect. Attached Figure Description

[0044] Figure 1 This is a schematic diagram of the architecture of a communication system provided in an embodiment of this application.

[0045] Figure 2 This is a signaling interaction diagram of a communication method provided in an embodiment of this application.

[0046] Figure 3 This is a schematic diagram of the first information in a communication method provided in an embodiment of this application.

[0047] Figure 4 This is a signaling interaction diagram of a communication method provided in an embodiment of this application.

[0048] Figure 5 This is a signaling interaction diagram of a communication method provided in an embodiment of this application.

[0049] Figure 6 This is a signaling interaction diagram of a communication method provided in an embodiment of this application.

[0050] Figure 7 This is a schematic diagram of the structure of a communication device provided in an embodiment of this application.

[0051] Figure 8This is a schematic diagram of the structure of a communication device provided in an embodiment of this application.

[0052] Figure 9 This is a schematic diagram of the structure of a communication device provided in an embodiment of this application.

[0053] Figure 10 This is a schematic diagram of the structure of a communication device provided in an embodiment of this application. Detailed Implementation

[0054] In this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects 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, or c alone can mean: a alone, b alone, c alone, a combination of a and b, a combination of a and c, a combination of b and c, or a, b, and c, where a, b, and c can be single or multiple. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0055] This application provides a communication method, apparatus, and system. When a terminal device needs to support a certain service, the terminal device informs a network device of one or more models that can be used to support that service. The models can be AI models or ML models. The network device can then send one or more models that support the service to the terminal device, so that the terminal device can quickly obtain one or more models that support the service. This helps the terminal device to use one or more models to implement the service, enabling the widespread application of AI or ML in wireless communication networks.

[0056] The aforementioned services are used by terminal devices to implement one or more services, such as positioning, signal detection, signal quality management, and signal quality notification. These services can be, for example, positioning, beam management, or CSI feedback; this application does not limit the specific services offered.

[0057] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. It should be noted that, unless otherwise specified, different technical features in this application can be combined with each other.

[0058] Figure 1This is a schematic diagram of the architecture of a communication system provided in one embodiment of this application. Please refer to [link / reference]. Figure 1 The communication system may include one or more terminal devices and one or more network devices. For ease of explanation, Figure 1 The illustration uses one terminal device and one network device.

[0059] The communication system may include, but is not limited to, wireless communication systems, such as narrowband Internet of Things (NB-IoT), long term evolution (LTE) systems, fifth-generation (5G) communication systems, sixth-generation (6G) communication systems, and other communication systems that have evolved after 5G.

[0060] The scenarios for which this communication system is applicable may include, but are not limited to: terrestrial cellular communication, non-terrestrial network (NTN), satellite communication, high altitude platform station (HAPS) communication, vehicle-to-everything (V2X) communication, integrated access and backhaul (IAB) communication, and reconfigurable intelligent surface (RIS) communication.

[0061] The terminal device can be a wireless terminal or a wired terminal. A wireless terminal can be a device that provides voice and / or other service data connectivity to a user, such as a handheld device with wireless connectivity, or other processing device connected to a wireless modem. The wireless terminal can communicate with one or more core networks via a radio access network (RAN). The wireless terminal can be a mobile terminal, such as a mobile phone (or "cellular" phone) or a computer with a mobile terminal, for example, a portable, pocket-sized, handheld, computer-embedded, or vehicle-mounted mobile device, which exchanges voice and / or data with the radio access network.

[0062] Examples include personal communication service (PCS) phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), drones, wearable devices, and terminals in vehicle-to-everything (V2X) networks. Wireless terminals can also be referred to as systems, subscriber units, subscriber stations, mobile stations, mobile devices, remote stations, remote terminals, access terminals, user terminals, user agents, user devices or user equipment (UE), and no specific terminology is used here. Furthermore, terminal devices can use mobile operating systems such as iOS, Android, or HarmonyOS, and this application does not impose any limitations on this.

[0063] The network device can be a base station, an access point, or an access network device, or it can refer to a device in the access network that communicates with a wireless terminal via one or more sectors on the air interface. The network device can be used to convert received air frames to and from IP packets, and acts as a router between the wireless terminal and the rest of the access network, which may include an Internet Protocol (IP) network. The network device can also coordinate the attribute management of the air interface.

[0064] For example, network equipment can be a satellite, a drone, a base station (BTS) in Global System for Mobile Communications (GSM) or Code Division Multiple Access (CDMA), a base station (NodeB, NB) in Wideband Code Division Multiple Access (WCDMA), an evolved Node B (eNB or eNodeB) in Long Term Evolution (LTE), or a terminal, relay station, or access point that performs base station functions in V2X (vehicular to everything), Device-to-Device (D2D), and Machine-to-Machine (M2M) communications, or a base station in a 5G network, such as a gNB, or a base station in a future 6G network; there are no limitations on this.

[0065] Figure 2 This is a signaling interaction diagram of a communication method provided in an embodiment of this application. For example... Figure 2 As shown, the communication method of this application can be applied to the above-mentioned... Figure 1 In the communication system shown, the first communication device can be a terminal device or a module within a terminal device, and the second communication device can be a network device or a module within a network device. For ease of explanation, taking the first communication device as a terminal device and the second communication device as a network device as an example, the architecture method of this application may specifically include the following steps:

[0066] Step 100: The terminal device sends the first information to the network device.

[0067] Correspondingly, the network device receives the first information sent by the terminal device.

[0068] The first information may be triggered and sent by a terminal device, or the first information may be triggered and sent by a network device.

[0069] For example, when a terminal device accesses a network, it sends an access request to the network device, and the access request contains first information.

[0070] For example, a terminal device may periodically send terminal capability information, which includes first information.

[0071] For example, a network device can send terminal capability query information, and a terminal device can send first information to the network device based on the terminal capability query information.

[0072] For example, in a location-based scenario, when a terminal device enters a factory area, it can periodically send terminal capability information to a network device, including first information. Alternatively, the terminal device can send an access request to the network device, including the first information. Or, when the network device detects that the terminal device has entered or is about to enter the factory area, it sends terminal capability query information to the terminal device, enabling the terminal device to send the first information to the network device based on the terminal capability query information.

[0073] The first information is used to indicate the first function of one or more models that the terminal device can use; the model can be an artificial intelligence model or a machine learning model. In some examples, the first information is used to indicate the first function of one or more models that the terminal device can use.

[0074] The first function is used by the terminal device to support a first service related to the first function, and the first service is used by the terminal device to implement one or more services. For example, if the first service is a positioning service, the corresponding first function is the positioning function of one or more models. If the first service is a beam management service, the corresponding first function is the beam management function of one or more models. If the first service is a CSI feedback service, the corresponding first function is the CSI feedback function of one or more models. Based on this, the first information can be indicated in various ways.

[0075] In one possible implementation, the first information may include model identifiers (IDs) for all models that the terminal device can use. The model ID is used to uniquely identify the model.

[0076] In one possible implementation, the first information may include model identifiers (IDs) of one or more models that the terminal device can use and supports the first service. And / or, the first information may include model IDs of one or more models that the terminal device can use but does not support the first service.

[0077] In one possible implementation, the first information may include the function IDs of all models that the terminal device can use. The function IDs of the models are used to identify the functions that the model possesses, or the services that the model supports.

[0078] In one possible implementation, the first information may include the function IDs of one or more models that the terminal device can use and supports the first service. And / or, the first information may include the function IDs of one or more models that the terminal device can use but does not support the first service. The function ID of the model is used to identify that the model has the functionality to support the first service. That is, the terminal device can use the functionality of the model to implement the first service.

[0079] In one possible implementation, the first information may include the model ID and function ID of all models that the terminal device can use.

[0080] In one possible implementation, the first information may include the model ID and function ID of one or more models that the terminal device can use and supports the first service. And / or, the first information may include the model ID and function ID of one or more models that the terminal device can use but does not support the first service.

[0081] Below, in conjunction with Figure 3 The detailed information includes the specific details of the model IDs and function IDs of all models that the terminal device can use.

[0082] like Figure 3 As shown, the first information may include the model ID and function ID that the terminal device can use and support for location services, the non-artificial intelligence / machine learning function ID that the terminal device can use and support for location services, and the model ID and function ID that the terminal device can use and support for beam management services.

[0083] As an example, assume the terminal device supports location services and beam management services. The function ID corresponding to the location service is Artificial Intelligence / Machine Learning Function 1, and the model IDs that the terminal device can use and supports for the location service include Model 1, Model 2, and Model 3. The function ID for all models that the terminal device cannot use is Artificial Intelligence / Machine Learning Function 2. The function ID corresponding to the beam management service is Artificial Intelligence / Machine Learning Function 2, and the model IDs that the terminal device can use and supports for the beam management service include Model 1, Model 2, and Model 3.

[0084] As an example, assume the terminal device supports location services, with corresponding function IDs of AI / Machine Learning Function 1 and AI / Machine Learning Function 2. AI / Machine Learning Function 1 can achieve location functionality using a first location method, and AI / Machine Learning Function 2 can achieve location functionality using a second location method. The model IDs that the terminal device can use and support location services using the first location method include Model 1, Model 2, and Model 3. Similarly, the model IDs that the terminal device can use and support location services using the second location method include Model 1, Model 2, and Model 3. The first location method, for example, can directly output the terminal device's location information, while the second location method, for example, can output intermediate values ​​to facilitate the calculation of the terminal device's location information based on these intermediate values.

[0085] In another possible implementation, the first information may include: a device identifier (ID) of the terminal device. The device ID is used to determine the first function of one or more models that the terminal device can use. For example, the device ID may include one or more of the following: device model, software information, and hardware information. The software information may be the software version of the terminal device or the device's ID in the network, such as the International Mobile Equipment Identity (IMEI), International Mobile Subscriber Identity (IMSI), Globally Unique Temporary Identifier (GUTI), or Temporary Mobile Subscriber Identity (TMSI). The hardware information may be the chipset model of the model the terminal device runs on, etc.

[0086] For example, when the first information includes the hardware information of the chipset of the terminal device's operating model and the corresponding software version, the network device can learn about the first functions of one or more models that the terminal device can use by querying other network entities or third-party network entities within the network.

[0087] Step 120: The network device sends the model data of the first model to the terminal device.

[0088] Correspondingly, the terminal device receives the model data of the first model sent by the network device.

[0089] The first model is determined by the second communication device based on the first information, and the first model is a model that the first communication device can use and supports the first service.

[0090] After receiving the first information, the network device can determine, based on the first information, one or more models that the terminal device can use and supports the first service, i.e., the first model. Therefore, the network device can send the model data of the first model to the terminal device.

[0091] The model data of the first model is used by the terminal device to activate and run the first model when using the first function related to the first model, so as to provide the first service related to the first function.

[0092] In some examples, the first model may include its model structure and / or model parameters. The model structure refers to the framework structure of the first model, such as ResNet-18, ResNet-50, VGG-16, DenseNet-12, etc. Another example is the use of the general framework of Open Neural Net Exchange (ONNX). The model parameters refer to the specific parameters within each neuron or other component based on the model structure of the first model.

[0093] For example, the network device can determine whether to send the model structure of the first model, the model parameters of the first model, or the model structure and model parameters of the first model, depending on the specific application scenario and actual situation.

[0094] For example, in a positioning scenario, when a network device learns that a terminal device supports and stores the ResNet-50 model structure, it can send the ResNet-50 model parameters for positioning services to the terminal device.

[0095] For example, based on the first information, the network device determines that the terminal device can use the first function of model X. At this time, the network device can send the model structure and model parameters of model X to the terminal device.

[0096] In some examples, the model data of the first model may include auxiliary information about the first model. The auxiliary information is used to describe relevant information about the first model. For example, the auxiliary information may include at least model identification information to uniquely identify the first model, hardware and software requirements to support the model's operation, model performance information, and external environment requirements for the model's normal operation.

[0097] Furthermore, the model data of the first model can also be processed, such as through encryption and compilation, ensuring the security and privacy of the model data. For example, a network device can encrypt the entire content of the model data of the first model. Alternatively, a network device can compile the hardware and software information in the model data of the first model.

[0098] Step 140: The terminal device sends a third notification to the network device.

[0099] Correspondingly, the network device receives the third notification sent by the terminal device.

[0100] The third notification is used to instruct the terminal device to receive the model data of the first model.

[0101] Step 140 is optional. If the terminal device does not receive the model data of the first model within the first time period, it can resend the first information to the network device, that is, the terminal device can re-execute step 100. This application does not limit the specific length of the first time period. Therefore, when the terminal device receives the model data of the first model, it can selectively send a third notification to the network device, enabling the network device to promptly know that the terminal device has received the model data of the first model.

[0102] Through the communication method of this application, the terminal device sends first information to the network device. The network device can determine the first model of the first service that the first communication device can use and support based on the first information, and send the model data of the first model to the terminal device. Thus, the terminal device can quickly obtain one or more first models that support the service, which helps the terminal device to implement the service using one or more first models, enabling AI or ML to be widely used in wireless communication networks.

[0103] Based on the description of the above embodiments, and considering the actual scenario and specific circumstances, the terminal device may achieve a high-quality first service. That is, the terminal device requires a high-performance first model. High performance may include high precision or high accuracy. Therefore, not only must the first model be a model that the terminal device can use and supports the first service, but the actual performance indicators of the first model must also meet the expected performance indicators. Thus, the terminal device can use the first model to support a high-quality first service.

[0104] Among them, actual performance indicators refer to the performance indicators actually achieved by the terminal device when providing the first service using the third model. Expected performance indicators refer to the performance indicators that the terminal device is expected to achieve when providing the service.

[0105] Below, in conjunction with Figure 4 The specific implementation process of the communication method in this application will be explained in detail.

[0106] Figure 4 This is a signaling interaction diagram of a communication method provided in an embodiment of this application. For example... Figure 4 As shown, the communication method of this application may include the following steps:

[0107] Step 210: The terminal device sends the first information to the network device.

[0108] Among them, step 210 and Figure 2 Step 100 in the embodiment is implemented in a similar manner, and will not be described again here.

[0109] Step 220: The terminal device sends its second information to the network device.

[0110] Correspondingly, the network device receives the second information sent by the terminal device.

[0111] The second piece of information is used to indicate the expected performance metrics of the first service supported by the terminal device.

[0112] The second information may be triggered and sent by the terminal device, or the second information may be triggered and sent by the network device.

[0113] For example, when a terminal device accesses a network, it sends an access request to the network device, and the access request contains the second information.

[0114] For example, a terminal device may periodically send terminal capability information, which includes second information.

[0115] For example, a network device can send terminal capability query information, and a terminal device can send second information to the network device based on the terminal capability query information.

[0116] For example, in a location-based scenario, when a terminal device enters a factory area, it can periodically send terminal capability information to the network device, including the second information. Alternatively, the terminal device can send an access request to the network device, including the second information. Or, when the network device detects that the terminal device has entered or is about to enter the factory area, it sends terminal capability query information to the terminal device, enabling the terminal device to send the second information to the network device based on the terminal capability query information.

[0117] The expected performance metric refers to the performance metrics that the terminal device expects to achieve when using the service. For example, when a terminal device is about to enter or enters a factory area or other area, it sends its expected positioning accuracy in that area to the network device so that the network device can determine a positioning model that meets the expected positioning accuracy and can be used by the terminal device.

[0118] There is no temporal order between steps 210 and 220, and steps 210 and 220 can be executed simultaneously or sequentially.

[0119] Furthermore, the first piece of information and the second piece of information can be the same information or they can be different information.

[0120] Step 230: The network device sends the model data of the first model to the terminal device.

[0121] Correspondingly, the terminal device receives the model data of the first model sent by the network device.

[0122] The first model is determined by the second communication device based on the first information and the second information. The first model is a model that the first communication device can use and supports the first service.

[0123] Step 240: The terminal device sends a third notification to the network device.

[0124] Among them, step 240 and Figure 2 Step 140 in the embodiment is implemented in a similar manner, and will not be described again here.

[0125] In summary, the terminal device can quickly obtain a first model whose actual performance indicators meet the expected performance indicators. Therefore, the terminal device can use the first model to support high-quality first services.

[0126] Based on the description of the above embodiments, the first model can be determined by the network device, or it can be jointly determined by the terminal device and the network device; this application does not limit this. Furthermore, the first model can also be determined by the terminal device.

[0127] Below, in conjunction with Figure 5 and Figure 6 The document describes in detail the specific implementation process of the first model, which is jointly determined by the terminal device and the network device.

[0128] Figure 5 This is a signaling interaction diagram of a communication method provided in an embodiment of this application. For example... Figure 5 As shown, the communication method provided in this application may further include:

[0129] Step 310: The terminal device sends the first information to the network device.

[0130] Among them, step 310 and Figure 2 Step 100 in the embodiment is implemented in a similar manner, and will not be described again here.

[0131] Step 320: The network device sends third information to the terminal device.

[0132] Correspondingly, the terminal device receives third information sent by the network device.

[0133] The third information is determined by the network device based on the first information. The third information is used to indicate the model data of all models. All models include models that can be used by the terminal device, or models that can be used by the terminal device and meet the expected performance indicators.

[0134] After receiving the first information, if the network device can determine all the models that the terminal device can use based on the first information, the network device can send all the models to the terminal device.

[0135] Alternatively, after receiving the first and second information, the network device can determine, based on the first and second information, all models that the terminal device can use and that meet the expected performance indicators, and then send all models to the terminal device.

[0136] Step 330: The terminal device determines the first model based on the third information.

[0137] The terminal device can determine the model data of all the above models based on the third information, and thus the terminal device can select one or more models as the first model from all the above models.

[0138] Step 340: The terminal device sends the first result to the network device.

[0139] Correspondingly, the network device receives the first result sent by the terminal device.

[0140] The first result is used to indicate the first model.

[0141] After determining the first model, the terminal device can send the first result to the network device, so that the network device can know the first model selected by the terminal device in a timely manner.

[0142] This application does not limit the specific implementation of the first result. For example, the first result may include the model ID of the first module.

[0143] Step 350: The network device sends the first notification to the terminal device.

[0144] Correspondingly, the terminal device receives the first notification sent by the network device.

[0145] The first notification is used to instruct the network device to receive the first result.

[0146] Step S350 is optional. After receiving the first result, the network device can send the model data of the first model to the terminal device. Therefore, when the terminal device receives the model data of the first model, it can determine that the network device has received the first result. If the terminal device does not receive the model data of the first model within a second time period, it can determine that the network device has not received the first result, and the terminal device can resend the first result to the network device, i.e., the terminal device can re-execute step 340. This application does not limit the specific length of the second time period.

[0147] Based on this, when a network device receives the first result, it can selectively send a first notification to the terminal device, so that the terminal device can be informed in a timely manner that the network device has received the first result.

[0148] Step 360: The network device sends the model data of the first model to the terminal device.

[0149] Correspondingly, the terminal device receives the model data of the first model sent by the network device.

[0150] The first model is determined by the network device based on the first result. The first model is a model that the terminal device can use and supports the first service, or a model that the terminal device can use, supports the first service and meets the expected performance indicators.

[0151] After receiving the first result from the terminal device, the network device can determine the first model selected by the terminal device based on the first result. The first model can be selected by the terminal device from a total of all models sent by the network device, which are models that the terminal device can use; or, the total number of models can be models that the terminal device can use and that meet the expected performance indicators. Therefore, the network device can determine the first model based on the first result and send the model data of the first model to the terminal device.

[0152] Step 370: The terminal device sends a third notification to the network device.

[0153] Among them, step 370 and Figure 2 Step 140 in the embodiment is implemented in a similar manner, and will not be described again here.

[0154] It should be noted that, in addition to the above implementation methods, Figure 5 In addition, the terminal device can also combine first information, third information, and... Figure 4 The second piece of information shown determines the first model. The specific implementation of the aforementioned content can be combined with... Figure 4 and Figure 5 The steps are not detailed here.

[0155] In summary, the terminal device sends first information to the network device. Based on the first information, the network device can determine all models that the first communication device can use or that meet the expected performance indicators. The network device then sends all models to the terminal device via third information, enabling the terminal device to select one or more models as the first model from the entire set of models. The terminal device then indicates the first model to the network device via the first result. As a result, the terminal device can quickly obtain one or more first models that support the service, which helps the terminal device to implement the service using one or more first models. This enables AI or ML to be widely used in wireless communication networks.

[0156] Figure 6 This is a signaling interaction diagram of a communication method provided in an embodiment of this application. For example... Figure 6 As shown, the communication method of this application may further include:

[0157] Step 410: The terminal device sends the first information to the network device.

[0158] Among them, step 410 is respectively with Figure 2 Step 100 in the embodiment is implemented in a similar manner, and will not be described again here.

[0159] Step 420: The network device sends the fourth information to the terminal device.

[0160] Correspondingly, the terminal device receives the fourth piece of information sent by the network device.

[0161] The fourth information is determined by the second communication device based on the first information. The fourth information includes auxiliary information indicating all models. All models include models that the first communication device can use, or models that the first communication device can use and that meet the expected performance indicators.

[0162] After receiving the first information, the network device can determine all the models that the terminal device can use based on the first information, and the network device can send auxiliary information for all models to the terminal device.

[0163] Alternatively, after receiving the first and second information, the network device can determine, based on the first and second information, all models that the terminal device can use and that meet the expected performance indicators, and then send auxiliary information for all models to the terminal device.

[0164] Step 430: The terminal device determines the auxiliary information of the first model based on the fourth information.

[0165] Based on the fourth information, the terminal device can select one or more auxiliary information from all the auxiliary information of the above models as the auxiliary information of the first model.

[0166] Step 440: The terminal device sends the second result to the network device.

[0167] Correspondingly, the network device receives the second result sent by the terminal device.

[0168] The second result is used to indicate auxiliary information for the first model.

[0169] After determining the auxiliary information of the first model, the terminal device can send the second result to the network device, so that the network device can know the first model selected by the terminal device in a timely manner.

[0170] This application does not limit the specific implementation of the second result. For example, the first result may include one or more of the following: the model ID of the first module, the auxiliary information ID of the first model, or auxiliary information of the first model.

[0171] Step 450: The network device sends a second notification to the terminal device.

[0172] Correspondingly, the terminal device receives the second notification sent by the network device.

[0173] The second notification is used to instruct the network device to receive the second result.

[0174] Step S450 is optional. After receiving the second result, the network device can send the model data of the first model to the terminal device. Therefore, when the terminal device receives the model data of the first model, it can determine that the network device has received the second result. If the terminal device does not receive the model data of the first model within a third time period, it can determine that the network device has not received the second result, and the terminal device can resend the second result to the network device, i.e., the terminal device can re-execute step 440. This application does not limit the specific length of the third time period.

[0175] Based on this, when a network device receives a second result, it can selectively send a second notification to the terminal device, so that the terminal device can be informed in a timely manner that the network device has received the second result.

[0176] Step 460: The network device sends the model data of the first model to the terminal device.

[0177] Correspondingly, the terminal device receives the model data of the first model sent by the network device.

[0178] The first model is determined by the network device based on the second result. The first model is a model that the terminal device can use and supports the first service, or a model that the terminal device can use, supports the first service and meets the expected performance indicators.

[0179] After receiving the first result from the terminal device, the network device can determine the first model selected by the terminal device based on the auxiliary information of the first model in the first result. The auxiliary information of the first model can be selected by the terminal device from the auxiliary information of all models sent by the network device, where all models are models that the terminal device can use; or, where all models are models that the terminal device can use and meet the expected performance indicators. Therefore, the network device can determine the first model based on the first result and send the model data of the first model to the terminal device.

[0180] Step 470: The terminal device sends a third notification to the network device.

[0181] Among them, step 470 and Figure 2 Step 140 in the embodiment is implemented in a similar manner, and will not be described again here.

[0182] It should be noted that, in addition to the above implementation methods, Figure 6 In addition, the terminal device can also combine the first information, the fourth information, and... Figure 4 The second piece of information shown determines the first model. The specific implementation of the aforementioned content can be combined with... Figure 4 and Figure 6 The steps are not detailed here.

[0183] In summary, the terminal device sends first information to the network device. Based on the first information, the network device can determine the auxiliary information of all models that the first communication device can use or that meet the expected performance indicators. The network device then sends the auxiliary information of all models to the terminal device via fourth information. This allows the terminal device to select the auxiliary information of one or more models from the auxiliary information of all models as the auxiliary information of the first model. The terminal device then indicates the auxiliary information of the first model to the network device via the first result. As a result, the terminal device can quickly obtain one or more first models that support the service. This helps the terminal device to implement the service using one or more first models, enabling the widespread application of AI or ML in wireless communication networks.

[0184] Based on the description of the above embodiments, during the use of the first model, the actual scenario and specific circumstances may change, causing the terminal device to be unable to use the first model to implement the first service, or the terminal device to achieve poor results in implementing the first service using the first model. Therefore, network devices and / or terminal devices can monitor the usage of the first model to facilitate timely replacement of the first model.

[0185] In some examples, the terminal device may send a message to the network device indicating the monitoring method. This monitoring method may include monitoring by the network device, monitoring by the terminal device, or monitoring jointly by both the terminal device and the network device.

[0186] The above information can be sent as a new message, or it can reuse the same message as previously sent information, such as... Figure 4 The second information in step 220 shown, or Figure 5 The third information in step 320 shown, or Figure 6 The fourth piece of information in step 420 shown is not limited in this application. This information may be sent before the terminal device receives the model data of the first model. For example, the information is sent in... Figure 2 Send before step 120 shown, or before Figure 4Send before step 230 shown, or with Figure 5 The first result in step 340 shown is sent together with, or with Figure 6 The second result from step 440 shown is sent together.

[0187] And / or, the above information may be sent after the terminal device receives the model data of the first model. For example, the above information in Figure 2 The information is sent after step 120 shown, or it may be sent during the use of the first model on the terminal device.

[0188] When the monitoring method is network device monitoring, the terminal device sends one or more actual performance indicators of the first service corresponding to the first model to the network device. The terminal device may send one or more actual performance indicators of the first service corresponding to the second model to the network device in any way, such as real-time, timed, periodic, untimed, or random; this application does not limit this.

[0189] The actual performance indicators can be expressed in ways such as percentages, numerical values, or binary representations.

[0190] For one or more first models, if the actual performance indicators of the first service corresponding to the first model do not meet the preset performance indicators, the network device deletes the first model; if the actual performance indicators of the first service corresponding to the first model meet the preset performance indicators, the first model is retained to update one or more first models.

[0191] After updating one or more first models, the network device may send a fourth notification to the terminal device. The fourth notification is used to indicate the updated one or more first models.

[0192] The network device first obtains one or more first models. Based on the judgment result of whether the actual performance indicators of the first service corresponding to the first model meet the preset performance indicators, it obtains an updated first or more first models. Then, the network device sends a fourth notification to the terminal device, enabling the terminal device to determine the accurate one or more first models after receiving the updated one or more first models, based on the first result and the updated one or more first models, and send a third result to the network device. The third result indicates the accurate one or more first models. Thus, the network device knows the accurate one or more first models ultimately selected by the terminal device, facilitating the network device's monitoring of the usage of the accurate one or more first models.

[0193] When the monitoring method is terminal device monitoring, the terminal device obtains the actual performance indicators of the first service corresponding to one or more first models. The actual performance indicators refer to the performance indicators of the first service when the terminal device provides the first service using one or more first models. These performance indicators may include, for example, time synchronization accuracy, signal-to-noise ratio, and wireless environment, etc., and this application does not impose any limitations on them.

[0194] For one or more first models, if the actual performance index of the first service corresponding to the first model does not meet the preset performance index, the terminal device deletes the first model; if the actual performance index of the first service corresponding to the first model meets the preset performance index, the first model is retained to update one or more first models.

[0195] Specifically, for any given first model, the terminal device can determine whether the actual performance indicators of the first service corresponding to that first model meet preset performance indicators. If not, the terminal device can delete the first model. If it does meet the requirements, the terminal device can retain the first model.

[0196] The terminal device sends a fifth notification to the network device. This fifth notification indicates one or more updated first models.

[0197] The terminal device can first obtain one or more updated first models, and then send a third result to the network device. The third result indicates the accurate one or more first models. This allows the network device to know the accurate one or more first models ultimately selected by the terminal device, reducing the network device's workload and facilitating monitoring of the usage of the accurate one or more first models.

[0198] In addition, the above information can also be sent from network devices to terminal devices.

[0199] In summary, it is possible to monitor the actual performance indicators of the first service corresponding to one or more second models of network devices or terminal devices. When the actual performance indicators are found to be unsatisfactory, the corresponding second model is deleted, and one or more second models are updated, thereby ensuring the service quality of the first service supported by the terminal device.

[0200] By way of example, this application also provides a communication device. Figure 7 This is a schematic diagram of a communication device according to an embodiment of this application. The communication device 500 can be used to perform... Figure 2 , Figure 4 , Figure 5 and Figure 6 The process executed by the first communication device in the embodiment shown is described in detail in the relevant descriptions of the above method embodiments.

[0201] The communication device 500 includes a transceiver unit 501. Optionally, the communication device 500 also includes a processing unit 502. The transceiver unit 501 can implement corresponding communication functions, and the processing unit 502 is used for data processing. The transceiver unit 501 can also be referred to as a communication interface or a communication unit.

[0202] Optionally, the communication device 500 may further include a storage unit, which can be used to store instructions and / or data. The processing unit 502 can read the instructions and / or data in the storage unit so that the communication device can implement the aforementioned method embodiments.

[0203] The communication device 500 can be used to perform the actions performed by the first communication device in the above method embodiment. The communication device 600 can be the first communication device or a component that can be configured on the first communication device. The transceiver unit 501 is used to perform reception-related operations on the first communication device side in the above method embodiment, and the processing unit 502 is used to perform processing-related operations on the first communication device side in the above method embodiment.

[0204] Optionally, the transceiver unit 501 may include a sending unit and a receiving unit. The sending unit is used to perform the sending operation in the above method embodiments. The receiving unit is used to perform the receiving operation in the above method embodiments.

[0205] It should be noted that the communication device 500 may include a transmitting unit but not a receiving unit. Alternatively, the communication device 500 may include a receiving unit but not a transmitting unit. Specifically, it depends on whether the above-described scheme executed by the communication device 500 includes both transmitting and receiving actions.

[0206] As an example, the communication device 500 is used to perform the above. Figure 2 The actions performed by the first communication device in the illustrated embodiment.

[0207] The transceiver unit 501 is configured to send first information to the second communication device, the first information indicating a first function that the terminal device can use, the first function having one or more models, the models being artificial intelligence modules or machine learning models; receive model data of a first model sent by the second communication device, the first model being determined by the second communication device based on the first information, the first model being a model that the first communication device can use and supports the first service; and send a third notification to the second communication device, the third notification indicating that the terminal device has received the model data of the first model.

[0208] As an example, the communication device 500 is used to perform the above. Figure 4 The actions performed by the first communication device in the illustrated embodiment.

[0209] The transceiver unit 501 is configured to send first information to the second communication device, the first information indicating a first function that the first communication device can use, the first function having one or more models, which may be an artificial intelligence module or a machine learning model; send second information to the second communication device, the second information indicating the expected performance indicators of a first service supported by the first communication device; receive model data of a first model sent by the second communication device, the first model being determined by the second communication device based on the first and second information, the first model being a model that the first communication device can use and supports the first service; and send a third notification to the second communication device, the third notification indicating that the first communication device has received the model data of the first model.

[0210] As an example, the communication device 500 is used to perform the above. Figure 5 The actions performed by the first communication device in the illustrated embodiment.

[0211] The transceiver unit 501 is configured to: send first information to the second communication device, the first information indicating a first function that the first communication device can use, the first function having one or more models, which may be an artificial intelligence module or a machine learning model; receive third information sent by the second communication device, the third information being determined by the second communication device based on the first information; determine a first model based on the third information; send a first result to the second communication device, the first result indicating the first model; receive a first notification sent by the second communication device, the first notification indicating that the second communication device has received the first result; receive model data of the first model sent by the second communication device, the first model being determined by the second communication device based on the first result; and send a third notification to the second communication device, the third notification indicating that the first communication device has received the model data of the first model.

[0212] As an example, the communication device 500 is used to perform the above. Figure 6 The actions performed by the first communication device in the illustrated embodiment.

[0213] The transceiver unit 501 is used to send first information to the second communication device and receive fourth information sent by the second communication device.

[0214] Processing unit 502 is used to determine auxiliary information of the first model based on the first information.

[0215] The transceiver unit 501 is used to send a second result to the second communication device; receive a second notification sent by the second communication device; receive model data of the first model sent by the second communication device; and send a third notification to the second communication device, the third notification being used to instruct the first communication device to receive the model data of the first model.

[0216] It should be understood that the corresponding processes performed by each unit have been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0217] The processing unit 502 in the above embodiments can be implemented by at least one processor or processor-related circuitry. The transceiver unit 501 can be implemented by a transceiver or transceiver-related circuitry. The transceiver unit 501 can also be referred to as a communication unit or communication interface. The storage unit can be implemented by at least one memory.

[0218] By way of example, this application also provides a communication device. Figure 8 This is a schematic diagram of a communication device according to an embodiment of this application. The communication device 600 can be used to perform... Figure 2 , Figure 4 , Figure 5 and Figure 6 The process executed by the second communication device in the embodiment shown is described in detail in the relevant descriptions of the above method embodiments.

[0219] The communication device 600 includes a transceiver unit 601. Optionally, the communication device 600 also includes a processing unit 602. The transceiver unit 601 can implement corresponding communication functions, and the processing unit 602 is used for data processing. The transceiver unit 601 can also be referred to as a communication interface or a communication unit.

[0220] Optionally, the communication device 600 may further include a storage unit, which can be used to store instructions and / or data. The processing unit 602 can read the instructions and / or data in the storage unit so that the communication device can implement the aforementioned method embodiments.

[0221] The communication device 600 can be used to perform the actions performed by the second communication device in the above method embodiment. The communication device 600 can be the second communication device or a component that can be configured on the second communication device. The transceiver unit 601 is used to perform reception-related operations on the second communication device side in the above method embodiment, and the processing unit 602 is used to perform processing-related operations on the second communication device side in the above method embodiment.

[0222] Optionally, the transceiver unit 601 may include a sending unit and a receiving unit. The sending unit is used to perform the sending operation in the above method embodiments. The receiving unit is used to perform the receiving operation in the above method embodiments.

[0223] It should be noted that the communication device 600 may include a transmitting unit but not a receiving unit. Alternatively, the communication device 600 may include a receiving unit but not a transmitting unit. Specifically, it depends on whether the above-described scheme executed by the communication device 600 includes both transmitting and receiving actions.

[0224] As an example, the communication device 600 is used to perform the above. Figure 2 The actions performed by the second communication device in the illustrated embodiment.

[0225] The transceiver unit 601 is configured to receive first information sent by a first communication device, the first information indicating a first function that the first communication device can use, the first function having one or more models, the models being artificial intelligence modules or machine learning models; based on the first information, sending model data of a first model to the first communication device, the first model being determined by a second communication device based on the first information, the first model being a model that the first communication device can use and supports a first service; and receiving a third notification sent by the first communication device, the third notification indicating that the first communication device has received the model data of the first model.

[0226] As an example, the communication device 600 is used to perform the above. Figure 4 The actions performed by the second communication device in the illustrated embodiment.

[0227] The transceiver unit 601 is configured to receive first information sent by the first communication device, the first information indicating a first function that the first communication device can use, the first function having one or more models, the models being artificial intelligence modules or machine learning models; receive second information sent by the first communication device, the second information indicating the expected performance indicators of a first service supported by the first communication device; send model data of a first model to the first communication device, the first model being determined by the second communication device based on the first and second information, the first model being a model that the first communication device can use and supports the first service; and receive a third notification sent by the first communication device, the third notification indicating that the first communication device has received the model data of the first model.

[0228] As an example, the communication device 600 is used to perform the above. Figure 5 The actions performed by the second communication device in the illustrated embodiment.

[0229] The transceiver unit 601 is configured to receive first information sent by the first communication device, send third information to the first notification device (the third information being determined by the second communication device based on the first information), receive a first result sent by the first communication device, send a first notification to the first communication device (the first notification being used to indicate that the second communication device has received the first result), receive the first result sent by the first communication device (the first result being used to indicate the first model), send model data of the first model to the first communication device, and receive a third notification sent by the first communication device (the third notification being used to indicate that the first communication device has received the model data of the first model).

[0230] As an example, the communication device 600 is used to perform the above. Figure 6The actions performed by the second communication device in the illustrated embodiment.

[0231] The transceiver unit 601 is configured to receive first information sent by the first communication device, the first information indicating a first function that the first communication device can use, the first function having one or more models, which may be an artificial intelligence module or a machine learning model; send fourth information to the first communication device; receive a second result sent by the first communication device; send a second notification to the first communication device; send model data of the first model to the first communication device; and receive a third notification sent by the first communication device, the third notification indicating that the first communication device has received the model data of the first model.

[0232] It should be understood that the corresponding processes performed by each unit have been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0233] The processing unit 602 in the above embodiments can be implemented by at least one processor or processor-related circuitry. The transceiver unit 601 can be implemented by a transceiver or transceiver-related circuitry. The transceiver unit 601 can also be referred to as a communication unit or communication interface. The storage unit can be implemented by at least one memory.

[0234] By way of example, this application also provides a communication device. Please refer to [link to relevant documentation]. Figure 9 , Figure 9 This is a schematic diagram of a communication device according to an embodiment of this application. The communication device 700 includes a processor 710 coupled to a memory 720. The memory 720 is used to store computer programs or instructions and / or data. The processor 710 is used to execute the computer programs or instructions and / or data stored in the memory 720, so that the methods in the above method embodiments are executed.

[0235] Optionally, the communication device 700 may include one or more processors 710.

[0236] Optionally, such as Figure 9 As shown, the communication device 700 may also include a memory 720.

[0237] Optionally, the communication device 700 may include one or more memory 720s.

[0238] Alternatively, the memory 720 may be integrated with the processor 710 or set separately.

[0239] Optionally, such as Figure 9 As shown, the communication device 700 may further include a transceiver 730 for receiving and / or transmitting signals. For example, a processor 710 is used to control the transceiver 730 to receive and / or transmit signals.

[0240] As one option, the communication device 700 is used to implement the operations performed by the first communication device in the above method embodiments.

[0241] For example, processor 710 is used to implement the processing-related operations performed by the first communication device in the above method embodiment, and transceiver 730 is used to implement the transmission-reception-related operations performed by the first communication device in the above method embodiment.

[0242] As an alternative, the communication device 700 is used to implement the operations performed by the second communication device in the above method embodiments.

[0243] For example, processor 710 is used to implement the processing-related operations performed by the second communication device in the above method embodiment, and transceiver 730 is used to implement the transmission-reception-related operations performed by the second communication device in the above method embodiment.

[0244] The above Figure 9 In the communication device shown, the device in transceiver 730 used for receiving power can be considered a receiving unit, and the device in transceiver 730 used for transmitting can be considered a transmitting unit. That is, transceiver 730 can include a receiver and a transmitter. Transceiver 730 can also be called a transceiver unit, transceiver circuit, etc. Receiver can also be called a receiver, receiving unit, receiver, or receiving circuit, etc. Transmitter can also be called a transmitter, transmitter, transmitting unit, or transmitting circuit, etc. Processor 710 has processing functions and can be called a processing unit. Memory 720 is used to store computer program code and data; memory 720 can also be called a storage unit.

[0245] This application also provides a communication device 800, which may be a first communication device or a second communication device, or a chip of a first communication device or a second communication device. This communication device 800 can be used to perform the operations performed by the first communication device or the second communication device in the above method embodiments.

[0246] Figure 10A schematic diagram of a communication device is shown. The first or second communication device includes sections 810, 820, and 830. Section 810 is mainly used for baseband processing and controlling the base station; section 810 is typically the control center of the base station, often referred to as a processor or processing unit, used to control the first or second communication device to perform processing operations on the first or second communication device side in the above method embodiments. Section 820 is mainly used for storing computer program code and data, and can typically be called a memory or storage unit. Section 830 is mainly used for transmitting and receiving radio frequency signals and converting radio frequency signals to baseband signals; section 830 can typically be called a transceiver unit, transceiver, transceiver circuit, or transceiver. The transceiver unit of section 830, also called a transceiver, includes an antenna 833 and a radio frequency circuit (not shown in the figure), wherein the radio frequency circuit is mainly used for radio frequency processing. Optionally, the device used to implement the receiving function in part 830 can be regarded as a receiver, and the device used to implement the transmitting function can be regarded as a transmitter. That is, part 830 includes receiver 832 and transmitter 831. The receiver can also be called a receiving unit, receiver, or receiving circuit, etc., and the transmitter can be called a transmitting unit, transmitting unit, transmitter, or transmitting circuit, etc.

[0247] Sections 810 and 820 may include one or more circuit boards, each of which may include one or more processors and one or more memories. The processors are used to read and execute programs from the memories to implement baseband processing functions and control the base station. If multiple circuit boards exist, they can be interconnected to enhance processing capabilities. As an alternative implementation, multiple circuit boards may share one or more processors, multiple circuit boards may share one or more memories, or multiple circuit boards may simultaneously share one or more processors.

[0248] In one implementation, the transceiver unit of section 830 is used to perform... Figures 2 to 6 The transmit / receive related processes are performed by the first or second communication device in the illustrated embodiment. The processor in section 810 is used to execute... Figures 2 to 6 The process related to the processing performed by the first communication device or the second communication device in the illustrated embodiment.

[0249] It should be understood that Figure 10 This is merely an example and not a limitation; the second communication device described above, including the processor, memory, and transceiver, may be independent of... Figure 10 The structure shown.

[0250] When the communication device 800 is a chip, the chip includes a transceiver, a memory, and a processor. The transceiver can be an input / output circuit or a communication interface; the processor is a processor, microprocessor, or integrated circuit integrated on the chip. In the above method embodiments, the transmitting operation of the first or second communication device can be understood as the chip's output, and the receiving operation of the first or second communication device in the above method embodiments can be understood as the chip's input.

[0251] For example, this application provides a communication device, including: a processor; the processor is configured to execute a computer-executable program or instructions in a memory, causing the communication device to perform the methods described in the preceding embodiments.

[0252] For example, this application provides a chip, including: an interface circuit and a logic circuit. The interface circuit is used to receive signals from other chips outside the chip and transmit them to the logic circuit, or to send signals from the logic circuit to other chips outside the chip. The logic circuit is used to implement the methods in the above embodiments.

[0253] For example, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, causes an electronic device to implement the methods described in the preceding embodiments.

[0254] For example, this application provides a computer program product, including: execution instructions stored in a readable storage medium, at least one processor of an electronic device can read the execution instructions from the readable storage medium, and the at least one processor executes the execution instructions to cause the electronic device to implement the method in the foregoing embodiments.

[0255] In the above embodiments, all or part of the functionality can be implemented by software, hardware, or a combination of software and hardware. When implemented using software, it can be implemented wholly or partially in the form of a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0256] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A communication method, characterized in that, The method includes: A first communication device sends first information to a second communication device. The first information is used to indicate a first function that the first communication device can use. The first function has one or more models, which are artificial intelligence models or machine learning models. The first function is used by the first communication device to support a first service related to the first function. The first information includes the model ID and function ID of the one or more models that the first communication device can use and support the first service. The first communication device sends second information to the second communication device, the second information being used to indicate the expected performance indicators of the first service supported by the first communication device; The first communication device receives model data of a first model sent by the second communication device. The first model is determined by the second communication device based on the first information, or the first information and the second information. The first model is a model that the first communication device can use and supports the first service. The model data of the first model is used by the first communication device to activate and run the first model when using the first function related to the first model, so as to provide the first service related to the first function. The model data of the first model includes auxiliary information of the first model, which includes at least the model ID of the first model, the hardware and software requirements supporting the operation of the first model, the performance information of the first model, and the external environment requirements for the normal operation of the first model. Alternatively, the model data of the first model includes the model structure and / or model parameters of the first model. The first communication device receives third information sent by the second communication device. The third information is determined by the second communication device based on the first information. The third information is used to indicate the model data of all models. The all models include models that the first communication device can use, or models that the first communication device can use and that meet the expected performance indicators. The first communication device determines the first model based on the third information; The first communication device sends a first result to the second communication device, the first result being used to indicate the first model.

2. The method according to claim 1, characterized in that, The method further includes: The first communication device receives fourth information sent by the second communication device. The fourth information is determined by the second communication device based on the first information. The fourth information includes auxiliary information indicating all models. The all models include models that the first communication device can use, or models that the first communication device can use and that meet the expected performance indicators. The first communication device determines the auxiliary information of the first model based on the fourth information; The first communication device sends a second result to the second communication device, the second result being used to indicate auxiliary information for the first model.

3. A communication method, characterized in that, The method includes: The second communication device receives first information from the first communication device. The first information is used to indicate a first function that the first communication device can use. The first function has one or more models, which are artificial intelligence models or machine learning models. The first function is used by the first communication device to support a first service related to the first function. The first information includes the model ID and function ID of the one or more models that the first communication device can use and support the first service. The second communication device receives second information, which is used to indicate the expected performance indicators of the first service supported by the first communication device; The second communication device sends model data of a first model to the first communication device. The first model is determined by the second communication device based on the first information, or the first information and the second information. The first model is a model that the first communication device can use and supports the first service. The model data of the first model is used by the first communication device to activate and run the first model when using the first function related to the first model, so as to provide the first service related to the first function. The model data of the first model includes auxiliary information of the first model, which includes at least the model ID of the first model, the hardware and software requirements supporting the operation of the first model, the performance information of the first model, and the external environment requirements for the normal operation of the first model. Alternatively, the model data of the first model includes the model structure and / or model parameters of the first model. The second communication device sends third information to the first communication device. The third information is determined by the second communication device based on the first information. The third information is used to indicate the model data of all models. The all models include models that the first communication device can use, or models that the first communication device can use and that meet the expected performance indicators. The second communication device receives a first result sent by the first communication device, and the first result is used to indicate the first model.

4. The method according to claim 3, characterized in that, The method further includes: The second communication device sends a fourth message to the first communication device. The fourth message is determined by the second communication device based on the first message. The fourth message includes auxiliary information indicating all models. The all models include models that the first communication device can use, or models that the first communication device can use and that meet the expected performance indicators. The second communication device receives a second result from the first communication device, the second result being used to indicate auxiliary information for the first model.

5. A communication device, characterized in that, It includes a module for performing the method as described in claim 1 or 2; or a module for performing the method as described in claim 3 or 4.

6. A communication device, characterized in that, include: processor; The processor is configured to execute a computer-executable program or instructions in memory, causing the communication device to perform the method of claim 1 or 2; or, causing the communication device to perform the method of claim 3 or 4.

7. A communication system, characterized in that, The communication system includes: a communication device for performing the method as claimed in claim 1 or 2, and a communication device for performing the method as claimed in claim 3 or 4.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer-executable program or instructions configured to perform the method of claim 1 or 2; or, the computer-executable program or instructions are configured to perform the method of claim 3 or 4.

9. A chip, characterized in that, include: An interface circuit and a logic circuit, wherein the interface circuit is used to receive signals from other chips outside the chip and transmit them to the logic circuit, or to send signals from the logic circuit to other chips outside the chip, and the logic circuit is used to implement the method as described in claim 1 or 2; or, the logic circuit is used to implement the method as described in claim 3 or 4.

Citation Information

Patent Citations

  • Machine learning model parameter transmission method and device

    CN113570062A

  • Model distribution method and device

    CN115250485A