Wireless communication method, terminal device, and network device

Abstract

Provided are a wireless communication method, a terminal device, and a network device. The method comprises: a terminal device sends first capability information to a network device, wherein the first capability information is related to an AI model or an AI function actually deployed by the terminal device, and the first capability information comprises any one of the following pieces of information: first information used for indicating an AI model set or an AI function set actually deployed by the terminal device; one or more pieces of second information, each piece of second information among the one or more pieces of second information being used for indicating an application condition of an AI model or an AI function associated with each piece of second information; identification information of one or more AI models; and identification information of one or more AI functions.

Description

Wireless communication method, terminal device and network device Technical Field

[0001] The present application relates to the field of communication technology, and more specifically, to a wireless communication method, terminal equipment, and network equipment. Background Art

[0002] In a wireless communication system, a terminal device may indicate to a network device that it supports a capability through a capability information reporting process, and the network device may configure the configuration associated with the capability information or activate the function associated with the capability information at any time.

[0003] After the introduction of AI models, there is currently no clear solution for how terminal devices will report capability information.

[0004] Summary of the Invention

[0005] The present application provides a wireless communication method, terminal device, and network device. The following introduces various aspects involved in the present application.

[0006] In a first aspect, a wireless communication method is provided, including: a terminal device sends first capability information to a network device, where the first capability information is related to an AI model or AI function actually deployed by the terminal device, and the first capability information includes any one of the following information: first information, where the first information is used to indicate the set of AI models or AI function sets actually deployed by the terminal device; one or more second information, where each of the one or more second information is used to indicate the applicable conditions of the AI ​​model or AI function associated with each second information; identification information of one or more AI models; and identification information of one or more AI functions.

[0007] According to a second aspect, a wireless communication method is provided, including: a network device receives first capability information sent by a terminal device, the first capability information is related to an AI model or AI function actually deployed by the terminal device, and the first capability information includes one or more of the following information: first information, the first information is used to indicate the set of AI models or AI function sets actually deployed by the terminal device; one or more second information, each of the one or more second information is used to indicate the applicable conditions of the AI ​​model or AI function associated with each second information; identification information of one or more AI models; identification information of one or more AI functions.

[0008] According to a third aspect, a wireless communication method is provided, including: a terminal device sends second capability information to a network device, wherein the second capability information is related to an AI model or AI function supported by the terminal device, and the second capability information includes any one of the following information: one or more fifth information, each of the one or more fifth information is used to indicate the applicable conditions of the AI ​​model or AI function associated with each fifth information; one or more AI function identification information; one or more AI model identification information.

[0009] In a fourth aspect, a wireless communication method is provided, including: a network device receives second capability information sent by a terminal device, the second capability information is related to an AI model or AI function supported by the terminal device, and the second capability information includes any one of the following: one or more fifth information, each of the one or more fifth information is used to indicate the applicable conditions of the AI ​​model or AI function associated with each fifth information; one or more AI function identification information; one or more AI model identification information.

[0010] In a fifth aspect, a terminal device is provided, including: a sending unit, used to send first capability information to a network device, wherein the first capability information is related to the AI ​​model or AI function actually deployed by the terminal device, and the first capability information includes any one of the following information: first information, wherein the first information is used to indicate the AI ​​model set or AI function set actually deployed by the terminal device; one or more second information, wherein each of the one or more second information is used to indicate the applicable conditions of the AI ​​model or AI function associated with each second information; identification information of one or more AI models; identification information of one or more AI functions.

[0011] Aspect 6: A network device is provided, comprising: a receiving unit for receiving first capability information sent by a terminal device, wherein the first capability information is related to the AI ​​model or AI function actually deployed by the terminal device, and the first capability information includes one or more of the following information: first information, wherein the first information is used to indicate the AI ​​model set or AI function set actually deployed by the terminal device; one or more second information, wherein each of the one or more second information is used to indicate the applicable conditions of the AI ​​model or AI function associated with each second information; identification information of one or more AI models; and identification information of one or more AI functions.

[0012] In the seventh aspect, a terminal device is provided, including: a sending unit for sending second capability information to a network device, wherein the second capability information is related to an AI model or AI function supported by the terminal device, and the second capability information includes any one of the following information: one or more fifth information, each of the one or more fifth information is used to indicate the applicable conditions of the AI ​​model or AI function associated with each fifth information; one or more AI function identification information; one or more AI model identification information.

[0013] In an eighth aspect, a network device is provided, comprising: a receiving unit for receiving second capability information sent by a terminal device, the second capability information being related to an AI model or AI function supported by the terminal device, the second capability information including any one of the following: one or more fifth information, each of the one or more fifth information being used to indicate the applicable conditions of the AI ​​model or AI function associated with each fifth information; one or more AI function identification information; one or more AI model identification information.

[0014] In the ninth aspect, a terminal device is provided, comprising a processor, a memory, and a communication interface, wherein the memory is used to store one or more computer programs, and the processor is used to call the computer program in the memory so that the terminal device executes part or all of the steps in the method of the first aspect or the third aspect.

[0015] In the tenth aspect, a network device is provided, comprising a processor, a memory, and a transceiver, wherein the memory is used to store one or more computer programs, and the processor is used to call the computer program in the memory so that the network device executes part or all of the steps in the method of the second aspect or the fourth aspect.

[0016] In an eleventh aspect, a device is provided, comprising a processor for calling a program from a memory so that the device executes the method described in any one of the first to fourth aspects above.

[0017] In a twelfth aspect, a chip is provided, comprising a processor for calling a program from a memory so that a device equipped with the chip executes the method described in any one of the first to fourth aspects above.

[0018] In a thirteenth aspect, a computer-readable storage medium is provided, on which a program is stored, wherein the program enables a computer to execute the method described in any one of the first to fourth aspects above.

[0019] In a fourteenth aspect, a computer program product is provided, comprising a program, wherein the program enables a computer to execute the method described in any one of the first to fourth aspects above.

[0020] In a fifteenth aspect, a computer program is provided, which enables a computer to execute the method described in any one of the first to fourth aspects above.

[0021] In this application, by sending capability information related to the actually deployed AI model or AI function to the network device, or sending capability information related to the supported AI model or AI function to the network device, the network device can clearly understand which AI models or AI functions are actually deployed by the terminal device, or which AI models or AI functions are actually supported, thereby assisting the network device to perform operations related to the AI ​​model or AI function. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] FIG1 is a system architecture diagram of a wireless communication system to which an embodiment of the present application may be applied.

[0023] FIG2 is a flow chart of a communication method according to an embodiment of the present application.

[0024] FIG3 is a flow chart of another communication method provided in an embodiment of the present application.

[0025] FIG4 is a flow chart of another communication method provided in an embodiment of the present application.

[0026] FIG5 is a flow chart of another communication method provided in an embodiment of the present application.

[0027] FIG6 is a schematic structural diagram of a terminal device provided in an embodiment of the present application.

[0028] FIG7 is a schematic structural diagram of another terminal device provided in an embodiment of the present application.

[0029] FIG8 is a schematic diagram of the structure of a network device provided in an embodiment of the present application.

[0030] FIG9 is a schematic diagram of the structure of another network device provided in an embodiment of the present application.

[0031] FIG10 is a schematic structural diagram of a device to which an embodiment of the present application can be applied. DETAILED DESCRIPTION

[0032] The technical solution in this application will be described below with reference to the accompanying drawings.

[0033] Figure 1 illustrates a wireless communication system 100 used in an embodiment of the present application. The wireless communication system 100 may include a network device 110 and a terminal device 120. The network device 110 may be a device that communicates with the terminal device 120. The network device 110 may provide communication coverage for a specific geographic area and may communicate with the terminal device 120 within the coverage area.

[0034] FIG1 exemplarily shows a network device and two terminals. Optionally, the wireless communication system 100 may include multiple network devices and each network device may include other numbers of terminal devices within its coverage area, which is not limited in the embodiments of the present application.

[0035] Optionally, the wireless communication system 100 may further include other network entities such as a network controller and a mobility management entity, which is not limited in the embodiment of the present application.

[0036] It should be understood that the technical solutions of the embodiments of the present application can be applied to various communication systems, such as: fifth generation (5G) system or new radio (NR), long term evolution (LTE) system, LTE frequency division duplex (FDD) system, LTE time division duplex (TDD), etc. The technical solutions provided in this application can also be applied to future communication systems, such as the sixth generation mobile communication system, satellite communication system, etc.

[0037] The terminal device in the embodiments of the present application may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station (MS), mobile terminal (MT), remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device. The terminal device in the embodiments of the present application may refer to a device that provides voice and / or data connectivity to a user and can be used to connect people, objects and machines, such as a handheld device with wireless connection function, a vehicle-mounted device, etc. The terminal device in the embodiments of the present application can be a mobile phone, a tablet computer, a laptop computer, a PDA, a mobile internet device (MID), a wearable device, a virtual reality (VR) device, an augmented reality (AR) device, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical surgery, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, etc. Optionally, the UE can be used to act as a base station. For example, the UE can act as a scheduling entity that provides sidelink signals between UEs in V2X or D2D, etc. For example, a cellular phone and a car communicate with each other using sidelink signals. The cellular phone and smart home devices communicate without relaying the communication signal through the base station.

[0038] The network device in the embodiments of the present application may be a device for communicating with a terminal device, and may also be referred to as an access network device or a radio access network device. For example, the network device may be a base station. The network device in the embodiments of the present application may refer to a radio access network (RAN) node (or device) that connects a terminal device to a wireless network. A base station may broadly cover various names as follows, or be replaced with the following names, such as: NodeB, evolved NodeB (eNB), next generation NodeB (gNB), relay station, transmitting and receiving point (TRP), transmitting point (TP), master station MeNB, secondary station SeNB, multi-standard radio (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), centralized unit-control plane (CU-CP), centralized unit-user plane (CU-UP), positioning node, etc. The base station can be a macro base station, a micro base station, a relay node, a donor node or the like, or a combination thereof. The base station can also refer to a communication module, a modem or a chip for being provided in the aforementioned device or apparatus. The base station can also be a mobile switching center and a device to device D2D, vehicle-to-everything (V2X), a device that performs the base station function in machine-to-machine (M2M) communications, a network side device in a 6G network, a device that performs the base station function in a future communication system, and the like. The base station can support networks with the same or different access technologies. The embodiments of the present application do not limit the specific technology and specific device form adopted by the network equipment.

[0039] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move based on the location of the mobile base station. In other examples, a helicopter or drone can be configured to act as a device that communicates with another base station.

[0040] In some deployments, the network device in the embodiments of the present application may be a core network device or an OAM device. The core network device may be a location management function (LMF) network element, a network slice selection function (NSSF), an authentication server function (AUSF), a unified data management (UDM), an access and mobility management function (AMF), a session management function (SMF), a policy control function (PCF), a user plane function (UPF), a sensing control function (SF), a network data analytics function (NWDAF) network element, and an AI function management entity.

[0041] In some deployments, the network device in the embodiments of the present application may refer to a CU or a DU, or the network device may include a CU and a DU. The gNB may also include an AAU.

[0042] The network equipment and terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; they can also be deployed in the air on aircraft, balloons, and satellites. The embodiments of this application do not limit the scenarios in which the network equipment and terminal devices are located.

[0043] It should be understood that all or part of the functions of the communication device in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (such as a cloud platform).

[0044] In traditional wireless communication methods, the capability information reported by terminal devices is often reported in a "what you see is what you get" (WYSIWYG) manner. This "what you see is what you get" approach can be understood as ensuring that the capability information reported by the terminal device clearly reflects the functions that the terminal device actually supports. Therefore, if a terminal device indicates support for a particular capability through capability information reporting, the network device can configure the capability at any time, including configuring the configuration associated with the capability information or activating the function associated with the capability information, without questioning whether the terminal device has the ability to execute the configuration or function associated with the capability information.

[0045] With the advancement of communications technology, the industry has begun researching artificial intelligence (AI) and machine learning (ML) models for the air interfaces of some communication systems, such as 5G and 6G. For certain air interface functions, AI-based solutions may offer performance gains compared to traditional non-AI-based solutions.

[0046] AI models typically require a large number of models, and AI models change dynamically. Due to limited memory, terminal devices cannot pre-store the large number of models required for all scenarios. They are likely to adaptively download the corresponding model when a specific scenario is encountered. In other words, the AI ​​models actually deployed on terminal devices are changing dynamically. There is currently no clear solution for how terminal devices should report capability information after introducing AI models.

[0047] In response to the above problems, this application proposes that the terminal device can report capability information related to the actually deployed AI model or AI function to the network device, or report capability information related to the AI ​​model or AI function supported by the terminal device. Correspondingly, the network device can clarify which AI models or AI functions are actually deployed by the terminal device, or which AI models or AI functions are actually supported, through the AI ​​capability information reported by the terminal device, thereby assisting the network device in performing operations related to the AI ​​model or AI function, such as: AI function activation, AI function deactivation, AI model activation, AI model deactivation, and AI model switching.

[0048] The following describes the wireless communication method provided in the embodiment of the present application in conjunction with Figures 2 to 5. The methods shown in Figures 2 to 5 can be performed by a terminal device and a network device. The terminal device may be, for example, the terminal device 120 mentioned above, and the network device may be, for example, the network device 110 mentioned above. Figures 2 and 3 illustrate a scheme in which a terminal device reports capability information related to an actually deployed AI model or AI function to a network device. Figures 4 and 5 illustrate a scheme in which a terminal device reports capability information related to an AI model or AI function supported by the terminal device to a network device.

[0049] The following two embodiments are used to introduce the above two reporting methods. It is understood that the relevant contents of the following two embodiments can be combined with each other. In the absence of conflicts, the contents of the following two embodiments can be used in combination with each other.

[0050] Example 1

[0051] Referring to Figure 2, in step S210, the terminal device sends first capability information to the network device. The first capability information may be capability information related to the AI ​​function. The embodiment of the present application does not specifically limit the content of the first capability information. For example, the first capability information is related to the AI ​​function actually deployed by the terminal device, or in other words, the first capability information can be used to indicate the AI ​​function actually deployed by the terminal device. The actually deployed AI function means that the terminal device has stored the AI ​​model corresponding to the AI ​​function. For another example, the first capability information is related to the AI ​​model actually deployed by the terminal device, or in other words, the first capability information can be used to indicate the AI ​​model actually deployed by the terminal device. The actually deployed AI model can also be referred to as the actually installed AI model, the actually stored AI model, the actually arranged AI model, the actually deployed AI model, the actually configured AI model, the actually set AI model, or the actually downloaded AI model, etc.

[0052] Accordingly, the network device can use the first capability information to know which AI models or AI functions are currently deployed on the terminal device and require the network device's management. Since the first capability information reflects the AI ​​models or AI functions actually deployed on the terminal device, the network device can directly configure and manage the terminal device based on the first capability information, which can simplify the implementation of the network device.

[0053] It should be understood that the actually deployed AI model or AI function means that the terminal device has actually deployed the AI ​​model corresponding to the corresponding AI function. When the conditions are met, the network device or terminal device can activate the corresponding AI function at any time. The essence of activating the AI ​​function is to activate the AI ​​model associated with the AI ​​function.

[0054] The embodiments of the present application do not specifically limit the relationship between AI models and AI functions. In some embodiments, AI functions and AI models may correspond one to one, for example, one AI model corresponds to one AI function, and one AI function corresponds to one AI model. In other embodiments, one AI model may correspond to multiple AI functions. In other embodiments, one AI function may correspond to multiple AI models applicable to different scenarios, or one AI function may be associated with multiple AI models applicable to different scenarios. For example, multiple AI models may implement the same AI function. Different types of AI models associated with the same AI function may correspond to different applicable conditions or applicable scenarios.

[0055] There are multiple ways to report the first capability information, which are not specifically limited in the embodiments of this application. For example, the first capability information can be reported at one or more of the following information granularities: AI function (or AI model) granularity, carrier granularity, frequency band granularity, frequency band combination granularity, and frequency range granularity.

[0056] The terminal device can report the first capability information at a single granularity, for example, at AI function (or AI model) granularity, carrier granularity, frequency band granularity, frequency band combination granularity, or frequency band range granularity. The terminal device may also report the first capability information according to a composite granularity consisting of at least two single granularities, for example, reporting according to the AI ​​function (or AI model) granularity and the carrier granularity, reporting according to the AI ​​function (or AI model) granularity and the frequency band granularity, reporting according to the AI ​​function (or AI model) granularity and the frequency band combination granularity, reporting according to the frequency band granularity and the frequency band combination granularity, reporting according to the carrier granularity and the frequency band granularity, reporting according to the carrier granularity and the frequency band granularity and the frequency band combination granularity, reporting according to the frequency band granularity and the frequency band range granularity, reporting according to the carrier granularity and the frequency band granularity and the frequency band combination granularity, reporting according to the frequency band granularity and the frequency band range granularity, reporting according to the carrier granularity and the frequency point range granularity, reporting according to the carrier granularity and the frequency band granularity and the frequency point range granularity. In some embodiments, the carrier granularity may also be replaced by the frequency point granularity, and the two may be interchangeable in the absence of conflict. Reporting the first capability information according to different granularities can realize the flexible reporting of AI capabilities, which is convenient for network devices to perform differentiated management.

[0057] The embodiments of this application do not specifically limit the content of the first capability information. The first capability information may include one or more of the following information: first information, one or more second information, one or more AI model identification information, or one or more AI function identification information. The following describes each of these types of information.

[0058] In some implementations, the first capability information may include one or more AI model identification information and one or more AI function identification information. In some implementations, the first capability information may include the first information and one or more AI model identification information. In some implementations, the first capability information may include the first information and identification information of one or more AI functions. In some implementations, the first capability information may include one or more second information and one or more AI model identification information. In some implementations, the first capability information may include one or more second information and one or more AI function identification information. In some implementations, the first capability information may include one or more second information, one or more AI function identification information, and one or more AI model identification information. In some implementations, the first capability information may include the first information, one or more AI function identification information, and one or more AI model identification information.

[0059] In some implementations, the first capability information may include first information, and the first information is used to indicate the AI ​​model set and / or AI function set actually deployed by the terminal device, or the first information is used to indicate the AI ​​model set information and / or AI function set information actually deployed by the terminal device, or the first information is used to indicate the AI ​​model and / or AI function actually deployed by the terminal device. It should be understood that the AI ​​model set here may include one or more AI models, and similarly, the AI ​​function set may include one or more AI functions. In some embodiments, the first information can be used to indicate the AI ​​model set actually deployed by the terminal device, or the first information can be used to indicate the AI ​​function set actually deployed by the terminal device, or the first information can be used to indicate the AI ​​model set and AI function set actually deployed by the terminal device.

[0060] Through the first information, the network device can know which AI model sets (or AI models or AI model set information) are currently actually deployed by the terminal device and require the network device to participate in management, or the network device can know which AI function sets (or AI functions) are currently actually deployed by the terminal device and require the network device to participate in management.

[0061] In some embodiments, there is a correspondence between the value of the first information and the AI ​​model set or AI function set. The network device can determine the AI ​​model set or AI function set actually deployed on the terminal device based on the first information reported by the terminal device and the above correspondence. The above correspondence can also be referred to as a model management mapping relationship. The network device can store and maintain the model management mapping relationship.

[0062] When the first capability information includes the first information, the first information may be sent at any of the following granularities: terminal device granularity, AI function granularity, or AI model granularity. The following describes, with reference to specific examples, how the first information may be sent at different granularities.

[0063] Example 1: The first message is sent according to the terminal device granularity

[0064] The first information is sent at the terminal device granularity, that is, from the perspective of the terminal device, reporting the first information supported by the terminal device. Based on the first information, the network device can know the AI ​​model set or AI function set actually deployed by the terminal device.

[0065] In this implementation, the value of the first information corresponds to the AI ​​model set or AI function set actually deployed by the terminal device. It can be understood that when the first information is sent according to the granularity of the terminal device, the network device will maintain a mapping relationship between each value of the first information and a specific AI model set or AI function set. Therefore, the network device can determine the AI ​​model set or AI function set actually deployed by the terminal device through the value of the first information reported by the terminal device. Furthermore, the information associated with the AI ​​model set or AI function set can be known through the AI ​​model set or AI function set. Among them, the information associated with each AI model or AI function set can include management information related to one or more AI models or AI functions.

[0066] This application does not specifically limit the content of management information related to AI models or AI functions. For example, the management information may include identification information of the AI ​​model or AI function, as well as information such as the applicable conditions and / or instructions for use of the associated AI model or AI function. In some embodiments, each AI model or AI function has its corresponding applicable conditions to indicate that the AI ​​model or AI function can be used under the conditions, and different conditions may correspond to different AI models or AI functions. For example, for the beam management function, the models corresponding to high-speed and low-speed scenarios are different. In other words, different beam management models correspond to high-speed and low-speed scenarios, respectively.

[0067] The following, in conjunction with Table 1, describes in more detail the content of the first information sent according to the granularity of the terminal device. In the following example, the network device maintains the collection information of 3 types of AI models or the collection information of AI functions, and the model-related management information includes the identification information of the AI ​​model or AI function and the applicable conditions and / or instructions for use of the AI ​​model or AI function. It should be noted that the content shown in Table 1 is only an example and should not limit this application. For example, the value of the first information can also be other values, or the value of the first information can include other numbers of values.

[0068] Table 1. Model management information mapping relationship of local maintenance of network equipment

[0069] As shown in Table 1, the network device maintains three types of first information values, each of which is associated with an AI model set or AI function set. Each AI model (or AI function) set can correspond to the identifiers of multiple AI models (or AI functions) actually deployed on the terminal device, as well as the applicable conditions or usage instructions of the associated model (or function).

[0070] For example, when the first information takes the value of "1", the associated AI model set is AI model set 1, AI model set 1 includes the identification of AI model 1 and the applicable conditions or usage instructions of the associated model (i.e., AI model 1), the identification of AI model 2 and the applicable conditions or usage instructions of the associated model (i.e., AI model 2), the identification of AI model 3 and the applicable conditions or usage instructions of the associated model (i.e., AI model 3); the associated AI function set is AI function set 1, AI function set 1 includes the identification of AI function 1 and the applicable conditions or usage instructions of the associated function (i.e., AI function 1), the identification of AI function 2 and the applicable conditions or usage instructions of the associated function (i.e., AI function 2), the identification of AI function 3 and the applicable conditions or usage instructions of the associated function (i.e., AI function 3).

[0071] For another example, when the first information takes the value of "2", the associated AI model set is AI model set 2, which includes the identifier of AI model 4 and the applicable conditions or usage instructions of the associated model (i.e., AI model 4), the identifier of AI model 5 and the applicable conditions or usage instructions of the associated model (i.e., AI model 5); the associated AI function set is AI function set 2, which includes the identifier of AI function 4 and the applicable conditions or usage instructions of the associated function (i.e., AI function 4), the identifier of AI function 5 and the applicable conditions or usage instructions of the associated function (i.e., AI function 5).

[0072] For another example, when the first information takes the value of "3", the associated AI model set is AI model set 3, which includes the identifier of AI model 6 and the applicable conditions or usage instructions of the associated model (i.e., AI model 6), the identifier of AI model 7 and the applicable conditions or usage instructions of the associated model (i.e., AI model 7); the associated AI function set is AI function set 3, which includes the identifier of AI function 6 and the applicable conditions or usage instructions of the associated function (i.e., AI function 6), the identifier of AI function 7 and the applicable conditions or usage instructions of the associated function (i.e., AI function 7).

[0073] In some implementations, when the value of the first information is the first value, it is used to indicate that the terminal device has not deployed any AI model or AI function, or to indicate that the terminal device has not actually deployed any AI model set or AI function set. The embodiment of the present application does not specifically limit the way in which the first value is taken. For example, the first value can be a special value. Exemplarily, the first value can be "0", which is used to indicate to the network device that the terminal device has not deployed any AI model or AI function, or to indicate to the network device that the terminal device has not actually deployed any AI model set or AI function set.

[0074] In some implementations, the first capability information further includes first indication information, which is used to indicate whether the terminal device has actually deployed the AI ​​model or AI function. The embodiment of the present application does not specifically limit the value of the first indication information.

[0075] In some implementations, the first indication information can be a Boolean variable. When the first indication information takes a first value, it indicates that the terminal device has actually deployed the AI ​​model or AI function; when the first indication information takes a second value, it indicates that the terminal device has not actually deployed the AI ​​model or AI function.

[0076] For example, when the value of the first indication information is 1, it indicates that the terminal device has actually deployed the AI ​​model or AI function; when the value of the first indication information is 0, it indicates that the terminal device has not actually deployed the AI ​​model or AI function.

[0077] The above description uses an example in which the first indication information is represented by one bit, but the embodiments of the present application are not limited thereto. For example, the first indication information may be represented by two bits, or the first indication information may be represented by three bits or more. This application does not impose any specific limitation on this.

[0078] In some implementations, when the first value of the first indication information indicates that the terminal device has actually deployed an AI model or AI function, the first information can further indicate the AI ​​model set or AI function set actually deployed by the terminal device.

[0079] Example 2: The first message is sent according to the AI ​​function granularity

[0080] The first information is sent at the AI ​​function granularity. That is, from the perspective of the AI ​​function, the first information related to the AI ​​function actually deployed on the terminal device is reported. For different AI functions, the terminal device can report the first information corresponding to each AI function. In other words, each AI function can correspond to one piece of first information. Based on the first information, the network device can know the AI ​​model set or AI function set actually deployed on the terminal device.

[0081] The embodiments of the present application do not specifically limit the manner in which the AI ​​function corresponding to the first information is indicated. For example, the position of the first information in the first capability information may indicate the AI ​​function corresponding to the first information. This indication method may be referred to as an implicit indication method. In another example, the AI ​​function corresponding to the first information may be indicated by an AI function identifier. This indication method may be referred to as an explicit indication method. These two indication methods are described below with reference to specific examples.

[0082] In some implementations, the AI ​​function corresponding to the first information can be indicated by the position of the first information in the first capability information. The position of each first information in the first capability information can be predefined by the protocol. Therefore, by simply determining the position of any first information in the first capability information and combining it with the definition of the first information at that position in the protocol, the AI ​​function associated with the first information can be determined. In other words, the AI ​​function corresponding to the first information can be implicitly obtained by the position information of the first information in the first capability information.

[0083] In this implementation, the first capability information may include one or more capability parameters, and any one of the one or more capability parameters may include first information corresponding to an AI function, that is, each of the one or more capability parameters corresponds to a first information. The position where each capability parameter appears in the first capability information is predefined by the protocol. Therefore, as long as the position where any capability parameter appears in the first capability information is determined, and combined with the definition description of the capability parameter at that position in the protocol, the AI ​​function associated with the capability parameter can be confirmed. In other words, the AI ​​function corresponding to the capability parameter can be implicitly obtained through the position information where the corresponding capability parameter appears in the first capability information.

[0084] The present application does not impose any specific restrictions on the content of the capability parameter, as long as it can indicate the content of the capability parameter. For example, the capability parameter can be represented by bits to indicate different capability parameters.

[0085] Taking the example of using bits to represent capability parameters and capability parameter 1 occupying 2 bits, or taking the example of using 2 bits to represent capability parameters, the first information contained in capability parameter 1 can have values ​​of "00", "01", "10" and "11".

[0086] The number of bits occupied by different capability parameters may be the same or different, and this embodiment of the present application does not specifically limit this. For example, capability parameter 1 may occupy 2 bits, capability parameter 2 may occupy 3 bits, and capability parameter 3 may occupy 2 bits.

[0087] In conjunction with Table 2, the following example illustrates the first capability information reported by a terminal device, where n capability parameters are included, and the first capability information is sent at an AI function granularity, and the AI ​​function is implicitly indicated by the position of the first information in the first capability information. Here, n is a positive integer.

[0088] Table 2: Schematic diagram of sending the first information according to the AI ​​function granularity

[0089] As shown in Table 2, the capability parameter list includes n capability parameters, namely capability parameter 1, capability parameter 2, through capability parameter n, each of which corresponds to a first information item. Each capability parameter corresponds to a position in the first capability information item and is associated with an AI function n.

[0090] For example, capability parameter 1 corresponds to a first information, wherein capability parameter 1 corresponds to parameter position 1 and is associated with AI function 1.

[0091] For another example, capability parameter 2 corresponds to a first information, wherein capability parameter 2 corresponds to parameter position 2 and is associated with AI function 2.

[0092] For another example, capability parameter n corresponds to a first information, wherein capability parameter N corresponds to parameter position N and is associated with AI function n.

[0093] In some implementations, when the value of the first information is the second value, it is used to indicate that the terminal device has not deployed any AI model corresponding to the AI ​​function corresponding to the first information. This embodiment of the application does not specifically limit the method for determining the second value. For example, the second value can be a special value. Exemplarily, the second value can be "0", which is used to indicate to the network device that the terminal device has not deployed any AI model corresponding to the AI ​​function corresponding to the first information.

[0094] In some implementations, the first information is associated with the second indication information, and the second indication information is used to indicate whether the terminal device has actually deployed the AI ​​function corresponding to the first information associated with the second indication information. The embodiment of the present application does not specifically limit the value of the second indication information.

[0095] In some implementations, the second indication information can be a Boolean variable. When the second indication information takes the first value, it indicates that the terminal device has actually deployed the AI ​​function corresponding to the first information associated with the second indication information; when the second indication information takes the second value, it indicates that the terminal device has not actually deployed the AI ​​function corresponding to the first information associated with the second indication information.

[0096] For example, when the first value of the second indication information is 1, it means that the terminal device has actually deployed the AI ​​function corresponding to the first information associated with the second indication information; when the second value of the second indication information is 0, it means that the terminal device has not actually deployed the AI ​​function corresponding to the first information associated with the second indication information.

[0097] In other implementations, the second indication information may be represented by a bit to indicate whether the terminal device has actually deployed the AI ​​function corresponding to the first information associated with the second indication information. Taking the second indication information represented by 1 bit as an example, the value of the second indication information may be "0" or "1". For example, "1" may be used to indicate that the terminal device has actually deployed the AI ​​function corresponding to the first information associated with the second indication information, and "0" may be used to indicate that the AI ​​function corresponding to the first information associated with the second indication information is not deployed. Alternatively, "0" may be used to indicate that the terminal device has actually deployed the AI ​​function corresponding to the first information associated with the second indication information, and "1" may be used to indicate that the AI ​​function corresponding to the first information associated with the second indication information is not deployed.

[0098] The above description uses an example in which the second indication information is represented by one bit, but the embodiments of the present application are not limited thereto. For example, the second indication information may be represented by two bits, or the second indication information may be represented by three bits or more. This application does not make any specific limitations on this.

[0099] In some implementations, when the first value of the second indication information indicates that the terminal device has actually deployed an AI function corresponding to a capability parameter, the first information can further indicate the AI ​​model set or AI function set actually deployed by the terminal device.

[0100] In some implementations, among the one or more capability parameters reported by the terminal device, the first information contained in any capability parameter can have multiple values, and any of these multiple values ​​can point to the management information corresponding to different groups of AI models associated with the same AI function. The network device can maintain corresponding mapping relationships for different capability parameters. The following uses Table 3 as an example to illustrate the mapping relationship between different values ​​of the first information contained in the capability parameter k and the AI ​​model management information associated with the AI ​​function. The value range of k can be {1, 2, ..., n}, where n is a positive integer.

[0101] Table 3. Model management information mapping relationship of local maintenance of network devices

[0102] Referring to Table 3, different values ​​of the first information contained in the capability parameter k can point to the function identifier associated with the same AI function k, and can point to the management information corresponding to a group of AI models associated with the same AI function. The function identifier associated with AI function k can also be understood as the identifier of AI function k. Simply put, the capability parameter k can correspond to the AI ​​function k, and different values ​​of the first information in the capability parameter k can correspond to different AI model sets or management information corresponding to different AI models.

[0103] For example, the first information value 1 contained in the capability parameter k may correspond to the function identifier associated with the AI ​​function k, and point to the model applicability conditions or usage instructions corresponding to the AI ​​model 1 associated with the AI ​​function k, the model applicability conditions or usage instructions corresponding to the AI ​​model 2 associated with the AI ​​function k, and the model applicability conditions or usage instructions corresponding to the AI ​​model 3 associated with the AI ​​function k.

[0104] For example, the first information value 2 contained in the capability parameter k can also correspond to the function identifier associated with the AI ​​function k, and point to the model applicability conditions or usage instructions corresponding to the AI ​​model 2 associated with the AI ​​function k, as well as the model applicability conditions or usage instructions corresponding to the AI ​​model 3 associated with the AI ​​function k.

[0105] For example, the first information value 3 contained in the capability parameter k can also correspond to the function identifier associated with the AI ​​function k, and point to the model applicability conditions or usage instructions corresponding to the AI ​​model 4 associated with the AI ​​function k, the model applicability conditions or usage instructions corresponding to the AI ​​model 5 associated with the AI ​​function k, and the model applicability conditions or usage instructions corresponding to the AI ​​model 6 associated with the AI ​​function k.

[0106] For example, terminal device A reports one or more capability parameters through the first capability information, and the one or more capability parameters include three capability parameters, namely capability parameter 1, capability parameter 2, and capability parameter 3.

[0107] Among them, capability parameter 1 occupies 2 bits and is associated with the spatial domain prediction function of beam measurement results. The first information contained in the reported capability parameter 1 is "01". After the network device obtains the first information contained in capability parameter 1 with a value of "01", by querying Table 3 corresponding to the locally maintained AI function, it can be known that the terminal device has deployed 3 types of AI models for the spatial domain prediction function of beam measurement results (for example, one type for high-speed scenarios, one type for low-speed scenarios, and one type for medium-speed scenarios).

[0108] Capability parameter 2 occupies 3 bits and is associated with the layer 3 mobility function. The first information contained in the reported capability parameter 2 is "010". After the network device obtains the first information value contained in the capability parameter 2 is "010", it queries Table 3 corresponding to the locally maintained AI function to know that the terminal device has deployed 2 types of AI models for the layer 3 mobility function (for example, one for layer 3 measurement event prediction and one for layer 3 cell-level measurement result prediction).

[0109] Capability parameter 3 occupies 2 bits and is associated with the indoor positioning function. The first information contained in the capability parameter 3 reported this time is "11". After the network device obtains the first information contained in the capability parameter 3 with a value of "11", it is known that the terminal device has deployed 2 types of AI models for indoor positioning functions by querying Table 3 corresponding to the locally maintained AI function (for example, one type for indoor factory environment positioning and the other type for indoor office environment positioning).

[0110] It should be understood that, for the same capability parameter, the values ​​of the first information included in the capability parameter reported by different terminal devices may be the same or different, and this application does not limit this. For example, for the same capability parameter, multiple terminal devices may report the same value of the first information. For another example, for the same capability parameter, multiple terminal devices may report different values ​​of the first information.

[0111] The above describes in detail the manner in which the AI ​​function corresponding to the first information is indicated by the position of the first information in the first capability information when the first information is sent at the AI ​​function granularity.

[0112] In another implementation, the AI ​​function corresponding to the first information can be displayed and indicated by an AI function identifier. The network device can determine which AI function is associated with each capability parameter by the value of the AI ​​function identifier included in each capability parameter. This approach is relatively simple to implement.

[0113] If the first information is sent at an AI function granularity and the AI ​​function is explicitly indicated by AI function identification information, the first capability information also includes identification information of one or more AI functions. The AI ​​function here can be an AI function actually deployed on the terminal device or an AI function that can be actually activated and used.

[0114] The embodiments of the present application do not specifically limit the relationship between the first information and the identification information of the AI ​​function. For example, the relationship between the first information and the identification information of the AI ​​function can be a one-to-one relationship; another example, the relationship between the first information and the identification information of the AI ​​function can be a one-to-many relationship; another example, the relationship between the first information and the identification information of the AI ​​function can be a many-to-one relationship.

[0115] In this implementation, the first capability information may include one or more capability parameters, and any one of the one or more capability parameters may include an AI function identifier and the first information corresponding to the AI ​​function identifier. In some embodiments, the first capability information may include a first capability parameter list, and the first capability parameter list may include the one or more capability parameters described above. In some embodiments, the first capability parameter list may also be replaced by a capability parameter list, or may also be replaced by a list, for example, a first list.

[0116] Since there is a default association between each value of the AI ​​function identifier and a specific AI function, the value of the AI ​​function identifier contained in each capability parameter can be used to confirm which AI function the capability parameter is associated with. That is, the network device can determine which AI function corresponds to the mapping relationship in Table 3 through the value of the AI ​​function identifier contained in the capability parameter, and then determine which types of AI models under the AI ​​function are currently actually deployed on the terminal device, which facilitates subsequent model management operations under the AI ​​function.

[0117] In conjunction with Table 4, the following example illustrates a case where the first capability information reported by a terminal device includes m capability parameters. The first capability information is sent at AI function granularity and the AI ​​function is indicated by AI function identification information. Here, m is a positive integer. In this case, the network device can process the first information included in the first capability information in Table 4 according to the processing method in Table 3.

[0118] Table 4: Schematic diagram of sending the first information according to the AI ​​function granularity

[0119] Referring to Table 4, the capability parameter list includes m capability parameters, namely capability parameter 1, capability parameter 2 to capability parameter m, each capability parameter corresponds to an AI function identifier and first information corresponding to the AI ​​function identifier.

[0120] For example, capability parameter 1 corresponds to AI function identifier 1 and the first information corresponding to AI function identifier 1, wherein capability parameter 1 corresponds to the first element in the capability parameter list.

[0121] For another example, capability parameter 2 corresponds to AI function identifier 2 and the first information corresponding to AI function identifier 2, wherein capability parameter 2 corresponds to the second element in the capability parameter list.

[0122] For another example, the capability parameter m corresponds to the AI ​​function identifier m and the first information corresponding to the AI ​​function identifier M, wherein the capability parameter m corresponds to the mth element in the capability parameter list.

[0123] In some implementations, if the terminal device reports a capability parameter through the first capability parameter list, it indicates that the terminal device has actually deployed at least one AI model associated with the AI ​​function corresponding to the capability parameter. In other words, if the terminal device does not deploy any AI model associated with a certain AI function, the terminal device does not need to include the capability parameter corresponding to the AI ​​function in the reported first capability parameter list information.

[0124] Example 3: The first message is sent according to the AI ​​model granularity

[0125] The first information is sent at the AI ​​model granularity. That is, from the perspective of the AI ​​model, the first information related to the AI ​​model actually deployed on the terminal device is reported. For different AI functions, the terminal device can report the first information corresponding to each AI function. In other words, each AI function can correspond to one piece of first information. Based on the first information, the network device can know the set of AI models actually deployed on the terminal device.

[0126] The embodiments of the present application do not specifically limit the manner in which the AI ​​model corresponding to the first information is indicated. For example, the position of the first information in the first capability information may be used to indicate the AI ​​model corresponding to the first information. This indication method may be referred to as an implicit indication method. In another example, the AI ​​function corresponding to the first information may be indicated by an AI model identifier. This indication method may be referred to as an explicit indication method. These two indication methods are described below with reference to specific examples.

[0127] In some implementations, the AI ​​model corresponding to the first information can be indicated by the position of the first information in the first capability information. Since the position where each first information appears in the first capability information can be predefined by the protocol, the AI ​​model associated with the first information can be determined by simply determining the position where any first information appears in the first capability information and combining it with the definition of the first information at that position in the protocol. In other words, the AI ​​model corresponding to the first information can be implicitly obtained by the position information where the first information appears in the first capability information.

[0128] In another implementation, the AI ​​model corresponding to the first information can be indicated by an AI model identifier. The network device can determine which AI model is associated with each capability parameter by the value of the AI ​​model identifier included in each capability parameter. This approach is relatively simple to implement.

[0129] If the first information is sent at the AI ​​model granularity and the AI ​​model is explicitly indicated by AI model identification information, the first capability information also includes identification information of one or more AI models. The AI ​​model here can be an AI model actually deployed on the terminal device, or an actually deployed AI model, or an actually installed AI model.

[0130] The embodiments of the present application do not specifically limit the relationship between the first information and the identification information of the AI ​​model. For example, the relationship between the first information and the identification information of the AI ​​model can be a one-to-one relationship; in another example, the relationship between the first information and the identification information of the AI ​​model can be a one-to-many relationship; in another example, the relationship between the first information and the identification information of the AI ​​model can be a many-to-one relationship.

[0131] In conjunction with Table 5, the following example illustrates a case where the first capability information reported by a terminal device includes m capability parameters. The first capability information is sent at the AI ​​model granularity and the AI ​​model is indicated by AI model identification information. Here, m is a positive integer. In this case, the network device can process the first information included in the first capability information in Table 5 according to the processing method in Table 3.

[0132] Table 5: Schematic diagram of sending the first information according to the AI ​​model granularity

[0133] Referring to Table 5, the capability parameter list includes m capability parameters, namely capability parameter 1, capability parameter 2 to capability parameter m. Each capability parameter corresponds to an AI model identifier and the first information corresponding to the AI ​​model identifier.

[0134] For example, capability parameter 1 corresponds to AI model identifier 1 and the first information corresponding to AI model identifier 1, wherein capability parameter 1 corresponds to the first element in the capability parameter list.

[0135] For another example, capability parameter 2 corresponds to AI model identifier 2 and the first information corresponding to AI model identifier 2, wherein capability parameter 2 corresponds to the second element in the capability parameter list.

[0136] For another example, the capability parameter m corresponds to the AI ​​model identifier m and the first information corresponding to the AI ​​model identifier m, wherein the capability parameter m corresponds to the mth element in the capability parameter list.

[0137] In this implementation, the first capability information may include one or more capability parameters, and any one of the one or more capability parameters includes an AI model identifier and the first information corresponding to the AI ​​model identifier. In some embodiments, the first capability information may include a second capability parameter list, and the second capability parameter list may include the one or more capability parameters mentioned above. In some embodiments, the second capability parameter list may also be replaced by a capability parameter list, or may also be replaced by a list, for example, a second list.

[0138] In some implementations, in the second capability parameter list reported by the terminal device, the first information contained in any capability parameter can have multiple values, and any of these multiple values ​​can point to management information corresponding to different groups of AI models associated with the same AI function. The network device maintains corresponding mapping relationships for different capability parameters.

[0139] Since each value of the AI ​​model identifier has a default association with a specific AI model, the value of the AI ​​model identifier included in each capability parameter can be used to determine which AI model the capability parameter is associated with. That is, the network device can use the value of the AI ​​model identifier included in the capability parameter to determine which AI model corresponds to the mapping relationship shown in Table 6, and then determine which types of AI models under the AI ​​model are currently deployed on the terminal device, facilitating subsequent model management operations under the AI ​​model. Therefore, it can also be understood that the first capability information includes the first information corresponding to the AI ​​model identifier.

[0140] Table 6: Model management information mapping relationship for local maintenance of network devices

[0141] Referring to Table 6, different values ​​of the first information contained in the capability parameter k can point to the model identifier associated with the same AI function k, and can point to the management information corresponding to a group of AI models associated with the same AI function.

[0142] For example, the first information value 1 contained in the capability parameter k may correspond to the model identifier associated with the AI ​​function k, and point to the model applicability conditions or usage instructions corresponding to the AI ​​model 1 associated with the AI ​​function k, the model applicability conditions or usage instructions corresponding to the AI ​​model 2 associated with the AI ​​function k, and the model applicability conditions or usage instructions corresponding to the AI ​​model 3 associated with the AI ​​function k.

[0143] For example, the first information value 2 contained in the capability parameter k can correspond to the model identifier associated with the AI ​​function k, and point to the model applicability conditions or usage instructions corresponding to the AI ​​model 2 associated with the AI ​​function k, as well as the model applicability conditions or usage instructions corresponding to the AI ​​model 3 associated with the AI ​​function k.

[0144] For example, the first information value 3 contained in the capability parameter k can correspond to the model identifier associated with the AI ​​function k, and point to the model applicability conditions or usage instructions corresponding to the AI ​​model 4 associated with the AI ​​function k, the model applicability conditions or usage instructions corresponding to the AI ​​model 5 associated with the AI ​​function k, and the model applicability conditions or usage instructions corresponding to the AI ​​model 6 associated with the AI ​​function k.

[0145] In some implementations, if the terminal device reports a capability parameter through the second capability parameter list, it indicates that the terminal device has actually deployed at least one AI model associated with the AI ​​function corresponding to the capability parameter. In other words, if the terminal device does not deploy any AI model associated with a certain AI function, the terminal device does not need to include the capability parameter corresponding to the AI ​​function in the reported second capability parameter list information.

[0146] In some implementations, the first capability information may include one or more second information, each of which is used to indicate the applicable conditions of the AI ​​model and / or AI function associated with each second information. In some embodiments, an AI model or AI function may correspond to one or more second information, and one second information may be associated with one applicable condition, that is, an AI model or AI function may correspond to one or more applicable conditions. Applicable conditions may also be referred to as applicable scenarios.

[0147] The applicable conditions mentioned here can be understood as each AI model or AI function has its corresponding applicable conditions, indicating that the AI ​​model or AI function can be used under these conditions. Different conditions may correspond to different types of AI models.

[0148] As an example, for the photo function, the corresponding models during the day and at night may be different. In other words, the applicable conditions of the photo model during the day and the photo model at night are different, although they are both for the photo function.

[0149] As another example, for a specific AI function, the terminal device deploys three types of AI models for the spatial domain prediction function of beam measurement results. Among them, each AI model or AI function has its corresponding applicable conditions. For example, AI model 1 associated with AI function k is for high-speed scenarios, that is, the applicable condition of AI model 1 associated with AI function k is high-speed scenarios; AI model 2 associated with AI function k is for low-speed scenarios, that is, the applicable condition of AI model 2 associated with AI function k is low-speed scenarios; AI model 3 associated with AI function k is for medium-speed scenarios, that is, the applicable condition of AI model 3 associated with AI function k is medium-speed scenarios.

[0150] When the first capability information includes one or more second information, the one or more second information can be sent at any of the following granularities: AI function granularity or AI model granularity. The following examples illustrate the content of the second information sent at different granularities.

[0151] Example 1: The second message is sent according to the AI ​​function granularity

[0152] The second information is sent at the AI ​​function granularity, that is, from the perspective of the AI ​​function, reporting one or more second information related to the AI ​​function actually deployed on the terminal device. Based on the second information, the network device can understand the applicable conditions associated with the corresponding AI function of the terminal device.

[0153] The embodiments of the present application do not specifically limit the manner in which the AI ​​function corresponding to the second information is indicated. For example, the AI ​​function corresponding to the second information may be indicated by its position within the first capability information. This manner of indication may be referred to as an implicit indication manner. In another example, the AI ​​function corresponding to the second information may be indicated by an AI function identifier. This manner of indication may be referred to as an explicit indication manner. These two manners of indication are described below with reference to specific examples.

[0154] In some implementations, the AI ​​functionality associated with the second information can be indicated by the location of the second information within the first capability information. Since the location of each set of second information within the first capability information is predefined by the protocol, the AI ​​functionality associated with any set of second information can be determined by determining the location of the second information within the first capability information and combining it with the protocol's definition of that location. In other words, the AI ​​functionality associated with a set of second information can be implicitly determined by the location of the second information within the first capability information.

[0155] In this implementation, the first capability information may include one or more capability parameters, and one capability parameter in the one or more capability parameters includes one or more second information corresponding to an AI function, that is, each capability parameter in the one or more capability parameters corresponds to a set of second information. The position where each capability parameter appears in the first capability information is predefined by the protocol. Therefore, as long as the position where any capability parameter appears in the first capability information is determined, and combined with the definition description of the capability parameter at that position in the protocol, the AI ​​function associated with the capability parameter can be confirmed. In other words, the AI ​​function corresponding to the capability parameter can be implicitly obtained through the position information where the corresponding capability parameter appears in the first capability information.

[0156] The present application does not impose any specific restrictions on the content of the capability parameter, as long as it can indicate the content of the capability parameter. For example, the capability parameter can be represented by bits to indicate different capability parameters.

[0157] Taking the example of using bits to represent the capability parameter and capability parameter 1 occupying 2 bits, or taking the example of using 2 bits to represent the capability parameter, any second information value contained in capability parameter 1 can be "00", "01", "10" and "11".

[0158] The number of bits occupied by different capability parameters may be the same or different, and this embodiment of the present application does not specifically limit this. For example, capability parameter 1 may occupy 2 bits, capability parameter 2 may occupy 3 bits, and capability parameter 3 may occupy 2 bits.

[0159] In conjunction with Table 7, the following example illustrates the first capability information reported by a terminal device, which includes n capability parameters. The second information is sent at the AI ​​function granularity, and the AI ​​function is implicitly indicated by the position of the second information in the first capability information. Here, n is a positive integer.

[0160] Table 7 Second information is sent according to AI function granularity

[0161] As shown in Table 7, the capability parameter list includes n capability parameters, namely capability parameter 1, capability parameter 2, through capability parameter n, each of which corresponds to one or more pieces of second information. Each capability parameter corresponds to a position in the first capability information and is associated with an AI function.

[0162] For example, capability parameter 1 corresponds to one or more second information, wherein capability parameter 1 corresponds to parameter position 1 and is associated with AI function 1.

[0163] For another example, capability parameter 2 corresponds to one or more second information, wherein capability parameter 2 corresponds to parameter position 2 and is associated with AI function 2.

[0164] For another example, capability parameter n corresponds to one or more second information, wherein capability parameter n corresponds to parameter position n and is associated with AI function n.

[0165] In some implementations, a set of second information is associated with third indication information, and the third indication information is used to indicate whether the terminal device has actually deployed an AI function corresponding to a set of second information associated with the third indication information. The embodiment of the present application does not specifically limit the value of the third indication information. For example, if the third indication information is a Boolean variable, then when the third indication information takes the first value, it indicates that the terminal device has actually deployed an AI function corresponding to a set of second information associated with the third indication information; when the third indication information takes the second value, it indicates that the terminal device has not actually deployed an AI function corresponding to the second information associated with the third indication information.

[0166] For example, when the second value of the third indication information is 1, it means that the terminal device has actually deployed an AI function corresponding to a set of second information associated with the third indication information; when the second value of the third indication information is 0, it means that the terminal device has not actually deployed an AI function corresponding to the second information associated with the third indication information.

[0167] In some implementations, when the first value of the third indication information indicates that the terminal device has actually deployed an AI function corresponding to a capability parameter, a set of second information associated with the third indication information can further indicate the AI ​​model actually deployed by the terminal device or the model applicability conditions or usage instructions corresponding to the AI ​​function.

[0168] The following uses Table 8 as an example to illustrate the mapping relationship between the function identifier associated with AI function k and the AI ​​model management information associated with AI function k. The value range of k can be {1, 2, ..., n}, where n is a positive integer.

[0169] Table 8: Mapping relationship of model management information maintained locally by network devices

[0170] As shown in Table 8, for an AI function, the network device or operator will maintain the applicable conditions or usage instructions associated with all AI models that can be managed under the AI ​​function. Each second information value is associated with the applicable conditions or usage instructions of a category of AI models under the same AI function. Based on one or more second information reported by the terminal device, the network device can query the mapping relationship to determine which categories of AI models are deployed on the terminal device under the AI ​​function and the applicable conditions or usage instructions associated with each category of AI models, thereby managing the AI ​​models deployed on the terminal device under the AI ​​function.

[0171] Continuing with Table 8, when a terminal device reports the function identifier of AI function k, by querying the mapping relationship in Table 8, the network device can determine that the terminal device has deployed w types of AI models for the current function. It can also determine the applicable conditions and / or usage instructions associated with each type of model, thereby managing the AI ​​models deployed on the terminal device for that AI function. The value range of w can be {1, 2, ..., n}, where n is a positive integer.

[0172] For example, when the second information value of AI function k is the second information value 1 corresponding to the AI ​​model associated with AI function k, by querying the mapping relationship in Table 8, the network device can know that the second information value 1 is associated with the applicable conditions or usage instructions associated with the first type of AI model under the AI ​​function.

[0173] For example, when the second information value of AI function k is the second information value 2 corresponding to the AI ​​model associated with AI function k, by querying the mapping relationship in Table 8, the network device can know that the second information value 2 is associated with the applicable conditions or usage instructions of the second type of AI model under the AI ​​function.

[0174] For example, when the second information value of AI function k is the second information value w corresponding to the AI ​​model associated with AI function k, by querying the mapping relationship of Table 8 corresponding to the AI ​​function, the network device can know that the second information value w is associated with the applicable conditions or usage instructions associated with the wth type of AI model under the AI ​​function.

[0175] For example, the terminal device reports three capability parameters through the first capability information, namely capability parameter 1, capability parameter 2, and capability parameter 3.

[0176] Among them, capability parameter 1 occupies 3 bits and is associated with the beam measurement result airspace prediction function. The capability parameter 1 reported this time contains three second information, with values ​​of "001", "010" and "110" respectively. After the network device obtains the three second information values ​​contained in the capability parameter 1 reported by the terminal device, it can know which types of AI models under the AI ​​function are currently deployed by the terminal device by querying Table 8, so as to facilitate the subsequent model management operations under the AI ​​function. When the second information value is "001", it is associated with the applicable conditions of the beam measurement result airspace prediction function in high-speed scenarios. When the second information value is "010", it is associated with the applicable conditions of the beam measurement result airspace prediction function in low-speed scenarios. When the second information value is "110", it is associated with the applicable conditions of the beam measurement result airspace prediction function in medium-speed scenarios.

[0177] Capability parameter 2 occupies 2 bits and is associated with the layer 3 mobility function. The reported capability parameter 2 contains two second information, with values ​​of "01" and "10" respectively. After the network device obtains the two second information values ​​contained in the capability parameter 1 reported by the terminal device, it can query Table 8 corresponding to the AI ​​function to know which types of AI models under the AI ​​function are currently deployed by the terminal device, so as to facilitate subsequent model management operations under the AI ​​function. When the second information value is "01", it is associated with the applicable conditions of the layer 3 measurement event prediction function. When the second information value is "10", it is associated with the applicable conditions of the layer 3 cell-level measurement result prediction function.

[0178] Capability parameter 3 occupies 3 bits and is associated with the indoor positioning function. The reported capability parameter 3 includes two second information values, with values ​​of "010" and "110" respectively. After the network device obtains the two second information values ​​contained in capability parameter 1 reported by the terminal device, it can query Table 8 corresponding to the AI ​​function to determine which types of AI models under the AI ​​function are currently deployed on the terminal device, facilitating subsequent model management operations under the AI ​​function. When the second information value is "010", it is associated with the applicable conditions of the indoor factory environment positioning function. When the second information value is "110", it is associated with the applicable conditions of the indoor office environment positioning function.

[0179] It should be understood that, for the same capability parameter, the values ​​of the second information included in the capability parameter reported by different terminal devices may be the same or different, and this application does not limit this. For example, for the same capability parameter, multiple terminal devices may report the same value of the second information. For another example, for the same capability parameter, multiple terminal devices may report different values ​​of the second information.

[0180] In some implementations, if a terminal device reports a capability parameter, it indicates that the terminal device has actually deployed at least one AI model associated with the AI ​​function corresponding to the capability parameter. In other words, if the terminal device does not deploy any AI model associated with a certain AI function, the terminal device does not need to include the capability parameter corresponding to the AI ​​function in the reported capability parameter information.

[0181] The above describes in detail the content indicated by the position of the second information in the first capability information when the second information is sent at the AI ​​function granularity.

[0182] In another implementation, the AI ​​function corresponding to the second information can be indicated by an AI function identifier. The network device can determine which AI function is associated with each capability parameter based on the value of the AI ​​function identifier included in each capability parameter. This approach is relatively simple to implement.

[0183] If the second information is sent at the AI ​​function granularity, and the AI ​​function is explicitly indicated by AI function identification information, the first capability information also includes identification information of one or more AI functions. The AI ​​function here refers to the AI ​​function actually deployed on the terminal device, or it can be activated for use.

[0184] The embodiments of the present application do not specifically limit the relationship between the second information and the identification information of the AI ​​function. For example, the relationship between the second information and the identification information of the AI ​​function can be a one-to-one relationship; another example, the relationship between the second information and the identification information of the AI ​​function can be a one-to-many relationship; another example, the relationship between the second information and the identification information of the AI ​​function can be a many-to-one relationship.

[0185] In this implementation, the first capability information may include one or more capability parameters, any one of which includes an AI function identifier and one or more second information corresponding to the AI ​​function identifier. In some embodiments, the first capability information may include a third capability parameter list, which may include the one or more capability parameters. In some embodiments, the third capability parameter list may also be replaced by a capability parameter list, or may also be replaced by a list, for example, a third list.

[0186] Since there is a default association between each value of the AI ​​function identifier and a specific AI function, the value of the AI ​​function identifier contained in each capability parameter can be used to confirm which AI function the capability parameter is associated with. That is, the network device can determine the mapping relationship corresponding to which AI function through the value of the AI ​​function identifier contained in the capability parameter, and then determine which types of AI models under the AI ​​function are currently actually deployed on the terminal device, which facilitates subsequent model management operations under the AI ​​function.

[0187] In conjunction with Table 9, the following example illustrates the first capability information reported by the terminal device, which includes m capability parameters, when the second information is sent according to the AI ​​function granularity and the AI ​​function is indicated by the AI ​​function identification information. Here, m is a positive integer.

[0188] Table 9: Schematic diagram of sending one or more second information according to AI function granularity

[0189] Referring to Table 9, the capability parameter list includes m capability parameters, namely capability parameter 1, capability parameter 2, up to capability parameter m. Each capability parameter corresponds to the mth element in the capability parameter list. Each capability parameter corresponds to an AI function identifier and one or more second information corresponding to the AI ​​function identifier.

[0190] For example, capability parameter 1 corresponds to AI function identifier 1 and one or more second information corresponding to AI function identifier 1, wherein capability parameter 1 corresponds to the first element in the capability parameter list.

[0191] For another example, capability parameter 2 corresponds to AI function identifier 2 and one or more second information corresponding to AI function identifier 2, wherein capability parameter 2 corresponds to the second element in the capability parameter list.

[0192] For another example, the capability parameter m corresponds to the AI ​​function identifier m and one or more second information corresponding to the AI ​​function identifier m, wherein the capability parameter m corresponds to the mth element in the capability parameter list.

[0193] In some implementations, if the terminal device reports a capability parameter through the third capability parameter list, it indicates that the terminal device has actually deployed at least one AI model associated with the AI ​​function corresponding to the capability parameter. In other words, if the terminal device does not deploy any AI model associated with a certain AI function, the terminal device does not need to include the capability parameter corresponding to the AI ​​function in the reported third capability parameter list information.

[0194] Example 2: The second message is sent according to the AI ​​model granularity

[0195] The second information is sent at the AI ​​model granularity level. That is, from the perspective of the AI ​​model, one or more second information related to the AI ​​model actually deployed on the terminal device is reported. For different AI models, the terminal device can report the second information corresponding to each AI model. In other words, each AI model can correspond to one piece of second information. Based on the second information, the network device can understand the applicable conditions of the AI ​​model deployed on the terminal device.

[0196] The embodiments of the present application do not specifically limit the manner in which the AI ​​model corresponding to the second information is indicated. For example, the AI ​​model corresponding to the second information may be indicated by its position in the first capability information. This indication method may be referred to as an implicit indication method. In another example, the AI ​​model corresponding to the second information may be indicated by its AI model identifier. This indication method may be referred to as an explicit indication method. These two indication methods are described below with reference to specific examples.

[0197] In some implementations, the AI ​​model corresponding to the second information can be indicated by the position of the second information in the first capability information. The position where a set of second information appears in the first capability information can be predefined by the protocol. Therefore, by simply determining the position where any set of second information appears in the first capability information and combining it with the definition of the second information at that position in the protocol, the AI ​​model associated with that set of second information can be determined. In other words, the AI ​​model corresponding to a set of second information can be implicitly obtained by the position information where the corresponding set of second information appears in the first capability information.

[0198] In another implementation, the AI ​​model corresponding to the second information can be displayed and indicated by an AI model identifier. The network device can determine which AI model is associated with each capability parameter by the value of the AI ​​model identifier included in the capability parameter. This method is relatively simple to implement.

[0199] When the second information is sent at the AI ​​model granularity and the AI ​​model is explicitly indicated by AI model identification information, the first capability information also includes identification information of one or more AI models. The AI ​​model here can be the AI ​​model actually deployed on the terminal device, or the actually deployed AI model, or the actually installed AI model.

[0200] The embodiments of the present application do not specifically limit the relationship between the second information and the identification information of the AI ​​model. For example, the relationship between the second information and the identification information of the AI ​​model can be a one-to-one relationship; in another example, the relationship between the second information and the identification information of the AI ​​model can be a one-to-many relationship; in another example, the relationship between the second information and the identification information of the AI ​​model can be a many-to-one relationship.

[0201] The following uses Table 10 as an example to illustrate the first capability information when the second information is at the AI ​​model granularity.

[0202] Table 10: Schematic diagram of sending one or more second information according to AI model granularity

[0203] Referring to Table 10, the capability parameter list includes m capability parameters, namely capability parameter 1, capability parameter 2 to capability parameter m. Each capability parameter corresponds to an AI model identifier and one or more second information corresponding to the AI ​​model identifier.

[0204] For example, capability parameter 1 corresponds to AI model identifier 1 and one or more second information corresponding to AI model identifier 1, wherein capability parameter 1 corresponds to the first element in the capability parameter list.

[0205] For another example, capability parameter 2 corresponds to AI model identifier 2 and one or more second information corresponding to AI model identifier 2, wherein capability parameter 2 corresponds to the second element in the capability parameter list.

[0206] For another example, the capability parameter m corresponds to the AI ​​model identifier m and one or more second information corresponding to the AI ​​model identifier m, wherein the capability parameter M corresponds to the mth element in the capability parameter list.

[0207] In this implementation, the first capability information may include one or more capability parameters, and any one of the one or more capability parameters includes an AI model identifier and one or more second information corresponding to the AI ​​model identifier. In some embodiments, the first capability information may include a fourth capability parameter list, and the fourth capability parameter list may include the one or more capability parameters mentioned above. In some embodiments, the fourth capability parameter list may also be replaced by a capability parameter list, or may also be replaced by a list, for example, a fourth list.

[0208] Since each value of the AI ​​model identifier has a default association with a specific AI model, the value of the AI ​​model identifier contained in each capability parameter can be used to confirm which AI model the capability parameter is associated with. That is, the network device can determine which AI model mapping relationship to query through the value of the AI ​​model identifier contained in the capability parameter, and then determine which types of AI models under the AI ​​model are actually deployed on the terminal device, which facilitates subsequent model management operations under the AI ​​model.

[0209] In some implementations, if a terminal device reports a capability parameter through a capability parameter list, it indicates that the terminal device has actually deployed at least one AI model associated with the AI ​​function corresponding to the capability parameter. In other words, if the terminal device does not deploy any AI model associated with a certain AI function, the terminal device does not need to include the capability parameter corresponding to the AI ​​function in the reported capability parameter list information.

[0210] The first capability information may also include identification information of one or more AI models, where the AI ​​model may be an AI model actually deployed on the terminal device or an AI model actually installed.

[0211] In this example, since the first capability information reflects the AI ​​model or AI function actually deployed on the terminal device, the network device can directly configure and manage the terminal device based on the first capability information, which can simplify the implementation of the network device.

[0212] Referring to FIG. 3 , in some embodiments, the wireless communication method of the embodiment of the present application may further include step S240, where the terminal device sends updated first capability information to the network device. The updated first capability information includes capability parameters associated with the second AI function or capability parameters associated with the second AI model.

[0213] In some embodiments, when the first capability information is updated, the terminal device may only send the updated first capability information to the network device (or a partial update of the terminal device capabilities). This can avoid the huge overhead of updating all the terminal device capability information. In other embodiments, the terminal device may also send the updated first capability information to the network device under the instruction of the network device. The following describes a solution in which the terminal device sends the updated first capability information to the network device under the instruction of the network device.

[0214] Continuing to refer to Figure 3, in some embodiments, the wireless communication method of the embodiment of the present application may further include step S230, where the network device may send fourth information to the terminal device, and the fourth information is used to instruct the terminal device to report the updated first capability information. After receiving the fourth information sent by the network device, the terminal device may send the updated first capability information to the network device. This can avoid unnecessary reporting by the terminal device, which is conducive to reducing reporting overhead. The fourth information may contain various contents, and the embodiment of the present application does not specifically limit this. For example, the fourth information may include the identifiers of one or more AI functions. For another example, the fourth information may include the identifiers of one or more AI models. For another example, the fourth information may include an indication information, which is used to trigger the terminal device to report the updated first capability information.

[0215] In some implementations, the fourth information may include identification information of one or more second AI models. Furthermore, the second AI model may be an AI model of interest to the network device. The identification information of the second AI model here can be determined based on the identification information of the first AI model included in the third information. The embodiment of the present application does not specifically limit the number of second AI models. For example, the identification information of the second AI model may include the identification information of some AI models in the identification information of the first AI model, or include the identification information of all AI models in the identification information of the first AI model. Exemplarily, the second AI model may be a subset of the first AI model.

[0216] In some implementations, the fourth information may include identification information of any one or more second AI functions. Furthermore, the second AI function may be an AI function of interest to the network device. The identification information of the second AI function here can be determined based on the identification information of the first AI function included in the third information. The embodiment of the present application does not specifically limit the number of second AI functions. For example, the identification information of the second AI function may include identification information of some AI functions in the identification information of the first AI function, or include identification information of all AI functions in the identification information of the first AI function. Exemplarily, the second AI function may be a subset of the first AI function.

[0217] The AI ​​function identification information or AI model identification information contained in the fourth information can assist the terminal device in filtering the content of the fed-back first capability information, thereby saving the overhead of uplink information feedback of the terminal device.

[0218] For example, the first capability information of the terminal device after update includes capability parameters corresponding to three AI functions, namely capability parameter 1 (associated with AI function 1), capability parameter 2 (associated with AI function 2), and capability parameter 3 (associated with AI function 3). If the network device informs the terminal device through the fourth information that it only needs to report capability parameters related to AI function 2 and AI function 3, then the first capability information reported by the terminal device only needs to include capability parameters related to AI function 2 and AI function 3.

[0219] Continuing with FIG3 , in some embodiments, the wireless communication method of the embodiment of the present application may further include step S220, where the terminal device sends third information to the network device, where the third information is used to indicate that the first capability information has been updated. After receiving the third information, the network device may determine whether the terminal device needs to report the updated capability information. The network device may determine whether the terminal device needs to report the updated capability information based on its own implementation, thereby avoiding the terminal device blindly reporting the updated first capability information.

[0220] The third information may contain a variety of contents, and the embodiments of the present application do not specifically limit this. For example, the third information may include the identifier of the first AI function whose corresponding capability information has been updated. For another example, the third information may include the identifier of the first AI model whose corresponding capability information has been updated. For another example, the third information includes an indication information, which indicates to the network device that the first capability information previously reported by the terminal device has been updated. The first AI model here may be an updated AI model, including a newly added AI model, or an AI model whose capability parameters have changed. The embodiments of the present application do not specifically limit the number of first AI models, and the number of first AI models may include one or more. Similarly, the first AI function here may also be an AI function whose corresponding capability information has been updated, including a newly added AI function, or an AI function whose capability parameters have changed. The embodiments of the present application do not specifically limit the number of first AI functions, and the number of first AI functions may include one or more.

[0221] This application does not specifically limit the manner in which the third information is carried. For example, the third information may be carried in one or more of the following messages: a connection establishment complete message, a reconfiguration complete message, a connection reestablishment complete message, a connection recovery complete message, a terminal assistance information message, or a radio resource control (RRC) message. The RRC message may be any RRC message, for example, the RRC message may be the first RRC message sent after the terminal device enters a connected state.

[0222] The AI ​​function identification information or AI model identification information contained in the third information is used to indicate to the network device which AI functions or AI model-related capability parameters of the terminal device have been updated. After receiving the third information, the network device can respond to the third information to instruct the terminal device to report the updated first capability information. The network device can determine whether it is interested in the AI ​​capability parameters updated by the terminal device based on the AI ​​function identification information or AI model identification information contained in the third information. If it is not interested, the network device may not make any response to the received third information. If it is interested, the network device can respond to the third information through the fourth information to instruct the terminal device to report the updated first capability information.

[0223] In order to inform the network device of the updated first capability information as soon as possible, in some implementations, the terminal device can directly report the capability parameters of the updated AI model or AI function without the need to indicate through third information and then report the updated first capability information.

[0224] Continuing with Figure 3, in step S230, the terminal device receives fourth information sent by the network device, where the fourth information is used to instruct the terminal device to report the updated first capability information. The above details the sending of capability information related to the actually deployed AI model or AI function by the terminal device to the network device, allowing the network device to clearly understand which AI models or AI functions are actually deployed by the terminal device, thereby assisting the network device in performing operations related to the AI ​​model or AI function, such as: AI function activation, AI function deactivation, AI model activation, AI model deactivation, and AI model switching.

[0225] Example 2

[0226] The following describes how to send capability information related to supported AI models or AI functions to network devices through terminal devices, so that the network devices can clearly understand which AI models or AI functions the terminal devices support, thereby assisting the network devices in performing operations related to the AI ​​models or AI functions. It is understandable that the methods described above and below can be used in combination with each other.

[0227] FIG4 is a flow chart of another wireless communication method provided by an embodiment of the present application. The method of FIG4 can be executed by a terminal device and a network device. The terminal device can be, for example, the terminal device 120 mentioned above, and the network device can be, for example, the network device 110 mentioned above.

[0228] Referring to Figure 4, in step S410, the terminal device sends second capability information to the network device. The second capability information may be capability information related to the AI ​​function. The embodiment of the present application does not specifically limit the content of the second capability information. For example, the second capability information may be the AI ​​function supported by the terminal device. For another example, the second capability information may be the AI ​​model supported by the terminal device. For another example, the second capability information may be the AI ​​function and AI model supported by the terminal device. Among them, the AI ​​model may be the AI ​​model supported by the terminal device, or the terminal device has the potential to run these AI models, and the AI ​​function may be the AI ​​function supported by the terminal device, or the terminal device has the potential to run these AI functions.

[0229] Accordingly, the network device can use the AI-related capabilities included in the second capability information to determine which AI models or AI functions the terminal device supports. In other words, the network device can use the AI-related capabilities included in the second capability information to determine which AI models or AI functions the terminal device is capable of potentially running. Because the second capability information only contains general AI function information, and specific AI model deployment information is reported through a non-capability information reporting process, the definition of AI function-related capability information can be simplified.

[0230] The embodiments of the present application do not specifically limit the relationship between AI models and AI functions. In some embodiments, AI functions and AI models may correspond one to one, for example, one AI model corresponds to one AI function, and one AI function corresponds to one AI model. In other embodiments, one AI model may correspond to multiple AI functions. In other embodiments, one AI function may correspond to one AI model, or in other words, one AI function may correspond to multiple AI models. For example, multiple AI models may implement the same AI function. Different AI models may correspond to different applicable conditions or scenarios.

[0231] There are multiple ways to report the second capability information, which are not specifically limited in the embodiments of this application. For example, the second capability information can be reported at one or more of the following information granularities: AI function (or AI model) granularity, carrier granularity, frequency band granularity, frequency band combination granularity, and frequency band range granularity.

[0232] The terminal device can report the second capability information at a single granularity, for example, at AI function (or AI model) granularity, carrier granularity, frequency band granularity, frequency band combination granularity, or frequency band range granularity. The terminal device may also report the second capability information according to a composite granularity consisting of at least two single granularities, for example, reporting according to AI function (or AI model) granularity and carrier granularity, reporting according to AI function (or AI model) granularity and frequency band granularity, reporting according to AI function (or AI model) granularity and frequency band combination granularity, reporting according to frequency band granularity and frequency band combination granularity, reporting according to carrier granularity and frequency band granularity, reporting according to carrier granularity and frequency band combination granularity, reporting according to frequency band granularity and frequency point range granularity, reporting according to carrier granularity and frequency band range granularity, reporting according to carrier granularity and frequency band granularity and frequency band combination granularity. In some embodiments, carrier granularity may also be replaced by frequency point granularity, and the two may be interchangeable if there is no conflict.

[0233] The present embodiment of the present application does not specifically limit the content of the second capability information. The second capability information may include one or more of the following information: one or more fifth information, one or more AI model identification information, and one or more AI function identification information. The content of the second capability information is described in detail below.

[0234] In some implementations, the second capability information may include one or more AI model identification information and one or more AI function identification information. In some implementations, the second capability information may include one or more fifth information and one or more AI model identification information. In some implementations, the second capability information may include one or more fifth information and one or more AI function identification information. In some implementations, the second capability information may include one or more fifth information, one or more AI function identification information, and one or more AI model identification information.

[0235] In some implementations, the second capability information may include one or more fifth information items, each of which indicates the applicable conditions for the AI ​​model and / or AI function associated with the fifth information item. It can be understood that one AI model or AI function may correspond to one or more fifth information items, and one piece of fifth information item may be associated with one applicable condition. In other words, one AI model or AI function may correspond to one or more applicable conditions.

[0236] The applicable conditions mentioned here can be understood as each AI model or AI function has its corresponding applicable conditions, indicating that the AI ​​model or AI function can be used under these conditions. Different conditions may correspond to different AI models under the same AI function.

[0237] As an example, for the photo-taking function, the corresponding models are different during the day and at night. In other words, the applicable conditions of the photo-taking model during the day and the photo-taking model at night are different, although they are both related to the photo-taking function.

[0238] As another example, for a specific AI function, the terminal device deploys three types of AI models for the spatial prediction function of beam measurement results. Each type of AI model has its corresponding applicable conditions. For example, AI model 1 associated with AI function k is for high-speed scenarios, which means that the applicable condition of AI model 1 associated with AI function k is high-speed scenarios; AI model 2 associated with AI function k is for low-speed scenarios, which means that the applicable condition of AI model 2 associated with AI function k is low-speed scenarios; AI model 3 associated with AI function k is for medium-speed scenarios, which means that the applicable condition of AI model 3 associated with AI function k is medium-speed scenarios.

[0239] When the second capability information includes one or more fifth information, the one or more fifth information may be sent at any of the following granularities: AI function granularity or AI model granularity. The following examples illustrate the content of the fifth information sent at different granularities.

[0240] Example 1: The fifth message is sent according to the AI ​​function granularity

[0241] The fifth information is sent at the AI ​​function granularity. That is, from the perspective of the AI ​​function, one or more fifth information related to the AI ​​function supported by the terminal device is reported. For different AI functions, the terminal device can report one or more fifth information corresponding to each AI function. Based on the one or more fifth information, the network device can understand the one or more applicable conditions corresponding to the AI ​​function supported by the terminal device.

[0242] The embodiments of this application do not specifically limit the manner in which the AI ​​function corresponding to the fifth information is indicated. For example, the AI ​​function corresponding to a set of fifth information can be indicated by its position in the second capability information. This indication method can be called an implicit indication method. In another example, the AI ​​function corresponding to the set of fifth information can be indicated by an AI function identifier. This indication method can be called an explicit indication method. The following describes these two indication methods with specific examples.

[0243] In some implementations, the AI ​​functionality associated with a set of fifth information can be indicated by the location of the fifth information within the second capability information. The location of each set of fifth information within the second capability information is predefined by the protocol. Therefore, by simply determining the location of any set of fifth information within the second capability information and combining it with the protocol definition of the fifth information at that location, the AI ​​functionality associated with that set of fifth information can be determined. In other words, the AI ​​functionality associated with the fifth information can be implicitly determined by the location of the corresponding fifth information within the second capability information.

[0244] In this implementation, the second capability information may include one or more capability parameters, one of which includes one or more fifth information corresponding to an AI function, i.e., each of the one or more capability parameters includes a set of fifth information. The position where each capability parameter appears in the second capability information is predefined by the protocol. Therefore, by simply determining the position where any capability parameter appears in the second capability information and combining it with the definition of the capability parameter at that position in the protocol, the AI ​​function associated with the capability parameter can be determined. In other words, the AI ​​function corresponding to the capability parameter can be implicitly obtained through the position information where the corresponding capability parameter appears in the second capability information.

[0245] The present application does not impose any specific restrictions on the content of the capability parameter, as long as it can indicate the content of the capability parameter. For example, the capability parameter can be represented by bits to indicate different capability parameters.

[0246] Taking the example of using bits to represent capability parameters and capability parameter 1 occupying 2 bits, or taking the example of using 2 bits to represent capability parameters, the fifth information contained in capability parameter 1 can have values ​​of "00", "01", "10" and "11".

[0247] The number of bits occupied by different capability parameters may be the same or different, and this embodiment of the present application does not specifically limit this. For example, capability parameter 1 may occupy 2 bits, capability parameter 2 may occupy 3 bits, and capability parameter 3 may occupy 2 bits.

[0248] In conjunction with Table 11, the following example illustrates the second capability information reported by a terminal device, where n capability parameters are included. The fifth information is sent at AI function granularity, and the AI ​​function is implicitly indicated by the position of each group of fifth information in the second capability information. Here, n is a positive integer.

[0249] Table 11: Schematic diagram of sending the fifth information according to the AI ​​function granularity

[0250] As shown in Table 11, the capability parameter list includes n capability parameters, namely capability parameter 1, capability parameter 2, through capability parameter n, each of which corresponds to a set of fifth information. Each capability parameter corresponds to a position in the second capability information and is associated with an AI function n.

[0251] For example, capability parameter 1 corresponds to a set of fifth information, wherein capability parameter 1 corresponds to parameter position 1 and is associated with AI function 1.

[0252] For another example, capability parameter 2 corresponds to a set of fifth information, wherein capability parameter 2 corresponds to parameter position 2 and is associated with AI function 2.

[0253] For another example, capability parameter n corresponds to a set of fifth information, wherein capability parameter n corresponds to parameter position n and is associated with AI function n.

[0254] In some implementations, when the fifth information is the second value, it is used to indicate that the terminal device does not support the AI ​​function corresponding to the fifth information. This embodiment of the application does not specifically limit the method for determining the second value. For example, the second value can be a special value. Exemplarily, the second value can be "0" to indicate to the network device that the terminal device does not support the AI ​​function corresponding to the fifth information.

[0255] In some implementations, the fifth information is associated with the fourth indication information, and the fourth indication information is used to indicate whether the terminal device supports the AI ​​function corresponding to the fifth information associated with the fourth indication information. The embodiment of the present application does not specifically limit the value of the fourth indication information. For example, the fourth indication information can be a Boolean variable. When the value of the fourth indication information is the first value, it indicates that the terminal device supports the AI ​​function corresponding to the fifth information associated with the fourth indication information; when the value of the fourth indication information is the second value, it indicates that the terminal device does not support the AI ​​function corresponding to the fifth information associated with the fourth indication information.

[0256] For example, when the second value of the fourth indication information is "1", it means that the terminal device supports the AI ​​function corresponding to the fifth information associated with the fourth indication information; when the second value of the fourth indication information is "0", it means that the terminal device does not support the AI ​​function corresponding to the fifth information associated with the fourth indication information.

[0257] In some implementations, when the first value of the fourth indication information indicates that the terminal device supports an AI function corresponding to a capability parameter, one or more fifth information associated with the fourth indication information can further indicate the AI ​​model supported by the terminal device or the model applicability conditions or usage instructions corresponding to the AI ​​function.

[0258] In some implementations, among the one or more capability parameters reported by the terminal device, any fifth information contained in any capability parameter can have multiple values, and these multiple values ​​can point to management information corresponding to a group of AI models associated with the same AI function. The network device maintains mapping relationships for different capability parameters. Table 12 is used below as an example to illustrate the mapping relationship between different values ​​of the fifth information contained in the capability parameter k and the AI ​​model management information associated with the AI ​​function. The value range of k can be {1, 2, ..., n}, where n is a positive integer.

[0259] Table 12: Model management information mapping relationship for local maintenance of network devices

[0260] As shown in Table 12, for an AI function, the network device or operator will maintain the applicable conditions or usage instructions associated with all AI models that can be managed under the AI ​​function. Each fifth information value is associated with the applicable conditions or usage instructions of a category of AI models under the same AI function. Based on one or more fifth information reported by the terminal device, the network device can query the mapping relationship to determine which categories of AI models are deployed on the terminal device under the AI ​​function and the applicable conditions or usage instructions associated with each category of AI models, thereby managing the AI ​​models deployed on the terminal device under the AI ​​function.

[0261] Continuing with Table 12, when a terminal device reports the function identifier of AI function k, by querying the mapping relationship in Table 12, the network device can determine that the terminal device has deployed w types of AI models for the current function. It can also determine the applicable conditions and / or usage instructions associated with each type of model, thereby managing the AI ​​models deployed on the terminal device for that AI function. The value range of w can be {1, 2, ..., n}, where n is a positive integer.

[0262] For example, when the fifth information value of AI function k is the fifth information value 1 corresponding to the AI ​​model associated with AI function k, by querying the mapping relationship in Table 12, the network device can know that the fifth information value 1 is associated with the applicable conditions or usage instructions associated with the first type of AI model under the AI ​​function.

[0263] For example, when the fifth information value of AI function k is the fifth information value 2 corresponding to the AI ​​model associated with AI function k, by querying the mapping relationship in Table 12, the network device can know that the fifth information value 2 is associated with the applicable conditions or usage instructions of the second type of AI model under the AI ​​function.

[0264] For example, when the fifth information value of AI function k is the fifth information value w corresponding to the AI ​​model associated with AI function k, by querying the mapping relationship of Table 12 corresponding to the AI ​​function, the network device can know that the fifth information value w is associated with the applicable conditions or usage instructions associated with the wth type of AI model under the AI ​​function.

[0265] For example, terminal device A reports three capability parameter lists through the second capability information, namely capability parameter 1, capability parameter 2, and capability parameter 3.

[0266] Among them, capability parameter 1 occupies 3 bits and is associated with the beam measurement result airspace prediction function. The capability parameter 1 reported this time contains three fifth information, with values ​​of "001", "010" and "110" respectively. After the network device obtains the three fifth information values ​​contained in the capability parameter 1 reported by the terminal device, it can know which types of AI models under the AI ​​function are currently actually deployed by the terminal device by querying Table 12, so as to facilitate subsequent model management operations under the AI ​​function. When the fifth information value is "001", it is associated with the applicable conditions of the beam measurement result airspace prediction function in high-speed scenarios. When the fifth information value is "010", it is associated with the applicable conditions of the beam measurement result airspace prediction function in low-speed scenarios. When the fifth information value is "110", it is associated with the applicable conditions of the beam measurement result airspace prediction function in medium-speed scenarios.

[0267] Capability parameter 2 occupies 2 bits and is associated with the layer 3 mobility function. The reported capability parameter 2 contains two fifth information values, which are "01" and "10" respectively. After the network device obtains the two fifth information values ​​contained in the capability parameter 1 reported by the terminal device, it can query Table 12 corresponding to the AI ​​function to know which types of AI models under the AI ​​function are currently deployed by the terminal device, so as to facilitate subsequent model management operations under the AI ​​function. When the fifth information value is "01", it is associated with the applicable conditions of the layer 3 measurement event prediction function. When the fifth information value is "10", it is associated with the applicable conditions of the layer 3 cell-level measurement result prediction function.

[0268] Capability parameter 3 occupies 3 bits and is associated with the indoor positioning function. The reported capability parameter 3 includes two fifth information values, with values ​​of "010" and "110" respectively. After the network device obtains the two fifth information values ​​contained in capability parameter 1 reported by the terminal device, it can query Table 12 corresponding to the AI ​​function to know which types of AI models under the AI ​​function are currently deployed on the terminal device, facilitating subsequent model management operations under the AI ​​function. When the fifth information value is "010", it is associated with the applicable conditions of the indoor factory environment positioning function. When the fifth information value is "110", it is associated with the applicable conditions of the indoor office environment positioning function.

[0269] It should be understood that for the same capability parameter, the value of the fifth information included in the capability parameter reported by different terminal devices may be the same or different, and this application does not limit this. For example, for the same capability parameter, multiple terminal devices may report the same value of the fifth information. For another example, for the same capability parameter, multiple terminal devices may report different values ​​of the fifth information.

[0270] In some implementations, if a terminal device reports a capability parameter, it indicates that the terminal device supports at least one AI model associated with the AI ​​function corresponding to the capability parameter. In other words, if the terminal device does not support any AI model associated with a certain AI function, the terminal device does not need to include the capability parameter corresponding to the AI ​​function in the reported capability parameter information.

[0271] The above describes in detail the content indicated by the position of the fifth information in the second capability information when the fifth information is sent at the AI ​​function granularity.

[0272] In another implementation, the AI ​​function corresponding to the fifth information can be indicated by an AI function identifier. The network device can determine which AI function is associated with each capability parameter by the value of the AI ​​function identifier included in each capability parameter. This approach is relatively simple to implement.

[0273] If the fifth information is sent at the AI ​​function granularity and the AI ​​function is explicitly indicated by the AI ​​function identification information, the second capability information also includes identification information of one or more AI functions. The AI ​​function here is the AI ​​function supported by the terminal device, that is, the AI ​​function with potential activation capability.

[0274] In some implementations, the identification information of one or more AI functions may be combined with other information in the second capability information. For example, the identification information of the AI ​​function may be combined with the fifth information. In other words, the second capability information may include both the fifth information and the identification information of one or more AI functions.

[0275] The embodiments of this application do not specifically limit the relationship between the fifth information and the identification information of the AI ​​function. For example, the relationship between the fifth information and the identification information of the AI ​​function can be a one-to-one relationship; another example, the relationship between the fifth information and the identification information of the AI ​​function can be a one-to-many relationship; another example, the relationship between the fifth information and the identification information of the AI ​​function can be a many-to-one relationship.

[0276] In this implementation, the second capability information may include one or more capability parameters, any one of which includes an AI function identifier and one or more fifth information corresponding to the AI ​​function identifier. In some embodiments, the second capability information may include a fifth capability parameter list, which may include the one or more capability parameters. In some embodiments, the fifth capability parameter list may be replaced by a capability parameter list, or may be replaced by a list, for example, a fifth list.

[0277] Since there is a default association between each value of the AI ​​function identifier and a specific AI function, the value of the AI ​​function identifier contained in each capability parameter can be used to confirm which AI function the capability parameter is associated with. That is, the network device can determine which AI function corresponds to the mapping relationship in Table 13 through the value of the AI ​​function identifier contained in the capability parameter, and then determine which types of AI models under the AI ​​function are currently actually deployed on the terminal device, so as to facilitate subsequent model management operations under the AI ​​function.

[0278] In conjunction with Table 13, the second capability information reported by the terminal device includes m capability parameters as an example, and the second capability information is exemplified when the fifth information is sent according to the AI ​​function granularity and the AI ​​function is indicated by the AI ​​function identification information. Here, m is a positive integer.

[0279] Table 13: Schematic diagram of sending the fifth information according to the AI ​​function granularity

[0280] Referring to Table 13, the capability parameter list contains m capability parameters, namely capability parameter 1, capability parameter 2 to capability parameter m, each capability parameter corresponds to the mth element in the capability parameter list, each capability parameter corresponds to an AI function identifier and one or more fifth information corresponding to the AI ​​function identifier.

[0281] For example, capability parameter 1 corresponds to AI function identifier 1 and one or more fifth information corresponding to AI function identifier 1, wherein capability parameter 1 corresponds to the first element in the capability parameter list.

[0282] For another example, capability parameter 2 corresponds to AI function identifier 2 and one or more fifth information corresponding to AI function identifier 2, wherein capability parameter 2 corresponds to the second element in the capability parameter list.

[0283] Furthermore, the capability parameter m corresponds to the AI ​​function identifier m and one or more fifth information corresponding to the AI ​​function identifier M, wherein the capability parameter m corresponds to the mth element in the capability parameter list.

[0284] In some implementations, if the terminal device reports a capability parameter through the fifth capability parameter list, it indicates that the terminal device supports at least one AI model associated with the AI ​​function corresponding to the capability parameter. In other words, if the terminal device does not support any AI model associated with a certain AI function, the terminal device does not need to include the capability parameter corresponding to the AI ​​function in the reported fifth capability parameter list information.

[0285] Example 2: The fifth message is sent according to the AI ​​model granularity

[0286] The fifth information is sent at the AI ​​model granularity, that is, from the perspective of the AI ​​model, reporting one or more fifth information related to the AI ​​model supported by the terminal device. Based on the one or more fifth information, the network device can understand one or more applicable conditions of the AI ​​model supported by the terminal device.

[0287] The embodiments of the present application do not specifically limit the manner in which the AI ​​model corresponding to the fifth information is indicated. For example, the AI ​​model corresponding to the fifth information may be indicated by the position of the fifth information in the second capability information. This manner of indication may be referred to as an implicit manner of indication. In another example, the AI ​​function corresponding to the fifth information may be indicated by an AI model identifier. This manner of indication may be referred to as an explicit manner of indication. These two manners of indication are described below with reference to specific examples.

[0288] In some implementations, the AI ​​model corresponding to the fifth information can be indicated by the location of the fifth information in the second capability information. The location of each set of fifth information in the second capability information can be predefined by the protocol. Therefore, by simply determining the location of any set of fifth information in the second capability information and combining it with the definition of the fifth information at that location in the protocol, the AI ​​model associated with that set of fifth information can be determined. In other words, the AI ​​model corresponding to a set of fifth information can be implicitly obtained by the location information of the fifth information in the second capability information.

[0289] In another implementation, the AI ​​model corresponding to the fifth information can be indicated by an AI model identifier. The network device can determine which AI model is associated with each capability parameter by the value of the AI ​​model identifier included in the capability parameter. This approach is relatively simple to implement.

[0290] When the fifth information is sent at the AI ​​model granularity and the AI ​​model is explicitly indicated by the AI ​​model identification information, the second capability information also includes identification information of one or more AI models. The AI ​​model here can be an AI model supported by the terminal device.

[0291] The embodiments of the present application do not specifically limit the relationship between the fifth information and the identification information of the AI ​​model. For example, the relationship between the fifth information and the identification information of the AI ​​model can be a one-to-one relationship; in another example, the relationship between the fifth information and the identification information of the AI ​​model can be a one-to-many relationship; in another example, the relationship between the fifth information and the identification information of the AI ​​model can be a many-to-one relationship.

[0292] The following uses Table 14 as an example to illustrate the second capability information of the fifth information according to the AI ​​model granularity.

[0293] Table 14: Schematic diagram of sending the fifth information according to the AI ​​model granularity

[0294] Referring to Table 14, the capability parameter list includes m capability parameters, namely capability parameter 1, capability parameter 2 to capability parameter m. Each capability parameter corresponds to an AI model identifier and one or more fifth information corresponding to the AI ​​model identifier.

[0295] For example, capability parameter 1 corresponds to AI model identifier 1 and one or more fifth information corresponding to AI model identifier 1, wherein capability parameter 1 corresponds to the first element in the capability parameter list.

[0296] For another example, capability parameter 2 corresponds to AI model identifier 2 and one or more fifth information corresponding to AI model identifier 2, wherein capability parameter 2 corresponds to the second element in the capability parameter list.

[0297] For another example, the capability parameter m corresponds to the AI ​​model identifier m and one or more fifth information corresponding to the AI ​​model identifier m, wherein the capability parameter m corresponds to the mth element in the capability parameter list.

[0298] In this implementation, the second capability information may include one or more capability parameters, and any one of the one or more capability parameters includes an AI model identifier and one or more fifth information corresponding to the AI ​​model identifier. In some embodiments, the second capability information may include a sixth capability parameter list, and the sixth capability parameter list may include the above-mentioned one or more capability parameters. In some embodiments, the sixth capability parameter list may also be replaced by a capability parameter list, or may also be replaced by a list, for example, a sixth list.

[0299] Since each value of the AI ​​model identifier has a default association with a specific AI model, the value of the AI ​​model identifier contained in each capability parameter can be used to determine which AI model the capability parameter is associated with. That is, the network device can determine which AI model mapping relationship to query based on the value of the AI ​​model identifier contained in the capability parameter, and then determine which types of AI models under the AI ​​model are supported by the terminal device, facilitating subsequent model management operations under the AI ​​model. In some implementations, if a terminal device reports a capability parameter through a capability parameter list, it indicates that the terminal device supports at least one AI model associated with the AI ​​function corresponding to the capability parameter. In other words, if the terminal device does not support any AI model associated with a certain AI function, the terminal device does not need to include the capability parameter corresponding to the AI ​​function in the reported capability parameter list information.

[0300] The second capability information may also include identification information of one or more AI models, where the AI ​​model may be an AI model supported by the terminal device. In some implementations, the identification information of the AI ​​model may be combined with other information included in the first capability information. For example, the identification information of the AI ​​model may be combined with the first information, that is, the first capability information may include the first information and the identification information of one or more AI models at the same time. For another example, the identification information of the AI ​​model may be combined with the second information, that is, the first capability information may include the second information and the identification information of one or more AI models at the same time.

[0301] In this example, the second capability information contains rough AI function information, and the specific AI model deployment information is carried out through the non-capability information reporting process. On the one hand, it can simplify the definition of capability information related to AI functions, and on the other hand, it can avoid the excessive overhead caused by frequently updating the capability information reported by all terminal devices due to the dynamic changes of the AI ​​model.

[0302] Referring to Figure 5, in some embodiments, the wireless communication method of the embodiment of the present application may further include step S440, where the terminal device sends sixth information to the network device. The sixth information may be capability information related to the AI ​​model or AI function, or in other words, the sixth information is related to the AI ​​model or AI function actually deployed by the terminal device. Among them, the AI ​​model may be an actually deployed AI model or an actually installed AI model, and the AI ​​function may be an actually deployed AI function or an activatable AI function. Accordingly, the network device can know which AI models or AI functions currently actually deployed by the terminal device require the network device to participate in management through the AI-related capabilities contained in the sixth information.

[0303] In some implementations, the sixth information may include one or more seventh information, each of which indicates the applicable conditions of the AI ​​model or AI function associated with the seventh information. It can be understood that one AI model or AI function may correspond to one or more seventh information, and one piece of seventh information may be associated with one applicable condition. In other words, one AI model or AI function may correspond to one or more applicable conditions.

[0304] The applicable conditions mentioned here can be understood as each AI model or AI function has its corresponding applicable conditions, indicating that the AI ​​model or AI function can be used under these conditions, and different conditions may correspond to different AI models or AI functions.

[0305] As an example, for the photo-taking function, the corresponding models are different during the day and at night. In other words, the applicable conditions of the photo-taking model during the day and the photo-taking model at night are different.

[0306] As another example, for a specific AI function, the terminal device deploys three types of AI models for the spatial prediction function of beam measurement results. Each type of AI model has its corresponding applicable conditions. For example, AI model 1 associated with AI function k is for high-speed scenarios, which means that the applicable condition of AI model 1 associated with AI function k is high-speed scenarios; AI model 2 associated with AI function k is for low-speed scenarios, which means that the applicable condition of AI model 2 associated with AI function k is low-speed scenarios; AI model 3 associated with AI function k is for medium-speed scenarios, which means that the applicable condition of AI model 3 associated with AI function k is medium-speed scenarios.

[0307] When the sixth information includes the seventh information, the seventh information may be sent at any of the following granularities: AI function granularity or AI model granularity. The following examples illustrate the content of the seventh information sent at different granularities.

[0308] Example 1: The seventh message is sent according to the AI ​​function granularity

[0309] The seventh information is sent at the AI ​​function granularity level. That is, from the perspective of the AI ​​function, one or more seventh information items related to the AI ​​function actually deployed on the terminal device are reported. Based on the seventh information, the network device can understand one or more applicable conditions associated with the AI ​​function deployed on the terminal device.

[0310] The embodiments of the present application do not specifically limit the manner in which the AI ​​function corresponding to the seventh information is indicated. For example, the position of a set of seventh information within the sixth information may indicate the AI ​​function corresponding to the set of seventh information. This indication method may be referred to as an implicit indication method. In another example, the AI ​​function corresponding to the set of seventh information may be indicated by an AI function identifier. This indication method may be referred to as an explicit indication method. These two indication methods are described below with reference to specific examples.

[0311] In some implementations, the AI ​​function corresponding to the seventh information can be indicated by the position of the set of seventh information within the sixth information. The position of each set of seventh information within the sixth information can be predefined by the protocol. Therefore, by simply determining the position of any set of seventh information within the sixth information and combining it with the protocol definition of the seventh information at that position, the AI ​​function associated with that set of seventh information can be determined. In other words, the AI ​​function corresponding to the seventh information can be implicitly obtained by the position of the set of seventh information within the sixth information.

[0312] In conjunction with Table 15, the following example illustrates the sixth information reported by a terminal device, including n capability parameters, when the seventh information is sent at AI function granularity and the AI ​​function is implicitly indicated by the position of a set of seventh information in the sixth information. Here, n is a positive integer.

[0313] Table 15: Schematic diagram of sending the seventh information according to the AI ​​function granularity

[0314] As shown in Table 15, the capability parameter list includes n capability parameters, namely capability parameter 1, capability parameter 2, through capability parameter n, each of which corresponds to a set of seventh information. Each capability parameter corresponds to a position in the sixth information and is associated with an AI function n.

[0315] For example, capability parameter 1 corresponds to a set of seventh information, wherein capability parameter 1 corresponds to parameter position 1 and is associated with AI function 1.

[0316] For another example, capability parameter 2 corresponds to a set of seventh information, wherein capability parameter 2 corresponds to parameter position 2 and is associated with AI function 2.

[0317] For another example, capability parameter n corresponds to a set of seventh information, wherein capability parameter n corresponds to parameter position n and is associated with AI function n.

[0318] The above describes in detail the situation where a group of seventh information is sent at the AI ​​function granularity, and the AI ​​function corresponding to the group of seventh information is indicated by the position of the group of seventh information in the sixth information.

[0319] In another implementation, the AI ​​function corresponding to the seventh information can be displayed and indicated by an AI function identifier. The network device can determine which AI function is associated with each capability parameter by the value of the AI ​​function identifier included in each capability parameter. This approach is relatively simple to implement.

[0320] If the seventh information is sent at the AI ​​function granularity and the AI ​​function is explicitly indicated by the AI ​​function identification information, the second capability information also includes the identification information of one or more AI functions. The AI ​​function here refers to the AI ​​function actually deployed on the terminal device, or it can also be an AI function that can be actually activated.

[0321] The embodiments of the present application do not specifically limit the relationship between the seventh information and the identification information of the AI ​​function. For example, the relationship between the seventh information and the identification information of the AI ​​function can be a one-to-one relationship; another example, the relationship between the seventh information and the identification information of the AI ​​function can be a one-to-many relationship; another example, the relationship between the seventh information and the identification information of the AI ​​function can be a many-to-one relationship.

[0322] In this implementation, the sixth information may include one or more capability parameters, any one of which may include an AI function identifier and one or more seventh information corresponding to the AI ​​function identifier. In some embodiments, the sixth information may include a seventh capability parameter list, which may include the one or more capability parameters. In some embodiments, the seventh capability parameter list may be replaced by a capability parameter list, or may be replaced by a list, for example, a seventh list.

[0323] Example 3: The seventh information is sent according to the AI ​​model granularity

[0324] The seventh information is sent at the AI ​​model granularity, that is, from the perspective of the AI ​​model, reporting one or more seventh information actually deployed on the terminal device. Based on one or more seventh information, the network device can understand one or more applicable conditions corresponding to the AI ​​model actually deployed on the terminal device.

[0325] The embodiments of the present application do not specifically limit the manner in which the AI ​​model corresponding to the seventh information is indicated. For example, the position of a set of seventh information within the sixth information may be used to indicate the AI ​​model corresponding to the set of seventh information. This indication method may be referred to as an implicit indication method. In another example, the AI ​​function corresponding to the set of seventh information may be indicated by an AI model identifier. This indication method may be referred to as an explicit indication method. These two indication methods are described below with reference to specific examples.

[0326] In some implementations, the AI ​​model corresponding to a set of seventh information can be indicated by the position of the set of seventh information in the sixth information. The position of each set of seventh information in the sixth information can be predefined by the protocol. Therefore, by simply determining the position of any set of seventh information in the sixth information and combining it with the definition of the seventh information at that position in the protocol, the AI ​​model associated with that set of seventh information can be determined. In other words, the AI ​​model corresponding to a set of seventh information can be implicitly obtained by the position information of the corresponding set of seventh information in the sixth information.

[0327] In another implementation, the AI ​​model corresponding to the seventh information can be indicated by an AI model identifier. The network device can determine which AI model is associated with each capability parameter by the value of the AI ​​model identifier included in the capability parameter. This method is relatively simple to implement.

[0328] If the seventh capability information is sent at the AI ​​model granularity and the AI ​​model is explicitly indicated by the AI ​​model identification information, the second capability information also includes the identification information of one or more AI models. The AI ​​model here can be an AI model actually deployed on the terminal device or an AI model that can be actually activated and used.

[0329] The embodiments of the present application do not specifically limit the relationship between the seventh information and the identification information of the AI ​​model. For example, the relationship between the seventh information and the identification information of the AI ​​model can be a one-to-one relationship; in another example, the relationship between the seventh information and the identification information of the AI ​​model can be a one-to-many relationship; in another example, the relationship between the seventh information and the identification information of the AI ​​model can be a many-to-one relationship.

[0330] The following uses Table 16 as an example to illustrate the sixth information when the seventh information is based on the AI ​​model granularity.

[0331] Table 16: Schematic diagram of sending the seventh information according to the AI ​​model granularity

[0332] Referring to Table 16, the capability parameter list includes m capability parameters, namely capability parameter 1, capability parameter 2 to capability parameter m. Each capability parameter corresponds to an AI model identifier and one or more seventh information corresponding to the AI ​​model identifier.

[0333] For example, capability parameter 1 corresponds to AI model identifier 1 and one or more seventh information corresponding to AI model identifier 1, wherein capability parameter 1 corresponds to the first element in the capability parameter list.

[0334] For another example, capability parameter 2 corresponds to AI model identifier 2 and one or more seventh information corresponding to AI model identifier 2, wherein capability parameter 2 corresponds to the second element in the capability parameter list.

[0335] For example, the capability parameter m corresponds to the AI ​​model identifier m and one or more seventh information corresponding to the AI ​​model identifier m, wherein the capability parameter m corresponds to the mth element in the capability parameter list.

[0336] In this implementation, the sixth information may include one or more capability parameters, any one of which includes an AI model identifier and one or more seventh information corresponding to the AI ​​model identifier. In some embodiments, the sixth information may include an eighth capability parameter list, which may include the one or more capability parameters mentioned above. In some embodiments, the eighth capability parameter list may also be replaced by a capability parameter list, or may also be replaced by a list, for example, an eighth list.

[0337] In some embodiments, the terminal device may send the sixth information to the network device, which helps the network device to promptly obtain the AI ​​model or AI function information actually deployed by the terminal device. In other embodiments, the terminal device may also send the sixth information to the network device under the instruction of the network device. The following describes a solution in which the terminal device sends the sixth information to the network device under the instruction of the network device.

[0338] Continuing to refer to Figure 5, in some embodiments, the wireless communication method of the embodiment of the present application may also include step S430, and the network device may send eighth information to the terminal device, and the eighth information is used to instruct the terminal device to send model deployment information to the network device. The model deployment information here can be understood as the AI ​​model or AI function information that the network device is interested in, or the AI ​​model or AI function information that the network device pays attention to.

[0339] The eighth information may contain a variety of contents, which are not specifically limited in the embodiments of this application. The eighth information may include one or more of the following information: identification information corresponding to the AI ​​model of interest to the network device; identification information corresponding to the AI ​​function of interest to the network device; and fifth indication information. The contents of the eighth information are described in detail below.

[0340] In some implementations, the eighth information may include one or more AI function identification information, which may be identification information corresponding to the AI ​​function that the network device is concerned about. In other words, the AI ​​function corresponding to these AI function identification information is the AI ​​function that the network device is concerned about. Accordingly, the AI ​​function set associated with the sixth information sent by the terminal device should be a subset of the AI ​​function set associated with one or more AI function identification information contained in the eighth information.

[0341] In some implementations, the eighth information may include one or more AI model identification information, which may be identification information corresponding to the AI ​​model that the network device pays attention to. In other words, the AI ​​model corresponding to these AI model identification information is the AI ​​model that the network device pays attention to. Accordingly, the AI ​​model set associated with the sixth information sent by the terminal device should be a subset of the AI ​​model set associated with one or more AI function identification information contained in the eighth information.

[0342] In some other implementations, the eighth information may include fifth indication information, where the fifth indication information is used to instruct the terminal device to send model deployment information to the network device.

[0343] In some implementations, before the terminal device receives the eighth information sent by the network device, the terminal device may send ninth information to the network device, where the ninth information is used to indicate to the terminal device that there is reportable model deployment information, or that the terminal device has deployed an AI model or AI function. By reporting the model deployment information or the deployed AI model or AI function through the sixth information, the dynamic update process of the AI ​​model or AI function deployment information can be decoupled from the capability information reporting process, thereby making the AI ​​model or AI function update process flexible and independent, which is conducive to the flexible commercial use of AI functions.

[0344] Continuing to refer to FIG. 5 , in some embodiments, the wireless communication method of the embodiment of the present application may further include step S420 , where the terminal device sends ninth information to the network device.

[0345] It should be understood that the eighth information mentioned above is sent based on the ninth information, that is, the eighth information may be part or all of the AI ​​model indicated in the ninth information.

[0346] If the ninth information is used to indicate that the terminal device has actually deployed an AI model or AI function, the ninth information may include one or more of the following information: one or more AI model identification information, one or more AI function identification information. At this time, if the information provided by the ninth information is sufficient for the network device to perform subsequent AI model or AI function management operations (for example, model activation), then the network device does not need to perform the subsequent steps in Figure 5, that is, the network device does not need to perform the sending behavior of the sixth information and the receiving behavior of the eighth information.

[0347] If the ninth information is used to indicate that the terminal device has reportable model deployment information, the ninth information may include one or more of the following information: the sixth indication information, one or more AI model identification information, and one or more AI function identification information.

[0348] In some implementations, the ninth information may include one or more AI function identification information, indicating that the model deployment information that the terminal device can report is related to the AI ​​function corresponding to the one or more AI function identification information contained in the ninth information.

[0349] In some implementations, the ninth information may include one or more AI model identification information, indicating that the model deployment information that can be reported by the terminal device is related to the AI ​​model corresponding to the one or more AI model identification information contained in the ninth information.

[0350] In some implementations, the ninth information may include sixth indication information, where the sixth indication information is used to indicate whether the terminal device has model deployment information that can be reported. The embodiment of the present application does not specifically limit the value of the sixth indication information.

[0351] In some implementations, the sixth indication information may be a Boolean variable. When the sixth indication information takes the third value, it indicates that the terminal device has reportable model deployment information. When the sixth indication information takes the fourth value, it indicates that the terminal device does not have reportable model deployment information. In this case, the ninth information may not carry the identification information of the AI ​​model. It should be understood that the sixth indication information is only used to indicate whether the terminal device has reportable model deployment information. In other words, the terminal device does not inform the network device which AI functions or AI models the reportable model deployment information is related to.

[0352] For example, when the third value of the sixth indication information is 1, it indicates that the terminal device has model deployment information that can be reported, but the terminal device has not informed the network device which AI functions or AI models the reportable model deployment information is related to; when the second value of the sixth indication information is 0, it indicates that the terminal device has no model deployment information that can be reported.

[0353] In other implementations, the sixth indication information may be represented by a bit to indicate whether the terminal device has reportable model deployment information. Taking the sixth indication information represented by 1 bit as an example, the value of the sixth indication information may be "0" or "1". For example, "1" may be used to indicate that there is reportable model deployment information, and "0" may be used to indicate that there is no reportable model deployment information. Alternatively, "0" may be used to indicate that there is reportable model deployment information, and "1" may be used to indicate that there is no reportable model deployment information.

[0354] The above description uses an example in which the sixth indication information is represented by one bit, but the embodiments of the present application are not limited thereto. For example, the sixth indication information may be represented by two bits, or by three or more bits. This application does not impose any specific limitation on this.

[0355] The above article details how terminal devices send capability information related to supported AI models or AI functions to network devices, allowing network devices to clearly understand which AI models or AI functions the terminal devices support, thereby assisting network devices in performing operations related to AI models or AI functions, such as: AI function activation, AI function deactivation, AI model activation, AI model deactivation, and AI model switching.

[0356] In some embodiments, the applicable conditions mentioned above can be replaced by usage scenarios, data sets, matching conditions, etc.

[0357] In some embodiments, the applicable condition may be indicated by an identifier or index. For example, the terminal device may send an identifier or index of the applicable condition to the network device, and the network device may determine the corresponding applicable condition based on the identifier or index of the applicable condition.

[0358] The method embodiment of the present application is described in detail above in conjunction with Figures 1 to 5 , and the device embodiment of the present application is described in detail below in conjunction with Figures 6 to 10 . It should be understood that the description of the method embodiment corresponds to the description of the device embodiment, and therefore, for portions not described in detail, reference can be made to the above method embodiment.

[0359] Figure 6 is a structural diagram of a terminal device provided in an embodiment of the present application. The terminal device 600 shown in Figure 6 may include a sending unit 610. The sending unit 610 is used to send first capability information to a network device, where the first capability information is related to the AI ​​model or AI function actually deployed by the terminal device, and the first capability information includes any one of the following information: first information, where the first information is used to indicate the set of AI models or AI function sets actually deployed by the terminal device; one or more second information, where each of the one or more second information is used to indicate the applicable conditions of the AI ​​model or AI function associated with each second information; identification information of one or more AI models; identification information of one or more AI functions.

[0360] In some implementations, the first information is sent at any one of the following granularities: terminal device granularity, AI function granularity, or AI model granularity.

[0361] In some implementations, the first information is sent according to the granularity of the terminal device, and the value of the first information corresponds to the AI ​​model set or AI function set actually deployed on the terminal device.

[0362] In some implementations, the value of the first information is a first value, which is used to indicate that the terminal device does not deploy any AI model or AI function.

[0363] In some implementations, the first capability information also includes first indication information, and the first indication information is used to indicate whether the terminal device has actually deployed an AI model or AI function.

[0364] In some implementations, the first information is sent according to AI function granularity, and the AI ​​function corresponding to the first information is indicated by the position of the first information in the first capability information.

[0365] In some implementations, the value of the first information is a second value, and the second value is used to indicate that the terminal device is not deployed with the AI ​​function corresponding to the first information.

[0366] In some implementations, the first information is associated with second indication information, and the second indication information is used to indicate whether the terminal device has actually deployed the AI ​​function corresponding to the first information associated with the second indication information.

[0367] In some implementations, the first information is sent according to an AI function granularity, and the AI ​​function corresponding to the first information is indicated by an AI function identifier.

[0368] In some implementations, the first capability information includes a first capability parameter list, the first capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI function identifier and first information corresponding to the AI ​​function identifier.

[0369] In some implementations, the first information is sent according to an AI model granularity, and the AI ​​model corresponding to the first information is indicated by an AI model identifier.

[0370] In some implementations, the first capability information includes a second capability parameter list, the second capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI model identifier and first information corresponding to the AI ​​model identifier.

[0371] In some implementations, the second information is sent at any one of the following granularities: AI function granularity or AI model granularity.

[0372] In some implementations, the second information is sent at an AI function granularity, and the AI ​​function corresponding to the second information is indicated by the position of the second information in the first capability information.

[0373] In some implementations, the second information is associated with third indication information, and the third indication information is used to indicate whether the terminal device has actually deployed the AI ​​function corresponding to the second information associated with the third indication information.

[0374] In some implementations, the second information is sent according to an AI function granularity, and the AI ​​function corresponding to the second information is indicated by an AI function identifier.

[0375] In some implementations, the first capability information includes a third capability parameter list, the third capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI function identifier and one or more second information corresponding to the AI ​​function identifier.

[0376] In some implementations, the second information is sent according to AI model granularity, and the AI ​​model corresponding to the second information is indicated by an AI model identifier.

[0377] In some implementations, the first capability information includes a fourth capability parameter list, the fourth capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI model identifier and one or more second information corresponding to the AI ​​model identifier.

[0378] In some implementations, the terminal device 600 further includes: the sending unit is configured to send third information to the network device, where the third information is configured to indicate that the first capability information has been updated.

[0379] In some implementations, the third information includes an identifier of the updated first AI function or an identifier of the first AI model.

[0380] In some implementations, the third information is carried in one or more of the following messages: connection establishment completion message, reconfiguration completion message, connection re-establishment completion message, connection recovery completion message, terminal assistance information message, and the first RRC message sent after the terminal device enters the connected state.

[0381] In some implementations, the terminal device 600 further includes: a receiving unit, configured to receive fourth information sent by the network device, where the fourth information is used to instruct the terminal device to report the updated first capability information.

[0382] In some implementations, the fourth information includes an identifier of the second AI function or an identifier of the second AI model.

[0383] In some implementations, the terminal device 600 further includes: the sending unit is used to send updated first capability information to the network device, where the updated first capability information includes capability parameters associated with the second AI function or capability parameters associated with the second AI model.

[0384] In some implementations, the first capability information is sent at one or more of the following granularities: carrier granularity, frequency band granularity, frequency band combination granularity, and frequency band range granularity.

[0385] Figure 7 is a structural diagram of another terminal device provided in an embodiment of the present application. The terminal device 700 shown in Figure 7 may include a sending unit 710. The sending unit 710 can be used to send second capability information to the network device, where the second capability information is related to the AI ​​model or AI function supported by the terminal device, and the second capability information includes any one of the following information: one or more fifth information, each of the one or more fifth information is used to indicate the applicable conditions of the AI ​​model or AI function associated with each fifth information; one or more AI function identification information; one or more AI model identification information.

[0386] In some implementations, the fifth information is sent at any one of the following granularities: AI function granularity or AI model granularity.

[0387] In some implementations, the fifth information is sent according to AI function granularity, and the AI ​​function corresponding to the fifth information is indicated by the position of the fifth information in the second capability information.

[0388] In some implementations, the fifth information is associated with fourth indication information, and the fourth indication information is used to indicate whether the terminal device supports the AI ​​function corresponding to the fifth information associated with the fourth indication information.

[0389] In some implementations, the fifth information is sent according to an AI function granularity, and the AI ​​function corresponding to the fifth information is indicated by an AI function identifier.

[0390] In some implementations, the second capability information includes a fifth capability parameter list, the fifth capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI function identifier and one or more fifth information corresponding to the AI ​​function identifier.

[0391] In some implementations, the fifth information is sent according to the AI ​​model granularity, and the AI ​​model corresponding to the fifth information is indicated by an AI model identifier.

[0392] In some implementations, the second capability information includes a sixth capability parameter list, the sixth capability parameter list includes one or more capability parameters, any one of the one or more capability parameters includes an AI model identifier and one or more fifth information corresponding to the AI ​​model identifier.

[0393] In some implementations, the second capability information is sent according to one or more of the following granularities: carrier granularity, frequency band granularity, frequency band combination granularity, and frequency band range granularity.

[0394] In some implementations, the sending unit is used to send sixth information to the network device, where the sixth information is related to the AI ​​model or AI function actually deployed on the terminal device. The sixth information includes one or more seventh information, and each of the one or more seventh information is used to indicate the applicable conditions of the AI ​​model or AI function associated with each seventh information.

[0395] In some implementations, the seventh information is sent at any one of the following granularities: AI function granularity or AI model granularity.

[0396] In some implementations, the seventh information is sent according to AI function granularity, and the AI ​​function corresponding to the seventh information is indicated by the position of the seventh information in the sixth information.

[0397] In some implementations, the seventh information is sent according to an AI function granularity, and the AI ​​function corresponding to the seventh information is indicated by an AI function identifier.

[0398] In some implementations, the sixth information includes a seventh capability parameter list, the seventh capability parameter list includes one or more capability parameters, any one of the one or more capability parameters includes an AI function identifier and one or more seventh information corresponding to the AI ​​function identifier.

[0399] In some implementations, the seventh information is sent according to AI model granularity, and the AI ​​model corresponding to the seventh information is indicated by an AI model identifier.

[0400] In some implementations, the sixth information includes an eighth capability parameter list, the eighth capability parameter list includes one or more capability parameters, any one of the one or more capability parameters includes an AI model identifier and one or more seventh information corresponding to the AI ​​model identifier.

[0401] In some implementations, the terminal device 700 further includes: a receiving unit, configured to receive eighth information sent by the network device, wherein the eighth information is configured to instruct the terminal device to send model deployment information to the network device.

[0402] In some implementations, the eighth information includes one or more of the following information: identification information corresponding to the AI ​​model that the network device is concerned about; identification information corresponding to the AI ​​function that the network device is concerned about; and fifth indication information, wherein the fifth indication information is used to instruct the terminal device to send model deployment information to the network device.

[0403] In some implementations, the sending unit is used to send ninth information to the network device, where the ninth information is used to indicate that the terminal device has reportable model deployment information, or to indicate that the terminal device has actually deployed an AI model or AI function.

[0404] In some implementations, the ninth information is used to indicate that the terminal device has reportable model deployment information, and the ninth information includes one or more of the following information: sixth indication information, the value of the sixth indication information is a third value, and the third value is used to indicate that the terminal device has reportable model deployment information; one or more AI model identification information; one or more AI function identification information.

[0405] In some implementations, the ninth information is used to indicate that the terminal device has actually deployed an AI model or AI function, and the ninth information includes one or more of the following information: one or more AI model identification information, and one or more AI function identification information.

[0406] Figure 8 is a structural diagram of a network device provided in an embodiment of the present application. The network device 800 shown in Figure 8 may include a receiving unit 810. The receiving unit 810 is used to receive first capability information sent by a terminal device, where the first capability information is related to the AI ​​model or AI function supported by the terminal device, and the first capability information includes one or more of the following information: first information, where the first information is used to indicate the set of AI models or AI function sets actually deployed by the terminal device; one or more second information, where each of the one or more second information is used to indicate the applicable conditions of the AI ​​model or AI function associated with each second information; identification information of one or more AI models; identification information of one or more AI functions.

[0407] In some implementations, the first information is sent at any one of the following granularities: terminal device granularity, AI function granularity, or AI model granularity.

[0408] In some implementations, the first information is sent according to the granularity of the terminal device, and the value of the first information corresponds to the AI ​​model set or AI function set actually deployed on the terminal device.

[0409] In some implementations, the value of the first information is a first value, which is used to indicate that the terminal device does not deploy any AI model or AI function.

[0410] In some implementations, the first capability information also includes first indication information, and the first indication information is used to indicate whether the terminal device has actually deployed an AI model or AI function.

[0411] In some implementations, the first information is sent according to AI function granularity, and the AI ​​function corresponding to the first information is indicated by the position of the first information in the first capability information.

[0412] In some implementations, the value of the first information is a second value, and the second value is used to indicate that the terminal device is not deployed with the AI ​​function corresponding to the first information.

[0413] In some implementations, the first information is associated with second indication information, and the second indication information is used to indicate whether the terminal device has actually deployed the AI ​​function corresponding to the first information associated with the second indication information.

[0414] In some implementations, the first information is sent according to an AI function granularity, and the AI ​​function corresponding to the first information is indicated by an AI function identifier.

[0415] In some implementations, the first capability information includes a first capability parameter list, the first capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI function identifier and first information corresponding to the AI ​​function identifier.

[0416] In some implementations, the first information is sent according to an AI model granularity, and the AI ​​model corresponding to the first information is indicated by an AI model identifier.

[0417] In some implementations, the first capability information includes a second capability parameter list, the second capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI model identifier and first information corresponding to the AI ​​model identifier.

[0418] In some implementations, the second information is sent at any one of the following granularities: AI function granularity or AI model granularity.

[0419] In some implementations, the second information is sent at an AI function granularity, and the AI ​​function corresponding to the second information is indicated by the position of the second information in the first capability information.

[0420] In some implementations, the second information is associated with third indication information, and the third indication information is used to indicate whether the terminal device has actually deployed the AI ​​function corresponding to the second information associated with the third indication information.

[0421] In some implementations, the second information is sent according to an AI function granularity, and the AI ​​function corresponding to the second information is indicated by an AI function identifier.

[0422] In some implementations, the first capability information includes a third capability parameter list, the third capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI function identifier and one or more second information corresponding to the AI ​​function identifier.

[0423] In some implementations, the second information is sent according to AI model granularity, and the AI ​​model corresponding to the second information is indicated by an AI model identifier.

[0424] In some implementations, the first capability information includes a fourth capability parameter list, the fourth capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI model identifier and one or more second information corresponding to the AI ​​model identifier.

[0425] In some implementations, the receiving unit is further configured to receive third information sent by the terminal device, where the third information is configured to indicate that the first capability information has been updated.

[0426] In some implementations, the third information includes an identifier of the updated first AI function or an identifier of the first AI model.

[0427] In some implementations, the third information is carried in one or more of the following messages: connection establishment completion message, reconfiguration completion message, connection re-establishment completion message, connection recovery completion message, terminal assistance information message, and the first RRC message sent after the terminal device enters the connected state.

[0428] In some implementations, the network device 800 further includes: a sending unit, configured to send fourth information to the network device, where the fourth information is configured to instruct the terminal device to report the updated first capability information.

[0429] In some implementations, the fourth information includes an identifier of the second AI function or an identifier of the second AI model.

[0430] In some implementations, the receiving unit is further configured to receive updated first capability information sent by the terminal device, where the updated first capability information includes capability parameters associated with the second AI function or capability parameters associated with the second AI model.

[0431] In some implementations, the first capability information is sent at one or more of the following granularities: carrier granularity, frequency band granularity, frequency band combination granularity, and frequency band range granularity.

[0432] Figure 9 is a schematic diagram of the structure of a network device provided in an embodiment of the present application. The network device 900 shown in Figure 9 may include a receiving unit 910. The receiving unit 910 is used to receive second capability information sent by a terminal device, where the second capability information is related to an AI model or AI function supported by the terminal device, and the second capability information includes any one of the following information: one or more fifth information, each of the one or more fifth information is used to indicate the applicable conditions of the AI ​​model or AI function associated with each fifth information; one or more AI function identification information; one or more AI model identification information.

[0433] In some implementations, the fifth information is sent at any one of the following granularities: AI function granularity or AI model granularity.

[0434] In some implementations, the fifth information is sent according to AI function granularity, and the AI ​​function corresponding to the fifth information is indicated by the position of the fifth information in the second capability information.

[0435] In some implementations, the fifth information is associated with fourth indication information, and the fourth indication information is used to indicate whether the terminal device supports the AI ​​function corresponding to the fifth information associated with the fourth indication information.

[0436] In some implementations, the fifth information is sent according to an AI function granularity, and the AI ​​function corresponding to the fifth information is indicated by an AI function identifier.

[0437] In some implementations, the second capability information includes a fifth capability parameter list, the fifth capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI function identifier and one or more fifth information corresponding to the AI ​​function identifier.

[0438] In some implementations, the fifth information is sent according to the AI ​​model granularity, and the AI ​​model corresponding to the fifth information is indicated by an AI model identifier.

[0439] In some implementations, the second capability information includes a sixth capability parameter list, the sixth capability parameter list includes one or more capability parameters, any one of the one or more capability parameters includes an AI model identifier and one or more fifth information corresponding to the AI ​​model identifier.

[0440] In some implementations, the second capability information is sent according to one or more of the following granularities: carrier granularity, frequency band granularity, frequency band combination granularity, and frequency band range granularity.

[0441] In some implementations, the receiving unit is further used to receive sixth information sent by the terminal device, where the sixth information is related to the AI ​​model or AI function actually deployed by the terminal device. The sixth information includes one or more seventh information, and each of the one or more seventh information is used to indicate the applicable conditions of the AI ​​model or AI function associated with each seventh information.

[0442] In some implementations, the seventh information is sent at any one of the following granularities: AI function granularity or AI model granularity.

[0443] In some implementations, the seventh information is sent according to AI function granularity, and the AI ​​function corresponding to the seventh information is indicated by the position of the seventh information in the sixth information.

[0444] In some implementations, the seventh information is sent according to an AI function granularity, and the AI ​​function corresponding to the seventh information is indicated by an AI function identifier.

[0445] In some implementations, the sixth information includes a seventh capability parameter list, the seventh capability parameter list includes one or more capability parameters, any one of the one or more capability parameters includes an AI function identifier and one or more seventh information corresponding to the AI ​​function identifier.

[0446] In some implementations, the seventh information is sent according to AI model granularity, and the AI ​​model corresponding to the seventh information is indicated by an AI model identifier.

[0447] In some implementations, the sixth information includes an eighth capability parameter list, the eighth capability parameter list includes one or more capability parameters, any one of the one or more capability parameters includes an AI model identifier and one or more seventh information corresponding to the AI ​​model identifier.

[0448] In some implementations, the network device 900 further includes: a sending unit, configured to send eighth information to the terminal device, wherein the eighth information is configured to instruct the terminal device to send model deployment information to the network device.

[0449] In some implementations, the eighth information includes one or more of the following information: identification information corresponding to the AI ​​model that the network device is concerned about; identification information corresponding to the AI ​​function that the network device is concerned about; and fifth indication information, wherein the fifth indication information is used to instruct the terminal device to send model deployment information to the network device.

[0450] In some implementations, the receiving unit is further used to receive ninth information sent by the terminal device, where the ninth information is used to indicate that the terminal device has reportable model deployment information, or to indicate an AI model or AI function that has been deployed by the terminal device.

[0451] In some implementations, the ninth information is used to indicate that the terminal device has reportable model deployment information, and the ninth information includes one or more of the following information: sixth indication information, the value of the sixth indication information is a third value, and the third value is used to indicate that the terminal device has reportable model deployment information; one or more AI model identification information; one or more AI function identification information.

[0452] In some implementations, the ninth information is used to indicate that the terminal device has actually deployed an AI model or AI function, and the ninth information includes one or more of the following information: one or more AI model identification information, and one or more AI function identification information.

[0453] Figure 10 is a schematic block diagram of a communication device according to an embodiment of the present application. The dashed lines in Figure 10 indicate that the unit or module is optional. The device 1000 may be used to implement the method described in the above method embodiment. The device 1000 may be a chip, a terminal device, or a network device.

[0454] The device 1000 may include one or more processors 1010. The processor 1010 may support the device 1000 to implement the method described in the method embodiment above. The processor 1010 may be a general-purpose processor or a special-purpose processor. For example, the processor may be a central processing unit (CPU). Alternatively, the processor may be another general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0455] The apparatus 1000 may further include one or more memories 1020. The memories 1020 store programs that can be executed by the processor 1010, causing the processor 1010 to perform the methods described in the above method embodiments. The memories 1020 may be independent of the processor 1010 or integrated into the processor 1010.

[0456] The apparatus 1000 may further include a transceiver 1030. The processor 1010 may communicate with other devices or chips via the transceiver 1030. For example, the processor 1010 may transmit and receive data with other devices or chips via the transceiver 1030.

[0457] The present application also provides a computer-readable storage medium for storing a program. The computer-readable storage medium can be applied to a terminal or network device provided in the present application, and the program enables a computer to execute the method performed by the terminal or network device in each embodiment of the present application.

[0458] The present application also provides a computer program product. The computer program product includes a program. The computer program product can be applied to a terminal or network device provided in the present application, and the program causes a computer to execute the method performed by the terminal or network device in each embodiment of the present application.

[0459] The embodiments of the present application also provide a computer program. The computer program can be applied to the terminal or network device provided in the embodiments of the present application, and the computer program enables a computer to execute the method performed by the terminal or network device in each embodiment of the present application.

[0460] It should be understood that the terms "system" and "network" in this application can be used interchangeably. In addition, the terms used in this application are only used to explain the specific embodiments of this application and are not intended to limit this application. The terms "first", "second", "third", and "fourth" in the specification and claims of this application and the accompanying drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0461] In the embodiments of this application, the term "indication" may refer to a direct indication, an indirect indication, or an indication of an association. For example, "A indicates B" may refer to a direct indication of B, e.g., B can obtain information through A; it may refer to an indirect indication of B, e.g., A indicates C, e.g., B can obtain information through C; or it may refer to an association between A and B.

[0462] In the embodiment of the present application, "B corresponding to A" means that B is associated with A and B can be determined based on A. However, it should be understood that determining B based on A does not mean determining B based solely on A, but B can also be determined based on A and / or other information.

[0463] In 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 indication, configuration and configuration, etc.

[0464] In the embodiments of the present application, "pre-definition" or "pre-configuration" 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., a terminal device and a network device). The present application does not limit the specific implementation method. For example, pre-definition may refer to information defined in a protocol.

[0465] In the embodiments of the present application, the “protocol” may refer to a standard protocol in the communications field, for example, it may include an LTE protocol, an NR protocol, and related protocols used in future communication systems, and the present application does not limit this.

[0466] In the embodiments of this application, the term "and / or" is simply a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this document generally indicates that the related objects are in an "or" relationship.

[0467] In various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0468] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0469] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0470] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0471] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be read by a computer or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0472] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A wireless communication method, characterized in that: include: The terminal device sends first capability information to the network device. The first capability information is related to the artificial intelligence (AI) model or AI function actually deployed by the terminal device. The first capability information includes any one of the following information: First information, where the first information is used to indicate the AI ​​model set or AI function set actually deployed on the terminal device; One or more second information, each of the one or more second information being used to indicate an applicable condition of an AI model or AI function associated with the second information; Identification information of one or more AI models; Identification information of one or more AI functions.

2. The method according to claim 1, characterized in that The first information is sent according to any one of the following granularities: terminal device granularity, AI function granularity or AI model granularity.

3. The method according to claim 2, characterized in that The first information is sent according to the granularity of the terminal device, and the value of the first information corresponds to the AI ​​model set or AI function set actually deployed by the terminal device.

4. The method according to claim 3, characterized in that The value of the first information is a first value, which is used to indicate that the terminal device does not deploy any AI model or AI function.

5. The method according to claim 3, characterized in that The first capability information also includes first indication information, and the first indication information is used to indicate whether the terminal device has actually deployed an AI model or AI function.

6. The method according to claim 2, characterized in that The first information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the first information is indicated by the position of the first information in the first capability information.

7. The method according to claim 6, characterized in that The value of the first information is a second value, and the second value is used to indicate that the terminal device is not deployed with the AI ​​function corresponding to the first information.

8. The method according to claim 6, characterized in that The first information is associated with second indication information, and the second indication information is used to indicate whether the terminal device has actually deployed the AI ​​function corresponding to the first information associated with the second indication information.

9. The method according to claim 2, characterized in that The first information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the first information is indicated by an AI function identifier.

10. The method according to claim 9, characterized in that The first capability information includes a first capability parameter list, the first capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI function identifier and first information corresponding to the AI ​​function identifier.

11. The method according to claim 2, characterized in that The first information is sent according to the AI ​​model granularity, and the AI ​​model corresponding to the first information is indicated by an AI model identifier.

12. The method according to claim 11, characterized in that The first capability information includes a second capability parameter list, the second capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI model identifier and first information corresponding to the AI ​​model identifier.

13. The method according to claim 1, wherein The second information is sent according to any one of the following granularities: AI function granularity or AI model granularity.

14. The method according to claim 13, characterized in that The second information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the second information is indicated by the position of the second information in the first capability information.

15. The method according to claim 14, characterized in that The second information is associated with third indication information, and the third indication information is used to indicate whether the terminal device has actually deployed the AI ​​function corresponding to the second information associated with the third indication information.

16. The method according to claim 13, characterized in that The second information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the second information is indicated by an AI function identifier.

17. The method according to claim 16, characterized in that The first capability information includes a third capability parameter list, the third capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI function identifier and one or more second information corresponding to the AI ​​function identifier.

18. The method according to claim 13, characterized in that The second information is sent according to the AI ​​model granularity, and the AI ​​model corresponding to the second information is indicated by the AI ​​model identifier.

19. The method according to claim 18, characterized in that The first capability information includes a fourth capability parameter list, the fourth capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI model identifier and one or more second information corresponding to the AI ​​model identifier.

20. The method according to any one of claims 1 to 19, characterized in that The method further comprises: The terminal device sends third information to the network device, where the third information is used to indicate that the first capability information has been updated.

21. The method according to claim 20, characterized in that The third information includes an identifier of the updated first AI function or an identifier of the first AI model.

22. The method according to claim 20 or 21, characterized in that The third information is carried in one or more of the following messages: connection establishment completion message, reconfiguration completion message, connection re-establishment completion message, connection recovery completion message, terminal assistance information message, and the first radio resource control RRC message sent after the terminal device enters the connected state.

23. The method according to any one of claims 20 to 22, characterized in that The method further comprises: The terminal device receives fourth information sent by the network device, where the fourth information is used to instruct the terminal device to report the updated first capability information.

24. The method according to claim 23, wherein The fourth information includes an identifier of the second AI function or an identifier of the second AI model.

25. The method according to any one of claims 20 to 24, characterized in that The method further comprises: The terminal device sends updated first capability information to the network device, where the updated first capability information includes capability parameters associated with the second AI function or capability parameters associated with the second AI model.

26. The method according to any one of claims 1 to 25, characterized in that The first capability information is sent according to one or more of the following granularities: carrier granularity, frequency band granularity, frequency band combination granularity, and frequency band range granularity.

27. A wireless communication method, characterized in that: include: The network device receives first capability information sent by the terminal device, where the first capability information is related to an artificial intelligence (AI) model or AI function actually deployed by the terminal device, and the first capability information includes one or more of the following information: First information, where the first information is used to indicate the AI ​​model set or AI function set actually deployed on the terminal device; One or more second information, each of the one or more second information being used to indicate an applicable condition of an AI model or AI function associated with the second information; Identification information of one or more AI models; Identification information of one or more AI functions.

28. The method according to claim 27, characterized in that The first information is sent according to any one of the following granularities: terminal device granularity, AI function granularity or AI model granularity.

29. The method according to claim 28, characterized in that The first information is sent according to the granularity of the terminal device, and the value of the first information corresponds to the AI ​​model set or AI function set actually deployed by the terminal device.

30. The method according to claim 29, wherein The value of the first information is a first value, which is used to indicate that the terminal device does not deploy any AI model or AI function.

31. The method according to claim 29, wherein The first capability information also includes first indication information, and the first indication information is used to indicate whether the terminal device has actually deployed an AI model or AI function.

32. The method according to claim 28, wherein The first information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the first information is indicated by the position of the first information in the first capability information.

33. The method according to claim 32, characterized in that The value of the first information is a second value, and the second value is used to indicate that the terminal device is not deployed with the AI ​​function corresponding to the first information.

34. The method according to claim 32, wherein The first information is associated with second indication information, and the second indication information is used to indicate whether the terminal device has actually deployed the AI ​​function corresponding to the first information associated with the second indication information.

35. The method according to claim 28, wherein The first information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the first information is indicated by an AI function identifier.

36. The method according to claim 35, characterized in that The first capability information includes a first capability parameter list, the first capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI function identifier and first information corresponding to the AI ​​function identifier.

37. The method according to claim 28, wherein The first information is sent according to the AI ​​model granularity, and the AI ​​model corresponding to the first information is indicated by an AI model identifier.

38. The method according to claim 37, wherein The first capability information includes a second capability parameter list, the second capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI model identifier and first information corresponding to the AI ​​model identifier.

39. The method according to claim 27, wherein The second information is sent according to any one of the following granularities: AI function granularity or AI model granularity.

40. The method according to claim 39, wherein The second information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the second information is indicated by the position of the second information in the first capability information.

41. The method according to claim 40, wherein The second information is associated with third indication information, and the third indication information is used to indicate whether the terminal device has actually deployed the AI ​​function corresponding to the second information associated with the third indication information.

42. The method according to claim 39, wherein The second information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the second information is indicated by an AI function identifier.

43. The method according to claim 42, characterized in that The first capability information includes a third capability parameter list, the third capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI function identifier and one or more second information corresponding to the AI ​​function identifier.

44. The method according to claim 39, wherein The second information is sent according to the AI ​​model granularity, and the AI ​​model corresponding to the second information is indicated by the AI ​​model identifier.

45. The method according to claim 44, wherein The first capability information includes a fourth capability parameter list, the fourth capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI model identifier and one or more second information corresponding to the AI ​​model identifier.

46. ​​The method according to any one of claims 27 to 45, wherein: The method further comprises: The network device receives third information sent by the terminal device, where the third information is used to indicate that the first capability information has been updated.

47. The method according to claim 46, wherein The third information includes an identifier of the updated first AI function or an identifier of the first AI model.

48. The method according to claim 46 or 47, characterized in that The third information is carried in one or more of the following messages: connection establishment completion message, reconfiguration completion message, connection re-establishment completion message, connection recovery completion message, terminal assistance information message, and the first radio resource control RRC message sent after the terminal device enters the connected state.

49. The method according to any one of claims 46 to 48, wherein The method further comprises: The network device sends fourth information to the terminal device, where the fourth information is used to instruct the terminal device to report the updated first capability information.

50. The method according to claim 49, wherein The fourth information includes an identifier of the second AI function or an identifier of the second AI model.

51. The method according to any one of claims 46 to 50, wherein: The method further comprises: The network device receives updated first capability information sent by the terminal device, where the updated first capability information includes capability parameters associated with the second AI function or capability parameters associated with the second AI model.

52. The method according to any one of claims 27 to 51, wherein: The first capability information is sent according to one or more of the following granularities: carrier granularity, frequency band granularity, frequency band combination granularity, and frequency band range granularity.

53. A wireless communication method, characterized in that: include: The terminal device sends second capability information to the network device, where the second capability information is related to an artificial intelligence (AI) model or AI function supported by the terminal device, and the second capability information includes any one of the following information: One or more fifth information, each of the one or more fifth information being used to indicate an applicable condition of an AI model or AI function associated with the fifth information; One or more AI function identification information; One or more AI model identification information.

54. The method according to claim 53, wherein The fifth information is sent according to any one of the following granularities: AI function granularity or AI model granularity.

55. The method according to claim 54, characterized in that The fifth information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the fifth information is indicated by the position of the fifth information in the second capability information.

56. The method according to claim 55, characterized in that The fifth information is associated with the fourth indication information, and the fourth indication information is used to indicate whether the terminal device supports the AI ​​function corresponding to the fifth information associated with the fourth indication information.

57. The method according to claim 54, characterized in that The fifth information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the fifth information is indicated by the AI ​​function identifier.

58. The method according to claim 57, wherein The second capability information includes a fifth capability parameter list, the fifth capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI function identifier and one or more fifth information corresponding to the AI ​​function identifier.

59. The method according to claim 54, wherein The fifth information is sent according to the AI ​​model granularity, and the AI ​​model corresponding to the fifth information is indicated by the AI ​​model identifier.

60. The method according to claim 59, wherein The second capability information includes a sixth capability parameter list, the sixth capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI model identifier and one or more fifth information corresponding to the AI ​​model identifier.

61. The method according to any one of claims 53 to 60, wherein: The second capability information is sent according to one or more of the following granularities: carrier granularity, frequency band granularity, frequency band combination granularity, and frequency band range granularity.

62. The method according to any one of claims 53 to 61, wherein: The method further comprises: The terminal device sends sixth information to the network device, where the sixth information is related to the AI ​​model or AI function actually deployed by the terminal device. The sixth information includes one or more seventh information, and each of the one or more seventh information is used to indicate the applicable conditions of the AI ​​model or AI function associated with each seventh information.

63. The method according to claim 62, characterized in that The seventh information is sent according to any one of the following granularities: AI function granularity or AI model granularity.

64. The method according to claim 63, wherein The seventh information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the seventh information is indicated by the position of the seventh information in the sixth information.

65. The method according to claim 63, wherein The seventh information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the seventh information is indicated by the AI ​​function identifier.

66. The method according to claim 65, characterized in that The sixth information includes a seventh capability parameter list, the seventh capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI function identifier and one or more seventh information corresponding to the AI ​​function identifier.

67. The method according to claim 63, characterized in that The seventh information is sent according to the AI ​​model granularity, and the AI ​​model corresponding to the seventh information is indicated by the AI ​​model identifier.

68. The method according to claim 67, characterized in that The sixth information includes an eighth capability parameter list, the eighth capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI model identifier and one or more seventh information corresponding to the AI ​​model identifier.

69. The method according to any one of claims 62 to 68, wherein The method further comprises: The terminal device receives the eighth information sent by the network device, where the eighth information is used to instruct the terminal device to send model deployment information to the network device.

70. The method according to claim 69, wherein The eighth information includes one or more of the following information: Identification information corresponding to the AI ​​model that the network device is concerned about; Identification information corresponding to the AI ​​function that the network device is concerned about; Fifth indication information, the fifth indication information is used to instruct the terminal device to send model deployment information to the network device.

71. The method according to any one of claims 62 to 70, wherein: The method further comprises: The terminal device sends ninth information to the network device, where the ninth information is used to indicate that the terminal device has reportable model deployment information, or to indicate that the terminal device has actually deployed an AI model or AI function.

72. The method according to claim 71, characterized in that The ninth information is used to indicate that the terminal device has reportable model deployment information, and the ninth information includes one or more of the following information: Sixth indication information, where the value of the sixth indication information is a third value, and the third value is used to indicate that the terminal device has reportable model deployment information; One or more AI model identification information; One or more AI function identification information.

73. The method according to claim 71, characterized in that The ninth information is used to indicate that the terminal device has actually deployed an AI model or AI function, and the ninth information includes one or more of the following information: one or more AI model identification information, and one or more AI function identification information.

74. A wireless communication method, characterized in that: include: The network device receives second capability information sent by the terminal device, where the second capability information is related to an artificial intelligence (AI) model supported by the terminal device, and the second capability information includes any one of the following: One or more fifth information, each of the one or more fifth information being used to indicate an applicable condition of an AI model or AI function associated with the fifth information; One or more AI function identification information; One or more AI model identification information.

75. The method according to claim 74, wherein The fifth information is sent according to any one of the following granularities: AI function granularity or AI model granularity.

76. The method according to claim 75, characterized in that The fifth information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the fifth information is indicated by the position of the fifth information in the second capability information.

77. The method according to claim 76, characterized in that The fifth information is associated with the fourth indication information, and the fourth indication information is used to indicate whether the terminal device supports the AI ​​function corresponding to the fifth information associated with the fourth indication information.

78. The method according to claim 75, characterized in that The fifth information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the fifth information is indicated by the AI ​​function identifier.

79. The method according to claim 78, characterized in that The second capability information includes a fifth capability parameter list, the fifth capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI function identifier and one or more fifth information corresponding to the AI ​​function identifier.

80. The method of claim 75, wherein: The fifth information is sent according to the AI ​​model granularity, and the AI ​​model corresponding to the fifth information is indicated by the AI ​​model identifier.

81. The method according to claim 80, characterized in that The second capability information includes a sixth capability parameter list, the sixth capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI model identifier and one or more fifth information corresponding to the AI ​​model identifier.

82. The method according to any one of claims 74 to 81, wherein The second capability information is sent according to one or more of the following granularities: carrier granularity, frequency band granularity, frequency band combination granularity, and frequency band range granularity.

83. The method according to any one of claims 74 to 82, wherein The method further comprises: The network device receives the sixth information sent by the terminal device, where the sixth information is related to the AI ​​model or AI function actually deployed by the terminal device. The sixth information includes one or more seventh information, and each of the one or more seventh information is used to indicate the applicable conditions of the AI ​​model or AI function associated with each seventh information.

84. The method according to claim 83, wherein The seventh information is sent according to any one of the following granularities: AI function granularity or AI model granularity.

85. The method according to claim 84, characterized in that The seventh information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the seventh information is indicated by the position of the seventh information in the sixth information.

86. The method according to claim 84, characterized in that The seventh information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the seventh information is indicated by the AI ​​function identifier.

87. The method according to claim 86, characterized in that The sixth information includes a seventh capability parameter list, the seventh capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI function identifier and one or more seventh information corresponding to the AI ​​function identifier.

88. The method according to claim 84, characterized in that The seventh information is sent according to the AI ​​model granularity, and the AI ​​model corresponding to the seventh information is indicated by the AI ​​model identifier.

89. The method according to claim 88, characterized in that The sixth information includes an eighth capability parameter list, the eighth capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI model identifier and one or more seventh information corresponding to the AI ​​model identifier.

90. The method according to any one of claims 83 to 89, wherein The method further comprises: The network device sends eighth information to the terminal device, where the eighth information is used to instruct the terminal device to send model deployment information to the network device.

91. The method according to claim 90, wherein The eighth information includes one or more of the following information: Identification information corresponding to the AI ​​model that the network device is concerned about; Identification information corresponding to the AI ​​function that the network device is concerned about; Fifth indication information, the fifth indication information is used to instruct the terminal device to send model deployment information to the network device.

92. The method according to any one of claims 83 to 91, wherein The method further comprises: The network device receives ninth information sent by the terminal device, where the ninth information is used to indicate that the terminal device has reportable model deployment information or that the terminal device has deployed an AI model or AI function.

93. The method according to claim 92, characterized in that The ninth information is used to indicate that the terminal device has reportable model deployment information, and the ninth information includes one or more of the following information: Sixth indication information, where the value of the sixth indication information is a third value, and the third value is used to indicate that the terminal device has reportable model deployment information; One or more AI model identification information; One or more AI function identification information.

94. The method according to claim 92, wherein The ninth information is used to indicate that the terminal device has actually deployed an AI model or AI function, and the ninth information includes one or more of the following information: one or more AI model identification information, and one or more AI function identification information.

95. A terminal device, characterized in that include: A sending unit, configured to send first capability information to a network device, where the first capability information is related to an artificial intelligence (AI) model or AI function actually deployed on the terminal device, and the first capability information includes any one of the following information: First information, where the first information is used to indicate the AI ​​model set or AI function set actually deployed on the terminal device; One or more second information, each of the one or more second information being used to indicate an applicable condition of an AI model or AI function associated with the second information; Identification information of one or more AI models; Identification information of one or more AI functions.

96. The terminal device according to claim 95, characterized in that The first information is sent according to any one of the following granularities: terminal device granularity, AI function granularity or AI model granularity.

97. The terminal device according to claim 96, characterized in that The first information is sent according to the granularity of the terminal device, and the value of the first information corresponds to the AI ​​model set or AI function set actually deployed by the terminal device.

98. The terminal device according to claim 97, characterized in that The value of the first information is a first value, which is used to indicate that the terminal device does not deploy any AI model or AI function.

99. The terminal device according to claim 98, characterized in that The first capability information also includes first indication information, and the first indication information is used to indicate whether the terminal device has actually deployed an AI model or AI function.

100. The terminal device according to claim 96, characterized in that The first information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the first information is indicated by the position of the first information in the first capability information.

101. The terminal device according to claim 100, characterized in that The value of the first information is a second value, and the second value is used to indicate that the terminal device is not deployed with the AI ​​function corresponding to the first information.

102. The terminal device according to claim 100, characterized in that The first information is associated with second indication information, and the second indication information is used to indicate whether the terminal device has actually deployed the AI ​​function corresponding to the first information associated with the second indication information.

103. The terminal device according to claim 96, characterized in that The first information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the first information is indicated by an AI function identifier.

104. The terminal device according to claim 103, characterized in that The first capability information includes a first capability parameter list, the first capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI function identifier and first information corresponding to the AI ​​function identifier.

105. The terminal device according to claim 96, characterized in that The first information is sent according to the AI ​​model granularity, and the AI ​​model corresponding to the first information is indicated by an AI model identifier.

106. The terminal device according to claim 105, characterized in that The first capability information includes a second capability parameter list, the second capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI model identifier and first information corresponding to the AI ​​model identifier.

107. The terminal device according to claim 95, characterized in that The second information is sent according to any one of the following granularities: AI function granularity or AI model granularity.

108. The terminal device according to claim 107, characterized in that The second information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the second information is indicated by the position of the second information in the first capability information.

109. The terminal device according to claim 108, characterized in that The second information is associated with third indication information, and the third indication information is used to indicate whether the terminal device has actually deployed the AI ​​function corresponding to the second information associated with the third indication information.

110. The terminal device according to claim 107, characterized in that The second information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the second information is indicated by an AI function identifier.

111. The terminal device according to claim 110, characterized in that The first capability information includes a third capability parameter list, the third capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI function identifier and one or more second information corresponding to the AI ​​function identifier.

112. The terminal device according to claim 107, characterized in that The second information is sent according to the AI ​​model granularity, and the AI ​​model corresponding to the second information is indicated by the AI ​​model identifier.

113. The terminal device according to claim 112, characterized in that The first capability information includes a fourth capability parameter list, the fourth capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI model identifier and one or more second information corresponding to the AI ​​model identifier.

114. The terminal device according to any one of claims 95-113, characterized in that The sending unit is further configured to: Sending third information to the network device, where the third information is used to indicate that the first capability information has been updated.

115. The terminal device according to claim 114, characterized in that The third information includes an identifier of the updated first AI function or an identifier of the first AI model.

116. The terminal device according to claim 114 or 115, characterized in that The third information is carried in one or more of the following messages: connection establishment completion message, reconfiguration completion message, connection re-establishment completion message, connection recovery completion message, terminal assistance information message, and the first radio resource control RRC message sent after the terminal device enters the connected state.

117. The terminal device according to any one of claims 114-116, characterized in that: The terminal device further includes: A receiving unit is used to receive fourth information sent by the network device, where the fourth information is used to instruct the terminal device to report the updated first capability information.

118. The terminal device according to claim 117, characterized in that The fourth information includes an identifier of the second AI function or an identifier of the second AI model.

119. The terminal device according to any one of claims 114-118, characterized in that The sending unit is further configured to: Sending updated first capability information to the network device, where the updated first capability information includes capability parameters associated with the second AI function or capability parameters associated with the second AI model.

120. The terminal device according to any one of claims 95-119, characterized in that: The first capability information is sent according to one or more of the following granularities: carrier granularity, frequency band granularity, frequency band combination granularity, and frequency band range granularity.

121. A network device, characterized in that include: A receiving unit is configured to receive first capability information sent by a terminal device, where the first capability information is related to an artificial intelligence (AI) model or AI function supported by the terminal device, and the first capability information includes one or more of the following information: First information, where the first information is used to indicate the AI ​​model set or AI function set actually deployed on the terminal device; One or more second information, each of the one or more second information being used to indicate an applicable condition of an AI model or AI function associated with the second information; Identification information of one or more AI models; Identification information of one or more AI functions.

122. The network device according to claim 121, characterized in that The first information is sent according to any one of the following granularities: terminal device granularity, AI function granularity or AI model granularity.

123. The network device according to claim 122, characterized in that The first information is sent according to the granularity of the terminal device, and the value of the first information corresponds to the AI ​​model set or AI function set actually deployed by the terminal device.

124. The network device according to claim 123, characterized in that The value of the first information is a first value, which is used to indicate that the terminal device does not deploy any AI model or AI function.

125. The network device according to claim 123, characterized in that The first capability information also includes first indication information, and the first indication information is used to indicate whether the terminal device has actually deployed an AI model or AI function.

126. The network device according to claim 122, characterized in that The first information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the first information is indicated by the position of the first information in the first capability information.

127. The network device according to claim 126, characterized in that The value of the first information is a second value, and the second value is used to indicate that the terminal device is not deployed with the AI ​​function corresponding to the first information.

128. The network device according to claim 126, wherein: The first information is associated with second indication information, and the second indication information is used to indicate whether the terminal device has actually deployed the AI ​​function corresponding to the first information associated with the second indication information.

129. The network device according to claim 122, wherein: The first information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the first information is indicated by an AI function identifier.

130. The network device according to claim 129, wherein: The first capability information includes a first capability parameter list, the first capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI function identifier and first information corresponding to the AI ​​function identifier.

131. The network device according to claim 122, wherein: The first information is sent according to the AI ​​model granularity, and the AI ​​model corresponding to the first information is indicated by an AI model identifier.

132. The network device according to claim 131, characterized in that The first capability information includes a second capability parameter list, the second capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI model identifier and first information corresponding to the AI ​​model identifier.

133. The network device according to claim 121, wherein: The second information is sent according to any one of the following granularities: AI function granularity or AI model granularity.

134. The network device according to claim 133, characterized in that The second information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the second information is indicated by the position of the second information in the first capability information.

135. The network device according to claim 134, characterized in that The second information is associated with third indication information, and the third indication information is used to indicate whether the terminal device has actually deployed the AI ​​function corresponding to the second information associated with the third indication information.

136. The network device according to claim 133, characterized in that The second information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the second information is indicated by an AI function identifier.

137. The network device according to claim 136, characterized in that The first capability information includes a third capability parameter list, the third capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI function identifier and one or more second information corresponding to the AI ​​function identifier.

138. The network device according to claim 133, characterized in that The second information is sent according to the AI ​​model granularity, and the AI ​​model corresponding to the second information is indicated by the AI ​​model identifier.

139. The network device according to claim 138, characterized in that The first capability information includes a fourth capability parameter list, the fourth capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI model identifier and one or more second information corresponding to the AI ​​model identifier.

140. The network device according to any one of claims 121-139, characterized in that The receiving unit is further configured to: Receive third information sent by the terminal device, where the third information is used to indicate that the first capability information has been updated.

141. The network device according to claim 140, characterized in that The third information includes an identifier of the updated first AI function or an identifier of the first AI model.

142. The network device according to claim 140 or 141, characterized in that The third information is carried in one or more of the following messages: connection establishment completion message, reconfiguration completion message, connection re-establishment completion message, connection recovery completion message, terminal assistance information message, and the first radio resource control RRC message sent after the terminal device enters the connected state.

143. The network device according to any one of claims 140-142, characterized in that The network device further includes: A sending unit is used to send fourth information to the terminal device, where the fourth information is used to instruct the terminal device to report the updated first capability information.

144. The network device according to claim 143, characterized in that The fourth information includes an identifier of the second AI function or an identifier of the second AI model.

145. The network device according to any one of claims 140-144, characterized in that The receiving unit is further configured to: Receive updated first capability information sent by the terminal device, where the updated first capability information includes capability parameters associated with the second AI function or capability parameters associated with the second AI model.

146. The network device according to any one of claims 121-145, characterized in that The first capability information is sent according to one or more of the following granularities: carrier granularity, frequency band granularity, frequency band combination granularity, and frequency band range granularity.

147. A terminal device, characterized in that include: A sending unit, configured to send second capability information to the network device, where the second capability information is related to an artificial intelligence (AI) model or AI function supported by the terminal device, and the second capability information includes any one of the following information: One or more fifth information, each of the one or more fifth information being used to indicate an applicable condition of an AI model or AI function associated with the fifth information; One or more AI function identification information; One or more AI model identification information.

148. The terminal device according to claim 147, characterized in that The fifth information is sent according to any one of the following granularities: AI function granularity or AI model granularity.

149. The terminal device according to claim 148, characterized in that The fifth information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the fifth information is indicated by the position of the fifth information in the second capability information.

150. The terminal device according to claim 149, characterized in that The fifth information is associated with the fourth indication information, and the fourth indication information is used to indicate whether the terminal device supports the AI ​​function corresponding to the fifth information associated with the fourth indication information.

151. The terminal device according to claim 148, characterized in that The fifth information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the fifth information is indicated by the AI ​​function identifier.

152. The terminal device according to claim 151, characterized in that The second capability information includes a fifth capability parameter list, the fifth capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI function identifier and one or more fifth information corresponding to the AI ​​function identifier.

153. The terminal device according to claim 148, characterized in that The fifth information is sent according to the AI ​​model granularity, and the AI ​​model corresponding to the fifth information is indicated by the AI ​​model identifier.

154. The terminal device according to claim 153, characterized in that The second capability information includes a sixth capability parameter list, the sixth capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI model identifier and one or more fifth information corresponding to the AI ​​model identifier.

155. The terminal device according to any one of claims 147-154, characterized in that The second capability information is sent according to one or more of the following granularities: carrier granularity, frequency band granularity, frequency band combination granularity, and frequency band range granularity.

156. The terminal device according to any one of claims 147-155, characterized in that The sending unit is further configured to: Send sixth information to the network device, where the sixth information is related to the AI ​​model or AI function actually deployed by the terminal device, and the sixth information includes one or more seventh information, where each of the one or more seventh information is used to indicate the applicable conditions of the AI ​​model or AI function associated with each seventh information.

157. The terminal device according to claim 156, characterized in that The seventh information is sent according to any one of the following granularities: AI function granularity or AI model granularity.

158. The terminal device according to claim 157, characterized in that The seventh information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the seventh information is indicated by the position of the seventh information in the sixth information.

159. The terminal device according to claim 157, characterized in that The seventh information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the seventh information is indicated by the AI ​​function identifier.

160. The terminal device according to claim 159, characterized in that The sixth information includes a seventh capability parameter list, the seventh capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI function identifier and one or more seventh information corresponding to the AI ​​function identifier.

161. The terminal device according to claim 157, characterized in that The seventh information is sent according to the AI ​​model granularity, and the AI ​​model corresponding to the seventh information is indicated by the AI ​​model identifier.

162. The terminal device according to claim 161, characterized in that The sixth information includes an eighth capability parameter list, the eighth capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI model identifier and one or more seventh information corresponding to the AI ​​model identifier.

163. The terminal device according to any one of claims 156-162, characterized in that The terminal device further includes: A receiving unit is used to receive eighth information sent by the network device, where the eighth information is used to instruct the terminal device to send model deployment information to the network device.

164. The terminal device according to claim 163, characterized in that The eighth information includes one or more of the following information: Identification information corresponding to the AI ​​model that the network device is concerned about; Identification information corresponding to the AI ​​function that the network device is concerned about; Fifth indication information, the fifth indication information is used to instruct the terminal device to send model deployment information to the network device.

165. The terminal device according to any one of claims 156-164, characterized in that The sending unit is further configured to: Ninth information is sent to the network device, where the ninth information is used to indicate that the terminal device has reportable model deployment information, or to indicate that the terminal device has actually deployed an AI model or AI function.

166. The terminal device according to claim 165, characterized in that The ninth information is used to indicate that the terminal device has reportable model deployment information, and the ninth information includes one or more of the following information: Sixth indication information, where the value of the sixth indication information is a third value, and the third value is used to indicate that the terminal device has reportable model deployment information; One or more AI model identification information; One or more AI function identification information.

167. The terminal device according to claim 165, characterized in that The ninth information is used to indicate that the terminal device has actually deployed an AI model or AI function, and the ninth information includes one or more of the following information: one or more AI model identification information, and one or more AI function identification information.

168. A network device, characterized in that include: A receiving unit is configured to receive second capability information sent by a terminal device, where the second capability information is related to an artificial intelligence (AI) model or AI function supported by the terminal device, and the second capability information includes any one of the following information: One or more fifth information, each of the one or more fifth information being used to indicate an applicable condition of an AI model or AI function associated with the fifth information; One or more AI function identification information; One or more AI model identification information.

169. The network device according to claim 168, characterized in that The fifth information is sent according to any one of the following granularities: AI function granularity or AI model granularity.

170. The network device according to claim 169, wherein: The fifth information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the fifth information is indicated by the position of the fifth information in the second capability information.

171. The network device according to claim 170, characterized in that The fifth information is associated with the fourth indication information, and the fourth indication information is used to indicate whether the terminal device supports the AI ​​function corresponding to the fifth information associated with the fourth indication information.

172. The network device according to claim 169, wherein: The fifth information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the fifth information is indicated by the AI ​​function identifier.

173. The network device according to claim 172, characterized in that The second capability information includes a fifth capability parameter list, the fifth capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI function identifier and one or more fifth information corresponding to the AI ​​function identifier.

174. The network device according to claim 169, characterized in that The fifth information is sent according to the AI ​​model granularity, and the AI ​​model corresponding to the fifth information is indicated by the AI ​​model identifier.

175. The network device according to claim 174, characterized in that The second capability information includes a sixth capability parameter list, the sixth capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI model identifier and one or more fifth information corresponding to the AI ​​model identifier.

176. The network device according to any one of claims 168-175, characterized in that The second capability information is sent according to one or more of the following granularities: carrier granularity, frequency band granularity, frequency band combination granularity, and frequency band range granularity.

177. The network device according to any one of claims 168-176, characterized in that The receiving unit is further configured to: Receive the sixth information sent by the terminal device, where the sixth information is related to the AI ​​model or AI function actually deployed by the terminal device, and the sixth information includes one or more seventh information, where each of the one or more seventh information is used to indicate the applicable conditions of the AI ​​model or AI function associated with each seventh information.

178. The network device according to claim 177, characterized in that The seventh information is sent according to any one of the following granularities: AI function granularity or AI model granularity.

179. The network device according to claim 178, characterized in that The seventh information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the seventh information is indicated by the position of the seventh information in the sixth information.

180. The network device according to claim 178, characterized in that The seventh information is sent according to the AI ​​function granularity, and the AI ​​function corresponding to the seventh information is indicated by the AI ​​function identifier.

181. The network device according to claim 180, characterized in that The sixth information includes a seventh capability parameter list, the seventh capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI function identifier and one or more seventh information corresponding to the AI ​​function identifier.

182. The network device according to claim 178, wherein: The seventh information is sent according to the AI ​​model granularity, and the AI ​​model corresponding to the seventh information is indicated by the AI ​​model identifier.

183. The network device according to claim 182, characterized in that The sixth information includes an eighth capability parameter list, the eighth capability parameter list includes one or more capability parameters, and any one of the one or more capability parameters includes an AI model identifier and one or more seventh information corresponding to the AI ​​model identifier.

184. The network device according to any one of claims 177-183, characterized in that The network device further includes: A sending unit is used to send eighth information to the terminal device, and the eighth information is used to instruct the terminal device to send model deployment information to the network device.

185. The network device according to claim 184, characterized in that The eighth information includes one or more of the following information: Identification information corresponding to the AI ​​model that the network device is concerned about; Identification information corresponding to the AI ​​function that the network device is concerned about; Fifth indication information, the fifth indication information is used to instruct the terminal device to send model deployment information to the network device.

186. The network device according to any one of claims 177-185, characterized in that The receiving unit is further configured to: Receive ninth information sent by the terminal device, where the ninth information is used to indicate that the terminal device has reportable model deployment information, or indicates that the terminal device has deployed an AI model or AI function.

187. The network device according to claim 186, characterized in that The ninth information is used to indicate that the terminal device has reportable model deployment information, and the ninth information includes one or more of the following information: Sixth indication information, where the value of the sixth indication information is a third value, and the third value is used to indicate that the terminal device has reportable model deployment information; One or more AI model identification information; One or more AI function identification information.

188. The network device according to claim 186, characterized in that The ninth information is used to indicate that the terminal device has actually deployed an AI model or AI function, and the ninth information includes one or more of the following information: one or more AI model identification information, and one or more AI function identification information.

189. A terminal device, characterized in that It includes a transceiver, a memory and a processor, the memory is used to store programs, the processor is used to call the programs in the memory and control the transceiver to receive or send signals so that the terminal device executes the method as described in any one of claims 1-26, 53-73.

190. A network device, characterized in that It includes a transceiver, a memory and a processor, the memory is used to store programs, the processor is used to call the programs in the memory and control the transceiver to receive or send signals so that the network device executes the method as described in any one of claims 27-52, 74-94.

191. A device, characterized in that The device comprises a processor configured to call a program from a memory so as to cause the device to execute the method according to any one of claims 1-26, 27-52, 53-73, and 74-94.

192. A chip, characterized in that: The device comprises a processor configured to call a program from a memory so that a device equipped with the chip executes the method according to any one of claims 1-26, 27-52, 53-73, and 74-94.

193. A computer-readable storage medium, characterized in that A program is stored thereon, the program causing the computer to execute the method according to any one of claims 1-26, 27-52, 53-73, 74-94.

194. A computer program product, characterized in that The method comprises a program for causing a computer to execute the method according to any one of claims 1-26, 27-52, 53-73, 74-94.

195. A computer program, characterized in that The computer program causes a computer to execute the method according to any one of claims 1-26, 27-52, 53-73, 74-94.

Images