Model processing method and apparatus, and storage medium

Abstract

The present disclosure relates to a model processing method and apparatus, and a storage medium. The method executed by a first network function comprises: receiving perception processing data sent by a second network function, wherein the perception processing data is determined by the second network function on the basis of perception data provided by a terminal, and the perception processing data is data required by the first network function to execute an AI model-based perception task; receiving perception related information sent by a third network function, wherein the perception related information is related information required by the first network function to execute the AI model-based perception task; and executing the AI model-based perception task on the basis of the perception processing data and the perception related information, to determine a perception processing result. Thus, computing resources can be effectively utilized, data privacy can be protected, and data management can be enhanced, thereby reducing signaling overhead and decreasing delay.

Description

Model processing method, device and storage medium Technical Field

[0001] The present disclosure relates to the field of communication technology, and in particular to a model processing method, device, and storage medium. Background Art

[0002] In related technologies, networks can implement local intelligence using technologies such as artificial intelligence (AI) and / or machine learning (ML). The network can monitor terminal or network function (NF) related information in real time, including access status and session flow.

[0003] Summary of the Invention

[0004] The embodiments of the present disclosure propose a model processing method, device, and storage medium to solve the problems in related technologies of collecting and processing AI model data concentrated in one network function, which have data security, excessive signaling overhead, and high latency.

[0005] According to a first aspect of an embodiment of the present disclosure, a model processing method is proposed, which is executed by a first network function, including: receiving perception processing data sent by a second network function, wherein the perception processing data is determined by the second network function based on perception data provided by a terminal, and the perception processing data is data required for the first network function to perform a perception task based on an AI model; receiving perception-related information sent by a third network function, wherein the perception-related information is relevant information required for the first network function to perform a perception task based on an AI model; performing a perception task based on the AI ​​model according to the perception processing data and the perception-related information, and determining a perception processing result.

[0006] In the above embodiment, the first network function can obtain perception processing data from the second network function, and obtain perception-related information from the third network function, and then perform perception tasks based on the AI ​​model based on the perception processing data and perception-related information, and determine the perception processing results. The data collection and preprocessing of the AI ​​model can be performed and stored at other network functions other than the first network function, which can ensure data security. Afterwards, the first network function obtains the data of the AI ​​model from other network functions, which can effectively utilize computing resources and enhance data management, and can save signaling overhead and reduce latency.

[0007] According to a second aspect of an embodiment of the present disclosure, a model processing method is proposed, which is executed by a second network function, including: determining perception processing data; sending the perception processing data to the first network function, wherein the perception processing data is data required for the first network function to perform a perception task based on an AI model.

[0008] In the above embodiment, the second network function can determine the perception processing data and provide it to the first network function, without the first network function using computing resources to determine the perception processing data. This can save computing resources of the first network function, protect data privacy, and enhance data management. In addition, the second network function directly provides the perception processing data to the first network function, which can also reduce latency.

[0009] According to a third aspect of an embodiment of the present disclosure, a model processing method is proposed, which is executed by a third network function, including: receiving a third message sent by a first network function, wherein the third message is used to instruct the third network function to provide perception-related information, where the perception-related information is the relevant information required for the first network function to perform a perception task based on an AI model; and sending the perception-related information to the first network function.

[0010] In the above embodiment, the third network function can determine the perception-related data and provide it to the first network function, without the first network function using computing resources to determine the perception processing data. This can save the computing resources of the first network function, protect data privacy, and enhance data management. In addition, the third network function directly provides the perception-related data to the first network function, which can also reduce latency.

[0011] According to a fourth aspect of an embodiment of the present disclosure, a model processing method is proposed, which is executed by a terminal, including: determining perception data; sending the perception data to a second network function, wherein the perception data is used by the second network function to determine perception processing data, and the perception processing data is data required for the first network function to perform a perception task based on an AI model.

[0012] In the above embodiment, the terminal is able to determine the perception data and provide it to the second network function, and after determining the perception processing data at the second network function, provide it to the first network function. The first network function does not need to use computing resources to determine the perception processing data, which can save computing resources of the first network function, protect data privacy, and enhance data management.

[0013] According to a fifth aspect of an embodiment of the present disclosure, a model processing method is proposed, wherein a terminal determines perception data; the terminal sends the perception data to a second network function; the second network function receives the perception data sent by the terminal; the second network function processes the perception data to determine perception processing data; the second network function sends the perception processing data to the first network function; the third network function receives a third message sent by the first network function, wherein the third message is used to instruct the third network function to provide perception-related information; the third network function sends perception-related information to the first network function; the first network function receives the perception processing data sent by the second network function; the first network function receives the perception-related information sent by the third network function; the first network function performs a perception task based on the AI ​​model according to the perception processing data and the perception-related information, and determines a perception processing result.

[0014] According to a sixth aspect of an embodiment of the present disclosure, a first network function is provided, including: a transceiver module for receiving perception processing data sent by a second network function, wherein the perception processing data is determined by the second network function based on perception data provided by a terminal, and the perception processing data is data required for the first network function to perform a perception task based on an AI model; the transceiver module is also used to receive perception-related information sent by a third network function, wherein the perception-related information is relevant information required for the first network function to perform a perception task based on an AI model; a processing module is used to perform a perception task based on an AI model according to the perception processing data and the perception-related information, and determine a perception processing result.

[0015] According to the seventh aspect of an embodiment of the present disclosure, a second network function is provided, including: a processing module for determining perception processing data; and a transceiver module for sending perception processing data to the first network function, wherein the perception processing data is data required for the first network function to perform a perception task based on an AI model.

[0016] According to an eighth aspect of an embodiment of the present disclosure, a third network function is provided, including: a transceiver module, configured to receive a third message sent by a first network function, wherein the third message is used to instruct the third network function to provide perception-related information, where the perception-related information is relevant information required for the first network function to perform a perception task based on an AI model; the transceiver module is further configured to send the perception-related information to the first network function.

[0017] According to a ninth aspect of an embodiment of the present disclosure, a terminal is provided, comprising: a processing module for determining perception data; and a transceiver module for sending the perception data to a second network function, wherein the perception data is used by the second network function to determine perception processing data, and the perception processing data is data required for the first network function to perform a perception task based on an AI model.

[0018] According to the tenth aspect of an embodiment of the present disclosure, a communication device is provided, comprising: one or more processors; a memory coupled to the processor, wherein the memory stores instructions, and when the instructions are executed by the processor, the communication device executes the method described in the first aspect.

[0019] According to an eleventh aspect of an embodiment of the present disclosure, a communication device is provided, comprising: one or more processors; a memory coupled to the processor, the memory storing instructions, which, when executed by the processor, enables the communication device to execute the method described in the second aspect.

[0020] According to the twelfth aspect of an embodiment of the present disclosure, a communication device is provided, comprising: one or more processors; a memory coupled to the processor, wherein the memory stores instructions, and when the instructions are executed by the processor, the communication device executes the method described in the third aspect.

[0021] According to the thirteenth aspect of the embodiment of the present disclosure, a communication device is provided, comprising: one or more processors; a memory coupled to the processor, the memory storing instructions, which, when executed by the processor, enables the communication device to execute the method described in the fourth aspect.

[0022] According to the fourteenth aspect of an embodiment of the present disclosure, a communication system is provided, including a first network function, a second network function, a third network function, and a terminal, wherein the first network function is configured to implement the method described in the first aspect, the second network function is configured to implement the method described in the second aspect, the third network function is configured to implement the method described in the third aspect, and the terminal is configured to implement the method described in the fourth aspect.

[0023] According to the fifteenth aspect of an embodiment of the present disclosure, a storage medium is provided, which stores instructions. When the instructions are executed on a communication device, the communication device executes the method described in the first aspect, the second aspect, the third aspect, or the fourth aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following drawings required for describing the embodiments are introduced. The following drawings are merely some embodiments of the present disclosure and do not impose specific limitations on the protection scope of the present disclosure.

[0025] FIG1A is a schematic diagram of a network architecture of a 5G communication system provided in an embodiment of the present disclosure.

[0026] FIG1B is a schematic diagram of a network architecture of another 5G communication system provided in an embodiment of the present disclosure.

[0027] Figure 1C is a schematic diagram of the network architecture of another 5G communication system provided in an embodiment of the present disclosure.

[0028] Figure 1D is a schematic diagram of the network architecture of another 5G communication system provided in an embodiment of the present disclosure.

[0029] Figure 1E is a schematic diagram of the network architecture of another 5G communication system provided in an embodiment of the present disclosure.

[0030] Figure 1F is a schematic diagram of the network architecture of another 5G communication system provided in an embodiment of the present disclosure.

[0031] FIG1G is a schematic diagram of a network architecture of a communication system provided in an embodiment of the present disclosure.

[0032] FIG2 is a flow chart of a model processing method provided by an embodiment of the present disclosure;

[0033] FIG3A is a flow chart of another model processing method provided by an embodiment of the present disclosure;

[0034] FIG3B is a flowchart of another model processing method provided by an embodiment of the present disclosure;

[0035] FIG4 is a flow chart of another model processing method provided by an embodiment of the present disclosure;

[0036] FIG5 is a flowchart of another model processing method provided by an embodiment of the present disclosure;

[0037] FIG6A is a flowchart of another model processing method provided by an embodiment of the present disclosure;

[0038] FIG6B is a flowchart of another model processing method provided by an embodiment of the present disclosure;

[0039] FIG7 is a flowchart of another model processing method provided by an embodiment of the present disclosure;

[0040] FIG8A is a structural diagram of a first network function provided by an embodiment of the present disclosure;

[0041] FIG8B is a structural diagram of a second network function provided by an embodiment of the present disclosure;

[0042] FIG8C is a structural diagram of a third network function provided by an embodiment of the present disclosure;

[0043] FIG8D is a structural diagram of a terminal provided by an embodiment of the present disclosure;

[0044] FIG9A is a structural diagram of a communication device provided by an embodiment of the present disclosure;

[0045] FIG9B is a schematic structural diagram of a chip provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0046] The embodiments of the present disclosure provide a model processing method, device, and storage medium.

[0047] In a first aspect, an embodiment of the present disclosure proposes a model processing method, which is executed by a first network function, including: receiving perception processing data sent by a second network function, wherein the perception processing data is determined by the second network function based on the perception data provided by the terminal, and the perception processing data is the data required for the first network function to perform a perception task based on the AI ​​model; receiving perception-related information sent by a third network function, wherein the perception-related information is the relevant information required for the first network function to perform a perception task based on the AI ​​model; performing the perception task based on the AI ​​model according to the perception processing data and the perception-related information, and determining the perception processing result.

[0048] In the above embodiment, the first network function can obtain perception processing data from the second network function, and obtain perception-related information from the third network function, and then perform perception tasks based on the AI ​​model based on the perception processing data and perception-related information, and determine the perception processing results. The data collection and preprocessing of the AI ​​model can be performed and stored at other network functions other than the first network function, which can ensure data security. Afterwards, the first network function obtains the data of the AI ​​model from other network functions, which can effectively utilize computing resources and enhance data management, and can save signaling overhead and reduce latency.

[0049] In combination with some embodiments of the first aspect, in some embodiments, the above method also includes: the first network function receives a first message sent by the terminal, wherein the first message is used to instruct the first network function to perform a perception task based on the AI ​​model; and sends a second message to the terminal, wherein the second message is used to instruct the terminal to provide perception data to the second network function.

[0050] In the above embodiment, the first network function can determine to perform a perception task based on the AI ​​model based on the request of the terminal, and instruct the terminal to report the perception data to the second network function so as to pre-process the perception data at the second network function, thereby effectively utilizing computing resources, protecting data privacy, and enhancing data management.

[0051] In combination with some embodiments of the first aspect, in some embodiments, the above method also includes: the first network function sends a third message to the third network function, wherein the third message is used to instruct the third network function to provide perception-related information.

[0052] In the above embodiment, the perception-related information is stored at the third network function. The first network function can instruct the third network function to provide the perception-related information, thereby facilitating the provision of relevant data analysis services, avoiding repeated calculations, and enhancing data management.

[0053] In combination with some embodiments of the first aspect, in some embodiments, the perception-related information includes an AI model, and the first network function performs a perception task based on the AI ​​model according to the perception processing data and the perception-related information, and determines the perception processing result, including: determining the perception processing result according to the perception processing data and the AI ​​model.

[0054] In the above embodiment, the perception-related information includes an AI model. The first network function can determine the perception processing result based on the perception processing data obtained from the second network function and the AI ​​model obtained from the third network function. The AI ​​model and the perception processing data are obtained from different network functions respectively, which can reduce the burden of data redundancy, effectively utilize computing resources, enhance data management, and protect data privacy.

[0055] In combination with some embodiments of the first aspect, in some embodiments, the perception-related information includes an initial AI model and historical perception data. The first network function performs a perception task based on the AI ​​model according to the perception processing data and the perception-related information, and determines the perception processing result, including: training the initial AI model according to the historical perception data to determine the AI ​​model; and determining the perception processing result according to the perception processing data and the AI ​​model.

[0056] In the above embodiment, the perception-related information includes an initial AI model and historical perception data. The first network function can determine the perception processing result based on the perception processing data obtained from the second network function and the initial AI model and historical perception data obtained from the third network function. The initial AI model, historical perception data and perception processing data are obtained from different network functions respectively, which can reduce the burden of data redundancy, effectively utilize computing resources, enhance data management, and protect data privacy.

[0057] In combination with some embodiments of the first aspect, in some embodiments, the above method also includes: the first network function sends a fourth message to the terminal, wherein the fourth message is used to indicate the perception processing result.

[0058] In the above embodiment, after determining the perception processing result, the first network function may indicate it to the terminal.

[0059] In combination with some embodiments of the first aspect, in some embodiments, the above method also includes: the first network function sends a fifth message to the third network function, wherein the fifth message is used to indicate the perception processing result.

[0060] In the above embodiment, after determining the perception processing result, the first network function can instruct the third network function to store it at the third network function, thereby saving historical analysis results, facilitating related data analysis services, and avoiding repeated calculations.

[0061] In combination with some embodiments of the first aspect, in some embodiments, the first network function sends the fourth message to the terminal, including: sending the fourth message to the terminal through a control plane or a user plane.

[0062] In the above embodiment, the first network function can send the perception processing result to the terminal through the control plane or the user plane, which can reduce the risk of network congestion caused by transmitting AI data on the control plane.

[0063] In combination with some embodiments of the first aspect, in some embodiments, the perception processing data is determined by the second network function based on perception data provided by the terminal through the user plane.

[0064] In the above embodiment, the terminal can provide perception data to the second network function through the user, which can reduce the risk of network congestion caused by transmitting AI data on the control plane.

[0065] In a second aspect, an embodiment of the present disclosure proposes a model processing method, which is executed by a second network function, including: determining perception processing data; sending perception processing data to a first network function, wherein the perception processing data is data required for the first network function to perform perception tasks based on an AI model.

[0066] In the above embodiment, the second network function can determine the perception processing data and provide it to the first network function, without the first network function using computing resources to determine the perception processing data. This can save computing resources of the first network function, protect data privacy, and enhance data management. In addition, the second network function directly provides the perception processing data to the first network function, which can also reduce latency.

[0067] In combination with some embodiments of the second aspect, in some embodiments, the second network function determines the perception processing data, including: receiving perception data sent by the terminal; processing the perception data to determine the perception processing data.

[0068] In the above embodiment, the second network function is capable of receiving the perception data sent by the terminal, and processing the perception data to determine the perception processed data.

[0069] In combination with some embodiments of the second aspect, in some embodiments, the second network function receives the perception data sent by the terminal, including: receiving the perception data sent by the terminal through the user plane.

[0070] In the above embodiment, the second network function can receive the perception data sent by the terminal through the user plane, and can reduce the risk of network congestion caused by transmitting AI data on the control plane.

[0071] In a third aspect, an embodiment of the present disclosure proposes a model processing method, which is executed by a third network function, including: receiving a third message sent by a first network function, wherein the third message is used to instruct the third network function to provide perception-related information, and the perception-related information is the relevant information required for the first network function to perform a perception task based on an AI model; and sending the perception-related information to the first network function.

[0072] In the above embodiment, the third network function can determine the perception-related data and provide it to the first network function, without the first network function using computing resources to determine the perception processing data. This can save the computing resources of the first network function, protect data privacy, and enhance data management. In addition, the third network function directly provides the perception-related data to the first network function, which can also reduce latency.

[0073] In combination with some embodiments of the third aspect, in some embodiments, the above method also includes: the third network function receives a fifth message sent by the first network function, wherein the fifth message is used to instruct the first network function to execute the perception processing result determined by the perception task based on the AI ​​model.

[0074] In the above embodiment, the third network function is capable of receiving the perception processing results sent by the first network function and storing them at the third network function, thereby saving historical analysis results, facilitating related data analysis services, and avoiding repeated calculations.

[0075] In a fourth aspect, an embodiment of the present disclosure proposes a model processing method, which is executed by a terminal, including: determining perception data; sending the perception data to a second network function, wherein the perception data is used by the second network function to determine perception processing data, and the perception processing data is the data required for the first network function to perform a perception task based on an AI model.

[0076] In the above embodiment, the terminal is able to determine the perception data and provide it to the second network function, and after determining the perception processing data at the second network function, provide it to the first network function. The first network function does not need to use computing resources to determine the perception processing data, which can save computing resources of the first network function, protect data privacy, and enhance data management.

[0077] In combination with some embodiments of the fourth aspect, in some embodiments, the above method also includes: the terminal determines an AI model-based perception task that needs to be performed by the first network function; sending a first message to the first network function, wherein the first message is used to instruct the first network function to perform the AI ​​model-based perception task; receiving a second message sent by the first network function, wherein the second message is used to instruct the terminal to provide perception data to the second network function.

[0078] In the above embodiment, when the terminal determines that the first network function is required to perform a perception task based on the AI ​​model, the terminal can initiate a request to the first network function, and after receiving an instruction from the first network function, report the perception data and report it to the second network function so that the perception data can be pre-processed at the second network function, which can effectively utilize computing resources, protect data privacy, and enhance data management.

[0079] In combination with some embodiments of the fourth aspect, in some embodiments, the above method also includes: the terminal receives a fourth message sent by the first network function, wherein the fourth message is used to instruct the first network function to execute the perception processing result determined by the perception task based on the AI ​​model.

[0080] In the above embodiment, after determining the perception processing result, the first network function may indicate it to the terminal.

[0081] In combination with some embodiments of the fourth aspect, in some embodiments, the terminal receives the fourth message sent by the first network function, including: receiving the fourth message sent by the first network function through the control plane or the user plane.

[0082] In the above embodiment, the first network function can send the perception processing result to the terminal through the control plane or the user plane, which can reduce the risk of network congestion caused by transmitting AI data on the control plane.

[0083] In combination with some embodiments of the fourth aspect, in some embodiments, the terminal sends the perception data to the second network function, including: sending the perception data to the second network function through the user.

[0084] In the above embodiment, the terminal can provide perception data to the second network function through the user, which can reduce the risk of network congestion caused by transmitting AI data on the control plane.

[0085] In a fifth aspect, an embodiment of the present disclosure proposes a model processing method, wherein the terminal determines perception data; the terminal sends the perception data to the second network function; the second network function receives the perception data sent by the terminal; the second network function processes the perception data to determine perception processing data; the second network function sends the perception processing data to the first network function; the third network function receives a third message sent by the first network function, wherein the third message is used to instruct the third network function to provide perception-related information; the third network function sends perception-related information to the first network function; the first network function receives the perception processing data sent by the second network function; the first network function receives the perception-related information sent by the third network function; the first network function performs a perception task based on the AI ​​model according to the perception processing data and the perception-related information, and determines the perception processing result.

[0086] In a sixth aspect, an embodiment of the present disclosure proposes a first network function, which includes at least one of a transceiver module and a processing module; wherein the first network function is used to execute the optional implementation method of the first aspect.

[0087] In the seventh aspect, an embodiment of the present disclosure proposes a second network function, which includes at least one of a transceiver module and a processing module; wherein the second network function is used to execute the optional implementation method of the second aspect.

[0088] In an eighth aspect, an embodiment of the present disclosure proposes a third network function, which includes at least one of a transceiver module and a processing module; wherein the third network function is used to execute the optional implementation method of the third aspect.

[0089] In a ninth aspect, an embodiment of the present disclosure proposes a terminal, which includes at least one of a transceiver module and a processing module; wherein the terminal is used to execute the optional implementation method of the fourth aspect.

[0090] In the tenth aspect, an embodiment of the present disclosure proposes a communication device, which includes: one or more processors; a memory coupled to the processor, on which instructions are stored, and when the instructions are executed by the processor, the communication device executes the optional implementation method of the first aspect.

[0091] In the eleventh aspect, an embodiment of the present disclosure proposes a communication device, which includes: one or more processors; a memory coupled to the processor, on which instructions are stored, and when the instructions are executed by the processor, the communication device executes the optional implementation method of the second aspect.

[0092] In the twelfth aspect, an embodiment of the present disclosure proposes a communication device, which includes: one or more processors; a memory coupled to the processor, on which instructions are stored, and when the instructions are executed by the processor, the communication device executes the optional implementation method of the third aspect.

[0093] In the thirteenth aspect, an embodiment of the present disclosure proposes a communication device, which includes: one or more processors; a memory coupled to the processor, on which instructions are stored, and when the instructions are executed by the processor, the communication device executes the optional implementation method of the fourth aspect.

[0094] In the fourteenth aspect, an embodiment of the present disclosure proposes a communication system, which includes: a first network function, a second network function, a third network function, and a terminal; wherein the first network function is configured to execute the method described in the optional implementation manner of the first aspect, the second network function is configured to execute the method described in the optional implementation manner of the second aspect, the third network function is configured to execute the method described in the optional implementation manner of the third aspect, and the terminal is configured to execute the method described in the optional implementation manner of the fourth aspect.

[0095] In the fifteenth aspect, an embodiment of the present disclosure proposes a storage medium, which stores instructions. When the instructions are executed on a communication device, the communication device executes the method described in the optional implementation of the first and second aspects, the third and fourth aspects.

[0096] In a sixteenth aspect, an embodiment of the present disclosure proposes a program product. When the program product is executed by a communication device, the communication device executes the method described in the optional implementation of the first and second aspects, and the third and fourth aspects.

[0097] In the seventeenth aspect, an embodiment of the present disclosure proposes a computer program, which, when executed on a computer, enables the computer to execute the method described in the optional implementation of the first aspect, the second aspect, the third aspect, and the fourth aspect.

[0098] In an eighteenth aspect, an embodiment of the present disclosure provides a chip or a chip system, wherein the chip or chip system includes a processing circuit configured to execute the method described in the optional implementation of the first aspect, the second aspect, the third aspect, and the fourth aspect.

[0099] It is understandable that the first network function, the second network function, the third network function, the terminal, the communication device, the communication system, the storage medium, the program product, the computer program, the chip, or the chip system are all used to perform the method proposed in the embodiment of the present disclosure. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects of the corresponding method and will not be repeated here.

[0100] The present disclosure provides a model processing method, device, and storage medium. In some embodiments, the terms model processing method, information processing method, communication method, etc. can be used interchangeably.

[0101] The embodiments of the present disclosure are not exhaustive and are merely illustrative of some embodiments, and are not intended to be a specific limitation on the scope of protection of the present disclosure. In the absence of contradiction, each step in a certain embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a certain embodiment can also be implemented as an independent embodiment, and the order of the steps in a certain embodiment can be arbitrarily exchanged. In addition, the optional implementation methods in a certain embodiment can be arbitrarily combined; in addition, the embodiments can be arbitrarily combined. For example, some or all steps of different embodiments can be arbitrarily combined, and a certain embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0102] In each embodiment of the present disclosure, unless otherwise specified or provided for by logic, the terms and / or descriptions between the embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form a new embodiment based on their inherent logical relationships.

[0103] The terms used in the embodiments of the present disclosure are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure.

[0104] In the embodiments of the present disclosure, unless otherwise specified, elements expressed in the singular, such as "a", "an", "the", "above", "said", "the", "the", etc., may mean "one and only one", or "one or more", "at least one", etc. For example, when using articles such as "a", "an", "the" in English in translation, the noun following the article may be understood as a singular expression or a plural expression.

[0105] In the embodiments of the present disclosure, “plurality” refers to two or more.

[0106] In some embodiments, the terms "at least one," "one or more," "a plurality of," "multiple," etc. may be used interchangeably.

[0107] In some embodiments, descriptions such as "at least one of A and B," "A and / or B," "A in one case, B in another case," or "in response to one case A, in response to another case B" may include the following technical solutions depending on the situation: in some embodiments, A (A is executed independently of B); in some embodiments, B (B is executed independently of A); in some embodiments, execution is selected from A and B (A and B are selectively executed); and in some embodiments, A and B (both A and B are executed). The above is also applicable when there are more branches such as A, B, and C.

[0108] In some embodiments, "A or B" and other descriptions may include the following technical solutions depending on the situation: in some embodiments, A (A is executed independently of B); in some embodiments, B (B is executed independently of A); in some embodiments, execution is selected from A and B (A and B are selectively executed). The above is also applicable when there are more branches such as A, B, C, etc.

[0109] The prefixes such as "first" and "second" in the embodiments of the present disclosure are only used to distinguish different description objects and do not constitute any restriction on the position, order, priority, quantity or content of the description objects. For the statement of the description object, please refer to the description in the context of the claims or embodiments, and no unnecessary restriction should be constituted due to the use of prefixes. For example, if the description object is a "field", the ordinal number before the "field" in the "first field" and the "second field" does not limit the position or order between the "fields". "First" and "second" do not limit whether the "fields" they modify are in the same message, nor do they limit the order of the "first field" and the "second field". For another example, if the description object is a "level", the ordinal number before the "level" in the "first level" and the "second level" does not limit the priority between the "levels". For another example, the number of description objects is not limited by the ordinal number and can be one or more. Taking "first device" as an example, the number of "devices" can be one or more. In addition, the objects modified by different prefixes can be the same or different. For example, if the description object is "device", then the "first device" and the "second device" can be the same device or different devices, and their types can be the same or different; for another example, if the description object is "information", then the "first information" and the "second information" can be the same information or different information, and their contents can be the same or different.

[0110] In some embodiments, “including A,” “comprising A,” “used to indicate A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0111] In some embodiments, terms such as "time / frequency" and "time / frequency domain" refer to the time domain and / or the frequency domain.

[0112] In some embodiments, terms such as "in response to...", "in response to determining...", "in the case of...", "at the time of...", "when...", "if...", "if...", etc. can be used interchangeably.

[0113] In some embodiments, terms such as "greater than", "greater than or equal to", "not less than", "more than", "more than or equal to", "not less than", "higher than", "higher than or equal to", "not less than", and "above" can be replaced with each other, and terms such as "less than", "less than or equal to", "not greater than", "less than", "less than or equal to", "not more than", "lower than", "lower than or equal to", "not higher than", and "below" can be replaced with each other.

[0114] In some embodiments, devices, etc. can be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. Terms such as "device", "equipment", "device", "circuit", "network element", "node", "function", "unit", "section", "system", "network", "chip", "chip system", "entity", and "subject" can be used interchangeably.

[0115] In some embodiments, "network" can be interpreted as devices included in the network (eg, access network equipment, core network equipment, etc.).

[0116] In some embodiments, the terms "access network device (AN device)", "radio access network device (RAN device)", "base station (BS)", "radio base station" "fixed station", "node", "access point", "transmission point (TP)", "reception point (RP)", "transmission / reception point (TRP)" "panel", "antenna panel", "antenna array", "cell", "macro cell", "small cell", "femto cell", "pico cell", "sector", "cell group", "serving cell", "carrier", "component carrier", "bandwidth part (BWP)" and the like may be used interchangeably.

[0117] In some embodiments, the terms "terminal", "terminal device", "user equipment (UE)", "user terminal", "mobile station (MS)", "mobile terminal (MT)", subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, etc. can be used interchangeably.

[0118] In some embodiments, the access network device, the core network device, or the network device can be replaced by a terminal. For example, the various embodiments of the present disclosure can also be applied to a structure in which the communication between the access network device, the core network device, or the network device and the terminal is replaced by communication between multiple terminals (for example, device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, it is also possible to set the structure in which the terminal has all or part of the functions of the access network device. In addition, terms such as "uplink" and "downlink" can also be replaced by terms corresponding to communication between terminals (for example, "side"). For example, uplink channels, downlink channels, etc. can be replaced by side channels, and uplinks, downlinks, etc. can be replaced by side links.

[0119] In some embodiments, the terminal may be replaced by an access network device, a core network device, or a network device. In this case, the access network device, the core network device, or the network device may have a structure that has all or part of the functions of the terminal.

[0120] In some embodiments, obtaining data, information, etc. may comply with the laws and regulations of the country where the data is obtained.

[0121] In some embodiments, data, information, etc. may be obtained with the user's consent.

[0122] In addition, each element, each row, or each column in the table of the embodiment of the present disclosure can be implemented as an independent embodiment, and the combination of any elements, any rows, and any columns can also be implemented as an independent embodiment.

[0123] FIG1A is a schematic diagram of a network architecture of a 5G communication system provided by an embodiment of the present disclosure. The 5G network includes (radio) access network (R)AN) equipment, user plane function (UPF), access and mobility management function (AMF), session management function (SMF), authentication server function (AUSF), network slice selection function (NSSF), network exposure function (NEF), network exposure function repository (NRF), policy control function (PCF), unified data management (UDM), unified data repository (UDR), application function (AF), etc.

[0124] It should be noted that Figure 1A only exemplifies some examples of network elements or entities in a 5G network. The 5G network may also include some network elements or entities not shown in Figure 1A, such as a network data analytics function (NWDAF). Moreover, the names of the network elements or entities in the 5G network illustrated in Figure 1A may remain unchanged or change in future communication systems (such as 6G communication systems), and the embodiments of the present disclosure do not specifically limit this.

[0125] Among them, AMF is a control plane network element provided by the operator network, responsible for access control and mobility management of terminal devices accessing the operator network, such as mobile status management, allocation of user temporary identity, authentication and authorization of users, etc.

[0126] SMF is a control plane network element provided by the operator network, responsible for managing the protocol data unit (PDU) session of the terminal device. A PDU session is a channel for transmitting PDUs. The terminal device needs to transmit PDUs to and from the data network (DN) through the PDU session. The SMF is responsible for establishing, maintaining, and deleting PDU sessions. SMF includes session management (such as session establishment, modification, and release, including tunnel maintenance between UPF and RAN), UPF selection and control, service and session continuity (SSC) mode selection, roaming, and other session-related functions.

[0127] The UPF is a gateway provided by the operator, serving as the gateway for communication between the operator's network and the DN. The UPF includes user-plane-related functions such as packet routing and transmission, packet inspection, service usage reporting, Quality of Service (QoS) processing, lawful interception, uplink packet inspection, and downlink packet storage.

[0128] The PCF is a control plane function provided by the operator and is used to provide PDU session policies to the SMF. Policies may include charging-related policies, QoS-related policies, and authorization-related policies.

[0129] The UDM is a control plane network element provided by the operator, responsible for storing information such as the subscriber permanent identifier (SUPI), security context, and subscription data of subscribers in the operator's network.

[0130] AF is a functional network element that provides various business services. It can interact with the core network through other network elements and can interact with the policy management framework to perform policy management.

[0131] NEF is used to provide the framework, authentication, and interface related to network capability exposure, and to transmit information between 5G system network functions and other network functions.

[0132] UDR is mainly used to store user-related contract data, policy data, open structured data, and application data.

[0133] In this network architecture, the N1 interface is the interface between the terminal device and the AMF. The N2 interface is the interface between the RAN and the AMF, used for sending non-access stratum (NAS) messages, etc. The N3 interface is the interface between the (R)AN and the UPF, used for transmitting user plane data, etc. The N4 interface is the interface between the SMF and the UPF, used for transmitting information such as tunnel identification information of the N3 connection, data cache indication information, downlink data notification messages, etc. The N6 interface is the interface between the UPF and the DN, used for transmitting user plane data, etc. In addition, control plane functions such as the AUSF, AMF, SMF, NSSF, NEF, NRF, PCF, UDM, UDR, CHF or AF use service-based interfaces to interact. For example, the service-oriented interface provided by AUSF is Nausf; the service-oriented interface provided by AMF is Namf; the service-oriented interface provided by SMF is Nsmf; the service-oriented interface provided by NSSF is Nnssf; the service-oriented interface provided by NEF is Nnef; the service-oriented interface provided by NRF is Nnrf; the service-oriented interface provided by PCF is Npcf; the service-oriented interface provided by UDM is Nudm; the service-oriented interface provided by UDR is Nudr; the service-oriented interface provided by CHF is Nchf; and the service-oriented interface provided by AF is Naf. For the description of the relevant interfaces, please refer to the description in the relevant technology and will not be repeated here.

[0134] As shown in Figure 1A, service-based interfaces are used in the control plane. This architecture includes the following service-based interfaces (e.g., N1, N2) and reference points (e.g., Namf). Reference points show how various network functions interact with each other and how network functions (NFs) in the control plane transmit data / information to other NFs via the control bus.

[0135] In some embodiments, as shown in Figure 1B, the 5G system architecture allows any NF to store its unstructured data in a UDSF or retrieve it from a UDSF (e.g., terminal context). Control plane (CP) NFs can share a UDSF to store their respective unstructured data, or each NF can have its own UDSF (e.g., the UDSF may be located near each NF).

[0136] In some embodiments, as shown in Figure 1C, the 5G system architecture allows the UDM, PCF, and NEF to store data in the UDR, including subscription data and policy data of the UDM and PCF, structured data for openness, and application data of the NEF (including packet flow descriptions for application detection, AF request information of multiple terminals).

[0137] In some embodiments, based on network data analysis, NWDAF is used to analyze data. As shown in FIG1D , the 5G system architecture allows NWDAF to collect data from any 5G core network (5GC) NF.

[0138] In some embodiments, the 5G system architecture allows the NWDAF to collect data from any 5GC NF or operations administration management (OAM) using the data collection coordination function (DCCF) and related Ndccf services.

[0139] As shown in FIG1E , a data collection architecture using data collection coordination is shown.

[0140] As shown in Figure 1F, the data storage architecture for analyzing and collecting data. The 5G system architecture allows the analytics data repository function (ADRF) to store and retrieve collected data and analytics.

[0141] In related technologies, the collection and processing of AI model data are concentrated in one network function, which has problems with data security, excessive signaling overhead and high latency.

[0142] Based on this, the embodiments of the present disclosure provide a model processing method, device, and storage medium, wherein the method executed by the first network function includes: receiving perception processing data sent by the second network function, wherein the perception processing data is determined by the second network function based on the perception data provided by the terminal, and the perception processing data is data required for the first network function to perform a perception task based on the AI ​​model; receiving perception-related information sent by the third network function, wherein the perception-related information is relevant information required for the first network function to perform a perception task based on the AI ​​model; and performing a perception task based on the AI ​​model based on the perception processing data and the perception-related information, and determining a perception processing result. Thus, the first network function can obtain the perception processing data from the second network function and the perception-related information from the third network function, so as to perform a perception task based on the AI ​​model based on the perception processing data and the perception-related information, and determine a perception processing result, thereby effectively utilizing computing resources, protecting data privacy, enhancing data management, saving signaling overhead, and reducing latency.

[0143] Before introducing the embodiments of the present disclosure, the network architecture of the communication system to which the model processing method provided by the embodiments of the present disclosure is applicable is introduced.

[0144] As shown in Figure 1G, this network architecture simplifies network functions, is compatible with the 5G system (5G System, 5GS), retains basic network functions such as AMF / SMF to the maximum extent, and adds three NFs. At least one of the three added NFs replaces and reorganizes some existing NFs.

[0145] The three added NFs are: network data collection function (NDCF), network intelligent computing function (NICF), and network data repository function (NDRF).

[0146] It should be noted that the names of the three NFs can also be other names, and the names of network functions in the 5G system can be reused, or they can be named other names. The embodiments of this disclosure do not impose specific restrictions on this.

[0147] In some embodiments, the NDCF, NICF, and NDRF connect to both the control plane and the user plane. They can use control signaling to request or subscribe to operations and use the data bus to transmit various data (such as AI training data, location data, sensor data, and service data with low latency requirements). A dual-bus design scheme for the control plane and data plane is adopted. The control plane is used to transmit control signaling, and the data plane is used to calculate relevant training data and transmit the calculation and analysis results.

[0148] In some embodiments, based on the concept of network simplicity, network functions related to storage functions are reorganized into a unified data storage network element, that is, unified into NDRF.

[0149] In some embodiments, the control plane and the user plane use new transmission protocols. For example, the control plane can use the stream control transmission protocol (STCP) or the internet protocol (IP) to solve the latency problem and have higher reliability than the transmission control protocol (TCP). The user plane can use the user datagram protocol (UDP) or IP to ensure large data volume and low-latency service transmission.

[0150] In some embodiments, NICF includes: (1) computing power. It can re-compete and call data collected by NDCF and stored by NDRF. It can provide different operations for different services. For example, NICF can support AI-related services. NICF can provide model training and reasoning decisions throughout the AI ​​life cycle. The model training module adapts to distributed AI models such as federated learning and multi-agent reinforcement learning, and collaborates with access network devices or terminals to split data and models. NICF makes predictions, decisions, or recommendations based on the reasoning results.

[0151] (2) Intelligent control scheduling. Based on real-time network performance, it generates AI scheduling policies to allocate network resources. It is used to drive AI workflows, coordinate the collection of real-time and historical data, and is responsible for network configuration and performance management. In addition, it can divide AI tasks into multiple subtasks according to scenario requirements, and generate sub-slices of different tasks and corresponding resource scheduling policies based on resource information, and send them to each node for execution.

[0152] (3) AI model update, which enables model addition, update, and deletion. This function manages the data, trained models, and inference results obtained during the AI ​​service process, and adjusts model parameters in real time to improve learning efficiency and AI service level.

[0153] (4) Intelligent decision-making. Based on the configuration and parameter information obtained from different business requests and combined with the real-time network status, this function can generate methods and strategies.

[0154] In some embodiments, the Network Data Collection Function (NDCF) can acquire real-time network information from different NFs, such as real-time network traffic, network congestion, and unauthorized access. It can also collect data transmitted by NFs and access network devices. After data collection, it can be pre-processed (including normalization and regularization).

[0155] In some embodiments, NDRF integrates all storage-related functions, such as NRF, UDR, UDSF, and ADRF. It can store information including user data (user registration data, service-related data), NF configuration files, network data (network service service level agreement (SLA) data, network node load), and computing-related data (AI training data, computing resource status, location / perception auxiliary information). It can also store calculation results as historical data and provide them to service consumers, reducing resource waste caused by redundant calculations.

[0156] It can be understood that the communication system described in the embodiment of the present disclosure is for the purpose of more clearly illustrating the technical solution of the embodiment of the present disclosure, and does not constitute a limitation on the technical solution proposed in the embodiment of the present disclosure. Ordinary technicians in this field can know that with the evolution of the system architecture and the emergence of new business scenarios, the technical solution proposed in the embodiment of the present disclosure is also applicable to similar technical problems.

[0157] The following embodiments of the present disclosure may be applied to the communication system shown in FIG1G , or a portion of the entities, but are not limited thereto. The entities shown in FIG1G are illustrative only. The communication system may include all or part of the entities shown in FIG1G , or may include other entities other than those shown in FIG1G . The number and form of the entities are arbitrary. The entities may be physical or virtual. The connection relationship between the entities is illustrative only. The entities may be connected or disconnected, and the connection may be in any manner, including direct or indirect, wired or wireless.

[0158] The embodiments of the present disclosure can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), future radio access (FRA), new radio access technology (RAT), new radio (NR), new radio access (NX), future generation radio access (FX), Global System for Mobile communications (GSM (registered trademark)), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi (registered trademark)), IEEE 802.16 (WiMAX (registered trademark)), IEEE 802.20, Ultra-WideBand (UWB), Bluetooth (registered trademark), Public Land Mobile Network (PLMN) networks, Device-to-Device (D2D) systems, Machine-to-Machine (M2M) systems, Internet of Things (IoT) systems, Vehicle-to-Everything (V2X), systems utilizing other communication methods, and next-generation systems based on and extending these methods. Furthermore, multiple systems may be combined (for example, a combination of LTE or LTE-A with 5G).

[0159] FIG2 is an interactive diagram of a model processing method according to an embodiment of the present disclosure. As shown in FIG2 , the embodiment of the present disclosure relates to a model processing method, which includes:

[0160] S201: The terminal determines a perception task based on an AI model that needs to be performed by a first network function.

[0161] In an embodiment of the present disclosure, the terminal may determine an AI model-based perception task that needs to be performed by the first network function.

[0162] In some embodiments, the first network function is a NICF.

[0163] In some embodiments, the terminal determines one or more perception tasks based on the AI ​​model that need to be performed by the first network function.

[0164] In some embodiments, the terminal determines a perception task based on one or more AI models that needs to be performed by the first network function.

[0165] In some embodiments, the terminal determines one or more perception tasks based on one or more AI models that need to be performed by the first network function.

[0166] Exemplarily, the perception task based on the AI ​​model includes at least one of the following:

[0167] Image recognition tasks based on AI models;

[0168] Text processing tasks based on AI models;

[0169] Audio recognition tasks based on AI models.

[0170] For example, perception tasks based on AI models include identifying whether a driver is wearing a seat belt based on an AI model, identifying whether a vehicle is speeding based on an AI model, or identifying relevant voice commands based on an AI model, etc.

[0171] It is understandable that the AI ​​model can be at least one of a convolutional neural network (CNN) model, a long short term memory (LSTM) model, a spatial transformer (Transformer) network model, etc.

[0172] In the embodiment of the present disclosure, the terminal can independently determine the AI ​​model-based perception task that needs to be performed by the first network function, or can also determine the AI ​​model-based perception task that needs to be performed by the first network function based on the instruction of the access network device, or can also determine the AI ​​model-based perception task that needs to be performed by the first network function based on the protocol agreement.

[0173] Exemplarily, the access network device sends indication information to the terminal, indicating that the first network function needs to perform the perception task based on the AI ​​model, whereby the terminal determines that the first network function needs to perform the perception task based on the AI ​​model.

[0174] Exemplarily, the access network device sends an instruction message to the terminal, instructing the terminal to collect the perception data required for the first network function to perform the perception task based on the AI ​​model, thereby the terminal determines the perception task based on the AI ​​model that needs to be performed by the first network function.

[0175] Exemplarily, when the terminal obtains perception data for the first network function to perform a perception task based on the AI ​​model, and needs to obtain the perception result of the first network function performing the perception task based on the AI ​​model based on the perception data, it can be determined that the first network function needs to perform the perception task based on the AI ​​model.

[0176] S202: The terminal sends a first message to the first network function.

[0177] In some embodiments, the first message is used to instruct the first network function to perform a perception task based on an AI model.

[0178] In some embodiments, when the terminal determines that an AI model-based perception task needs to be performed by the first network function, the terminal sends a first message to the first network function.

[0179] In some embodiments, the terminal reuses existing signaling or messages to send the first message to the first network function, or uses new signaling or messages to send the first message to the first network function.

[0180] In some embodiments, the first network function receives a first message sent by the terminal.

[0181] Based on this, the first network function determines at least one of the following based on the first message:

[0182] The computing resources required to perform perception tasks based on AI models;

[0183] Relevant information needed to perform perception tasks based on AI models.

[0184] Exemplarily, the relevant information required to perform a perception task based on an AI model includes: the AI ​​model that needs to be used, the initial AI model that can be used, historical related data, etc.

[0185] It is understandable that the first network function can determine, based on the first message, that the computing resources are sufficient to perform the perception task based on the AI ​​model, or that the computing resources are insufficient to perform the perception task based on the AI ​​model.

[0186] In some embodiments, the terminal sends the first message to the first network function through a control plane or a user plane.

[0187] It can be understood that the terminal sends the first message to the first network function through the control surface, and can send the first message to the first network function through the access network device and AMF.

[0188] It can be understood that the terminal sends the first message to the first network function through the user, and can send the first message to the first network function through the access network device and UPF.

[0189] S203: The first network function sends a second message to the terminal.

[0190] In some embodiments, the second message is used to instruct the terminal to provide perception data to the second network function.

[0191] In an embodiment of the present disclosure, the first network function may send a second message to the terminal, instructing the terminal to provide perception data to the second network function.

[0192] In some embodiments, the second network function is an NDCF.

[0193] In some embodiments, when determining to perform a perception task based on an AI model, the first network function sends a second message to the terminal to instruct the terminal to provide perception data to the second network function.

[0194] In some embodiments, upon determining that computing resources are sufficient to perform the perception task based on the AI ​​model, the first network function sends a second message to the terminal to instruct the terminal to provide perception data to the second network function.

[0195] In some embodiments, upon obtaining relevant information required to perform a perception task based on an AI model, the first network function sends a second message to the terminal to instruct the terminal to provide perception data to the second network function.

[0196] In some embodiments, when the first network function determines that the computing resources are sufficient to perform the perception task based on the AI ​​model and obtains the relevant information required to perform the perception task based on the AI ​​model, the first network function sends a second message to the terminal to instruct the terminal to provide perception data to the second network function.

[0197] It is understandable that the terminal provides the perception data to the second network function, and the second network function can process the perception data and provide it to the first network function.

[0198] In some embodiments, the first network function sends the second message to the terminal via a control plane or a user plane.

[0199] It can be understood that the first network function sends the first message to the terminal by controlling the first message, and can send the first message to the terminal through AMF and access network equipment.

[0200] It can be understood that the first network function sends the first message to the terminal through the user, and can send the first message to the terminal through the UPF and the access network device.

[0201] S204: The terminal determines the perception data.

[0202] In the embodiment of the present disclosure, the terminal may determine the perception data.

[0203] In some embodiments, the terminal obtains the perception data by itself, or the terminal obtains the perception data based on the first message of the first network function.

[0204] Exemplarily, the terminal obtains data sent by a sensor and determines the sensing data. For example, the sensor is an infrared sensor, a camera, etc.

[0205] In some embodiments, the terminal initiates a sensing service to the sensor, and the sensor collects sensing data and sends the data to the terminal, thereby determining the sensing data.

[0206] In some embodiments, the terminal initiates the perception service to the sensor on its own, or initiates the perception service to the sensor based on a protocol agreement, or initiates the perception service to the sensor based on an instruction from an access network device.

[0207] S205: The terminal sends the perception data to the second network function.

[0208] In some embodiments, when the terminal determines the perception data, the terminal sends the perception data to the second network function.

[0209] In some embodiments, the terminal determines the perception data and sends the perception data to the second network function on its own, or sends the perception data to the second network function based on the instruction of the access network device, or sends the perception data to the second network function based on the instruction sent by other network functions through the access network device, or sends the perception data to the second network function based on the protocol agreement.

[0210] In some embodiments, the terminal determines the perception data and sends the perception data to the second network function upon receiving the second message sent by the first network function.

[0211] In some embodiments, the second network function receives and stores the perception data sent by the terminal.

[0212] In some embodiments, the terminal sends the perception data to the second network function, including: sending the perception data to the second network function through a user.

[0213] In the embodiment of the present disclosure, the terminal can send the perception data to the second network function through the user, which can reduce the risk of network congestion caused by sending the perception data to the second network function through the control direction.

[0214] S206: The second network function processes the perception data to determine perception processing data.

[0215] In the embodiment of the present disclosure, the second network function receives the perception data sent by the terminal, and then processes the perception data to determine the perception processing data.

[0216] In some embodiments, the second network function processes the perception data, including normalizing and regularizing the perception data.

[0217] It can be understood that the second network function processes the perception data to obtain perception processing data, and the perception processing data can be used by the first network function to perform perception tasks based on the AI ​​model.

[0218] Exemplarily, the perception data may be input data of the AI ​​model, and the first network function may input the perception processing data into the AI ​​model to perform the perception task and determine the perception processing result.

[0219] S207: The second network function sends the perception processing data to the first network function.

[0220] In an embodiment of the present disclosure, the second network function may send the perception processing data to the first network function when the perception processing data is determined.

[0221] In some embodiments, the second network function sends the perception processing data to the first network function on its own, or sends the perception processing data to the first network function based on an instruction from the first network function.

[0222] Exemplarily, the second network function receives the indication information sent by the first network function, sends a request message to the terminal, requests to obtain the perception data, and then receives the perception data sent by the terminal, processes the perception data to obtain a perception processing data set, and then sends it to the first network function.

[0223] Exemplarily, the second network function receives the indication information sent by the first network function, sends a request message to the terminal, requesting to obtain the perception processing data, and then receives the perception processing data sent by the terminal, and sends the perception processing data to the first network function.

[0224] In some embodiments, the second network function receives the perception data sent by the terminal, processes the perception data to determine perception processing data, and then sends the perception processing data to the first network function.

[0225] In some embodiments, the second network function receives the perception processing data sent by the terminal and sends the perception processing data to the first network function.

[0226] S208: The first network function sends a third message to the third network function.

[0227] In some embodiments, the third message is used to instruct the third network function to provide perception-related information.

[0228] It can be understood that when the first network function determines to perform a perception task based on the AI ​​model and determines that it is necessary to obtain perception-related information, it can send a third message to the third network function, wherein the third message is used to instruct the third network function to provide perception-related information.

[0229] In some embodiments, the perception-related information is used by the first network function to perform a perception task based on an AI model.

[0230] It is understandable that the perception-related information may be an AI model stored at the third network function, or an initial AI model and historical perception data stored at the third network function.

[0231] In some embodiments, the third network function is NDRF.

[0232] S209: The third network function sends perception-related information to the first network function.

[0233] In some embodiments, the first network function receives the perception-related information sent by the third network function.

[0234] In some embodiments, the third network function sends the perception-related information to the first network function on its own, or sends the perception-related information to the first network function based on an instruction of the first network function, or sends the perception-related information to the first network function based on an instruction of another device.

[0235] In some embodiments, upon receiving the third message sent by the first network function, the third network function sends the perception-related information to the first network function.

[0236] In some embodiments, the perception-related information includes at least one of the following:

[0237] AI models;

[0238] Initial AI model;

[0239] Historical perception data.

[0240] S210: The first network function executes a perception task based on the AI ​​model according to the perception processing data and the perception-related information, and determines a perception processing result.

[0241] In an embodiment of the present disclosure, the first network function, when determining the perception processing data and the perception related information, can perform a perception task based on the AI ​​model based on the perception processing data and the perception related information to determine the perception processing result.

[0242] In some embodiments, the perception-related information includes an AI model, and the first network function performs a perception task based on the AI ​​model according to the perception processing data and the perception-related information, and determines the perception processing result, including: determining the perception processing result according to the perception processing data and the AI ​​model.

[0243] In an embodiment of the present disclosure, the perception-related data includes an AI model. When the first network function determines the perception processing data and the AI ​​model, it can determine the perception processing result based on the perception processing data and the AI ​​model.

[0244] In some embodiments, the perception-related information includes an initial AI model and historical perception data. The first network function performs a perception task based on the AI ​​model according to the perception processing data and the perception-related information, and determines the perception processing result, including: training the initial AI model according to the historical perception data to determine the AI ​​model; and determining the perception processing result according to the perception processing data and the AI ​​model.

[0245] In an embodiment of the present disclosure, the perception-related data includes an initial AI model and historical perception data. When the first network function determines the perception processing data, the initial AI model and the historical perception data, it can train the initial AI model based on the historical perception data to determine the AI ​​model, and further determine the perception processing result based on the perception processing data and the AI ​​model.

[0246] Exemplarily, the first network function inputs the perception processing data into the AI ​​model to obtain the perception processing result.

[0247] S211: The first network function sends a fourth message to the terminal.

[0248] In some embodiments, the fourth message is used to indicate the perception processing result.

[0249] In an embodiment of the present disclosure, the first network function may send a fourth message to the terminal when determining the perception processing result, where the fourth message is used to indicate the perception processing result.

[0250] In some embodiments, the first network function sends the fourth message to the terminal through a control plane or a user plane.

[0251] It can be understood that the first network function sends the fourth message to the terminal by controlling the direction, and the fourth message can be sent to the terminal through the AMF and the access network device.

[0252] It can be understood that the first network function sends the fourth message to the terminal through the user, and can send the fourth message to the terminal through the UPF and the access network device.

[0253] S212: The first network function sends a fifth message to the third network function.

[0254] In some embodiments, the fifth message is used to indicate the perception processing result.

[0255] In an embodiment of the present disclosure, when the first network function determines the perception processing result, it may send a fifth message to the third network function, where the fifth message is used to indicate the perception processing result.

[0256] In the embodiment of the present disclosure, the third network function receives and stores the perception processing results sent by the first network function. The third network function can store historical analysis results to facilitate the provision of relevant data analysis services and avoid repeated calculations.

[0257] In some embodiments, the names of information, etc. are not limited to the names described in the embodiments, and terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", "field", "symbol", "symbol", "codeword", "codebook", "codeword", "codepoint", "bit", "data", "program", and "chip" can be used interchangeably.

[0258] In some embodiments, "obtain", "get", "get", "receive", "transmit", "bidirectional transmission", "send and / or receive" can be interchangeable, and can be interpreted as receiving from other entities, obtaining from protocols, obtaining from higher layers, obtaining by self-processing, autonomous implementation, etc.

[0259] In some embodiments, terms such as "send", "transmit", "report", "download", "transmit", "bidirectional transmission", "send and / or receive" can be used interchangeably.

[0260] In some embodiments, terms such as "certain", "preset", "preset", "setting", "indicated", "a certain", "any", and "first" can be interchangeable. "Specific A", "preset A", "preset A", "setting A", "indicated A", "a certain A", "any A", and "first A" can be interpreted as A pre-specified in a protocol, etc., or as A obtained through setting, configuration, or indication, etc., or as specific A, a certain A, any A, or first A, etc., but not limited to this.

[0261] The communication method involved in the embodiments of the present disclosure may include at least one of S201 to S212. For example, S201 can be implemented as an independent embodiment, S202 can be implemented as an independent embodiment, S203 can be implemented as an independent embodiment, S204 can be implemented as an independent embodiment, S205 can be implemented as an independent embodiment, S206 can be implemented as an independent embodiment, S207 can be implemented as an independent embodiment, S208 can be implemented as an independent embodiment, S209 can be implemented as an independent embodiment, S210 can be implemented as an independent embodiment, S211 can be implemented as an independent embodiment, S212 can be implemented as an independent embodiment, S207+S209+S210 can be implemented as an independent embodiment. It can be implemented as an independent embodiment, S207+S208+S209+S210 can be implemented as an independent embodiment, S207+S209+S210+S211 can be implemented as an independent embodiment, S207+S209+S210+S212 can be implemented as an independent embodiment, S207+S209+S210+S211+S212 can be implemented as an independent embodiment, S202+S207+S209+S210 can be implemented as an independent embodiment, and S201+S202+S207+S209+S210 can be implemented as an independent embodiment, but is not limited to this.

[0262] In some embodiments, S202 and S208 can be exchanged in order or executed simultaneously, S203 and S208 can be exchanged in order or executed simultaneously, S204 and S201 can be exchanged in order or executed simultaneously, S204 and S202 can be exchanged in order or executed simultaneously, S204 and S203 can be exchanged in order or executed simultaneously, S207 and S208 can be exchanged in order or executed simultaneously, S207 and S209 can be exchanged in order or executed simultaneously, and S211 and S212 can be exchanged in order or executed simultaneously.

[0263] In some embodiments, S201, S202, S203, S204, S205, S206, S208, S211, and S212 are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0264] In some embodiments, S201, S203, S204, S205, S206, S208, S211, and S212 are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0265] In some embodiments, S201, S203, S204, S205, S206, S211, and S212 are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0266] In some embodiments, S203, S204, S205, S206, S211, and S212 are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0267] In some embodiments, S203, S204, S205, and S206 are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0268] In some embodiments, reference may be made to other optional implementations described before or after the description corresponding to FIG. 2 .

[0269] FIG3A is a flow chart of a model processing method according to an embodiment of the present disclosure. As shown in FIG3A , the embodiment of the present disclosure relates to a model processing method, which is executed by a first network function and includes:

[0270] S301A, obtaining perception processing data.

[0271] Among them, the optional implementation of S301A can refer to the optional implementation of S207 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0272] In some embodiments, the first network function receives the perception processing data sent by the second network function, but is not limited thereto and may also receive the perception processing data sent by other entities.

[0273] In some embodiments, the first network function obtains sensory processing data specified by the protocol.

[0274] In some embodiments, the first network function obtains the sensory processing data from upper layer(s).

[0275] In some embodiments, the first network function performs processing to obtain sensory processing data.

[0276] In some embodiments, S301A is omitted, and the first network function autonomously implements the function indicated by the perception processing data, or the above function is default or by default.

[0277] In some embodiments, the perception processing data is determined by the second network function based on the perception data provided by the terminal, and the perception processing data is the data required for the first network function to perform the perception task based on the AI ​​model.

[0278] S302A, obtaining perception-related information.

[0279] Among them, the optional implementation of S302A can refer to the optional implementation of S209 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0280] In some embodiments, the first network function receives perception-related information sent by the third network function, but is not limited thereto and may also receive perception processing data sent by other entities.

[0281] In some embodiments, the first network function obtains perception-related information specified by a protocol.

[0282] In some embodiments, the first network function obtains the perception-related information from upper layer(s).

[0283] In some embodiments, the first network function performs processing to obtain the perception-related information.

[0284] In some embodiments, S302A is omitted, and the first network function autonomously implements the function indicated by the perception-related information, or the above function is default or by default.

[0285] In some embodiments, the perception-related information is the relevant information required for the first network function to perform a perception task based on an AI model.

[0286] S303A: Execute the perception task based on the AI ​​model according to the perception processing data and perception-related information, and determine the perception processing result.

[0287] Among them, the optional implementation of S303A can refer to the optional implementation of S210 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0288] In some embodiments, the perception-related information includes an AI model, and the first network function performs a perception task based on the AI ​​model according to the perception processing data and the perception-related information, and determines the perception processing result, including: determining the perception processing result according to the perception processing data and the AI ​​model.

[0289] In some embodiments, the perception-related information includes an initial AI model and historical perception data. The first network function performs a perception task based on the AI ​​model according to the perception processing data and the perception-related information, and determines the perception processing result, including: training the initial AI model according to the historical perception data to determine the AI ​​model; and determining the perception processing result according to the perception processing data and the AI ​​model.

[0290] FIG3B is a flow chart of a model processing method according to an embodiment of the present disclosure. As shown in FIG3B , the embodiment of the present disclosure relates to a model processing method, which is executed by a first network function and includes:

[0291] S301B, obtain the first message.

[0292] Among them, the optional implementation of S301B can refer to the optional implementation of S202 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0293] In some embodiments, the first network function receives the first message sent by the terminal, but is not limited thereto and may also receive the first message sent by other entities.

[0294] In some embodiments, the first network function obtains a first message specified by a protocol.

[0295] In some embodiments, the first network function obtains the first message from an upper layer(s).

[0296] In some embodiments, the first network function performs processing to obtain the first message.

[0297] In some embodiments, S301B is omitted, and the first network function autonomously implements the function indicated by the first message, or the above function is default or acquiescent.

[0298] In some embodiments, the first message is used to instruct the first network function to perform a perception task based on an AI model.

[0299] S302B, send a second message.

[0300] Among them, the optional implementation of S302B can refer to the optional implementation of S203 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0301] In some embodiments, the first network function sends the second message to the terminal, but is not limited thereto, and the second message may also be sent to other entities.

[0302] Optionally, the second message is used by the terminal to send the perception data to the second network function. For its optional implementation, please refer to the optional implementation of S205 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0303] In some embodiments, the second message is used to instruct the terminal to provide perception data to the second network function.

[0304] S303B, obtaining perception processing data.

[0305] Among them, the optional implementation of S303B can refer to the optional implementation of S207 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0306] Among them, the optional implementation of S303B can refer to the optional implementation of S301A in Figure 3A and other related parts in the embodiment involved in Figure 3A, which will not be repeated here.

[0307] S304B, send a third message.

[0308] Among them, the optional implementation of S304B can refer to the optional implementation of S208 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0309] In some embodiments, the first network function sends the third message to the third network function, but is not limited thereto. The third message may also be sent to other entities.

[0310] Optionally, the third message is used by the third network function to send the perception-related data to the first network function. Optional implementations thereof can be found in the optional implementations of S209 in FIG2 and other related parts in the embodiment involved in FIG2 , which will not be described in detail here.

[0311] In some embodiments, the third message is used to instruct the third network function to provide perception-related information.

[0312] S305B, obtaining perception-related information.

[0313] Among them, the optional implementation of S305B can refer to the optional implementation of S209 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0314] Among them, the optional implementation of S305B can refer to the optional implementation of S302A in Figure 3A and other related parts in the embodiment involved in Figure 3A, which will not be repeated here.

[0315] S306B, executing the perception task based on the AI ​​model according to the perception processing data and perception-related information, and determining the perception processing result.

[0316] Among them, the optional implementation of S306B can refer to the optional implementation of S210 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0317] Among them, the optional implementation of S306B can refer to the optional implementation of S303A in Figure 3A and other related parts in the embodiment involved in Figure 3A, which will not be repeated here.

[0318] S307B, sending the fourth message.

[0319] Among them, the optional implementation of S307B can refer to the optional implementation of S211 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0320] In some embodiments, the first network function sends the fourth message to the terminal, but is not limited thereto, and the fourth message may also be sent to other entities.

[0321] Optionally, the fourth message is used by the terminal to determine the perception processing result.

[0322] In some embodiments, the first network function sends the fourth message to the terminal through a control plane or a user plane.

[0323] In some embodiments, the fourth message is used to indicate the perception processing result.

[0324] S308B, sending the fifth message.

[0325] Among them, the optional implementation of S308B can refer to the optional implementation of S212 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0326] In some embodiments, the first network function sends the fifth message to the third network function, but is not limited thereto. The fifth message may also be sent to other entities.

[0327] Optionally, the fifth message is used by the third network function to determine and store the perception processing result.

[0328] In some embodiments, the fifth message is used to indicate the perception processing result.

[0329] The communication method involved in the embodiment of the present disclosure may include at least one of S301B to S312B. For example, S301B can be implemented as an independent embodiment, S302B can be implemented as an independent embodiment, S303B can be implemented as an independent embodiment, S304B can be implemented as an independent embodiment, S305B can be implemented as an independent embodiment, S306B can be implemented as an independent embodiment, S307B can be implemented as an independent embodiment, S308B can be implemented as an independent embodiment, S303B+S304B+S305B+S306B can be implemented as independent embodiments, and S303B+S304B+S305B+S306B can be implemented as independent embodiments. B+S304B+S305B+S306B+S308B can be implemented as an independent embodiment, S301B+S303B+S304B+S305B+S306B can be implemented as an independent embodiment, S301B+S303B+S304B+S305B+S306B+S307B can be implemented as an independent embodiment, and S301B+S302B+S303B+S304B+S305B+S306B+S307B can be implemented as an independent embodiment, but are not limited to this.

[0330] In some embodiments, S301B and S304B may be exchanged in order or executed simultaneously, S302B and S304B may be exchanged in order or executed simultaneously, S303B and S304B may be exchanged in order or executed simultaneously, S303B and S305B may be exchanged in order or executed simultaneously, and S307B and S308B may be exchanged in order or executed simultaneously.

[0331] In some embodiments, S301B, S302B, S304B, S307B, and S308B are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0332] In some embodiments, S302B, S304B, S307B, and S308B are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0333] In some embodiments, S302B, S307B, and S308B are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0334] In some embodiments, S307B and S308B are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0335] In some embodiments, S302B is optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0336] In some embodiments, reference may be made to other optional implementations described before or after the description corresponding to FIG. 3B .

[0337] FIG4 is a flow chart of a model processing method according to an embodiment of the present disclosure. As shown in FIG4 , the embodiment of the present disclosure relates to a model processing method, which is executed by a second network function and includes:

[0338] S401, acquiring perception data.

[0339] Among them, the optional implementation of S401A can refer to the optional implementation of S205 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0340] In some embodiments, the second network function receives the perception data sent by the terminal, but is not limited thereto and may also receive the perception data sent by other entities.

[0341] In some embodiments, the second network function obtains sensing data specified by the protocol.

[0342] In some embodiments, the second network function obtains the sensing data from upper layer(s).

[0343] In some embodiments, the second network function performs processing to obtain the sensing data.

[0344] In some embodiments, S401A is omitted, and the second network function autonomously implements the function indicated by the perception data, or the above function is default or by default.

[0345] In some embodiments, the second network function receives the perception data sent by the terminal through the user plane.

[0346] S402: Process the perception data to determine perception processing data.

[0347] Among them, the optional implementation of S402 can refer to the optional implementation of S206 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0348] S403: Send the perception processing data.

[0349] Among them, the optional implementation of S403 can refer to the optional implementation of S207 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0350] In some embodiments, the second network function sends the perception processing data to the first network function, but is not limited thereto and the perception processing data may also be sent to other entities.

[0351] Optionally, the above-mentioned perception processing data is used by the first network function to perform a perception task based on the AI ​​model and determine a perception processing result. Its optional implementation method can be referred to the optional implementation method of S210 in Figure 2 and other related parts in the embodiment involved in Figure 2, and will not be repeated here.

[0352] In some embodiments, the perception processing data is data required for the first network function to perform a perception task based on an AI model.

[0353] The communication method involved in the embodiments of the present disclosure may include at least one of S401 to S403. For example, S401 may be implemented as an independent embodiment, S402 may be implemented as an independent embodiment, S403 may be implemented as an independent embodiment, and S402+S403 may be implemented as independent embodiments, but the present invention is not limited thereto.

[0354] In some embodiments, S401 and S402 are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0355] Figure 5 is a flow chart of a model processing method according to an embodiment of the present disclosure. As shown in Figure 5, the embodiment of the present disclosure relates to a model processing method, which is executed by a third network function and includes:

[0356] S501: Obtain a third message.

[0357] Among them, the optional implementation of S501 can refer to the optional implementation of S208 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0358] In some embodiments, the third network function receives the third message sent by the first network function, but is not limited thereto and may also receive the first message sent by other entities.

[0359] In some embodiments, the third network function obtains a third message specified by the protocol.

[0360] In some embodiments, the third network function obtains the third message from upper layer(s).

[0361] In some embodiments, the third network function performs processing to obtain a third message.

[0362] In some embodiments, S501 is omitted, and the third network function autonomously implements the function indicated by the third message, or the above function is default or by default.

[0363] In some embodiments, the third message is used to instruct the third network function to provide perception-related information.

[0364] S502: Send perception-related information.

[0365] Among them, the optional implementation of S502 can refer to the optional implementation of S209 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0366] In some embodiments, the third network function sends the perception-related information to the first network function, but is not limited thereto and the perception-related information may also be sent to other entities.

[0367] Optionally, the above-mentioned perception-related information is used by the first network function to perform a perception task based on the AI ​​model and determine a perception processing result. Its optional implementation method can be referred to the optional implementation method of S210 in Figure 2 and other related parts of the embodiment involved in Figure 2, which will not be repeated here.

[0368] In some embodiments, the perception-related information is the relevant information required for the first network function to perform a perception task based on an AI model.

[0369] S503: Obtain the fifth message.

[0370] Among them, the optional implementation of S503 can refer to the optional implementation of S212 in Figure 2 and other related parts in the embodiment involved in Figure 2, and will not be repeated here.

[0371] In some embodiments, the third network function receives the fifth message sent by the first network function, but is not limited thereto and may also receive the fifth message sent by other entities.

[0372] In some embodiments, the third network function obtains a fifth message specified by the protocol.

[0373] In some embodiments, the third network function obtains the fifth message from an upper layer(s).

[0374] In some embodiments, the third network function performs processing to obtain the fifth message.

[0375] In some embodiments, S301B is omitted, and the third network function autonomously implements the function indicated by the fifth message, or the above function is default or by default.

[0376] In some embodiments, the fifth message is used to indicate the perception processing result.

[0377] The communication method involved in the embodiments of the present disclosure may include at least one of S501 to S503. For example, S501 may be implemented as an independent embodiment, S502 may be implemented as an independent embodiment, S503 may be implemented as an independent embodiment, and S501+S502 may be implemented as independent embodiments, but the present invention is not limited thereto.

[0378] In some embodiments, S501 and S503 are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0379] FIG6A is a flow chart of a model processing method according to an embodiment of the present disclosure. As shown in FIG6A , the embodiment of the present disclosure relates to a model processing method, which is executed by a terminal and includes:

[0380] S601A, determining perception data.

[0381] Among them, the optional implementation of S601A can refer to the optional implementation of S204 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0382] S602A, sending perception data.

[0383] Among them, the optional implementation of S602A can refer to the optional implementation of S205 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0384] In some embodiments, the terminal sends the perception data to the second network function, but is not limited thereto, and the perception data may also be sent to other entities.

[0385] Optionally, the above-mentioned perception data is used by the second network function to determine the perception processing data. The optional implementation method thereof can be referred to the optional implementation method of S206 in FIG2 and other related parts in the embodiment involved in FIG2, which will not be repeated here.

[0386] In some embodiments, the terminal sends the perception data to the second network function through the user.

[0387] FIG6B is a flow chart of a model processing method according to an embodiment of the present disclosure. As shown in FIG6B , the embodiment of the present disclosure relates to a model processing method, which is executed by a terminal and includes:

[0388] S601B, determining an AI model-based perception task that needs to be performed by the first network model.

[0389] Among them, the optional implementation of S601B can refer to the optional implementation of S201 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0390] S602B, send a first message.

[0391] Among them, the optional implementation of S602B can refer to the optional implementation of S203 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0392] In some embodiments, the terminal sends the first message to the first network function, but is not limited thereto, and the first message may also be sent to other entities.

[0393] Optionally, the first message is used by the first network function to send the second message to the terminal. For optional implementations thereof, please refer to the optional implementations of S203 in FIG2 and other related parts in the embodiment involved in FIG2 , which will not be described in detail here.

[0394] In some embodiments, the first message is used to instruct the first network function to perform a perception task based on the AI ​​model

[0395] S603B, obtain the second message.

[0396] Among them, the optional implementation of S603B can refer to the optional implementation of S203 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0397] In some embodiments, the terminal receives the second message sent by the first network function, but is not limited thereto, and may also receive the second message sent by other entities.

[0398] In some embodiments, the terminal obtains a second message specified by the protocol.

[0399] In some embodiments, the terminal obtains the second message from an upper layer(s).

[0400] In some embodiments, the terminal performs processing to obtain the second message.

[0401] In some embodiments, S603B is omitted, and the terminal autonomously implements the function indicated by the second message, or the above function is default or acquiescent.

[0402] In some embodiments, the second message is used to instruct the terminal to provide perception data to the second network function.

[0403] S604B, determining the perception data.

[0404] Among them, the optional implementation of S604B can refer to the optional implementation of S204 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0405] S605B, sending sensing data.

[0406] Among them, the optional implementation of S605B can refer to the optional implementation of S205 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0407] In some embodiments, the terminal sends the perception data to the second network function through the user.

[0408] S606B: Obtain the fourth message.

[0409] Among them, the optional implementation of S606B can refer to the optional implementation of S211 in Figure 2 and other related parts in the embodiment involved in Figure 2, which will not be repeated here.

[0410] In some embodiments, the terminal receives the fourth message sent by the first network function, but is not limited thereto, and may also receive the second message sent by other entities.

[0411] In some embodiments, the terminal obtains a fourth message specified by the protocol.

[0412] In some embodiments, the terminal obtains the fourth message from an upper layer(s).

[0413] In some embodiments, the terminal performs processing to obtain the fourth message.

[0414] In some embodiments, S606B is omitted, and the terminal autonomously implements the function indicated by the fourth message, or the above function is default or acquiescent.

[0415] In some embodiments, the fourth message is used to instruct the first network function to execute a perception processing result determined by the perception task based on the AI ​​model.

[0416] In some embodiments, the terminal receives a fourth message sent by the first network function through a control plane or a user plane.

[0417] The communication method involved in the embodiments of the present disclosure may include at least one of S601B to S606B. For example, S601B can be implemented as an independent embodiment, S602B can be implemented as an independent embodiment, S603B can be implemented as an independent embodiment, S604B can be implemented as an independent embodiment, S605B can be implemented as an independent embodiment, S606B can be implemented as an independent embodiment, S601B+S602B can be implemented as an independent embodiment, S603B+S604B+S605B can be implemented as an independent embodiment, and S602B+S606B can be implemented as an independent embodiment, but the present invention is not limited thereto.

[0418] In some embodiments, S601B and S604B may be executed in an exchanged order or simultaneously, S604B and S602B may be executed in an exchanged order or simultaneously, and S604B and S603B may be executed in an exchanged order or simultaneously.

[0419] In some embodiments, S601B, S603B, S604B, and S605B are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0420] In some embodiments, S601B and S606B are optional, and one or more of these steps may be omitted or replaced in different embodiments.

[0421] To facilitate understanding of the embodiments of the present disclosure, the following exemplary embodiments are provided.

[0422] In an exemplary embodiment, as shown in FIG7 , description is given by taking the case where the first network function is NICF, the second network function is NDCF, and the third network function is NDRF as an example.

[0423] In some embodiments, (1) the terminal initiates a sensing service to the sensor and collects sensing data.

[0424] In some embodiments, (2) the terminal sends a sensing service request to the NICF (such as the first message in some of the above embodiments), and uses the sensing data / task type to help the NICF select a suitable AI model.

[0425] In some embodiments, (3) NICF determines the AI ​​model and computing resources based on the metadata sent by the terminal, responds to the request (such as the second message in some of the above embodiments), and allows the terminal to upload sensor data.

[0426] In some embodiments, (4) the terminal sends the perception data to the NDCF through the data plane, and the NDCF needs to perform data preprocessing to convert the perception data into the format required for AI model training.

[0427] In some embodiments, (5) NDCF sends Nnicf_AICalculation_Request containing formatted data to NICF (such as sending perception processing data in some of the above embodiments).

[0428] In some embodiments, (6) the NICF requests the NDRF to send historical information related to the sensing task (such as the third message in some embodiments above) to obtain more comprehensive analysis information. The NDRF retrieves its repository and sends the stored relevant information to the NICF (such as the sensing-related information in some embodiments above).

[0429] In some embodiments, (7) NICF uses a suitable model (CNN / LSTM / Transformer) to train the AI ​​model and outputs analysis results (such as the perception processing results in some of the above embodiments), including statistical analysis of sensor data and trajectory / direction prediction.

[0430] In some embodiments, (8) if permitted, the NICF will send the analysis results (such as the perception processing results in some of the above embodiments) to the NDRF for storage so as to perform subsequent related tasks.

[0431] In some embodiments, (9) NICF sends the analysis results (such as the perception processing results in some of the above embodiments) to the terminal through the control / data plane, and the whole process ends.

[0432] By implementing the disclosed embodiments, external network intelligence based on NWDAF is transformed into distributed native intelligence, effectively utilizing computing resources and protecting data privacy. Dual-bus transmission reduces the potential risk of network congestion associated with transmitting AI data. Coupling all storage-related functions, including the storage of user and historical data, enhances data management and reduces the burden of data redundancy. Preserving historical analysis results facilitates related data analysis services and avoids duplicate computations.

[0433] The embodiments of the present disclosure further provide an apparatus for implementing any of the above methods. For example, an apparatus is provided, comprising units or modules for implementing each step performed by a terminal in any of the above methods. For another example, another apparatus is provided, comprising units or modules for implementing each step performed by a network device (e.g., the first network function, the second network function, the third network function, etc.) in any of the above methods.

[0434] It should be understood that the division of the various units or modules in the above device is merely a division of logical functions. In actual implementation, they may be fully or partially integrated into a physical entity, or they may be physically separated. In addition, the units or modules in the device may be implemented in the form of a processor calling software: for example, the device includes a processor, the processor is connected to a memory, and the memory stores instructions. The processor calls the instructions stored in the memory to implement any of the above methods or implement the functions of the various units or modules of the above device, wherein the processor is, for example, a general-purpose processor, such as a central processing unit (CPU) or a microprocessor, and the memory is a memory within the device or a memory outside the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits, and the functions of some or all of the units or modules can be realized by designing the hardware circuits. The above-mentioned hardware circuits can be understood as one or more processors; for example, in one implementation, the above-mentioned hardware circuit is an application-specific integrated circuit (ASIC), which realizes the functions of some or all of the above units or modules by designing the logical relationship of the components in the circuit; for example, in another implementation, the above-mentioned hardware circuit can be realized by a programmable logic device (PLD). Taking a field programmable gate array (FPGA) as an example, it can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by configuring the configuration file, thereby realizing the functions of some or all of the above units or modules. All units or modules of the above devices can be realized in the form of software called by the processor, or in the form of hardware circuits, or in part by the form of software called by the processor, and the rest by hardware circuits.

[0435] In the embodiments of the present disclosure, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction reading and execution capabilities, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationship of the hardware circuit. The logical relationship of the above-mentioned hardware circuit is fixed or reconfigurable. For example, the processor is a hardware circuit implemented by an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and implementing the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc.

[0436] FIG8A is a schematic diagram of the structure of the first network function proposed in an embodiment of the present disclosure. As shown in FIG8A , the first network function 10 may include at least one of a transceiver module 11 and a processing module 12 .

[0437] In some embodiments, the above-mentioned transceiver module 11 is used to receive perception processing data sent by the second network function, wherein the perception processing data is determined by the second network function based on the perception data provided by the terminal, and the perception processing data is the data required for the first network function to perform the perception task based on the AI ​​model; the transceiver module 11 is also used to receive perception-related information sent by the third network function, wherein the perception-related information is the relevant information required for the first network function to perform the perception task based on the AI ​​model; the processing module 12 is used to perform the perception task based on the AI ​​model according to the perception processing data and the perception-related information, and determine the perception processing result.

[0438] Optionally, the transceiver module 11 is configured to execute at least one of the communication steps (e.g., S202, S203, S207, S208, S209, S211, and S212, but not limited thereto) such as sending and / or receiving performed by the first network function 10 in any of the above methods, which are not described in detail here. Optionally, the processing module 12 is configured to execute at least one of the other steps (e.g., S210, but not limited thereto) performed by the first network function 10 in any of the above methods, which are not described in detail here.

[0439] FIG8B is a schematic diagram of the structure of the second network function proposed in an embodiment of the present disclosure. As shown in FIG8B , the second network function 20 may include: at least one of a transceiver module 21 and a processing module 22 .

[0440] In some embodiments, the above-mentioned processing module 21 is used to determine the perception processing data; the transceiver module 21 is used to send the perception processing data to the first network function, wherein the perception processing data is the data required for the first network function to perform the perception task based on the AI ​​model.

[0441] Optionally, the transceiver module 21 is configured to execute at least one of the communication steps (e.g., S205 and S207, but not limited thereto) such as sending and / or receiving performed by the second network function 20 in any of the above methods, which are not described in detail here. Optionally, the processing module 22 is configured to execute at least one of the other steps (e.g., S206, but not limited thereto) performed by the second network function 20 in any of the above methods, which are not described in detail here.

[0442] FIG8C is a schematic diagram of the structure of the third network function proposed in an embodiment of the present disclosure. As shown in FIG8C , the third network function 30 may include at least one of a transceiver module 31 and a processing module 32 .

[0443] In some embodiments, the above-mentioned transceiver module 31 is used to receive a third message sent by the first network function, wherein the third message is used to instruct the third network function to provide perception-related information, and the perception-related information is the relevant information required for the first network function to perform the perception task based on the AI ​​model; the transceiver module 31 is also used to send perception-related information to the first network function.

[0444] Optionally, the above-mentioned transceiver module 31 is used to perform at least one of the communication steps such as sending and / or receiving performed by the third network function 30 in any of the above methods (for example, S208, S209, S212, but not limited to these), which are not repeated here.

[0445] FIG8D is a schematic diagram of the structure of the third network function proposed in an embodiment of the present disclosure. As shown in FIG8D , the terminal 40 may include at least one of a transceiver module 41 and a processing module 42 .

[0446] In some embodiments, the above-mentioned processing module 42 is used to determine the perception data; the transceiver module 41 is used to send the perception data to the second network function, wherein the perception data is used by the second network function to determine the perception processing data, and the perception processing data is the data required for the first network function to perform the perception task based on the AI ​​model.

[0447] Optionally, the transceiver module 41 is configured to execute at least one of the communication steps (e.g., S202, S203, S205, S211, but not limited thereto) such as sending and / or receiving performed by the terminal 40 in any of the above methods, which are not described in detail here. Optionally, the processing module 42 is configured to execute at least one of the other steps (e.g., S201, S204, but not limited thereto) performed by the terminal 40 in any of the above methods, which are not described in detail here.

[0448] In some embodiments, the transceiver module may include a transmitting module and / or a receiving module, and the transmitting module and the receiving module may be separate or integrated. Optionally, the transceiver module may be interchangeable with the transceiver.

[0449] In some embodiments, the processing module can be a single module or can include multiple submodules. Optionally, the multiple submodules respectively execute all or part of the steps required to be executed by the processing module. Optionally, the processing module can be interchangeable with the processor.

[0450] Figure 9A is a schematic diagram of the structure of a communication device 8100 proposed in an embodiment of the present disclosure. Communication device 8100 can be a network device (e.g., a first network function, a second network function, a third network function, etc.), or a terminal (e.g., a user equipment, etc.), or a chip, chip system, or processor that supports a network device to implement any of the above methods, or a chip, chip system, or processor that supports a terminal to implement any of the above methods. Communication device 8100 can be used to implement the methods described in the above method embodiments. For details, please refer to the description of the above method embodiments.

[0451] As shown in Figure 9A, the communication device 8100 includes one or more processors 8101. The processor 8101 can be a general-purpose processor or a dedicated processor, for example, a baseband processor or a central processing unit. The baseband processor can be used to process the communication protocol and communication data, and the central processing unit can be used to control the communication device (such as a base station, a baseband chip, a terminal device, a terminal device chip, a DU or a CU, etc.), execute programs, and process program data. Optionally, the communication device 8100 is used to perform any of the above methods. Optionally, one or more processors 8101 are used to call instructions to enable the communication device 8100 to perform any of the above methods.

[0452] In some embodiments, the communication device 8100 further includes one or more transceivers 8102. When the communication device 8100 includes one or more transceivers 8102, the transceiver 8102 performs at least one of the communication steps such as sending and / or receiving in the above method (e.g., S202, S203, S205, S207, S208, S209, S211, S212, but not limited thereto), and the processor 8101 performs at least one of the other steps (e.g., S201, S204, S206, S210, but not limited thereto). In an optional embodiment, the transceiver may include a receiver and / or a transmitter, and the receiver and transmitter may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, interface circuit, and interface may be interchangeable, the terms transmitter, transmitting unit, transmitter, and transmitting circuit may be interchangeable, and the terms receiver, receiving unit, receiver, and receiving circuit may be interchangeable.

[0453] In some embodiments, the communication device 8100 further includes one or more memories 8103 for storing data. Alternatively, all or part of the memories 8103 may be located outside the communication device 8100. In alternative embodiments, the communication device 8100 may include one or more interface circuits 8104. Optionally, the interface circuits 8104 are connected to the memory 8102 and may be configured to receive data from the memory 8102 or other devices, or to send data to the memory 8102 or other devices. For example, the interface circuits 8104 may read data stored in the memory 8102 and send the data to the processor 8101.

[0454] The communication device 8100 described in the above embodiment may be a network device or a terminal, but the scope of the communication device 8100 described in the present disclosure is not limited thereto, and the structure of the communication device 8100 may not be limited by FIG. 9A. The communication device may be an independent device or may be part of a larger device. For example, the communication device may be: 1) an independent integrated circuit IC, or a chip, or a chip system or subsystem; (2) a collection of one or more ICs, optionally, the above IC collection may also include a storage component for storing data or programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, a terminal device, an intelligent terminal device, a cellular phone, a wireless device, a handheld device, a mobile unit, an in-vehicle device, a network device, a cloud device, an artificial intelligence device, etc.; (6) others, etc.

[0455] 9B is a schematic diagram of the structure of the chip 8200 proposed in an embodiment of the present disclosure. If the communication device 8100 can be a chip or a chip system, please refer to the schematic diagram of the structure of the chip 8200 shown in FIG9B , but the present disclosure is not limited thereto.

[0456] The chip 8200 includes one or more processors 8201. The chip 8200 is configured to execute any of the above methods.

[0457] In some embodiments, chip 8200 further includes one or more interface circuits 8202. Terms such as interface circuit, interface, and transceiver pins may be used interchangeably. In some embodiments, chip 8200 further includes one or more memories 8203 for storing data. Alternatively, all or part of memory 8203 may be located external to chip 8200. Optionally, interface circuit 8202 is connected to memory 8203 and may be used to receive data from memory 8203 or other devices, or may be used to send data to memory 8203 or other devices. For example, interface circuit 8202 may read data stored in memory 8203 and send the data to processor 8201.

[0458] In some embodiments, the interface circuit 8202 performs at least one of the communication steps (e.g., S202, S203, S205, S207, S208, S209, S211, and S212) of the above-described method. The interface circuit 8202 performing the communication steps (e.g., S202, S203, S205, S207, S208, S209, S211, and S212) of the above-described method, for example, means that the interface circuit 8202 performs data exchange between the processor 8201, the chip 8200, the memory 8203, or the transceiver device. In some embodiments, the processor 8201 performs at least one of the other steps (e.g., S201, S204, S206, and S210, but not limited thereto).

[0459] The present disclosure also proposes a storage medium having instructions stored thereon, which, when executed on the communication device 8100, causes the communication device 8100 to execute any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but is not limited thereto, and may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but is not limited thereto, and may also be a temporary storage medium.

[0460] The present disclosure also provides a program product, which, when executed by the communication device 8100, enables the communication device 8100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0461] The present disclosure also proposes a computer program, which, when executed on a computer, causes the computer to perform any one of the above methods.

[0462] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0463] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0464] The above description is merely a specific embodiment of the present disclosure, but the scope of protection of the present disclosure 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 disclosure should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.

Claims

1. A model processing method, characterized in that: The method is performed by a first network function, comprising: Receiving perception processing data sent by the second network function, wherein the perception processing data is determined by the second network function based on the perception data provided by the terminal, and the perception processing data is data required for the first network function to perform a perception task based on the AI ​​model; Receiving perception-related information sent by a third network function, wherein the perception-related information is relevant information required for the first network function to perform a perception task based on an AI model; According to the perception processing data and the perception related information, a perception task based on the AI ​​model is performed to determine a perception processing result.

2. The method according to claim 1, characterized in that The method further comprises: Receiving a first message sent by a terminal, wherein the first message is used to instruct the first network function to perform a perception task based on an AI model; A second message is sent to the terminal, wherein the second message is used to instruct the terminal to provide the perception data to a second network function.

3. The method according to claim 1 or 2, characterized in that The method further comprises: Send a third message to a third network function, wherein the third message is used to instruct the third network function to provide the perception-related information.

4. The method according to any one of claims 1 to 3, characterized in that The perception-related information includes the AI ​​model, and performing a perception task based on the AI ​​model according to the perception processing data and the perception-related information to determine a perception processing result includes: The perception processing result is determined based on the perception processing data and the AI ​​model.

5. The method according to any one of claims 1 to 3, characterized in that The perception-related information includes an initial AI model and historical perception data, and performing a perception task based on the AI ​​model according to the perception processing data and the perception-related information to determine a perception processing result includes: Training the initial AI model according to the historical perception data to determine the AI ​​model; The perception processing result is determined based on the perception processing data and the AI ​​model.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: A fourth message is sent to the terminal, wherein the fourth message is used to indicate the perception processing result.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: Send a fifth message to the third network function, wherein the fifth message is used to indicate the perception processing result.

8. The method according to claim 6, characterized in that The sending a fourth message to the terminal includes: The fourth message is sent to the terminal through the control plane or the user plane.

9. The method according to any one of claims 1 to 8, characterized in that The perception processing data is determined by the second network function based on the perception data provided by the terminal through the user plane.

10. A model processing method, characterized in that: The method is performed by a second network function, comprising: Determine sensory processing data; The perception processing data is sent to the first network function, wherein the perception processing data is data required for the first network function to perform a perception task based on the AI ​​model.

11. The method according to claim 10, characterized in that The determining of the perception processing data includes: Receiving sensing data sent by the terminal; The perception data is processed to determine the perception processing data.

12. The method according to claim 11, characterized in that The receiving terminal sends the sensing data, including: receiving the perception data sent by the terminal through the user plane.

13. A model processing method, characterized in that: The method is performed by a third network function, comprising: receiving a third message sent by the first network function, wherein the third message is used to instruct the third network function to provide perception-related information, where the perception-related information is relevant information required for the first network function to perform a perception task based on the AI ​​model; Sending the perception-related information to the first network function.

14. The method according to claim 13, characterized in that The method further comprises: Receive a fifth message sent by the first network function, wherein the fifth message is used to instruct the first network function to execute a perception processing result determined by a perception task based on an AI model.

15. A model processing method, characterized in that: The method is executed by a terminal, and includes: Determine sensory data; The perception data is sent to the second network function, wherein the perception data is used by the second network function to determine perception processing data, and the perception processing data is the data required for the first network function to perform a perception task based on the AI ​​model.

16. The method according to claim 15, characterized in that The method further comprises: Determining an AI model-based perception task that needs to be performed by the first network function; Sending a first message to the first network function, wherein the first message is used to instruct the first network function to perform a perception task based on the AI ​​model; A second message sent by the first network function is received, wherein the second message is used to instruct the terminal to provide perception data to the second network function.

17. The method according to claim 15 or 16, characterized in that The method further comprises: Receive a fourth message sent by the first network function, wherein the fourth message is used to instruct the first network function to execute a perception processing result determined by a perception task based on an AI model.

18. The method according to claim 17, characterized in that The receiving a fourth message sent by the first network function includes: receiving a fourth message sent by the first network function through a control plane or a user plane.

19. The method according to any one of claims 15 to 18, characterized in that The sending the perception data to the second network function includes: The perception data is sent through the user to the second network function.

20. A model processing method, characterized in that: The method comprises: The terminal determines the perception data; The terminal sends the perception data to the second network function; The second network function receives the perception data sent by the terminal; The second network function processes the perception data to determine perception processing data; The second network function sends the perception processing data to the first network function; The third network function receives a third message sent by the first network function, wherein the third message is used to instruct the third network function to provide perception-related information; The third network function sends the perception related information to the first network function; The first network function receives the perception processing data sent by the second network function; The first network function receives the perception-related information sent by the third network function; The first network function performs a perception task based on the AI ​​model according to the perception processing data and the perception-related information, and determines a perception processing result.

21. A first network function, characterized in that: include: A transceiver module, configured to receive perception processing data sent by a second network function, wherein the perception processing data is determined by the second network function based on the perception data provided by the terminal, and the perception processing data is data required for the first network function to perform a perception task based on an AI model; The transceiver module is further used to receive perception-related information sent by a third network function, wherein the perception-related information is relevant information required for the first network function to perform a perception task based on an AI model; A processing module is used to perform a perception task based on an AI model and determine a perception processing result according to the perception processing data and the perception-related information.

22. A second network function, characterized in that: include: A processing module for determining sensory processing data; A transceiver module is used to send the perception processing data to the first network function, wherein the perception processing data is the data required for the first network function to perform a perception task based on the AI ​​model.

23. A third network function, characterized in that: include: A transceiver module, configured to receive a third message sent by the first network function, wherein the third message is used to instruct the third network function to provide perception-related information, where the perception-related information is relevant information required for the first network function to perform a perception task based on an AI model; The transceiver module is further used to send perception related information to the first network function.

24. A terminal, characterized in that: include: a processing module for determining the sensed data; A transceiver module is used to send the perception data to the second network function, wherein the perception data is used by the second network function to determine perception processing data, and the perception processing data is the data required for the first network function to perform a perception task based on the AI ​​model.

25. A communication device, characterized in that: include: one or more processors; A memory coupled to the processor, wherein instructions are stored in the memory, and when the instructions are executed by the processor, the communication device executes the method according to any one of claims 1 to 9.

26. A communication device, characterized in that: include: one or more processors; A memory coupled to the processor, wherein instructions are stored in the memory, and when the instructions are executed by the processor, the communication device executes the method according to any one of claims 10 to 12.

27. A communication device, characterized in that: include: one or more processors; A memory coupled to the processor, wherein instructions are stored in the memory, and when the instructions are executed by the processor, the communication device executes the method of claim 13 or 14.

28. A communication device, characterized in that: include: one or more processors; A memory coupled to the processor, wherein instructions are stored in the memory, and when the instructions are executed by the processor, the communication device executes the method according to any one of claims 15 to 19.

29. [Corrected 21.11.2023 in accordance with Rule 91] A communication system, characterized in that The method comprises a first network function, a second network function, a third network function, and a terminal, wherein the first network function is configured to implement the method according to any one of claims 1 to 9, the second network function is configured to implement the method according to any one of claims 10 to 12, the third network function is configured to implement the method according to claim 13 or 14, and the terminal is configured to implement the method according to any one of claims 15 to 19.

30. A storage medium storing instructions, characterized in that: When the instructions are executed on a communication device, the communication device is caused to execute the method according to any one of claims 1 to 9, 10 to 12, 13 or 14, and 15 to 19.

Images