Communication method and device, equipment, storage medium and program product

Abstract

The invention discloses a communication method and device, equipment, a storage medium and a program product, and relates to the technical field of communication. The method comprises: a first device sending a first message to a second device, the first message comprising application model information related to a third device (320); according to the method, interaction of the application model information between the devices is realized, on one hand, synchronization of the application model information between the devices is facilitated, and on the other hand, a control process associated with the application model information can be triggered based on the synchronized application model information, so that management and application of the application model in a communication system are realized, and the performance of the communication system is improved.

Description

Communication method, device, equipment, storage medium and program product Technical Field

[0001] The embodiments of the present application relate to the field of communication technology, and in particular to a communication method, apparatus, device, storage medium, and program product. Background Art

[0002] In recent years, artificial intelligence research and related achievements have achieved remarkable results in many fields. Artificial intelligence has become a new approach for people to solve and address problems. Among these numerous studies, neural network-based artificial intelligence research is an extremely important category. The basic structure of a simple neural network consists of an input layer, hidden layers, and an output layer, as shown in Figure 1. The input layer receives data, the hidden layers process the data, and the output layer produces the final result.

[0003] From a protocol perspective, current communications systems haven't explicitly incorporated AI-related control processes. The application of AI in communications systems largely remains at the algorithm implementation level, for example, leveraging AI (Artificial Intelligence) / ML (Machine Learning) algorithms for network device resource scheduling and management. In other words, AI currently impacts communications systems through algorithmic implementation.

[0004] The use of AI / ML models in communication systems has become a trend. More and more research results show that the application of AI / ML models can optimize specific communication functions. As a large number of different types of AI / ML models are applied to communication systems, how to manage information related to AI / ML models has become an urgent problem that needs to be solved.

[0005] Summary of the Invention

[0006] The embodiments of the present application provide a communication method, apparatus, device, storage medium, and program product. The technical solution is as follows:

[0007] According to one aspect of an embodiment of the present application, a communication method is provided, the method comprising:

[0008] The first device sends a first message to the second device, where the first message includes application model information related to the third device.

[0009] According to one aspect of an embodiment of the present application, a communication method is provided, the method comprising:

[0010] The second device receives a first message sent by the first device, where the first message includes application model information related to the third device.

[0011] According to one aspect of an embodiment of the present application, a communication apparatus is provided, where the apparatus is provided in a first device, and includes:

[0012] A sending module is used to send a first message to the second device, where the first message includes application model information related to the third device.

[0013] According to one aspect of an embodiment of the present application, a communication apparatus is provided, where the apparatus is provided in a second device, and includes:

[0014] The receiving module is used to receive a first message sent by the first device, where the first message includes application model information related to the third device.

[0015] According to one aspect of an embodiment of the present application, a communication device is provided, comprising a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program to implement the communication method performed by the above-mentioned first device or second device.

[0016] According to one aspect of an embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored. The computer program is used to be executed by a processor to implement the communication method performed by the above-mentioned first device or second device.

[0017] According to one aspect of an embodiment of the present application, a chip is provided, which includes a programmable logic circuit and / or program instructions. When the chip is running, it is used to implement the communication method executed by the above-mentioned first device or second device.

[0018] According to one aspect of an embodiment of the present application, a computer program product is provided, which includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor reads and executes the computer instructions from the computer-readable storage medium to implement the communication method performed by the above-mentioned first device or second device.

[0019] The technical solutions provided by the embodiments of the present application include at least the following beneficial effects:

[0020] A first message is sent to a second device through a first device, and the first message includes application model information related to a third device, thereby realizing the interaction of application model information between devices. On the one hand, it helps to synchronize application model information between devices. On the other hand, the synchronized application model information can trigger a control process associated with application model information, thereby realizing the management and application of application models in the communication system and improving the performance of the communication system. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] FIG1 is a schematic diagram of a basic structure of a neural network provided by related art;

[0022] FIG2 is a schematic diagram of a network architecture provided by an embodiment of the present application;

[0023] FIG3 is a flow chart of a communication method provided by an embodiment of the present application;

[0024] FIG4 is a flow chart of a communication method provided by another embodiment of the present application;

[0025] FIG5 is a block diagram of a communication device provided by an embodiment of the present application;

[0026] FIG6 is a block diagram of a communication device provided by another embodiment of the present application;

[0027] FIG7 is a schematic structural diagram of a communication device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0029] The network architecture and business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. A person skilled in the art will appreciate that, with the evolution of the network architecture and the emergence of new business scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

[0030] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as: Global System of Mobile communication (GSM) system, Code Division Multiple Access (CDMA) system, Wideband Code Division Multiple Access (WCDMA) system, General Packet Radio Service (GPRS), Long Term Evolution (LTE) system, Advanced long term evolution (LTE-A) system, New Radio (NR) system, NR system evolution system, LTE-based access to unlicensed spectrum (LTE-U) system on unlicensed spectrum, NR-based access to unlicensed spectrum (NR-U) system on unlicensed spectrum, Non-Terrestrial Networks (NTN) system, Universal Mobile Telecommunication System (UMTS), Wireless Local Area Networks (WLAN), Wireless Fidelity (WiFi), fifth-generation communication system or other communication systems, etc.

[0031] Generally speaking, traditional communication systems support a limited number of connections and are easy to implement. However, with the development of communication technology, mobile communication systems will not only support traditional communications, but will also support, for example, device-to-device (D2D) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), vehicle-to-vehicle (V2V) communication, or vehicle-to-everything (V2X) communication, etc. The embodiments of the present application can also be applied to these communication systems.

[0032] The communication system in the embodiment of the present application can be applied to a carrier aggregation (CA) scenario, a dual connectivity (DC) scenario, and a standalone (SA) networking scenario.

[0033] The communication system in the embodiment of the present application can be applied to an unlicensed spectrum, where the unlicensed spectrum can also be considered as a shared spectrum; or, the communication system in the embodiment of the present application can also be applied to an authorized spectrum, where the authorized spectrum can also be considered as an unshared spectrum.

[0034] The embodiments of the present application can be applied to non-terrestrial networks (NTN) systems, and can also be applied to terrestrial networks (TN) systems.

[0035] Please refer to Figure 2, which shows a schematic diagram of a network architecture provided by an embodiment of the present application. The network architecture may include: a terminal device 10, an access network device 20, and a core network device 30.

[0036] The terminal device 10 may refer to a UE (User Equipment), an access terminal, a subscriber unit, a subscriber station, a mobile station, a mobile station, a remote station, a remote terminal, a mobile device, a wireless communication device, a user agent, or a user apparatus. In some embodiments, the terminal device 10 may also be a cellular phone, a cordless phone, a SIP phone, a WLL (Wireless Local Loop) station, a PDA (Personal Digital Assistant), a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, an in-vehicle device, a wearable device, a terminal device in a 5GS, or a terminal device in a future evolved PLMN (Public Land Mobile Network), etc., which is not limited in the embodiments of the present application. For ease of description, the devices mentioned above are collectively referred to as terminal devices. The number of terminal devices 10 is generally multiple, and one or more terminal devices 10 may be distributed in each cell managed by an access network device 20. In the embodiments of the present application, "terminal device" and "UE" are often used interchangeably, but those skilled in the art will understand their meanings.

[0037] Access network equipment 20 is a device deployed in an access network to provide wireless communication capabilities for terminal devices 10. Access network equipment 20 may include various forms of macro base stations, micro base stations, relay stations, access points, and the like. In systems employing different wireless access technologies, the names of devices that provide access network equipment functions may vary. For example, in 5G NR systems, they are referred to as gNodeBs or gNBs. As communication technologies evolve, the term "access network equipment" may change. For ease of description, in the embodiments of this application, the aforementioned devices that provide wireless communication capabilities for terminal devices 10 are collectively referred to as access network equipment. In some embodiments, access network equipment 20 enables communication between terminal devices 10 and core network equipment 30. For example, in an LTE (Long Term Evolution) system, access network equipment 20 may be an Evolved Universal Terrestrial Radio Access Network (EUTRAN) or one or more eNodeBs within EUTRAN. In a 5G NR system, access network equipment 20 may be a Radio Access Network (RAN) or one or more gNBs within the RAN.

[0038] The core network device 30 is a network element or device deployed in the core network. The function of the core network device 30 is mainly to provide user connection, user management, and service bearer, and to provide an interface to the external network as a bearer network. For example, the core network device in the 5G NR system may include network elements such as AMF (Access and Mobility Management Function), UPF (User Plane Function), and SMF (Session Management Function). In addition, the core network device can be regarded as a functional entity, and one or more core network devices can be deployed on a physical device.

[0039] In some embodiments, the access network device 20 and the core network device 30 communicate with each other via an air interface technology, such as the NG interface in the 5G NR system. The access network device 20 and the terminal device 10 communicate with each other via an air interface technology, such as the Uu interface.

[0040] The "5G NR system" in the embodiments of this application may also be referred to as a 5G system or an NR system, but those skilled in the art will understand its meaning. The technical solutions described in the embodiments of this application can be applied to LTE systems, 5G NR systems, subsequent evolution systems of 5G NR systems, and other communication systems such as NB-IoT (Narrow Band Internet of Things) systems, and this application does not limit this.

[0041] In an embodiment of the present application, the access network device can provide services for the cell, and the terminal device communicates with the access network device through the transmission resources (for example, frequency domain resources, or spectrum resources) on the carrier used by the cell. The cell can be a cell corresponding to the access network device (for example, a base station). The cell can belong to a macro base station or a base station corresponding to a small cell. The small cells here may include: metro cell, micro cell, pico cell, femto cell, etc. These small cells have the characteristics of small coverage and low transmission power, and are suitable for providing high-speed data transmission services.

[0042] Please refer to Figure 3, which shows a flow chart of a communication method provided by an embodiment of the present application. The method can be applied to the network architecture shown in Figure 1. The method may include the following step 320:

[0043] Step 320: The first device sends a first message to the second device, where the first message includes application model information related to the third device.

[0044] Correspondingly, the second device receives the first message sent by the first device.

[0045] In some embodiments, the application model includes, but is not limited to, at least one of the following: an AI model, an ML model, a supercomputing model, a neuron-like model, an authentication model, an encryption and decryption model, and a self-optimization model. Of course, the above examples of application models are merely exemplary and explanatory, and this application is not limited to other types of application models.

[0046] In some embodiments, the application model information includes but is not limited to at least one of the following information 1-6:

[0047] Information 1. Identification information of at least one application model supported by the third device.

[0048] The application model supported by the third device may refer to the application model that the third device is capable of running and / or using. The identification information of the application model is used to distinguish and identify different application models. For example, the identification information of the application model may be information such as the ID (Identifier), serial number, name, etc. of the application model, which is not limited in this application.

[0049] In one possible implementation, the identification information of the at least one application model supported by the third device includes only the identification information of at least one application model supported by the third device and for which no corresponding model data is stored. For example, if the application models supported by the third device include Model A, Model B, and Model C, and the third device stores model data for Model A but does not store model data for Models B and C, then the identification information of the at least one application model supported by the third device may include only the identification information of Models B and C, but not the identification information of Model A.

[0050] In another possible implementation, the identification information of at least one application model supported by the third device does not distinguish whether the third device stores the corresponding model data. As long as the third device is capable of supporting the application model to be run and / or used, it can carry the identification information of the application model. That is, the identification information of at least one application model supported by the third device includes the identification information of at least one application model that the third device supports and stores the corresponding model data, and includes the identification information of at least one application model that the third device supports and does not store the corresponding model data. For example, the application models supported by the third device include model A, model B, and model C. Regardless of whether the third device stores the corresponding model data, the identification information of at least one application model supported by the third device includes the identification information of model A, model B, and model C.

[0051] Information 2: The third device stores identification information of at least one application model corresponding to the model data.

[0052] The third device stores an application model with corresponding model data, which means that the third device has obtained the model data of the application model, and the application model can be run and / or used in the third device at any time.

[0053] In the embodiments of the present application, the method by which the third device obtains the model data of the application model is not limited, and includes but is not limited to at least one of the following: downloading through a third-party platform, downloading through a network device in the communication system, obtaining through local training of a third device, and forwarding through other devices. Among them, the third-party platform includes but is not limited to at least one of the following: various websites, platform servers, applications, etc. The network devices in the communication system include but are not limited to at least one of the following: access network devices, core network devices, application model management and control devices, and OAM (Operation Administration and Maintenance) devices.

[0054] In one implementation, the above-mentioned information 1 and information 2 are independently defined and reported separately, that is, information 1 or information 2 can be reported separately, and the type of reported data is identification information of the application model. For example, in order to avoid repeated reporting of the same application model identification information, it can be agreed that information 1 only contains identification information of at least one application model supported by the third device and for which corresponding model data is not stored; and information 2 only contains identification information of at least one application model supported by the third device and for which corresponding model data is stored. Of course, this application does not exclude another possible implementation of information 1. Please refer to the above-mentioned description of information 1 for details, which will not be repeated here.

[0055] In another implementation method, information 2 is implemented through information 1 and associated indication information, that is, the identification information of each application model or the identification information of each group of application models contained in information 1 is associated with an indication information, and the indication information is used to indicate whether the model data corresponding to the associated one or a group of application models has been saved by the first device.

[0056] Information 3: The third device does not store identification information of at least one application model corresponding to the model data.

[0057] The third device does not store an application model with corresponding model data, which means that the third device has not yet obtained the model data of the application model, and the application model cannot be run and / or used in the third device.

[0058] In one implementation, the above-mentioned information 1 and information 3 are independently defined and reported separately, that is, information 1 or information 3 can be reported separately, and the type of reported data is identification information of the application model. For example, in order to avoid repeated reporting of the same application model identification information, it can be agreed that information 1 only contains identification information of at least one application model supported by the third device and storing corresponding model data; and information 3 only contains identification information of at least one application model supported by the third device and not storing corresponding model data. Of course, this application does not exclude another possible implementation of information 1. Please refer to the above-mentioned information 1 for details and will not be repeated here.

[0059] In another implementation method, information 3 is implemented through information 1 and associated indication information, that is, the identification information of each application model or the identification information of each group of application models contained in information 1 is associated with an indication information, and the indication information is used to indicate whether the model data corresponding to the associated one or a group of application models has been saved by the first device.

[0060] Information 4. The third device stores usage instruction information of at least one application model corresponding to the model data.

[0061] The usage description information of the application model is used to restrict how the application model is used. For a detailed description of the usage description information, please refer to the following embodiment.

[0062] Information 5. Identification information of at least one application model activated and used by the third device.

[0063] Information 6. The third device stores activation indication information of at least one application model corresponding to the model data. The activation indication information of the application model is used to indicate whether the application model is activated for use.

[0064] There are two ways to inform other devices (such as the second device) that at least one application model in which the third device stores corresponding model data is in an activated state (referred to as "activated state") or an inactivated state (referred to as "inactivated state"): First, through an independent parameter, that is, as in the above-mentioned information 5, the application model information includes the identification information of at least one application model that has been activated and used by the third device. Compared with the corresponding parameters of the above-mentioned information 2, although information 5 and information 2 both contain the identification information of the application model, the meanings expressed by different parameters are different; second, through the corresponding parameter extension of information 2, for example, an activation indication information is associated with the identification information of each application model contained in information 2, that is, as in the information 6 here, the activation indication information is used to indicate whether the application model corresponding to the identification information is in an activated state. For example, the activation indication information value of "1" indicates that the associated application model is in an activated state, and the activation indication information value of "0" indicates that the associated application model is in an inactivated state. Of course, in some other embodiments, the meaning of the activation indication information value may also be opposite, and this application does not limit this.

[0065] In some embodiments, the application model information includes the above-mentioned information 1, information 2 and information 6. At this time, the following implementation method can be used to simplify the signaling overhead while retaining the functions of information 1, information 2 and information 6, namely: to associate an indication information with the identification information of each application model contained in information 1 (in order to distinguish it from the indication information appearing elsewhere in this application, it is recorded here as "joint indication information"), and the joint indication information is used to indicate whether the application model corresponding to the identification information stores the corresponding model data and whether it is in an activated state. For example, the joint indication information occupies at least two bits, and the value meaning is, for example: "11" indicates that the third device stores the model data corresponding to the application model and the application model has been activated for use by the third device, "10" indicates that the third device stores the model data corresponding to the application model and the application model has not been activated for use by the third device, and "01" indicates that the third device does not store the model data corresponding to the application model, that is, the third device only supports the operation and / or use of the application model in terms of capability, and does not actually obtain the model data of the application model. Of course, this application does not limit the correspondence between the value of the joint indication information and the specific meaning. The above example is just one implementation method. This joint reporting method of the identification information of the application model and the joint indication information can simplify the signaling overhead required for the first device to send the application model information.

[0066] In some embodiments, the usage instructions of the application model include but are not limited to at least one of the following information 4-1 to 4-7:

[0067] Information 4-1. Function information of the application model, used to indicate the functions associated with the application model.

[0068] Exemplarily, the functions associated with the application model include but are not limited to at least one of the following: application to terminal device connection state mobility, application to terminal device beam management, application to terminal device positioning function, and the like.

[0069] Information 4-2: Scenario information of the application model, used to indicate the scenario associated with the application model.

[0070] For example, the scenarios associated with the application model for the terminal device's positioning function may include at least one of the following: line-of-sight scenario, non-line-of-sight scenario, and mixed scenario; the scenarios associated with the application model for the terminal device's connected mobility function may include at least one of the following: FR1 (Frequency Range 1) scenario, FR2-1 scenario, and FR2-2 scenario. Furthermore, the subdivided scenarios corresponding to different functions generally differ, and this application does not limit this.

[0071] Information 4-3: Application model usage scope control information, used to indicate the usage scope of the application model.

[0072] Exemplarily, the scope of use of the application model is limited by geographic area coordinates. If the current geographic coordinates of the terminal device fall within the limited range of the geographic area coordinates associated with the corresponding application model, the application model is considered valid; otherwise, the application model is considered invalid or cannot be activated for use.

[0073] Exemplarily, the scope of use of the application model is limited by a logical identifier. If the area identifier assigned to the network device where the terminal device is currently located falls within the limited range of the logical identifier associated with the application model, the application model is considered valid; otherwise, the application model is considered invalid or cannot be activated for use. Commonly used logical identifiers include, but are not limited to: TA (Tracking Area) identifier, RANAC (Radio Access Network Area Code), cell identifier, PLMN (Public Land Mobile Network) identifier, frequency point identifier, frequency band identifier, etc., and this application does not limit this.

[0074] Information 4-4. A set of input information of the application model, used to indicate the type and / or quantity of input information of the application model.

[0075] The type and / or quantity of input information for each application model may be the same or different.

[0076] Information 4-5. Output information set of the application model, used to indicate the type and / or quantity of output information of the application model.

[0077] The type and / or quantity of output information of each application model may be the same or different.

[0078] Information 4-6. Input processing information of the application model, used to indicate the pre-processing method of the input information of the application model.

[0079] After obtaining input information for an application model, users of the application model may need to preprocess this input information before entering it into the application model for inference. Because the input information may come from different sources and have different formats, it must be converted to a unified format before entering the application model. Alternatively, the format of the input information may differ from the format defined by the application model itself, requiring preprocessing. For example, if the application model requires a 4x4 matrix as input, but the collected data is a 3x3 matrix, preprocessing can convert this 3x3 matrix into the 4x4 matrix required by the application model.

[0080] Information 4-7. Output processing information of the application model, used to indicate the post-processing method of the output information of the application model.

[0081] The output information of the application model is post-processed. This may be because the format of the output information of the application model is different from the information format requirements of the user of the output information, and the output information needs to be format converted.

[0082] Optionally, the association relationship between the usage description information of the application model and the application model is one-to-one or one-to-many, wherein one-to-many indicates that multiple application models correspond to the same usage description information.

[0083] In some embodiments, as shown in FIG4 , the above step 320 may further include the following step 310:

[0084] Step 310: The second device sends a second message to the first device, where the second message is used to trigger the first device to send the first message.

[0085] Correspondingly, the first device receives the second message sent by the second device.

[0086] The first device sends a first message to the second device. After receiving the second message sent by the second device, the first device may be triggered to send the first message to the second device. Alternatively, step 310 may be omitted, and the first device may independently decide when to send the first message to the second device. That is, step 310 is optional and this application does not limit it.

[0087] The technical solution provided in this embodiment sends a first message to a second device through a first device. The first message includes application model information related to a third device, thereby realizing the interaction of application model information between devices. On the one hand, it helps to synchronize application model information between devices. On the other hand, the synchronized application model information can trigger the control process of application model information association, thereby realizing the management and application of application models in the communication system and improving the performance of the communication system.

[0088] In some embodiments, the first device is a first terminal device, and the second device is a network device or a second terminal device; wherein the first terminal device and the second terminal device are different terminal devices.

[0089] Exemplarily, the first device is a first terminal device, the second device is a second terminal device, and the first terminal device sends a first message to the second terminal device, where the first message includes application model information related to the third device. Exemplarily, the third device is a first terminal device, and the first terminal device sends a first message to the second terminal device, where the first message includes application model information related to the first terminal device. In this way, the first terminal device can provide its own related application model information to at least one second terminal device, so that the second terminal device can know the application model information related to the first terminal device. Of course, in some other embodiments, the third device may not be the first terminal device. For example, the third device may be the second terminal device, or other terminal device other than the first terminal device and the second terminal device.

[0090] Exemplarily, the first device is a first terminal device, the second device is a network device, and the first terminal device sends a first message to the network device, where the first message includes application model information related to the third device. Exemplarily, the third device is a first terminal device, and the first terminal device sends a first message to the network device, where the first message includes application model information related to the first terminal device. Exemplarily, the network device is at least one of the following: an access network device, a core network device, an application model management and control device, and an OAM device. In this way, the first terminal device can provide its own related application model information to at least one network device, so that the network device can know the application model information related to the first terminal device. Of course, in some other embodiments, the third device may not be the first terminal device. For example, the third device may be a terminal device other than the first terminal device.

[0091] In some embodiments, the first device is a first network device, and the second device is a second network device or a terminal device; wherein the first network device and the second network device are different network devices.

[0092] Exemplarily, the first device is a first network device, and the second device is a second network device. The first network device sends a first message to the second network device, where the first message includes application model information related to the third device. Exemplarily, the third device is a first terminal device, and the first network device sends a first message to the second network device, where the first message includes application model information related to the first terminal device. In this way, application model information related to terminal devices can be exchanged between different network devices.

[0093] Exemplarily, the first device is a first network device, the second device is a terminal device, and the first network device sends a first message to the terminal device, where the first message includes application model information related to the third device. Exemplarily, the third device is a first terminal device, the second device is a second terminal device, and the first terminal device and the second terminal device are different terminal devices. The first network device sends a first message to the second terminal device, where the first message includes application model information related to the first terminal device. In this way, the first network device can provide the application model information related to the first terminal device to at least one other terminal device other than the first terminal device. Of course, in some other embodiments, the second device and the third device can also be the same first terminal device. For example, the first network device can send the application model information related to the first terminal device to the first terminal device through the first message.

[0094] Exemplarily, the first network device is at least one of the following: an access network device, a core network device, an application model management and control device, and an OAM device. The second network device is at least one of the following: an access network device, a core network device, an application model management and control device, and an OAM device. The first network device and the second network device can be network devices of the same type, such as an access network device, or a core network device, or an application model management and control device, or an OAM device. The first network device and the second network device can also be network devices of different types, such as the first network device is an access network device and the second network device is a core network device, or the first network device is a core network device and the second network device is an access network device, and so on. This application does not give examples one by one.

[0095] In addition, there are two possible implementation methods for the interaction messages between the first device and the second device (such as the first message and / or second message introduced above): first, the first device and the second device directly interact with each other, that is, there is no need for message relaying through other devices. For example, typical scenarios for direct interaction messages include direct communication between the access network device and the terminal device, or direct communication between the first terminal device and the second terminal device; second, the first device and the second device indirectly interact with each other, that is, there is a need for message relaying through other devices. For example, typical scenarios for indirect interaction messages include indirect communication between the core network device (or application model management and control device or OAM device) and the terminal device through the access network device, or indirect communication between the first terminal device and the second terminal device through at least one third terminal device (communication through one third terminal device represents single-hop indirect communication, and communication through two or more third terminal devices represents multi-hop indirect communication). This application does not limit the message interaction method between the first device and the second device.

[0096] The technical solution provided by this embodiment provides a solution for exchanging application model information related to a certain device (such as a certain terminal device) in a variety of different scenarios. For example, by exchanging application model information related to a terminal device between devices (such as between terminal devices and terminal devices, between terminal devices and network devices, between network devices and network devices, etc.), other devices (such as other terminal devices or network devices) can keep track of the following situations of the terminal device at any time: which application model capabilities are supported but the corresponding model data has not been obtained, which application models have obtained the corresponding model data, which application models have not only obtained the corresponding model data but have also been activated for use, etc. With the above information, other terminal devices or network devices will not transmit duplicate model data to the terminal device, and can also activate or deactivate the model data saved by the terminal device as needed, and can also adjust their own configuration or resources when the application model is activated or deactivated, thereby improving the operating efficiency of the communication system.

[0097] Exemplarily, the technical solution provided by this embodiment can solve the following problems: First, it avoids the terminal device from repeatedly obtaining the same application model after moving across cells or regions, because other terminal devices or network devices obtain the application model information related to the terminal device, which clearly indicates which application models the terminal device has saved the model data of; Second, it ensures the consistency of the understanding of the activation status of a specific application model between the terminal device and the network device or other terminal devices. On the one hand, it avoids the misunderstanding caused by one party using a certain application model and the other party not using the application model (for example, in the CSI compression feedback scenario, only one side using the AI / ML model may lead to poor performance or even reception errors on the other end); on the other hand, it avoids the situation where one party uses a certain application model and the other party does not cooperate in configuring the corresponding resources (for example, in the beam management process, the terminal device side deploys and activates the AI / ML model, and the network device side may need to send a specific beam pattern to enable the AI / ML model activated by the terminal device to achieve the best use effect).

[0098] Below, taking the first device as the first network device, the second device as the second network device, and the third device as the first terminal device as an example, several typical scenarios for transmitting application model information related to terminal devices between network devices are introduced and explained.

[0099] Scenario 1: A core network device sends application model information related to a first terminal device to an access network device. Specifically, the first network device is a core network device, and the second network device is an access network device. The core network device sends a first message to the access network device, including the application model information related to the first terminal device.

[0100] Exemplarily, the access network device does not always maintain the context information of the terminal device (such as the first terminal device) (the context information of the terminal device contains more information, such as: configuration information, capability information, other auxiliary information for assisting the network device to manage the terminal device, etc., and the application model information can be regarded as a type of auxiliary information that assists the network device to manage the terminal device). For example, after the terminal device returns to the idle state, the access network device will usually delete the access network context information of the terminal device. In order to allow the access network device to use the application model information related to the terminal device to manage the terminal device when the terminal device is in the connected state again, the core network device can provide the application model information related to the terminal device to the access network device. Of course, the process of the core network device transmitting the application model information related to the terminal device to the access network device may be triggered by the core network device or may be triggered by the access network device requesting the core network device. In addition, the access network device directly obtains the application model information from the terminal device through the above-mentioned first message, which is another implementation method, and this application does not limit it.

[0101] Scenario 2: The source core network device sends application model information related to the first terminal device to the target core network device. Specifically, the first network device is the source core network device, the second network device is the target core network device, and the source core network device sends a first message to the target core network device, the first message including the application model information related to the first terminal device.

[0102] For example, as a terminal device (such as a first terminal device) moves, the access network device and / or core network device providing services for the terminal device may change. Changing the service network of the terminal device is usually achieved through a re-registration process or a cell switching process. In order to allow the target core network device to manage the terminal device based on the application model information related to the terminal device, the source core network device can provide the target core network device with the application model information related to the terminal device. The transmission process may be triggered by the source core network device or may be triggered by the target core network device requesting the source core network device.

[0103] Scenario 3: The access network device sends application model information related to the first terminal device to the core network device. That is, the first network device is the access network device, the second network device is the core network device, and the access network device sends a first message to the core network device, where the first message includes the application model information related to the first terminal device.

[0104] For example, after a terminal device (such as a first terminal device) returns to an idle state, the access network device will typically delete the context information of the terminal device stored on the corresponding access network side. In order to save the application model information related to the terminal device, the access network device may provide the application model information related to the terminal device to the core network device before releasing the access network context information of the corresponding terminal device. In this way, even if the terminal device returns to an idle state, the context information of the terminal device at the core network device will still be normally saved and maintained by the core network device. After receiving the application model information related to the terminal device sent by the access network device, the core network device may save the information as part of the core network context information of the terminal device. When the access network device is ready to establish access network context information for the corresponding terminal device again (for example, the terminal device enters a connected state again), the core network device may also transmit the information back to the access network device, so that the access network device can continue to use the information to manage the corresponding terminal device. Of course, the core network device may also use the application model information related to the terminal device sent by the access network device for its own use. The process of the access network device transmitting the application model information related to the terminal device to the core network device may be triggered by the access network device or may be triggered by the core network device requesting the access network device.

[0105] Scenario 4: The source access network device sends application model information related to the first terminal device to the target access network device. Specifically, the first network device is the source access network device, the second network device is the target access network device, and the source access network device sends a first message to the target access network device, the first message including the application model information related to the first terminal device.

[0106] For example, as a terminal device (such as a first terminal device) moves, the access network device providing services for the terminal device may change. Changing the service access network of the terminal device is typically achieved through a cell handover process. During the handover process, the source access network device may provide the target access network device with application model information related to the terminal device so that the target access network device can use this information to manage the corresponding terminal device after the handover. The information transfer process may be triggered by the source access network device or by the target access network device requesting the source access network device.

[0107] The above scenarios 1 to 4 exemplify several scenarios for transmitting application model information related to terminal devices between network devices, but this is only exemplary and explanatory. This application does not limit it and may also include other scenarios, such as: between access network devices and application model management and control devices, between access network devices and OAM devices, between core network devices and application model management and control devices, between core network devices and OAM devices, between application model management and control devices and OAM devices, between application model management and control devices and application model management and control devices, between OAM devices and OAM devices, and so on.

[0108] The following describes how to activate and deactivate the application model.

[0109] In some embodiments, the first device activates and / or deactivates the application model storing the corresponding model data based on the first preset condition.

[0110] Model activation or deactivation can occur between network devices, i.e., one network device activates an application model deployed by another network device; it can also occur between a network device and a terminal device, i.e., a network device activates an application model deployed by a terminal device; or it can occur between terminal devices, i.e., one terminal device activates an application model deployed by another terminal device. In either case, the application model can be activated and / or deactivated based on the following first preset condition.

[0111] In some embodiments, the first preset condition includes but is not limited to at least one of the following conditions 1 to 5:

[0112] Condition 1: When the source device of the application model provides the model data of the application model to the first device, the source device indicates to the first device whether the application model is activated.

[0113] When a source device provides an application model to a first device, it specifies whether the application model needs to be activated. The source device of the application model refers to the provider of the application model. Exemplarily, the source device of the application model is a network device or a terminal device. For example, in the case where the application model is provided to the first device, the source device of the application model can be a device other than the first device, and the other device can be a network device or a terminal device.

[0114] Optionally, a non-first device may subsequently manage the application model stored on the first device through an activation instruction for the application model or a deactivation instruction for the application model. The non-first device is the source device of the application model, or is a device other than the source device of the application model and the first device. Exemplarily, the non-first device is a network device or a terminal device.

[0115] Condition 2: When the source device of the application model provides the model data of the application model to the first device, the default application model is in an inactive state or the default application model is in an active state.

[0116] When the source device provides the application model to the first device, the application model is in an inactive state by default, or the application model is in an active state by default. For an introduction to the source device, please refer to the above and will not be repeated here or below.

[0117] Optionally, the non-first device can subsequently manage the application model stored in the first device through an activation instruction of the application model or a deactivation instruction of the application model. For an introduction to the non-first device, please refer to the above and will not be repeated here or below.

[0118] Condition 3. When the source device of the application model provides the model data of the application model to the first device, it provides the activation condition and / or deactivation condition associated with the application model to the first device; and, when the activation condition is met or the deactivation condition is not met, the first device activates the application model or keeps the application model in an activated state, and / or, when the deactivation condition is met or the activation condition is not met, the first device deactivates the application model or keeps the application model in an inactivated state.

[0119] When the source device provides the application model to the first device, it also provides the activation conditions and / or deactivation conditions associated with the application model to the first device. When the application model meets the activation conditions, the first device activates the corresponding application model or puts the application model in an activated state. Otherwise, when the application model does not meet the activation conditions, the first device deactivates the corresponding application model or puts the application model in an inactivated state.

[0120] Optionally, the first device may also activate the application model when the application model meets the activation conditions or does not meet the deactivation conditions, and inform other network devices or other terminal devices of the information of the application model activation, and / or, the first device may also deactivate the application model when the application model does not meet the activation conditions or meets the deactivation conditions, and inform other network devices or other terminal devices of the information of the application model deactivation.

[0121] In some embodiments, taking the second device as an example, the source device sends configuration information of activation conditions and / or deactivation conditions to the first device, where the activation conditions and / or deactivation conditions are used to activate or deactivate the application model stored in the first device. Accordingly, the first device receives the configuration information of activation conditions and / or deactivation conditions sent by the second device, determines the activation conditions and / or deactivation conditions associated with the application model based on the configuration information, and subsequently activates and / or deactivates the application model based on the activation conditions and / or deactivation conditions.

[0122] Condition 4: The first device storing the model data of the application model autonomously decides to activate or deactivate the application model.

[0123] That is, the activation or deactivation operation of the application model saved by the first device does not depend on the activation instructions or deactivation instructions sent by other network devices or other terminal devices or the configured activation / deactivation conditions.

[0124] Optionally, when the first device activates an application model, the first device may also inform other network devices or other terminal devices of the application model activation information, and / or, when the first device deactivates an application model, the first device may also inform other network devices or other terminal devices of the application model deactivation information.

[0125] Condition 5: The first device receives an activation or deactivation instruction sent by a non-first device and activates or deactivates the application model.

[0126] The activation instruction is used to activate the application model, and the deactivation instruction is used to deactivate the application model.

[0127] In some embodiments, for example, the second device is not the first device. The second device sends an activation or deactivation instruction to the first device, where the activation or deactivation instruction is used to activate or deactivate the application model stored in the first device. Correspondingly, the first device receives the activation or deactivation instruction sent by the second device and activates or deactivates the application model stored in the first device according to the activation or deactivation instruction.

[0128] In some embodiments, the first device may also send an activation or deactivation instruction to the second device, where the activation or deactivation instruction is used to activate or deactivate the application model stored on the second device. Accordingly, the second device receives the activation or deactivation instruction sent by the first device and activates or deactivates the application model stored on the second device according to the activation or deactivation instruction.

[0129] In some embodiments, after the first device activates and / or deactivates the application model storing the corresponding model data based on the first preset condition, the first device may also send updated application model information related to the first device to the non-first device.

[0130] In addition, the network device mentioned in this embodiment may be an access network device, or a core network device, or an application model management and control device, or an OAM device, and this application does not limit this.

[0131] The technical solution provided in this embodiment clarifies the rules for activating and / or deactivating application models of terminal devices or network devices, avoiding performance degradation or even misunderstanding caused by inconsistent understanding of the activation or deactivation status of specific models among devices.

[0132] The following describes how to save and delete model data in an application model.

[0133] In some embodiments, the first device deletes the saved model data of the application model based on the second preset condition.

[0134] The model data of the application model involves save and delete operations, that is, under what conditions can the first device continue to save the model data of the application model, and under what conditions can the first device delete the model data of the application model.

[0135] In some embodiments, the second preset condition includes but is not limited to at least one of the following conditions 1 to 3:

[0136] Condition 1: The first device storing the model data of the application model receives a deletion instruction sent by a non-first device, and the first device deletes the model data of the application model.

[0137] Optionally, a single deletion instruction may be for deleting the model data of one saved application model, or for deleting the model data of multiple, a group or all saved application models.

[0138] For example, if the second device is not the first device, the second device sends a deletion instruction to the first device, which is used to delete the model data of the application model stored on the first device. In response, the first device receives the deletion instruction sent by the second device and deletes the model data of the application model stored on the first device according to the deletion instruction.

[0139] For example, the first device may also send a deletion instruction to the second device, where the deletion instruction is used to delete the model data of the application model stored on the second device. Accordingly, the second device receives the deletion instruction sent by the first device, and the second device deletes the model data of the application model stored on the second device according to the deletion instruction.

[0140] Condition 2: When a deletion condition associated with the application model is met, the first device deletes the model data of the application model, wherein the deletion condition is configured by the non-first device.

[0141] Optionally, each application model has an associated deletion condition. One deletion condition may be associated with only one application model, or may be associated with multiple, a group, or all application models.

[0142] For example, in the case where the second device is not the first device, the second device sends configuration information of deletion conditions to the first device. The deletion conditions are used to delete the model data of the application model stored by the first device. Accordingly, the first device receives the configuration information of the deletion conditions sent by the second device and determines the deletion conditions associated with the application model stored by the first device based on the configuration information.

[0143] Condition 3: The first device storing the model data of the application model independently decides to delete the model data of the application model.

[0144] The deletion operation of the application model saved by the first device does not depend on the deletion instructions sent by other devices, nor does it depend on the deletion conditions associated with the configured application model. The first device independently decides whether to delete and when to delete.

[0145] In some embodiments, the first device deletes the model data of the saved application model based on the second preset condition, and can notify the non-first device that the corresponding application model has been deleted, and / or send updated application model information related to the first device to the non-first device.

[0146] The non-first device mentioned in this embodiment can be any device other than the first device. For example, the non-first device is the source device of the application model, or the non-first device is a device other than the source device and the first device of the application model. For details about the non-first device and source device, please refer to the above section and will not be repeated here.

[0147] The technical solution provided in this embodiment clarifies the rules for storing and deleting model data by terminal devices or network devices, maintains consistency in understanding among various devices, and avoids the problem of inefficient memory usage caused by the continuous storage of model data.

[0148] Next, the exchange of auxiliary information between the first device and the non-first device is described.

[0149] In some embodiments, the first device sends auxiliary information to the non-first device, and correspondingly, the non-first device receives the auxiliary information sent by the first device. The auxiliary information includes but is not limited to at least one of the following:

[0150] identification information of at least one application model that the first device desires to activate;

[0151] identification information of at least one application model that the first device desires to deactivate;

[0152] Identification information of at least one application model that the first device expects to delete.

[0153] The non-first device may be any device other than the first device. For example, the non-first device is the source device of the application model, or is a device other than the source device of the application model and the first device. For example, the non-first device is the second device, for example, the first device sends auxiliary information to the second device, and the second device receives the auxiliary information sent by the first device.

[0154] The technical solution provided in this embodiment, by exchanging the above-mentioned auxiliary information between devices, can enable a non-first device to perform operations such as activation, deactivation or deletion on the application model saved by the first device based on the above-mentioned auxiliary information, thereby helping to improve the consistency of understanding between devices.

[0155] The following describes the behavior of processing application models after the device is shut down, deregistered, deactivated, or in sleep mode.

[0156] In this embodiment, taking the first device as an example, the first device can be any device that stores an application model. The first device can be a terminal device or a network device. For example, when the first device is a terminal device, after the terminal device is shut down or deregistered, the terminal device can perform any of the following actions 1 to 6. For example, when the first device is a network device, after the network device is deactivated or hibernated, the network device can perform any of the following actions 1 to 6.

[0157] In some embodiments, after the first device is shut down, deregistered, deactivated, or in hibernation, the first device may perform any one of the following actions 1 to 6:

[0158] Behavior 1. The model data of the saved application model is not deleted.

[0159] After the first device is shut down, deregistered, deactivated, or put into sleep, the first device continues to save the model data of the saved application model and does not delete the saved model data.

[0160] Optionally, after the first device is powered off, deregistered, deactivated, or put into sleep, the first device does not delete the model data of all the saved application models.

[0161] Action 2: Deactivate the saved application model, but do not delete the model data of the saved application model.

[0162] After the first device is shut down or deregistered or deactivated or sleeps, the first device deactivates the saved application models, but does not delete the model data of the saved application models.

[0163] Optionally, after the first device is shut down or deregistered or deactivated or put into sleep, the first device deactivates all stored application models but does not delete the model data of all stored application models.

[0164] Behavior 3. Delete the model data of the saved application model.

[0165] After the first device is powered off, deregistered, deactivated, or put into sleep mode, the first device deletes the saved model data of the application model.

[0166] Optionally, after the first device is shut down, deregistered, deactivated, or put into sleep, the first device deletes the model data of all saved application models.

[0167] Behavior 4. Model data of application models that meet the saving conditions are not deleted, and model data of application models that do not meet the saving conditions are deleted.

[0168] After the first device is shut down, deregistered, deactivated, or put into sleep, the first device does not delete the model data of the application model that meets the preservation condition, and deletes the model data of the application model that does not meet the preservation condition. Alternatively, after the first device is shut down, deregistered, deactivated, or put into sleep, the first device deletes the model data of the application model that meets the deletion condition, and does not delete the model data of the application model that does not meet the deletion condition.

[0169] For example, after the first device is shut down or deregistered or deactivated or put into sleep, the first device will retain all model data of the application model obtained through the non-3GPP (3rd Generation Partnership Project) system, but will delete all model data of the application model obtained through the 3GPP system.

[0170] Action 5: Determine whether to delete the model data of the application model according to the instruction information associated with the saved application model.

[0171] Exemplarily, the indication information associated with the application model can be represented by 1 bit, for example, a value of "1" indicates deletion, and a value of "0" indicates non-deletion; or vice versa, a value of "1" indicates non-deletion, and a value of "0" indicates deletion.

[0172] Action 6. Determine, based on default rules, an application model that needs to be deleted and / or an application model that needs to be saved.

[0173] Exemplarily, the default rule may be agreed upon by a protocol. For example, the protocol may, through the default rule, agree upon the type and / or identification information of application models to be deleted and / or the type and / or identification information of application models to be preserved. After the first device is shut down, deregistered, deactivated, or hibernated, the first device determines the application models to be deleted and / or the application models to be preserved based on the default rule.

[0174] The technical solution provided in this embodiment clarifies the behavior of processing application models after the device is shut down, deregistered, deactivated, or in sleep mode, and can ensure that the device saves application model data that needs to be saved and deletes application model data that does not need to be saved, thereby freeing up storage space of the device.

[0175] The following describes how to exchange enabling information and capability information between devices.

[0176] In some embodiments, the second device sends first indication information to the first device, and accordingly, the first device receives the first indication information sent by the second device, where the first indication information is used to indicate at least one of the following meanings:

[0177] 1. Whether the first device is allowed to send application model information related to the third device to the second device;

[0178] 2. Whether the first device is allowed to independently decide to activate and / or deactivate the application model;

[0179] 3. Whether the first device is allowed to independently determine the deletion of model data of the application model;

[0180] 4. Whether the first device is allowed to send auxiliary information to the second device.

[0181] In some embodiments, the first device sends second indication information to the second device, and accordingly, the second device receives the second indication information sent by the first device, where the second indication information is used to indicate at least one of the following meanings:

[0182] 1. Whether the first device is willing or able to provide the second device with application model information related to the third device;

[0183] 2. Whether the first device is capable of autonomously determining activation and / or deactivation of the application model;

[0184] 3. Whether the first device is capable of independently determining the deletion of model data of the application model;

[0185] 4. Whether the first device is willing or able to provide auxiliary information to the second device.

[0186] The technical solution provided in this embodiment enables devices to synchronize capabilities and requirements by exchanging enabling information and capability information between devices, thereby better managing and controlling application models.

[0187] Next, the transfer operation of the model data of the application model is introduced and explained.

[0188] In some embodiments, when at least one of the following conditions 1 to 5 is met, the model data of the application model is transferred between the first device and the source device of the application model:

[0189] Case 1: The source device of the application model deploys the application model to the first device.

[0190] Case 2: The source device of the application model actively updates or modifies the model data of the application model stored in the first device.

[0191] Case 3: A process in which the first device requests the source device of the application model to update or modify the model data of the application model stored in the first device.

[0192] Case 4: A process in which the first device requests the source device of the application model to download model data of the application model.

[0193] Case 5: The first device requests the source device of the application model to upload the model data of the application model.

[0194] For the above situations 1 to 4, the source device of the application model sends the model data of the application model to the first device; for the above situation 5, the first device sends the model data of the application model to the source device of the application model.

[0195] The model data of the application model transmitted between devices can be the complete model data of the application model, or partial model data of the application model, or part of the complete model data (that is, partial transmission of the model data of the application model is allowed). The behavior of transmitting model data between devices may be triggered by the source device (sender of the application model data) or by the target device (receiver of the application model data, such as the first device) requesting the source device. The reasons for triggering the transmission of model data between devices may include at least one of the above situations 1 to 5.

[0196] In addition, for the first device, the source device of the application model can be any other device different from the first device, such as a network device or a terminal device, and this application does not limit this.

[0197] The following examples illustrate several scenarios for transferring model data for application models:

[0198] Scenario 1: The first device and the source device of the application model are two different network devices, that is, the model data of the application model is transmitted between two different network devices. The network device can be an access network device, a core network device, an application model management and control device, or an OAM device.

[0199] For example, a typical scenario is that the application model management and control device transmits the model data of the trained application model to the access network device or core network device or OAM device, and the receiving device uses these application models for reasoning at the appropriate time.

[0200] Scenario 2: The first device is a terminal device, and the source device of the application model is a network device. That is, the network device transmits the model data of the application model to the terminal device, or vice versa. The network device can be an access network device, a core network device, an application model management and control device, or an OAM device.

[0201] For example, a typical scenario involves the application model management and control device transmitting the model data of a trained application model to a terminal device, which then uses the application model for inference at the appropriate time. Another typical scenario involves a terminal device uploading the model data of its own application model to the application model management and control device, allowing other terminal devices to obtain the model data of the application model from the application model management and control device.

[0202] Scenario 3: The first device and the source device of the application model are two different terminal devices, that is, the model data of the application model is transmitted between two different terminal devices.

[0203] In this scenario, the model data of the application model can be directly shared between terminal devices, which is more flexible than obtaining model data from network devices.

[0204] The technical solution provided in this embodiment provides the transmission conditions and methods of the model data of the application model, and introduces the transmission process in several typical scenarios, thereby realizing the transmission of model data between devices.

[0205] It should be noted that the above steps executed by the first device can be independently implemented as a communication method on the first device side, and the above steps executed by the second device can be independently implemented as a communication method on the second device side.

[0206] The following are device embodiments of the present application, which can be used to implement the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

[0207] Please refer to Figure 5, which shows a block diagram of a communication device provided by an embodiment of the present application. The device has the function of implementing the above-mentioned method example on the first device side. The function can be implemented by hardware or by hardware executing corresponding software. The device can be the first device or can be set in the first device. As shown in Figure 5, the device 500 can include: a sending module 510.

[0208] The sending module 510 is configured to send a first message to the second device, where the first message includes application model information related to the third device.

[0209] In some embodiments, the application model information includes at least one of the following:

[0210] identification information of at least one application model supported by the third device;

[0211] The third device stores identification information of at least one application model corresponding to the model data;

[0212] The third device does not store identification information of at least one application model corresponding to the model data;

[0213] The third device stores instruction information for use of at least one application model corresponding to the model data;

[0214] identification information of at least one application model activated and used by the third device;

[0215] The third device stores activation indication information of at least one application model corresponding to the model data, and the activation indication information of the application model is used to indicate whether the application model is activated for use.

[0216] In some embodiments, the usage instructions of the application model include at least one of the following:

[0217] Function information of the application model, used to indicate functions associated with the application model;

[0218] The scenario information of the application model is used to indicate the scenario associated with the application model;

[0219] The usage scope control information of the application model is used to indicate the usage scope of the application model;

[0220] The input information set of the application model is used to indicate the type and / or quantity of the input information of the application model;

[0221] The output information set of the application model is used to indicate the type and / or quantity of the output information of the application model;

[0222] The input processing information of the application model is used to indicate a preprocessing method of the input information of the application model;

[0223] The output processing information of the application model is used to indicate a post-processing method of the output information of the application model.

[0224] In some embodiments, as shown in FIG5 , the apparatus 500 further includes: a receiving module 520 configured to receive a second message sent by the second device, where the second message is used to trigger the first device to send the first message.

[0225] In some embodiments, as shown in FIG5 , the apparatus 500 further includes an activation module 530 configured to activate and / or deactivate the application model storing the corresponding model data based on a first preset condition.

[0226] In some embodiments, the first preset condition includes at least one of the following:

[0227] When the source device of the application model provides the model data of the application model to the first device, indicating to the first device whether the application model is activated;

[0228] When the source device of the application model provides the model data of the application model to the first device, the application model is in an inactive state or in an active state by default;

[0229] When the source device of the application model provides the model data of the application model to the first device, the source device provides the activation condition and / or deactivation condition associated with the application model to the first device; and when the activation condition is met or the deactivation condition is not met, the first device activates the application model or keeps the application model in an activated state, and / or when the deactivation condition is met or the activation condition is not met, the first device deactivates the application model or keeps the application model in an inactivated state;

[0230] The first device storing the model data of the application model autonomously decides to activate or deactivate the application model;

[0231] The first device receives an activation or deactivation instruction sent by the non-first device, and activates or deactivates the application model;

[0232] The non-first device is the source device of the application model, or the non-first device is a device other than the source device of the application model and the first device.

[0233] In some embodiments, the sending module 510 is further configured to send an activation or deactivation instruction to the second device, where the activation or deactivation instruction is configured to activate or deactivate the application model stored in the second device.

[0234] In some embodiments, as shown in FIG5 , the apparatus 500 further includes: a deleting module 540 configured to delete the saved model data of the application model based on a second preset condition.

[0235] In some embodiments, the second preset condition includes at least one of the following:

[0236] The first device storing the model data of the application model receives a deletion instruction sent by a non-first device, and the first device deletes the model data of the application model;

[0237] When a deletion condition associated with the application model is satisfied, the first device deletes the model data of the application model, wherein the deletion condition is configured by the non-first device;

[0238] The first device storing the model data of the application model independently decides to delete the model data of the application model;

[0239] The non-first device is the source device of the application model, or the non-first device is a device other than the source device of the application model and the first device.

[0240] In some embodiments, the sending module 510 is further used to send a deletion instruction to the second device, where the deletion instruction is used to delete the model data of the application model stored in the second device.

[0241] In some embodiments, the sending module 510 is further configured to send auxiliary information to the second device, where the auxiliary information includes at least one of the following:

[0242] identification information of at least one application model that the first device desires to activate;

[0243] identification information of at least one application model that the first device desires to deactivate;

[0244] identification information of at least one application model that the first device expects to delete.

[0245] In some embodiments, after the first device is shut down, deregistered, deactivated, or hibernated, the first device performs any one of the following actions:

[0246] Do not delete the model data of the saved application model;

[0247] Deactivate the saved application model, but do not delete the model data of the saved application model;

[0248] Delete the model data of the saved application model;

[0249] Not deleting the model data of the application models that meet the preservation conditions, and deleting the model data of the application models that do not meet the preservation conditions;

[0250] Determining whether to delete or not to delete model data of the application model according to the stored indication information associated with the application model;

[0251] According to the default rules, the application model to be deleted and / or the application model to be saved are determined.

[0252] In some embodiments, as shown in FIG5 , the apparatus 500 further includes a receiving module 520 configured to receive first indication information sent by the second device, where the first indication information is used to indicate at least one of the following meanings:

[0253] whether the first device is allowed to send application model information related to the third device to the second device;

[0254] whether the first device is allowed to autonomously determine activation and / or deactivation of the application model;

[0255] whether the first device is allowed to independently determine deletion of model data of the application model;

[0256] Whether the first device is allowed to send auxiliary information to the second device.

[0257] In some embodiments, the sending module 510 is further configured to send second indication information to the second device, where the second indication information is configured to indicate at least one of the following meanings:

[0258] whether the first device is willing or able to provide the second device with application model information related to the third device;

[0259] whether the first device is capable of autonomously determining activation and / or deactivation of an application model;

[0260] whether the first device is capable of autonomously determining deletion of model data of the application model;

[0261] Whether the first device is willing or able to provide auxiliary information to the second device.

[0262] In some embodiments, when at least one of the following conditions is met, the model data of the application model is transferred between the first device and the source device of the application model:

[0263] A process in which the source device of the application model deploys the application model to the first device;

[0264] A process in which the source device of the application model actively updates or modifies the model data of the application model stored by the first device;

[0265] A process in which the first device requests the source device of the application model to update or modify the model data of the application model stored by the first device;

[0266] A process in which the first device requests the source device of the application model to download model data of the application model;

[0267] The first device requests the source device of the application model to upload the model data of the application model.

[0268] In some embodiments, the first device is a first terminal device, and the second device is a network device or a second terminal device; wherein the first terminal device and the second terminal device are different terminal devices.

[0269] In some embodiments, the first device is a first network device, and the second device is a second network device or a terminal device; wherein the first network device and the second network device are different network devices.

[0270] In some embodiments, the network device is at least one of the following: an access network device, a core network device, an application model management and control device, and an OAM device.

[0271] In some embodiments, the third device is a first terminal device.

[0272] In some embodiments, the application model includes at least one of the following: an AI model, an ML model, a supercomputing model, a neuron-like model, an authentication model, an encryption and decryption model, and a self-optimization model.

[0273] Please refer to Figure 6, which shows a block diagram of a communication device provided by another embodiment of the present application. The device has the function of implementing the above-mentioned method example on the second device side. The function can be implemented by hardware or by hardware executing corresponding software. The device can be a second device or can be set in a second device. As shown in Figure 6, the device 600 can include: a receiving module 610.

[0274] The receiving module 610 is configured to receive a first message sent by a first device, where the first message includes application model information related to a third device.

[0275] In some embodiments, the application model information includes at least one of the following:

[0276] identification information of at least one application model supported by the third device;

[0277] The third device stores identification information of at least one application model corresponding to the model data;

[0278] The third device does not store identification information of at least one application model corresponding to the model data;

[0279] The third device stores instruction information for use of at least one application model corresponding to the model data;

[0280] identification information of at least one application model activated and used by the third device;

[0281] The third device stores activation indication information of at least one application model corresponding to the model data, and the activation indication information of the application model is used to indicate whether the application model is activated for use.

[0282] In some embodiments, the usage instructions of the application model include at least one of the following:

[0283] Function information of the application model, used to indicate functions associated with the application model;

[0284] The scenario information of the application model is used to indicate the scenario associated with the application model;

[0285] The usage scope control information of the application model is used to indicate the usage scope of the application model;

[0286] The input information set of the application model is used to indicate the type and / or quantity of the input information of the application model;

[0287] The output information set of the application model is used to indicate the type and / or quantity of the output information of the application model;

[0288] The input processing information of the application model is used to indicate a preprocessing method of the input information of the application model;

[0289] The output processing information of the application model is used to indicate a post-processing method of the output information of the application model.

[0290] In some embodiments, as shown in FIG6 , the apparatus 600 further includes: a sending module 620 configured to send a second message to the first device, where the second message is configured to trigger the first device to send the first message.

[0291] In some embodiments, as shown in Figure 6, the device 600 also includes a sending module 620, which is used to: send an activation or deactivation instruction to the first device, and the activation or deactivation instruction is used to activate or deactivate the application model stored in the first device; and / or, send configuration information of activation conditions and / or deactivation conditions to the first device, and the activation conditions and / or deactivation conditions are used to activate or deactivate the application model stored in the first device.

[0292] In some embodiments, the receiving module 610 is further used to receive an activation or deactivation instruction sent by the first device, where the activation or deactivation instruction is used to activate or deactivate the application model saved by the second device.

[0293] In some embodiments, as shown in Figure 6, the device 600 also includes a sending module 620, which is used to: send a deletion instruction to the first device, wherein the deletion instruction is used to delete the model data of the application model stored by the first device; and / or send configuration information of the deletion condition to the first device, wherein the deletion condition is used to delete the model data of the application model stored by the first device.

[0294] In some embodiments, the receiving module 610 is further used to receive a deletion instruction sent by the first device, where the deletion instruction is used to delete the model data of the application model stored by the second device.

[0295] In some embodiments, the receiving module 610 is further configured to receive auxiliary information sent by the first device, where the auxiliary information includes at least one of the following:

[0296] identification information of at least one application model that the first device desires to activate;

[0297] identification information of at least one application model that the first device desires to deactivate;

[0298] identification information of at least one application model that the first device expects to delete.

[0299] In some embodiments, as shown in FIG6 , the apparatus 600 further includes a sending module 620 configured to send first indication information to the first device, where the first indication information is used to indicate at least one of the following meanings:

[0300] whether the first device is allowed to send application model information related to the third device to the second device;

[0301] whether the first device is allowed to autonomously determine activation and / or deactivation of the application model;

[0302] whether the first device is allowed to independently determine deletion of model data of the application model;

[0303] Whether the first device is allowed to send auxiliary information to the second device.

[0304] In some embodiments, the receiving module 610 is further configured to receive second indication information sent by the first device, where the second indication information is configured to indicate at least one of the following meanings:

[0305] Whether the first device is willing or able to provide the second device with application model information related to the third device:

[0306] whether the first device is capable of autonomously determining activation and / or deactivation of an application model;

[0307] whether the first device is capable of autonomously determining deletion of model data of the application model;

[0308] Whether the first device is willing or able to provide auxiliary information to the second device.

[0309] In some embodiments, the first device is a first terminal device, and the second device is a network device or a second terminal device; wherein the first terminal device and the second terminal device are different terminal devices.

[0310] In some embodiments, the first device is a first network device, and the second device is a second network device or a terminal device; wherein the first network device and the second network device are different network devices.

[0311] In some embodiments, the network device is at least one of the following: an access network device, a core network device, an application model management and control device, and an OAM device.

[0312] In some embodiments, the third device is a first terminal device.

[0313] In some embodiments, the application model includes at least one of the following: an AI model, an ML model, a supercomputing model, a neuron-like model, an authentication model, an encryption and decryption model, and a self-optimization model.

[0314] It should be noted that, when the device provided in the above embodiment realizes its function, it only uses the division of the above-mentioned functional modules as an example. In actual application, the above-mentioned functions can be assigned to different functional modules according to actual needs, that is, the content structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0315] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0316] Please refer to Figure 7, which shows a schematic diagram of the structure of a communication device 700 provided in one embodiment of the present application. The communication device 700 can be any device described above, such as the first device or the second device. The communication device 700 can be used to execute the communication method on the first device side described above, or execute the communication method on the second device side described above. The communication device 700 may include: a processor 701, a transceiver 702, and a memory 703.

[0317] The processor 701 includes one or more processing cores, and executes various functional applications and information processing by running software programs and modules. The processor 701 is used to execute other steps in the above method embodiment except the receiving and sending steps.

[0318] The transceiver 702 may include a receiver and a transmitter. For example, the transceiver 702 may include a wired communication component, which may include a wired communication chip and a wired interface (such as a fiber optic interface). Alternatively, the transceiver 702 may also include a wireless communication component, which may include a wireless communication chip and a radio frequency antenna. The transceiver 702 is used to perform the receiving and transmitting steps in the above method embodiment.

[0319] The memory 703 may be connected to the processor 701 and the transceiver 702 .

[0320] The memory 703 may be used to store a computer program executed by the processor, and the processor 701 is used to execute the computer program to implement each step performed by the first device or the second device in the above method embodiment.

[0321] In addition, the memory 703 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, and the volatile or non-volatile storage device includes but is not limited to: a magnetic disk or optical disk, an electrically erasable programmable read-only memory, an erasable programmable read-only memory, a static access memory, a read-only memory, a magnetic memory, a flash memory, and a programmable read-only memory.

[0322] In some embodiments, when the communication device 700 is a first device, the transceiver 702 is configured to send a first message to a second device, where the first message includes application model information related to a third device.

[0323] In some embodiments, when the communication device 700 is a second device, the transceiver 702 is configured to receive a first message sent by a first device, where the first message includes application model information related to a third device.

[0324] For details not described in detail in this embodiment, please refer to the above embodiments and will not be described in detail here.

[0325] An embodiment of the present application also provides a computer-readable storage medium, in which a computer program is stored. The computer program is used to be executed by a processor of a communication device to implement the above-mentioned communication method on the first device side, or to implement the above-mentioned communication method on the second device side.

[0326] In some embodiments, the computer-readable storage medium may include: ROM (Read-Only Memory), RAM (Random-Access Memory), SSD (Solid State Drives), or an optical disk, etc. Among them, the random access memory may include ReRAM (Resistance Random Access Memory) and DRAM (Dynamic Random Access Memory).

[0327] An embodiment of the present application also provides a chip, which includes a programmable logic circuit and / or program instructions. When the chip runs on a communication device, it is used to implement the above-mentioned communication method on the first device side, or to implement the above-mentioned communication method on the second device side.

[0328] An embodiment of the present application also provides a computer program product, which includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the communication device reads and executes the computer instructions from the computer-readable storage medium to implement the above-mentioned communication method on the first device side, or implement the above-mentioned communication method on the second device side.

[0329] It should be understood that the "indication" mentioned in the embodiments of this application can be a direct indication, an indirect indication, or an indication of an association. For example, "A indicates B" can mean that A directly indicates B, for example, B can be obtained through A; it can also mean that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; it can also mean that there is an association between A and B.

[0330] In the description of the embodiments of the present application, the term "corresponding" may indicate a direct or indirect correspondence between the two, or an association relationship between the two, or a relationship between indication and being indicated, configuration and being configured, etc.

[0331] In some embodiments of the present application, "predefined" may be implemented by pre-storing corresponding codes, tables, or other methods that can be used to indicate relevant information in a device (e.g., including a terminal device and a network device), and the present application does not limit the specific implementation method. For example, predefined may refer to information defined in a protocol.

[0332] In some embodiments of the present application, the "protocol" may refer to a standard protocol in the field of communications, for example, it may include an LTE protocol, a NR protocol, and related protocols used in future communication systems, and this application does not limit this.

[0333] In this document, "plurality" refers to two or more. "And / or" describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, or B exists alone. The character " / " generally indicates an "or" relationship between the associated objects.

[0334] The term “less than” mentioned herein may be understood as less than, or may also be understood as less than or equal to; the term “greater than” mentioned herein may be understood as greater than, or may also be understood as greater than or equal to.

[0335] In addition, the step numbers described in this document only illustrate a possible execution order between the steps. In some other embodiments, the above steps may not be executed in the order of the numbers, such as two steps with different numbers are executed at the same time, or two steps with different numbers are executed in the opposite order of the diagram. The embodiments of the present application are not limited to this.

[0336] In addition, the embodiments provided herein may be arbitrarily combined to form new embodiments, which are all within the scope of protection of this application.

[0337] Those skilled in the art will appreciate that in one or more of the above examples, the functions described in the embodiments of the present application can be implemented using hardware, software, firmware, or any combination thereof. When implemented using software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any media that facilitates the transmission of computer programs from one place to another. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0338] The above description is merely an exemplary embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A communication method, characterized in that: The method comprises: The first device sends a first message to the second device, where the first message includes application model information related to the third device.

2. The method according to claim 1, characterized in that The application model information includes at least one of the following: identification information of at least one application model supported by the third device; The third device stores identification information of at least one application model corresponding to the model data; The third device does not store identification information of at least one application model corresponding to the model data; The third device stores instruction information for use of at least one application model corresponding to the model data; identification information of at least one application model activated and used by the third device; The third device stores activation indication information of at least one application model corresponding to the model data, and the activation indication information of the application model is used to indicate whether the application model is activated for use.

3. The method according to claim 2, characterized in that The usage description information of the application model includes at least one of the following: Function information of the application model, used to indicate functions associated with the application model; The scenario information of the application model is used to indicate the scenario associated with the application model; The usage scope control information of the application model is used to indicate the usage scope of the application model; The input information set of the application model is used to indicate the type and / or quantity of the input information of the application model; The output information set of the application model is used to indicate the type and / or quantity of the output information of the application model; The input processing information of the application model is used to indicate a preprocessing method of the input information of the application model; The output processing information of the application model is used to indicate a post-processing method of the output information of the application model.

4. The method according to any one of claims 1 to 3, characterized in that Before the first device sends the first message to the second device, the method further includes: The first device receives a second message sent by the second device, where the second message is used to trigger the first device to send the first message.

5. The method according to any one of claims 1 to 4, characterized in that The method further comprises: The first device activates and / or deactivates the application model storing the corresponding model data based on the first preset condition.

6. The method according to claim 5, characterized in that The first preset condition includes at least one of the following: When the source device of the application model provides the model data of the application model to the first device, indicating to the first device whether the application model is activated; When the source device of the application model provides the model data of the application model to the first device, the application model is in an inactive state or in an active state by default; When the source device of the application model provides the model data of the application model to the first device, the source device provides the activation condition and / or deactivation condition associated with the application model to the first device; Furthermore, when the activation condition is met or the deactivation condition is not met, the first device activates the application model or keeps the application model in an activated state, and / or, when the deactivation condition is met or the activation condition is not met, the first device deactivates the application model or keeps the application model in an inactivated state; The first device storing the model data of the application model autonomously decides to activate or deactivate the application model; The first device receives an activation or deactivation instruction sent by the non-first device, and activates or deactivates the application model; The non-first device is the source device of the application model, or the non-first device is a device other than the source device of the application model and the first device.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: The first device sends an activation or deactivation instruction to the second device, where the activation or deactivation instruction is used to activate or deactivate the application model saved by the second device.

8. The method according to any one of claims 1 to 7, characterized in that The method further comprises: The first device deletes the stored model data of the application model based on a second preset condition.

9. The method according to claim 8, characterized in that The second preset condition includes at least one of the following: The first device storing the model data of the application model receives a deletion instruction sent by a non-first device, and the first device deletes the model data of the application model; When a deletion condition associated with the application model is satisfied, the first device deletes the model data of the application model, wherein the deletion condition is configured by the non-first device; The first device storing the model data of the application model independently decides to delete the model data of the application model; The non-first device is the source device of the application model, or the non-first device is a device other than the source device of the application model and the first device.

10. The method according to any one of claims 1 to 9, characterized in that The method further comprises: The first device sends a deletion instruction to the second device, where the deletion instruction is used to delete model data of the application model stored by the second device.

11. The method according to any one of claims 1 to 10, characterized in that The method further comprises: The first device sends auxiliary information to the second device, where the auxiliary information includes at least one of the following: identification information of at least one application model that the first device desires to activate; identification information of at least one application model that the first device desires to deactivate; identification information of at least one application model that the first device expects to delete.

12. The method according to any one of claims 1 to 11, characterized in that After the first device is powered off, deregistered, deactivated, or in hibernation, the first device performs any one of the following actions: Do not delete the model data of the saved application model; Deactivate the saved application model, but do not delete the model data of the saved application model; Delete the model data of the saved application model; Not deleting the model data of the application models that meet the preservation conditions, and deleting the model data of the application models that do not meet the preservation conditions; Determining whether to delete or not to delete model data of the application model according to the stored indication information associated with the application model; According to the default rules, the application model to be deleted and / or the application model to be saved are determined.

13. The method according to any one of claims 1 to 12, characterized in that The method further includes, the first device receiving first indication information sent by the second device, where the first indication information is used to indicate at least one of the following meanings: whether the first device is allowed to send application model information related to the third device to the second device; whether the first device is allowed to autonomously determine activation and / or deactivation of the application model; whether the first device is allowed to independently determine deletion of model data of the application model; Whether the first device is allowed to send auxiliary information to the second device.

14. The method according to any one of claims 1 to 13, characterized in that The method further includes, the first device sending second indication information to the second device, where the second indication information is used to indicate at least one of the following meanings: whether the first device is willing or able to provide the second device with application model information related to the third device; whether the first device is capable of autonomously determining activation and / or deactivation of an application model; whether the first device is capable of autonomously determining deletion of model data of the application model; Whether the first device is willing or able to provide auxiliary information to the second device.

15. The method according to any one of claims 1 to 14, characterized in that When at least one of the following conditions is met, the model data of the application model is transmitted between the first device and the source device of the application model: A process in which the source device of the application model deploys the application model to the first device; A process in which the source device of the application model actively updates or modifies the model data of the application model stored by the first device; A process in which the first device requests the source device of the application model to update or modify the model data of the application model stored by the first device; A process in which the first device requests the source device of the application model to download model data of the application model; The first device requests the source device of the application model to upload the model data of the application model.

16. The method according to any one of claims 1 to 15, characterized in that The first device is a first terminal device, and the second device is a network device or a second terminal device; wherein the first terminal device and the second terminal device are different terminal devices.

17. The method according to any one of claims 1 to 15, characterized in that The first device is a first network device, and the second device is a second network device or a terminal device; wherein the first network device and the second network device are different network devices.

18. The method according to claim 16 or 17, characterized in that The network device is at least one of the following: access network equipment, core network equipment, application model management and control equipment, and operation management and maintenance OAM equipment.

19. The method according to any one of claims 1 to 18, characterized in that The third device is the first terminal device.

20. The method according to any one of claims 1 to 19, characterized in that The application model includes at least one of the following: artificial intelligence AI model, machine learning ML model, supercomputing model, neuron-like model, authentication model, encryption and decryption model, and self-optimization model.

21. A communication method, characterized in that: The method comprises: The second device receives a first message sent by the first device, where the first message includes application model information related to the third device.

22. The method according to claim 21, characterized in that The application model information includes at least one of the following: identification information of at least one application model supported by the third device; The third device stores identification information of at least one application model corresponding to the model data; The third device does not store identification information of at least one application model corresponding to the model data; The third device stores instruction information for use of at least one application model corresponding to the model data; identification information of at least one application model activated and used by the third device; The third device stores activation indication information of at least one application model corresponding to the model data, and the activation indication information of the application model is used to indicate whether the application model is activated for use.

23. The method according to claim 22, characterized in that The usage description information of the application model includes at least one of the following: Function information of the application model, used to indicate functions associated with the application model; The scenario information of the application model is used to indicate the scenario associated with the application model; The usage scope control information of the application model is used to indicate the usage scope of the application model; The input information set of the application model is used to indicate the type and / or quantity of the input information of the application model; The output information set of the application model is used to indicate the type and / or quantity of the output information of the application model; The input processing information of the application model is used to indicate a preprocessing method of the input information of the application model; The output processing information of the application model is used to indicate a post-processing method of the output information of the application model.

24. The method according to any one of claims 21 to 23, characterized in that Before the second device receives the first message sent by the first device, the method further includes: The second device sends a second message to the first device, where the second message is used to trigger the first device to send the first message.

25. The method according to any one of claims 21 to 24, characterized in that The method further comprises: The second device sends an activation or deactivation instruction to the first device, where the activation or deactivation instruction is used to activate or deactivate the application model saved by the first device; and / or, The second device sends configuration information of activation conditions and / or deactivation conditions to the first device, where the activation conditions and / or deactivation conditions are used to activate or deactivate the application model stored in the first device.

26. The method according to any one of claims 21 to 25, characterized in that The method further comprises: The second device receives the activation or deactivation instruction sent by the first device, where the activation or deactivation instruction is used to activate or deactivate the application model saved by the second device.

27. The method according to any one of claims 21 to 26, characterized in that The method further comprises: The second device sends a deletion instruction to the first device, where the deletion instruction is used to delete the model data of the application model stored by the first device; and / or, The second device sends configuration information of a deletion condition to the first device, where the deletion condition is used to delete model data of the application model stored by the first device.

28. The method according to any one of claims 21 to 27, characterized in that The method further comprises: The second device receives the deletion instruction sent by the first device, where the deletion instruction is used to delete the model data of the application model stored by the second device.

29. The method according to any one of claims 21 to 28, characterized in that The method further comprises: The second device receives auxiliary information sent by the first device, where the auxiliary information includes at least one of the following: identification information of at least one application model that the first device desires to activate; identification information of at least one application model that the first device desires to deactivate; identification information of at least one application model that the first device expects to delete.

30. The method according to any one of claims 21 to 29, characterized in that The method further includes, the second device sending first indication information to the first device, where the first indication information is used to indicate at least one of the following meanings: whether the first device is allowed to send application model information related to the third device to the second device; whether the first device is allowed to autonomously determine activation and / or deactivation of the application model; whether the first device is allowed to independently determine deletion of model data of the application model; Whether the first device is allowed to send auxiliary information to the second device.

31. The method according to any one of claims 21 to 30, characterized in that The method further includes, the second device receiving second indication information sent by the first device, where the second indication information is used to indicate at least one of the following meanings: Whether the first device is willing or able to provide the second device with application model information related to the third device: whether the first device is capable of autonomously determining activation and / or deactivation of an application model; whether the first device is capable of autonomously determining deletion of model data of the application model; Whether the first device is willing or able to provide auxiliary information to the second device.

32. The method according to any one of claims 21 to 31, characterized in that The first device is a first terminal device, and the second device is a network device or a second terminal device; wherein the first terminal device and the second terminal device are different terminal devices.

33. The method according to any one of claims 21 to 31, characterized in that The first device is a first network device, and the second device is a second network device or a terminal device; wherein the first network device and the second network device are different network devices.

34. The method according to claim 32 or 33, characterized in that The network device is at least one of the following: access network equipment, core network equipment, application model management and control equipment, and operation management and maintenance OAM equipment.

35. The method according to any one of claims 21 to 34, characterized in that The third device is the first terminal device.

36. The method according to any one of claims 21 to 35, characterized in that The application model includes at least one of the following: artificial intelligence AI model, machine learning ML model, supercomputing model, neuron-like model, authentication model, encryption and decryption model, and self-optimization model.

37. A communication device, characterized in that: The device is provided in a first device, and includes: A sending module is used to send a first message to the second device, where the first message includes application model information related to the third device.

38. The device according to claim 37, characterized in that The application model information includes at least one of the following: identification information of at least one application model supported by the third device; The third device stores identification information of at least one application model corresponding to the model data; The third device does not store identification information of at least one application model corresponding to the model data; The third device stores instruction information for use of at least one application model corresponding to the model data; identification information of at least one application model activated and used by the third device; The third device stores activation indication information of at least one application model corresponding to the model data, and the activation indication information of the application model is used to indicate whether the application model is activated for use.

39. The device according to claim 38, characterized in that The usage description information of the application model includes at least one of the following: Function information of the application model, used to indicate functions associated with the application model; The scenario information of the application model is used to indicate the scenario associated with the application model; The usage scope control information of the application model is used to indicate the usage scope of the application model; The input information set of the application model is used to indicate the type and / or quantity of the input information of the application model; The output information set of the application model is used to indicate the type and / or quantity of the output information of the application model; The input processing information of the application model is used to indicate a preprocessing method of the input information of the application model; The output processing information of the application model is used to indicate a post-processing method of the output information of the application model.

40. The device according to any one of claims 37 to 39, characterized in that The device further comprises: The receiving module is used to receive a second message sent by the second device, where the second message is used to trigger the first device to send the first message.

41. The device according to any one of claims 37 to 40, characterized in that The device further comprises: The activation module is used to activate and / or deactivate the application model storing the corresponding model data based on a first preset condition.

42. The device according to claim 41, characterized in that The first preset condition includes at least one of the following: When the source device of the application model provides the model data of the application model to the first device, indicating to the first device whether the application model is activated; When the source device of the application model provides the model data of the application model to the first device, the application model is in an inactive state or in an active state by default; When the source device of the application model provides the model data of the application model to the first device, the source device provides the activation condition and / or deactivation condition associated with the application model to the first device; Furthermore, when the activation condition is met or the deactivation condition is not met, the first device activates the application model or keeps the application model in an activated state, and / or, when the deactivation condition is met or the activation condition is not met, the first device deactivates the application model or keeps the application model in an inactivated state; The first device storing the model data of the application model autonomously decides to activate or deactivate the application model; The first device receives an activation or deactivation instruction sent by the non-first device, and activates or deactivates the application model; The non-first device is the source device of the application model, or the non-first device is a device other than the source device of the application model and the first device.

43. The device according to any one of claims 37 to 42, characterized in that The sending module is further used to send an activation or deactivation instruction to the second device, where the activation or deactivation instruction is used to activate or deactivate the application model saved by the second device.

44. The device according to any one of claims 37 to 43, characterized in that The device further comprises: The deletion module is used to delete the saved model data of the application model based on the second preset condition.

45. The device according to claim 44, characterized in that The second preset condition includes at least one of the following: The first device storing the model data of the application model receives a deletion instruction sent by a non-first device, and the first device deletes the model data of the application model; When a deletion condition associated with the application model is satisfied, the first device deletes the model data of the application model, wherein the deletion condition is configured by the non-first device; The first device storing the model data of the application model independently decides to delete the model data of the application model; The non-first device is the source device of the application model, or the non-first device is a device other than the source device of the application model and the first device.

46. ​​The device according to any one of claims 37 to 45, characterized in that The sending module is further used to send a deletion instruction to the second device, where the deletion instruction is used to delete the model data of the application model stored in the second device.

47. The device according to any one of claims 37 to 46, characterized in that The sending module is further configured to send auxiliary information to the second device, where the auxiliary information includes at least one of the following: identification information of at least one application model that the first device desires to activate; identification information of at least one application model that the first device desires to deactivate; identification information of at least one application model that the first device expects to delete.

48. The device according to any one of claims 37 to 47, characterized in that After the first device is powered off, deregistered, deactivated, or in hibernation, the first device performs any one of the following actions: Do not delete the model data of the saved application model; Deactivate the saved application model, but do not delete the model data of the saved application model; Delete the model data of the saved application model; Not deleting the model data of the application models that meet the preservation conditions, and deleting the model data of the application models that do not meet the preservation conditions; Determining whether to delete or not to delete model data of the application model according to the stored indication information associated with the application model; According to the default rules, the application model to be deleted and / or the application model to be saved are determined.

49. The device according to any one of claims 37 to 48, characterized in that The apparatus further includes a receiving module, configured to receive first indication information sent by the second device, where the first indication information is used to indicate at least one of the following meanings: whether the first device is allowed to send application model information related to the third device to the second device; whether the first device is allowed to autonomously determine activation and / or deactivation of the application model; whether the first device is allowed to independently determine deletion of model data of the application model; Whether the first device is allowed to send auxiliary information to the second device.

50. The device according to any one of claims 37 to 49, characterized in that The sending module is further configured to send second indication information to the second device, where the second indication information is used to indicate at least one of the following meanings: whether the first device is willing or able to provide the second device with application model information related to the third device; whether the first device is capable of autonomously determining activation and / or deactivation of an application model; whether the first device is capable of autonomously determining deletion of model data of the application model; Whether the first device is willing or able to provide auxiliary information to the second device.

51. The device according to any one of claims 37 to 50, characterized in that When at least one of the following conditions is met, the model data of the application model is transmitted between the first device and the source device of the application model: A process in which the source device of the application model deploys the application model to the first device; A process in which the source device of the application model actively updates or modifies the model data of the application model stored by the first device; A process in which the first device requests the source device of the application model to update or modify the model data of the application model stored by the first device; A process in which the first device requests the source device of the application model to download model data of the application model; The first device requests the source device of the application model to upload the model data of the application model.

52. The device according to any one of claims 37 to 51, characterized in that The first device is a first terminal device, and the second device is a network device or a second terminal device; wherein the first terminal device and the second terminal device are different terminal devices.

53. The device according to any one of claims 37 to 51, characterized in that The first device is a first network device, and the second device is a second network device or a terminal device; wherein the first network device and the second network device are different network devices.

54. The device according to claim 52 or 53, characterized in that The network device is at least one of the following: access network equipment, core network equipment, application model management and control equipment, and operation management and maintenance OAM equipment.

55. The device according to any one of claims 37 to 54, characterized in that The third device is the first terminal device.

56. The device according to any one of claims 37 to 55, characterized in that The application model includes at least one of the following: artificial intelligence AI model, machine learning ML model, supercomputing model, neuron-like model, authentication model, encryption and decryption model, and self-optimization model.

57. A communication device, characterized in that The device is provided in a second device, and includes: The receiving module is used to receive a first message sent by the first device, where the first message includes application model information related to the third device.

58. The device according to claim 57, characterized in that The application model information includes at least one of the following: identification information of at least one application model supported by the third device; The third device stores identification information of at least one application model corresponding to the model data; The third device does not store identification information of at least one application model corresponding to the model data; The third device stores instruction information for use of at least one application model corresponding to the model data; identification information of at least one application model activated and used by the third device; The third device stores activation indication information of at least one application model corresponding to the model data, and the activation indication information of the application model is used to indicate whether the application model is activated for use.

59. The device according to claim 58, characterized in that The usage description information of the application model includes at least one of the following: Function information of the application model, used to indicate functions associated with the application model; The scenario information of the application model is used to indicate the scenario associated with the application model; The usage scope control information of the application model is used to indicate the usage scope of the application model; The input information set of the application model is used to indicate the type and / or quantity of the input information of the application model; The output information set of the application model is used to indicate the type and / or quantity of the output information of the application model; The input processing information of the application model is used to indicate a preprocessing method of the input information of the application model; The output processing information of the application model is used to indicate a post-processing method of the output information of the application model.

60. The device according to any one of claims 57 to 59, characterized in that The device further comprises: A sending module is used to send a second message to the first device, where the second message is used to trigger the first device to send the first message.

61. The device according to any one of claims 57 to 60, characterized in that The device further includes a sending module, configured to: Sending an activation or deactivation instruction to the first device, where the activation or deactivation instruction is used to activate or deactivate the application model saved by the first device; and / or, Configuration information of activation conditions and / or deactivation conditions is sent to the first device, where the activation conditions and / or deactivation conditions are used to activate or deactivate the application model stored in the first device.

62. The device according to any one of claims 57 to 61, characterized in that The receiving module is further used to receive an activation or deactivation instruction sent by the first device, where the activation or deactivation instruction is used to activate or deactivate the application model saved by the second device.

63. The device according to any one of claims 57 to 62, characterized in that The device further includes a sending module, configured to: Sending a deletion instruction to the first device, where the deletion instruction is used to delete model data of the application model stored in the first device; and / or, Configuration information of a deletion condition is sent to the first device, where the deletion condition is used to delete model data of the application model stored by the first device.

64. The device according to any one of claims 57 to 63, characterized in that The receiving module is further used to receive a deletion instruction sent by the first device, where the deletion instruction is used to delete the model data of the application model stored by the second device.

65. The device according to any one of claims 57 to 64, characterized in that The receiving module is further configured to receive auxiliary information sent by the first device, where the auxiliary information includes at least one of the following: identification information of at least one application model that the first device desires to activate; identification information of at least one application model that the first device desires to deactivate; identification information of at least one application model that the first device expects to delete.

66. The device according to any one of claims 57 to 65, characterized in that The apparatus further includes a sending module, configured to send first indication information to the first device, where the first indication information is used to indicate at least one of the following meanings: whether the first device is allowed to send application model information related to the third device to the second device; whether the first device is allowed to autonomously determine activation and / or deactivation of the application model; whether the first device is allowed to independently determine deletion of model data of the application model; Whether the first device is allowed to send auxiliary information to the second device.

67. The device according to any one of claims 57 to 66, characterized in that The receiving module is further configured to receive second indication information sent by the first device, where the second indication information is used to indicate at least one of the following meanings: Whether the first device is willing or able to provide the second device with application model information related to the third device: whether the first device is capable of autonomously determining activation and / or deactivation of an application model; whether the first device is capable of autonomously determining deletion of model data of the application model; Whether the first device is willing or able to provide auxiliary information to the second device.

68. The device according to any one of claims 57 to 67, characterized in that The first device is a first terminal device, and the second device is a network device or a second terminal device; wherein the first terminal device and the second terminal device are different terminal devices.

69. The device according to any one of claims 57 to 67, characterized in that The first device is a first network device, and the second device is a second network device or a terminal device; wherein the first network device and the second network device are different network devices.

70. The device according to claim 68 or 69, characterized in that The network device is at least one of the following: access network equipment, core network equipment, application model management and control equipment, and operation management and maintenance OAM equipment.

71. The device according to any one of claims 57 to 70, characterized in that The third device is the first terminal device.

72. The device according to any one of claims 57 to 71, characterized in that The application model includes at least one of the following: artificial intelligence AI model, machine learning ML model, supercomputing model, neuron-like model, authentication model, encryption and decryption model, and self-optimization model.

73. A communication device, characterized in that The communication device includes a processor and a memory, wherein a computer program is stored in the memory, and the processor executes the computer program to implement the method according to any one of claims 1 to 20, or implements the method according to any one of claims 21 to 36.

74. A computer-readable storage medium, characterized in that The storage medium stores a computer program, which is used to be executed by a processor to implement the method according to any one of claims 1 to 20, or to implement the method according to any one of claims 21 to 36.

75. A chip, characterized in that The chip includes a programmable logic circuit and / or program instructions, and when the chip is running, is used to implement the method according to any one of claims 1 to 20, or to implement the method according to any one of claims 21 to 36.

76. A computer program product, characterized in that The computer program product includes computer instructions, which are stored in a computer-readable storage medium. A processor reads and executes the computer instructions from the computer-readable storage medium to implement the method according to any one of claims 1 to 20, or implements the method according to any one of claims 21 to 36.

Images