WO2024087125A1

WO2024087125A1 - Algorithm update method and apparatus

Info

Publication number: WO2024087125A1
Application number: PCT/CN2022/128089
Authority: WO
Inventors: 孙宇泽; 陈栋
Original assignee: 北京小米移动软件有限公司
Priority date: 2022-10-27
Filing date: 2022-10-27
Publication date: 2024-05-02

Abstract

The present disclosure belongs to the technical field of communications. Provided are an algorithm update method and apparatus, and a device and a storage medium. The method comprises: receiving an AI algorithm update query request, which is sent by means of an artificial intelligence service function (AISF); in response to there not being an AI algorithm in UDM which corresponds to the AI algorithm update query request, sending an Nudm AI algorithm authentication update request Nudm_Algorithm_Update_Request to an application function (AF); receiving an Nudm AI algorithm authentication update response Nudm_Algorithm_Update_Response message, which is sent by means of the AF, wherein the Nudm_Algorithm_Update_Response message comprises an AI algorithm which corresponds to the AI algorithm update query request; and sending to the AISF the AI algorithm which corresponds to the AI algorithm update query request. In the present disclosure, a processing method for an "algorithm update" case is provided, so as to update an AI algorithm in UDM, such that an algorithm update mechanism can be provided, an AI algorithm can be updated, and a corresponding AI network service is provided according to the AI algorithm, thereby improving the convenience of the AI network service.

Description

Algorithm updating method and device

Technical Field

The present disclosure relates to the field of communication technology, and in particular to an algorithm updating method, device, equipment and storage medium.

Background technique

In communication systems, artificial intelligence (AI) plays an increasingly important role, and AI technology will become one of the core technologies of future communications. For example, the sixth-generation mobile communication standard (6th-Generation, 6G) and the application scenarios of AI will have a lot of overlap. In this process, the diversity of AI algorithms and the use of AI algorithms can provide better services. Since each network element in the core network is responsible for its own tasks, corresponding services can be provided according to the stored AI algorithms. However, when the stored AI algorithm does not match the AI network service task initiated by the terminal device, the corresponding AI network service cannot be provided, making the convenience of AI network services poor.

Summary of the invention

The present invention discloses an algorithm updating method, device, equipment and storage medium to update the AI algorithm in Unified Data Management (UDM), which can provide an algorithm updating mechanism, update the AI algorithm and provide corresponding AI network services based on the AI algorithm, thereby improving the convenience of AI network services.

An algorithm updating method is provided in an embodiment of an aspect of the present disclosure. The method is executed by a unified data management function (UDM). The method includes:

Receive AI algorithm update query requests sent by the Artificial Intelligence Service Function (AISF);

In response to the AI algorithm corresponding to the AI algorithm update query request not existing in the UDM, sending a Nudm AI algorithm authentication update request Nudm_Algorithm_Update_Request to an application function (Application Function, AF);

Receive a Nudm AI algorithm authentication update response Nudm_Algorithm_Update_Response message sent by the AF, wherein the Nudm_Algorithm_Update_Response message includes an AI algorithm corresponding to the AI algorithm update query request;

Sending the AI algorithm corresponding to the AI algorithm update query request to the AISF.

Another aspect of the present disclosure provides an algorithm updating method, which is performed by an AISF and includes:

Determine the AI algorithms that correspond to the AI service requirements;

Sending an AI algorithm update query request for the AI algorithm to the UDM;

Receive an AI algorithm corresponding to the AI algorithm update query request sent by the UDM.

Another aspect of the present disclosure provides an algorithm update method, which is performed by an access and mobility management function (AMF), and includes:

Receiving a service request message sent by a terminal device via a radio access network (Radio Access Network, RAN), wherein the service request message is used to request to establish the AI session;

Sending a Network Slice Management Function (Nsmf) AI session establishment short message context Nsmf_AISession_CreateSMContext request to a Session Management Function (SMF), wherein the Nsmf_AISession_CreateSMContext request is used to establish the AI session;

Receive the AI Session create session context request result sent by the SMF, wherein the AI Session create session context request result includes the AI session identifier;

The session establishment result is sent to the terminal device.

Another aspect of the present disclosure provides an algorithm updating method, which is executed by a terminal device and includes:

Sending a service request message to an access and mobility management function AMF via a radio access network RAN, wherein the service request message is used to request establishment of an artificial intelligence AI session, wherein the AI session includes an AI service requirement;

Receive the AI recognition result sent by the AMF, where the AI recognition result is obtained according to the updated AI algorithm corresponding to the AI service requirement.

In another aspect of the present disclosure, an algorithm updating device is provided in an embodiment, and the device is arranged on the UDM side, and the device includes:

A receiving module, used to receive an AI algorithm update query request sent by an artificial intelligence service function AISF;

A sending module, configured to send a Nudm AI algorithm authentication update request Nudm_Algorithm_Update_Request to an application function AF in response to the AI algorithm corresponding to the AI algorithm update query request not existing in the UDM;

The receiving module is further used to receive a Nudm AI algorithm authentication update response Nudm_Algorithm_Update_Response message sent by the AF, wherein the Nudm_Algorithm_Update_Response message includes an AI algorithm corresponding to the AI algorithm update query request;

The sending module is further used to send the AI algorithm corresponding to the AI algorithm update query request to the AISF.

In another aspect of the present disclosure, an algorithm updating device is provided in an embodiment, and the device is arranged on an AISF side, and the device includes:

A determination module, used to determine the AI algorithm corresponding to the AI service requirements;

A sending module, used for sending an AI algorithm update query request for the AI algorithm to the UDM;

The receiving module is used to receive the AI algorithm corresponding to the AI algorithm update query request sent by the UDM.

In another aspect of the present disclosure, an algorithm updating device is provided in an embodiment, and the device is arranged on the AMF side, and the device includes:

A receiving module, configured to receive a service request message sent by a terminal device via a radio access network RAN, wherein the service request message is used to request to establish the AI session;

A sending module, used for sending an Nsmf AI session establishment short message context Nsmf_AISession_CreateSMContext request to SMF, wherein the Nsmf_AISession_CreateSMContext request is used to establish the AI session;

A receiving module, used for receiving an AI Session creation context request result sent by the SMF, wherein the AI Session creation context request result includes an AI session identifier;

The sending module is used to send the session establishment result to the terminal device.

In another aspect of the present disclosure, an algorithm updating device is provided in an embodiment, and the device is arranged on a terminal device side, and the device includes:

A sending module, configured to send a service request message to an access and mobility management function AMF via a radio access network RAN, wherein the service request message is used to request establishment of an artificial intelligence AI session, wherein the AI session includes an AI service requirement;

A receiving module is used to receive the AI recognition result sent by the AMF, where the AI recognition result is obtained according to the updated AI algorithm corresponding to the AI service requirement.

Another aspect of the present disclosure provides a UDM, wherein the device includes a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program stored in the memory so that the device performs the method as provided in the above aspect.

Another aspect of the present disclosure provides an AISF, wherein the device includes a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program stored in the memory so that the device performs the method as provided in the above aspect.

Another aspect of the present disclosure provides an AMF, wherein the device includes a processor and a memory, wherein a computer program is stored in the memory, and the processor executes the computer program stored in the memory so that the device performs the method as provided in the above aspect.

Another aspect of the present disclosure provides a terminal device, which includes a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program stored in the memory so that the device performs the method provided in the above aspect.

A communication device provided in another aspect of the present disclosure includes: a processor and an interface circuit;

The interface circuit is used to receive code instructions and transmit them to the processor;

The processor is used to run the code instructions to execute the method proposed in an embodiment of one aspect.

A computer-readable storage medium provided in yet another aspect of the present disclosure is used to store instructions, and when the instructions are executed, the method provided in the embodiment of the first aspect is implemented.

In another aspect of the present disclosure, an algorithm updating system is provided, the system comprising:

The AISF is used to respond to an AI service demand in an AI session and determine an AI algorithm corresponding to the AI service demand;

The AISF is used to send an AI algorithm update query request for the AI algorithm to the UDM;

The UDM is used to send a Nudm AI algorithm authentication update request Nudm_Algorithm_Update_Request to the application function AF in response to the AI algorithm corresponding to the AI algorithm update query request sent by the artificial intelligence service function AISF not existing in the UDM;

The UDM is used to receive a Nudm AI algorithm authentication update response Nudm_Algorithm_Update_Response message sent by the AF, wherein the Nudm_Algorithm_Update_Response message includes an AI algorithm corresponding to the AI algorithm update query request;

The UDM is used to send the AI algorithm corresponding to the AI algorithm update query request to the AISF.

In summary, in the disclosed embodiment, an AI algorithm update query request sent by an artificial intelligence service function AISF is received; in response to the AI algorithm corresponding to the AI algorithm update query request not existing in the UDM, a NudmAI algorithm authentication update request Nudm_Algorithm_Update_Request is sent to an application function AF; a NudmAI algorithm authentication update response Nudm_Algorithm_Update_Response message sent by the AF is received, wherein the Nudm_Algorithm_Update_Response message includes the AI algorithm corresponding to the AI algorithm update query request; and the AI algorithm corresponding to the AI algorithm update query request is sent to the AISF. In the disclosed embodiment, when the AI algorithm corresponding to the AI algorithm update query request does not exist in the UDM, the AI algorithm in the UDM can be updated so that the AI algorithm corresponding to the AI algorithm update query request exists in the UDM, so that the corresponding AI network service can be provided according to the AI algorithm, thereby reducing the situation where the AI network service cannot be provided when the AI algorithm corresponding to the AI algorithm update query request does not exist in the UDM. The present disclosure provides a processing method for an "algorithm update" scenario to update the AI algorithm in the UDM, and can provide an algorithm update mechanism, which can update the AI algorithm and provide corresponding AI network services based on the AI algorithm, thereby improving the convenience of AI network services.

BRIEF DESCRIPTION OF THE DRAWINGS

The above and/or additional aspects and advantages of the present disclosure will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

FIG1 is a schematic diagram of a flow chart of an algorithm updating method provided by an embodiment of the present disclosure;

FIG2 is an interactive schematic diagram of an algorithm updating method provided by yet another embodiment of the present disclosure;

FIG3 is a flow chart of an algorithm updating method provided by yet another embodiment of the present disclosure;

FIG4 is an interactive schematic diagram of an algorithm updating method provided by yet another embodiment of the present disclosure;

FIG5 is a flow chart of an algorithm updating method provided by yet another embodiment of the present disclosure;

FIG6 is an interactive schematic diagram of an algorithm updating method provided by yet another embodiment of the present disclosure;

FIG7 is a flow chart of an algorithm updating method provided by yet another embodiment of the present disclosure;

FIG8 is a schematic flow chart of an algorithm updating method provided by yet another embodiment of the present disclosure;

FIG9 is a schematic flow chart of an algorithm updating method provided by yet another embodiment of the present disclosure;

FIG10 is a flow chart of an algorithm updating method provided by yet another embodiment of the present disclosure;

FIG11 is a schematic diagram of the structure of an algorithm updating system provided by an embodiment of the present disclosure;

FIG12 is a schematic diagram of the architecture of an algorithm updating method provided by an embodiment of the present disclosure;

FIG13 is an interactive schematic diagram of an algorithm updating method provided by an embodiment of the present disclosure;

FIG14 is a schematic diagram of the structure of an algorithm updating device provided by an embodiment of the present disclosure;

FIG15 is a schematic diagram of the structure of an algorithm updating device provided by another embodiment of the present disclosure;

FIG16 is a schematic diagram of the structure of an algorithm updating device provided by another embodiment of the present disclosure;

FIG17 is a schematic diagram of the structure of an algorithm updating device provided by another embodiment of the present disclosure;

FIG18 is a block diagram of a terminal device provided by an embodiment of the present disclosure;

FIG19 is a block diagram of a network-side device provided by an embodiment of the present disclosure.

Detailed ways

Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the embodiments of the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the embodiments of the present disclosure as detailed in the appended claims.

The terms used in the disclosed embodiments are only for the purpose of describing specific embodiments and are not intended to limit the disclosed embodiments. The singular forms of "a" and "the" used in the disclosed embodiments and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and/or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

It should be understood that although the terms first, second, third, etc. may be used to describe various information in the disclosed embodiments, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the disclosed embodiments, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein may be interpreted as "at" or "when" or "in response to determination".

The network elements or network functions involved in the embodiments of the present disclosure may be implemented by independent hardware devices or by software in the hardware devices, and this is not limited in the embodiments of the present disclosure.

With the development of mobile communication technology, AI will become one of the core technologies of future communications. Among them, the typical application scenarios of 6G and AI have a high overlap, and the two are deeply integrated. In addition, the large-scale coverage of 6G networks can provide AI with ubiquitous carrying space, which can solve the huge pain point of lack of carriers and channels in the implementation of AI technology, and greatly promote the development and prosperity of the AI industry.

Among them, many automated means have been adopted in various stages of the network to improve the efficiency of operation and maintenance, but the overall level of network autonomy is still not high, and there is a lot of room for improvement. The architecture of Software Defined Network (SDN) and Network Function Virtualization (NFV) makes the network highly flexible and more complex. For example, there are more factors to consider in aspects such as the allocation of network resources, transmission paths, and optimization algorithm design, and more intelligent means are also needed. AI technology can help the network achieve a higher level of autonomy and achieve cost reduction and efficiency improvement. Since AI technology was applied to communication networks relatively late, most of the network intelligent applications are optimized and transformed on the traditional network architecture, and are generally plug-in applications. The network AI function is just a simple superposition on the existing network process, and the coordination of cross-domain and cross-layer intelligent applications is difficult. Therefore, it is considered to add AI as an independent network function NF to the core network architecture, and tightly couple it with other network elements to provide reliable and systematic AI service capabilities, which is called AI service function AISF.

In related technologies, the update of AI algorithms is an important consideration. Since each network element in the core network is responsible for its own tasks, the storage and transmission capabilities are limited, and for the security consideration of protecting user privacy, a large amount of data needs to be stored locally on the terminal device. The AI algorithm stored in the AISF itself is not sufficient to match any AI network service task initiated by the terminal device. The algorithm to be used needs to be determined based on the specific content provided when the task is initiated (including data and task description).

Also, in the related technologies, the Network Data Analytics Function (NWADF) in the fifth generation mobile communication technology system (5GS) only has the ability to make data analysis decisions. It is too macro, does not involve specific AI algorithms, and does not provide an AI algorithm update process, making it difficult to break down specific tasks.

An algorithm updating method, apparatus, device, and storage medium provided by an embodiment of the present disclosure are described in detail below with reference to the accompanying drawings.

FIG1 is a flow chart of an algorithm updating method provided by an embodiment of the present disclosure. The method is executed by a unified data management (UDM). As shown in FIG1 , the method may include the following steps:

Step 101: Receive an AI algorithm update query request sent by an artificial intelligence service function AISF;

Step 102: In response to the AI algorithm corresponding to the AI algorithm update query request not existing in the UDM, a Nudm AI algorithm authentication update request Nudm_Algorithm_Update_Request is sent to the application function AF;

In a possible implementation, after receiving the AI algorithm update query request sent by the artificial intelligence service function AISF, the UDM can determine whether there is an AI algorithm corresponding to the AI algorithm update query request sent by the artificial intelligence service function AISF in the UDM. When there is no AI algorithm corresponding to the AI algorithm update query request sent by the artificial intelligence service function AISF in the UDM, a Nudm AI algorithm authentication update request Nudm_Algorithm_Update_Request can be sent to the application function AF. When there is an AI algorithm corresponding to the AI algorithm update query request sent by the artificial intelligence service function AISF in the UDM, Nudm_Algorithm_Update_Response can be directly returned to NEF.

Step 103: Receive a Nudm AI algorithm authentication update response Nudm_Algorithm_Update_Response message sent by the AF, wherein the Nudm_Algorithm_Update_Response message includes the AI algorithm corresponding to the AI algorithm update query request;

In a possible implementation, UDM receives a Nudm AI algorithm authentication update response Nudm_Algorithm_Update_Response message sent by AF in response to Nudm_Algorithm_Update_Request, wherein the Nudm_Algorithm_Update_Response message includes the AI algorithm corresponding to the AI algorithm update query request;.

Step 104: Send the AI algorithm corresponding to the AI algorithm update query request to the AISF.

In a possible implementation, the UDM obtains the AI algorithm corresponding to the AI algorithm update query request through the steps described above, and may send the AI algorithm to the AISF.

It should be noted that, in one embodiment of the present disclosure, the terminal device may be a device that provides voice and/or data connectivity to a user. The terminal device may communicate with one or more core networks via a radio access network (RAN). The terminal device may be an IoT terminal device, such as a sensor device, a mobile phone (or a "cellular" phone), and a computer with an IoT terminal device, for example, a fixed, portable, pocket-sized, handheld, computer-built-in, or vehicle-mounted device. For example, a subscriber station (STA), a subscriber unit, a subscriber station, a mobile station, a mobile station, a mobile station, a remote station, an access point, a remote terminal device, an access terminal device, a user terminal device, or a user agent. Alternatively, the terminal device may also be a device of an unmanned aerial vehicle. Alternatively, the terminal device may also be a vehicle-mounted device, for example, a driving computer with wireless communication function, or a wireless terminal device connected to an external driving computer. Alternatively, the terminal device may also be a roadside device, for example, a street lamp, a traffic light or other roadside device with a wireless communication function.

In one embodiment of the present disclosure, the AI algorithm update query request refers to a request sent by the AISF to the UDM, and the AI algorithm update query request is used to query the AI algorithm corresponding to the AI service demand determined by the AISF. Since the AI algorithm corresponds to the AI service demand, when the AI service demand determined by the AISF changes, the AI algorithm can also change accordingly.

And, in one embodiment of the present disclosure, FIG2 is an interactive schematic diagram of an algorithm update method provided by an embodiment of the present disclosure. UDM can receive an AI algorithm update query request sent by AISF. When UDM receives an AI algorithm update query request sent by AISF, UDM can determine whether there is an AI algorithm corresponding to the AI algorithm update query request sent by AISF in UDM. Specifically, UDM can determine whether there is an AI algorithm corresponding to the AI algorithm update query request sent by AISF in the network function (Network Function, NF).

For example, in one embodiment of the present disclosure, in response to the absence of an AI algorithm corresponding to the AI algorithm update query request sent by the artificial intelligence service function AISF in the UDM, a Nudm AI algorithm authentication update request Nudm_Algorithm_Update_Request is sent to the application function AF. The UDM may send Nudm_Algorithm_Update_Request which may include description information of the AI algorithm and an identifier of the AI algorithm. When the AF determines the AI algorithm corresponding to the Nudm_Algorithm_Update_Request request, it may send a Nudm AI algorithm authentication update response Nudm_Algorithm_Update_Response message to the UDM. The Nudm_Algorithm_Update_Response message includes the AI algorithm corresponding to the AI algorithm update query request. That is, the AF may provide the AI algorithm corresponding to the AI algorithm update query request to the UDM.

And, in one embodiment of the present disclosure, the AF may be any AF among external third-party AFs. The AF may be an AF authorized by UDM.

And, in one embodiment of the present disclosure, when the AF fails to determine the AI algorithm corresponding to the Nudm_Algorithm_Update_Request request, the AF may send a response message to the UDM. The response message includes indication information, and the indication information is used to indicate the failure reason.

And, in one embodiment of the present disclosure, when the UDM obtains the AI algorithm, it can respond to the AI algorithm update query request and send the AI algorithm corresponding to the AI algorithm update query request to the AISF.

And, in one embodiment of the present disclosure, the method further includes:

Send an authorization request for AF to the Network Exposure Function (NEF);

Receive authorization information sent by NEF in response to the authorization request.

And, in one embodiment of the present disclosure, the method further includes:

Receive the AI session AISession registration request sent by the session management function SMF;

Send the contract information for the AISession registration request to SMF, where the contract information includes the authorization information of the AI session, the functions supported by the AI session, and the prohibited services.

In summary, in the disclosed embodiment, the UDM may receive an AI algorithm update query request sent by the artificial intelligence service function AISF; in response to the AI algorithm corresponding to the AI algorithm update query request not existing in the UDM, send a Nudm AI algorithm authentication update request Nudm_Algorithm_Update_Request to the application function AF; receive a Nudm AI algorithm authentication update response Nudm_Algorithm_Update_Response message sent by the AF, wherein the Nudm_Algorithm_Update_Response message includes the AI algorithm corresponding to the AI algorithm update query request; and send the AI algorithm corresponding to the AI algorithm update query request to the AISF. In the disclosed embodiment, when the AI algorithm corresponding to the AI algorithm update query request does not exist in the UDM, the AI algorithm in the UDM may be updated so that the AI algorithm corresponding to the AI algorithm update query request exists in the UDM, so that the corresponding AI network service can be provided according to the AI algorithm, thereby reducing the situation where the AI network service cannot be provided when the AI algorithm corresponding to the AI algorithm update query request does not exist in the UDM. The present disclosure provides a processing method for an "algorithm update" scenario to update the AI algorithm in the UDM, and can provide an algorithm update mechanism, which can update the AI algorithm and provide corresponding AI network services based on the AI algorithm, thereby improving the convenience of AI network services.

FIG3 is a flow chart of an algorithm updating method provided by an embodiment of the present disclosure. The method is executed by the UDM. As shown in FIG3 , the method may include the following steps:

Step 301: Receive an AI algorithm update query request sent by an artificial intelligence service function AISF;

Step 302: In response to the AI algorithm corresponding to the AI algorithm update query request not existing in the UDM, sending an authorization request for the AF to the network open function NEF;

Step 303: Receive authorization information sent by NEF in response to the authorization request;

Step 304: Send Nudm AI algorithm authentication update request Nudm_Algorithm_Update_Request to the application function AF;

Step 305: Receive a Nudm AI algorithm authentication update response Nudm_Algorithm_Update_Response message sent by the AF, wherein the Nudm_Algorithm_Update_Response message includes the AI algorithm corresponding to the AI algorithm update query request;

Step 306: Send the AI algorithm corresponding to the AI algorithm update query request to the AISF.

It should be understood that the description of

steps

301, 304, 304, 305 and 306 may correspond to

steps

101, 102, 103 and 104, and will not be repeated here.

In addition, in a possible implementation of the present disclosure, the method may include:

That is to say, when UDM determines that there is no AI algorithm corresponding to the AI algorithm update query request, it can request an authorization request for AF from NEF. For example, UDM can authorize a certain AF to provide the corresponding AI algorithm and NEF authorizes the request to a third-party AF outside the core network architecture. NEF sends Nudm_Algorithm_Update_Request to request AF to provide the corresponding algorithm. The message may include the provided algorithm description and ID.

Among them, in one embodiment of the present disclosure, Figure 4 is an interactive schematic diagram of an authorization information receiving method provided by an embodiment of the present disclosure. In response to the absence of an AI algorithm corresponding to the AI algorithm update query request sent by the artificial intelligence service function AISF in the UDM, the UDM may send an authorization request for the AF to the NEF. When the UDM receives the authorization information sent by the NEF in response to the authorization request, the UDM may authorize the AF corresponding to the authorization information to provide the AI algorithm. The AI algorithm may be an algorithm that does not exist in the UDM. That is, the UDM can update the AI algorithm stored in the UDM. In this process, the NEF may perform information search and function query based on the authorization request for the AF to determine whether the UDM makes an AI algorithm request to the AF.

In summary, in the disclosed embodiment, an AI algorithm update query request sent by an artificial intelligence service function AISF is received; in response to the AI algorithm corresponding to the AI algorithm update query request not existing in the UDM, an authorization request for AF is sent to the network open function NEF; the authorization information sent by the NEF in response to the authorization request is received; a Nudm AI algorithm authentication update request Nudm_Algorithm_Update_Request is sent to the application function AF; a Nudm AI algorithm authentication update response Nudm_Algorithm_Update_Response message is received from the AF, wherein the Nudm_Algorithm_Update_Response message includes the AI algorithm corresponding to the AI algorithm update query request; and the AI algorithm corresponding to the AI algorithm update query request is sent to the AISF. In the disclosed embodiment, when the AI algorithm corresponding to the AI algorithm update query request does not exist in the UDM, the AI algorithm in the UDM can be updated so that the AI algorithm corresponding to the AI algorithm update query request exists in the UDM, so that the corresponding AI network service can be provided according to the AI algorithm, thereby reducing the situation where the AI network service cannot be provided when the AI algorithm corresponding to the AI algorithm update query request does not exist in the UDM. The embodiments of the present disclosure specifically describe the scheme for authorization for AF, and NEF can provide information search and function query internally. The present disclosure provides a processing method for a situation of "algorithm update" to update the AI algorithm in UDM, and can provide an algorithm update mechanism, can update the AI algorithm and provide corresponding AI network services according to the AI algorithm.

FIG5 is a flow chart of an algorithm updating method provided by an embodiment of the present disclosure. The method is executed by the UDM. As shown in FIG5 , the method may include the following steps:

Step 501: Receive an AI session AISession registration request sent by a session management function SMF;

Step 502: Send the contract information for the AISession registration request to the SMF, where the contract information includes the authorization information of the AI session, the functions supported by the AI session, and the prohibited services.

It should be understood that the above-mentioned embodiments of the present disclosure may be implemented separately or in combination with other embodiments of the present disclosure, and the present disclosure is not limited thereto.

Among them, in one embodiment of the present disclosure, Figure 6 is an interactive schematic diagram of an algorithm update method provided by an embodiment of the present disclosure. Before the UDM receives the AI algorithm update query request sent by the AISF, the UDM may receive an AI session AISession registration request sent by the session management function SMF. Among them, the AISession registration request is used to establish an AISession.

And, in one embodiment of the present disclosure, UDM may send contract information for AISession registration request to SMF, wherein the contract information includes authorization information of AI session, functions supported by AI session and prohibited services. Among them, the functions supported by AI session do not specifically refer to a fixed function. For example, when the function name changes, the functions supported by the AI session may also change accordingly.

And, in one embodiment of the present disclosure, when SMF receives the signing information of UDM for AISession registration request, SMF can select a user plane function (UPF) and establish an N4 session to the selected UPF.

In summary, in the disclosed embodiment, an AI session AISession registration request sent by a session management function SMF is received; contract information for the AISession registration request is sent to the SMF, wherein the contract information includes the authorization information of the AI session, the functions supported by the AI session, and prohibited services. In the disclosed embodiment, contract information can be sent to the SMF according to the AISession registration request, which can improve the accuracy of AISession establishment and reduce the situation where AISession cannot transmit AI service requirements.

FIG. 7 is a flow chart of an algorithm updating method provided by an embodiment of the present disclosure. The method is executed by the AISF. As shown in FIG. 7 , the method may include the following steps:

Step 701: Determine an AI algorithm corresponding to the AI service requirement;

Step 702: Send an AI algorithm update query request for the AI algorithm to the UDM;

Step 703: Receive the AI algorithm corresponding to the AI algorithm update query request sent by the UDM.

Among them, in one embodiment of the present disclosure, when the UDM determines that there is an AI algorithm corresponding to the AI algorithm update query request in the UDM, the UDM can directly send the AI algorithm to the AISF. When there is no AI algorithm corresponding to the AI algorithm update query request in the UDM, the UDM can send a Nudm AI algorithm authentication update request Nudm_Algorithm_Update_Request to the application function AF. The UDM can receive a Nudm AI algorithm authentication update response Nudm_Algorithm_Update_Response message sent by the AF in response to the Nudm_Algorithm_Update_Request request, wherein the Nudm_Algorithm_Update_Response message includes the AI algorithm corresponding to the AI algorithm update query request. In response to the AI algorithm update query request, the UDM can send the AI algorithm corresponding to the AI algorithm update query request to the AISF.

In one embodiment of the present disclosure, different AI service requirements correspond to different AI algorithms. For example, when the AI service requirement is a target detection task, the AI algorithm may be, for example, the yolov5 algorithm or the yolov7 algorithm.

In one embodiment of the present disclosure, the method further includes:

Receive the data set sent by the User Data Repository (UDR);

Obtain AI recognition results corresponding to AI service requirements based on data sets and updated AI algorithms;

Send AI recognition results to AMF.

Further, in one embodiment of the present disclosure, when AISF obtains a data set and an updated AI algorithm, AISF can use the data set to train the updated AI algorithm to obtain a trained AI algorithm. AISF can use the trained AI algorithm to obtain an AI recognition result corresponding to the AI service requirement, and send the AI recognition result to AMF. AMF can send the AI recognition result to the terminal device via RAN.

For example, in one embodiment of the present disclosure, the data set sent by the UDR may be data stored in the UDR when the terminal device is registered and a service request is made.

In one embodiment of the present disclosure, the method further includes:

Receive AI service requirements sent by AMF via AI session.

And, in one embodiment of the present disclosure, after the AI session between the AMF and the AISF is established, the AMF can send the AI service requirement to the AISF via the AI session.

In summary, in the embodiments of the present disclosure, an AI algorithm corresponding to the AI service demand is determined; an AI algorithm update query request for the AI algorithm is sent to the UDM; and the AI algorithm corresponding to the AI algorithm update query request sent by the UDM is received. In the embodiments of the present disclosure, by sending an AI algorithm update query request to the UDM, the updated AI algorithm sent by the UDM can be received, thereby reducing the situation where the AI network service cannot be provided when there is no AI algorithm corresponding to the AI algorithm update query request, and there is no need for the terminal device to provide a detailed algorithm process, so that the automation of the AI network function service can be achieved. The present disclosure provides a processing method for a situation of "algorithm update" to update the AI algorithm, and an algorithm update mechanism can be provided to update the AI algorithm and provide corresponding AI network services based on the AI algorithm.

FIG8 is a flow chart of an algorithm updating method provided in an embodiment of the present disclosure. The method is executed by the AMF. As shown in FIG8 , the method may include the following steps:

Step 801: Receive a service request message sent by a terminal device via a radio access network RAN, wherein the service request message is used to request to establish an AI session;

Step 802: Send an Nsmf_AISession_CreateSMContext request to SMF to establish an AI session short message context, wherein the Nsmf_AISession_CreateSMContext request is used to establish an AI session;

Step 803: Receive the AI Session creation context request result sent by the SMF, wherein the AI Session creation context request result includes the AI session identifier;

Step 804: Send the session establishment result to the terminal device.

Among them, in one embodiment of the present disclosure, the service request message may be, for example, an AISession_CreateSMContext Request message. The AISession_CreateSMContext Request message is used to request the establishment of an AI session. The request message may, for example, indicate a pre-create AI session message. The AISession_CreateSMContext Request message may, for example, include at least one of an AI session identifier AI Session ID, a request type Request Type, and AI information AI info.

And, in one embodiment of the present disclosure, AMF can perform AISF selection according to the information included in the AISession_CreateSMContext Request message. In the process of AMF performing AISF selection, for example, according to the information provided in the AISession_CreateSMContext Request message, a suitable AISF can be selected by matching the existing AI configuration information in the NRF. For example, the deep learning (DL) function service is requested in the provided information, and the AISF function type recorded in the network repository function (NRF) is matched.

And, in one embodiment of the present disclosure, AMF sends a Nsmf_AISession_CreateSMContext request to SMF to create an association between AMF and SMF to support AI sessions.

And, in one embodiment of the present disclosure, the method further includes:

In response to the session establishment result being that the session establishment process is completed, receiving session establishment confirmation information sent by the terminal device;

Establish an AI session connection with the selected AISF and obtain the services provided by the AISF, where the function type of the AISF corresponds to the service request message.

For example, in one embodiment of the present disclosure, when the AMF obtains a service request message sent by a terminal device, the AMF can select an AISF corresponding to the service request message by matching the existing AI configuration information in the NRF according to the information included in the service request message. For example, when the service request message includes a deep learning function service, the AISF function type recorded in the NRF is matched to select the AISF corresponding to the service request message.

Further, in one embodiment of the present disclosure, the Nsmf_AISession_CreateSMContext request includes at least one of the following:

Subscriber Permanent Identifier (SUPI);

AI Session ID

Request TypeRequest Type;

AI informationAI info.

And, in one embodiment of the present disclosure, the method further includes:

AI service requirements sent via AI sessions to AISF;

Receive the AI recognition result sent by the AISF, where the AI recognition result is obtained according to the updated AI algorithm corresponding to the AI service demand.

In summary, in the embodiment of the present disclosure, a service request message sent by a terminal device via a radio access network RAN is received, wherein the service request message is used to request the establishment of an AI session; an Nsmf AI session establishment short message context Nsmf_AISession_CreateSMContext request is sent to SMF, wherein the Nsmf_AISession_CreateSMContext request is used to establish an AI session; an AI Session creation session context request result sent by SMF is received, wherein the AI Session creation session context request result includes an AI session identifier; and a session establishment result is sent to the terminal device. In the embodiment of the present disclosure, by sending a service request message, an AI session can be established according to the message, the accuracy of AI session establishment can be improved, the situation where AI service requirements cannot be transmitted after the AI session is established can be reduced, and the accuracy of AI service requirements transmitted by the AI session can be improved.

FIG9 is a flow chart of an algorithm updating method provided in an embodiment of the present disclosure. The method is executed by the AMF. As shown in FIG9 , the method may include the following steps:

Step 901: In response to the session establishment result indicating that the session establishment process is completed, receiving session establishment confirmation information sent by the terminal device;

Step 902: Establish an AI session connection with the selected AISF and obtain the services provided by the AISF, where the function type of the AISF corresponds to the service request message.

In one embodiment of the present disclosure, AMF may receive an AI Session creation context request result sent by SMF, wherein the AI Session creation context request result includes an AI session identifier, and AMF may send the AI Session creation context request result to the terminal device. The terminal device may feedback different information to AMF according to the AI Session creation context request result.

And, in one embodiment of the present disclosure, in response to the session establishment result being that the session establishment process is completed, the AMF receives a confirmation message of establishing the session sent by the terminal device. That is, the terminal device can send a confirmation message of establishing the session to the AMF.

In summary, in the embodiment of the present disclosure, in response to the session establishment result being the completion of the session establishment process, a confirmation message of session establishment sent by the terminal device is received; an AI session connection is established with the selected AISF, and the service provided by the AISF is obtained, wherein the function type of the AISF corresponds to the service request message. In the embodiment of the present disclosure, by confirming the establishment of the session information, it can be made clear that the AI session has been established, the accuracy of the AI session establishment can be improved, the situation where the AI service requirements cannot be transmitted after the AI session is established can be reduced, and the accuracy of the AI service requirements transmitted by the AI session can be improved.

FIG10 is a flow chart of an algorithm updating method provided by an embodiment of the present disclosure. The method is executed by a terminal device. As shown in FIG10 , the method may include the following steps:

Step 1001: Send a service request message to the access and mobility management function AMF via the radio access network RAN, wherein the service request message is used to request to establish an artificial intelligence AI session, wherein the AI session includes AI service requirements;

Step 1002: Receive the AI recognition result sent by AMF, where the AI recognition result is obtained according to the updated AI algorithm corresponding to the AI service requirement.

In one embodiment of the present disclosure, the service request message is AISession_CreateSMContext Request, and AISession_CreateSMContext Request includes at least one of the following:

AI Session ID

Request TypeRequest Type;

AI informationAI info.

And, in one embodiment of the present disclosure, the method further includes:

Receive the session establishment result sent by AMF in response to the service request message;

In response to the session establishment result being that the session establishment process is completed, a confirmation message for establishing the session is sent to AMF.

In summary, in the embodiment of the present disclosure, a service request message is sent to the access and mobility management function AMF via the radio access network RAN, wherein the service request message is used to request the establishment of an artificial intelligence AI session, wherein the AI session includes AI service requirements; and the AI recognition results sent by the AMF for the AI service requirements are received. In the embodiment of the present disclosure, by sending a service request message, an AI session can be established according to the message, the accuracy of the AI session establishment can be improved, the AI recognition results sent by the AMF for the AI service requirements can be obtained, the situation where the AI recognition results cannot be obtained after the AI session is established is reduced, and the accuracy of the AI service requirements transmitted by the AI session can be improved. The present disclosure provides a processing method for a situation of "algorithm update" to provide a transmission mechanism for AI recognition results, which can provide AI recognition results corresponding to the AI service requirements and improve the convenience of AI network services.

FIG11 is a schematic diagram of the structure of an algorithm updating system provided by an embodiment of the present disclosure. As shown in FIG11 , the system includes:

The AISF is used to respond to AI service requirements in the AI session and determine an AI algorithm corresponding to the AI service requirements;

AISF, used to send AI algorithm update query requests for AI algorithms to UDM;

UDM, for sending a Nudm AI algorithm authentication update request Nudm_Algorithm_Update_Request to the application function AF in response to the AI algorithm corresponding to the AI algorithm update query request not existing in the UDM;

UDM, used to receive a Nudm AI algorithm authentication update response Nudm_Algorithm_Update_Response message sent by the AF, wherein the Nudm_Algorithm_Update_Response message includes an AI algorithm corresponding to the AI algorithm update query request;

UDM is used to send the AI algorithm corresponding to the AI algorithm update query request to the AISF.

FIG12 is a schematic diagram of the architecture of an algorithm update method provided by an embodiment of the present disclosure. As shown in FIG12 , the system architecture includes: terminal equipment, UDM, AUSF, UDR, Policy Control Function (PCF), AISF, NRF, AMF, SMF, NEF, RAN, UPF and data network (DN). Among them, for example, an N1 session can be established between the terminal equipment and AMF. For example, an N2 session can be established between AMF and RAN. For example, an N3 session can be established between RAN and UPF. For example, an N4 session can be established between SMF and UPF. For example, an N6 session can be established between UPF and DN.

FIG13 is an interactive schematic diagram of an algorithm updating method provided by an embodiment of the present disclosure. As shown in FIG13 , the method includes:

In the first step, the terminal device creates an AI session request to AMF. For example, when the terminal device pre-calls AISF to initiate a service request process, the UE sends a service request message to AMF through (R)AN, that is, AISession_CreateSMContext Request message to request the establishment of AI Session message, indicating the information of pre-creating AI session. The request message includes AI Session ID, Request type and AI info, etc.

Step 2: AMF sends Nsmf_AISession_CreateSMContext request to SMF;

In the third step, SMF initiates AISession registration to UDM and obtains contract information. UDM will authorize wireless access to the AI session and check the functions supported and prohibited services of the AI session.

Step 4: SMF selects a UPF and establishes an N4 session to the selected UPF.

Step 5: SMF returns the AI Session creation context request result to AMF. If the session establishment process is successful, the AI Session ID will also be returned to AMF.

Step 6a: AMF receives the session establishment result and sends it to the terminal device. The terminal device can provide different feedback to AMF based on the result.

Step 6b: If the session establishment process is successful, the terminal device can reply to AMF to confirm the establishment of the session and establish a connection with the corresponding AISF to obtain services;

Step 7: AISF learns the user’s AI service needs through AI Session;

Step 8. AISF sends AI algorithm update query request Nudm_SDM_Inquire_request to UDM;

Step 9a, in response to the AI algorithm corresponding to the AI algorithm update query request sent by the artificial intelligence service function AISF not existing in the UDM, sending the Nudm AI algorithm authentication update request Nudm_Algorithm_Update_Request to the application function AF;

Step 9b: If AF can provide the corresponding update algorithm, it returns Nudm_Algorithm_Update_Response to UDM;

Step 10: UDM transmits the updated algorithm flow to AISF;

In the eleventh step, UDR provides the data set to AISF;

In the twelfth step, AISF uses the received data and uses the new algorithm process for training and prediction;

Step 13: AISF transmits AI recognition results to AMF;

In step 14, AMF sends the output result to the terminal device via RAN.

FIG. 14 is a schematic diagram of the structure of an algorithm updating device provided by an embodiment of the present disclosure. As shown in FIG. 14 , the device 1400 may be arranged on the UDM side. The device 1400 may include:

The receiving module 1401 is used to receive an AI algorithm update query request sent by an artificial intelligence service function AISF;

A sending module 1402 is configured to send a Nudm AI algorithm authentication update request Nudm_Algorithm_Update_Request to an application function AF in response to the AI algorithm corresponding to the AI algorithm update query request not existing in the UDM;

The receiving module 1401 is further used to receive a Nudm AI algorithm authentication update response Nudm_Algorithm_Update_Response message sent by the AF, wherein the Nudm_Algorithm_Update_Response message includes an AI algorithm corresponding to the AI algorithm update query request;

The sending module 1402 is further used to send the AI algorithm corresponding to the AI algorithm update query request to the AISF.

In summary, in the algorithm updating device of the embodiment of the present disclosure, the AI algorithm update query request sent by the artificial intelligence service function AISF is received by the receiving module; the sending module sends the Nudm AI algorithm authentication update request Nudm_Algorithm_Update_Request to the application function AF in response to the AI algorithm corresponding to the AI algorithm update query request not existing in the UDM; the receiving module receives the Nudm AI algorithm authentication update response Nudm_Algorithm_Update_Response message sent by the AF, wherein the Nudm_Algorithm_Update_Response message includes the AI algorithm corresponding to the AI algorithm update query request; the sending module sends the AI algorithm corresponding to the AI algorithm update query request to the AISF. In the embodiment of the present disclosure, when the AI algorithm corresponding to the AI algorithm update query request does not exist in the UDM, the AI algorithm in the UDM can be updated so that the AI algorithm corresponding to the AI algorithm update query request exists in the UDM, so that the corresponding AI network service can be provided according to the AI algorithm, thereby reducing the situation where the AI network service cannot be provided when the AI algorithm corresponding to the AI algorithm update query request does not exist in the UDM. The present disclosure provides a processing device for an "algorithm update" scenario to update the AI algorithm in the UDM, and can provide an algorithm update mechanism, which can update the AI algorithm and provide corresponding AI network services based on the AI algorithm.

Optionally, in an embodiment of the present disclosure, the sending module 1401 is further configured to send an authorization request for the AF to the network opening function NEF;

The receiving module 1402 is further configured to receive authorization information sent by the NEF in response to the authorization request.

Optionally, in an embodiment of the present disclosure, the receiving module 1402 is further configured to receive an AI session AISession registration request sent by a session management function SMF;

The sending module 1401 is also used to send the contract information for the AISession registration request to the SMF, wherein the contract information includes the authorization information of the AI session, the functions supported by the AI session, and the prohibited services.

FIG. 15 is a schematic diagram of the structure of an algorithm updating device provided by an embodiment of the present disclosure. As shown in FIG. 15 , the device 1500 may be arranged on the AISF side, and the device 1500 may include:

A determination module 1501 is used to determine an AI algorithm corresponding to the AI service requirement;

A sending module 1502 is used to send an AI algorithm update query request for the AI algorithm to the UDM;

The receiving module 1503 is used to receive the AI algorithm corresponding to the AI algorithm update query request sent by the UDM.

In summary, in the algorithm updating device of the embodiment of the present disclosure, the determination module responds to the AI service demand in the AI session to determine the AI algorithm corresponding to the AI service demand; the sending module sends an AI algorithm update query request for the AI algorithm to the UDM; the receiving module receives the AI algorithm corresponding to the AI algorithm update query request sent by the UDM. In the embodiment of the present disclosure, by sending the AI algorithm update query request to the UDM, the updated AI algorithm sent by the UDM can be received, thereby reducing the situation where the AI network service cannot be provided when there is no AI algorithm corresponding to the AI algorithm update query request. The present disclosure provides a processing device for a situation of "algorithm update" to update the AI algorithm, and can provide an algorithm update mechanism, which can update the AI algorithm and provide corresponding AI network services based on the AI algorithm.

Optionally, in an embodiment of the present disclosure, the receiving module 1503 is further configured to receive a data set sent by a user data register UDR;

The sending module 1502 is also used to send the AI recognition result to the AMF.

Optionally, in one embodiment of the present disclosure, the receiving module 1503 is further used to receive AI service requirements sent by the AMF via the AI session.

FIG. 16 is a schematic diagram of the structure of an algorithm updating device provided in an embodiment of the present disclosure. As shown in FIG. 16 , the device 1600 may be arranged on the AMF side, and the device 1600 may include:

The receiving module 1601 is configured to receive a service request message sent by a terminal device via a radio access network RAN, wherein the service request message is used to request to establish an AI session;

A sending module 1602 is used to send an Nsmf AI session establishment short message context Nsmf_AISession_CreateSMContext request to SMF, wherein the Nsmf_AISession_CreateSMContext request is used to establish an AI session;

The receiving module 1603 is used to receive the AI Session creation context request result sent by the SMF, wherein the AI Session creation context request result includes the AI session identifier;

The sending module 1604 is used to send the session establishment result to the terminal device.

In summary, in the algorithm updating device of the embodiment of the present disclosure, a service request message sent by a terminal device via a wireless access network RAN is received by a receiving module, wherein the service request message is used to request the establishment of an AI session; a sending module sends an Nsmf AI session establishment short message context Nsmf_AISession_CreateSMContext request to SMF, wherein the Nsmf_AISession_CreateSMContext request is used to establish an AI session; a receiving module receives an AI Session creation session context request result sent by SMF, wherein the AI Session creation session context request result includes an AI session identifier; and a sending module sends a session establishment result to the terminal device. In the embodiment of the present disclosure, by sending a service request message, an AI session can be established according to the message, the accuracy of AI session establishment can be improved, the situation where AI service requirements cannot be transmitted after the AI session is established can be reduced, and the accuracy of AI session transmission of AI service requirements can be improved.

Optionally, in an embodiment of the present disclosure, the receiving module 1603 is further configured to receive session establishment confirmation information sent by the terminal device in response to the session establishment result indicating that the session establishment process is completed;

Optionally, in an embodiment of the present disclosure, the Nsmf_AISession_CreateSMContext request includes at least one of the following:

Subscriber Permanent Identification SUPI;

AI Session ID

Request TypeRequest Type;

AI informationAI info.

Optionally, in an embodiment of the present disclosure, the receiving module 1603 is further configured to send the AI service demand to the AISF via the AI session;

FIG. 17 is a schematic diagram of the structure of an algorithm updating device provided by an embodiment of the present disclosure. As shown in FIG. 17 , the device 1700 may be arranged on a terminal device side, and the device 1700 may include:

The sending module 1701 is used to send a service request message to the access and mobility management function AMF via the radio access network RAN, wherein the service request message is used to request to establish an artificial intelligence AI session, wherein the AI session includes an AI service requirement;

The receiving module 1702 is used to receive the AI recognition result sent by the AMF, where the AI recognition result is obtained according to the updated AI algorithm corresponding to the AI service requirement.

In summary, in the algorithm update device of the embodiment of the present disclosure, a service request message is sent to the access and mobility management function AMF via the wireless access network RAN through the sending module, wherein the service request message is used to request the establishment of an artificial intelligence AI session, wherein the AI session includes AI service requirements; the receiving module receives the AI recognition result sent by the AMF, and the AI recognition result is obtained according to the updated AI algorithm corresponding to the AI service requirements. In the embodiment of the present disclosure, by sending a service request message, an AI session can be established according to the message, the accuracy of the establishment of the AI session can be improved, the AI recognition result sent by the AMF for the AI service requirements can be obtained, the situation where the AI recognition result cannot be obtained after the AI session is established can be reduced, and the accuracy of the AI service requirements transmitted by the AI session can be improved. The present disclosure provides a processing device for a situation of "algorithm update" to provide a transmission mechanism for AI recognition results, which can provide AI recognition results corresponding to AI service requirements and improve the convenience of AI network services.

Optionally, in an embodiment of the present disclosure, the service request message is AISession_CreateSMContext Request, and AISession_CreateSMContext Request includes at least one of the following:

AI Session ID

Request TypeRequest Type;

AI informationAI info.

Optionally, in an embodiment of the present disclosure, the receiving module 1702 is further configured to receive a session establishment result sent by the AMF for the service request message;

The sending module 1701 is also used to send confirmation information on session establishment to the AMF in response to the session establishment result indicating that the session establishment process is completed.

18 is a block diagram of a terminal device UE 1800 provided by an embodiment of the present disclosure. For example, UE 1800 may be a mobile phone, a computer, a digital broadcast terminal device, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

18 , UE 1800 may include at least one of the following components: a processing component 1802 , a memory 1804 , a power component 1806 , a multimedia component 1808 , an audio component 1810 , an input/output (I/O) interface 1812 , a sensor component 1814 , and a communication component 1816 .

The processing component 1802 generally controls the overall operation of the UE 1800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 1802 may include at least one processor 1820 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 1802 may include at least one module to facilitate the interaction between the processing component 1802 and other components. For example, the processing component 1802 may include a multimedia module to facilitate the interaction between the multimedia component 1808 and the processing component 1802.

The memory 1804 is configured to store various types of data to support the operation of the UE 1800. Examples of such data include instructions for any application or method operating on the UE 1800, contact data, phone book data, messages, pictures, videos, etc. The memory 1804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

The power component 1806 provides power to various components of the UE 1800. The power component 1806 may include a power management system, at least one power supply, and other components associated with generating, managing, and distributing power for the UE 1800.

The multimedia component 1808 includes a screen that provides an output interface between the UE 1800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes at least one touch sensor to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the wake-up time and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 1808 includes a front camera and/or a rear camera. When the UE 1800 is in an operating mode, such as a shooting mode or a video mode, the front camera and/or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 1810 is configured to output and/or input audio signals. For example, the audio component 1810 includes a microphone (MIC), and when the UE 1800 is in an operation mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 1804 or sent via the communication component 1816. In some embodiments, the audio component 1810 also includes a speaker for outputting audio signals.

I/O interface 1812 provides an interface between processing component 1802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: home button, volume button, start button, and lock button.

The sensor component 1814 includes at least one sensor for providing various aspects of status assessment for UE1800. For example, the sensor component 1814 can detect the open/closed state of the device 1800, the relative positioning of the components, such as the display and keypad of the UE1800, and the sensor component 1814 can also detect the position change of UE1800 or a component of UE1800, the presence or absence of user contact with UE1800, the orientation or acceleration/deceleration of UE1800 and the temperature change of UE1800. The sensor component 1814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor component 1814 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor component 1814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor or a temperature sensor.

The communication component 1816 is configured to facilitate wired or wireless communication between UE1800 and other devices. UE1800 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 1816 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 1816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

In an exemplary embodiment, UE1800 may be implemented by at least one application-specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing device (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic component to perform the above method.

FIG19 is a block diagram of a network side device 1900 provided in an embodiment of the present disclosure. For example, the network side device 1900 may be provided as a network side device. Referring to FIG19 , the network side device 1900 includes a processing component 1922, which further includes at least one processor, and a memory resource represented by a memory 1932 for storing instructions executable by the processing component 1922, such as an application. The application stored in the memory 1932 may include one or more modules, each of which corresponds to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform any method of the aforementioned method applied to the network side device.

The network side device 1900 may also include a power supply component 1929 configured to perform power management of the network side device 1900, a wired or wireless network interface 1950 configured to connect the network side device 1900 to the network, and an input/output (I/O) interface 1958. The network side device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server TM, Mac OS XTM, Unix TM, Linux TM, Free BSDTM or the like.

In the above embodiments provided by the present disclosure, the methods provided by the embodiments of the present disclosure are introduced from the perspectives of the network side device and the UE. In order to implement the functions in the methods provided by the above embodiments of the present disclosure, the network side device and the UE may include a hardware structure and a software module, and implement the above functions in the form of a hardware structure, a software module, or a hardware structure plus a software module. One of the above functions may be executed in the form of a hardware structure, a software module, or a hardware structure plus a software module.

The present disclosure provides a communication device. The communication device may include a transceiver module and a processing module. The transceiver module may include a sending module and/or a receiving module, the sending module is used to implement a sending function, the receiving module is used to implement a receiving function, and the transceiver module may implement a sending function and/or a receiving function.

The communication device may be a terminal device (such as the terminal device in the aforementioned method embodiment), or a device in the terminal device, or a device that can be used in conjunction with the terminal device. Alternatively, the communication device may be a network device, or a device in the network device, or a device that can be used in conjunction with the network device.

Another communication device provided in an embodiment of the present disclosure. The communication device may be a network device, or a terminal device (such as the terminal device in the aforementioned method embodiment), or a chip, a chip system, or a processor that supports the network device to implement the aforementioned method, or a chip, a chip system, or a processor that supports the terminal device to implement the aforementioned method. The device may be used to implement the method described in the aforementioned method embodiment, and the details may refer to the description in the aforementioned method embodiment.

The communication device may include one or more processors. The processor may be a general-purpose processor or a dedicated processor, etc. For example, it may be a baseband processor or a central processing unit. The baseband processor may be used to process the communication protocol and communication data, and the central processing unit may be used to control the communication device (such as a network side device, a baseband chip, a terminal device, a terminal device chip, a DU or a CU, etc.), execute a computer program, and process the data of the computer program.

Optionally, the communication device may further include one or more memories, on which a computer program may be stored, and the processor executes the computer program so that the communication device performs the method described in the above method embodiment. Optionally, data may also be stored in the memory. The communication device and the memory may be provided separately or integrated together.

Optionally, the communication device may further include a transceiver and an antenna. The transceiver may be referred to as a transceiver unit, a transceiver, or a transceiver circuit, etc., and is used to implement a transceiver function. The transceiver may include a receiver and a transmitter, the receiver may be referred to as a receiver or a receiving circuit, etc., and is used to implement a receiving function; the transmitter may be referred to as a transmitter or a transmitting circuit, etc., and is used to implement a transmitting function.

Optionally, the communication device may further include one or more interface circuits. The interface circuit is used to receive code instructions and transmit them to the processor. The processor runs the code instructions to enable the communication device to execute the method described in the above method embodiment.

The communication device is a UDM: the processor is used to execute any one of the methods shown in FIG. 1 to FIG. 6 .

The communication device is an AISF: the processor is used to execute any method shown in FIG. 7 .

The communication device is an AMF: the processor is used to execute any one of the methods shown in Figures 8-9.

The communication device is a terminal device (such as the terminal device in the aforementioned method embodiment): the processor is used to execute any of the methods shown in Figure 10. In one implementation, the processor may include a transceiver for implementing the receiving and sending functions. For example, the transceiver may be a transceiver circuit, or an interface, or an interface circuit. The transceiver circuit, interface or interface circuit for implementing the receiving and sending functions may be separate or integrated. The above-mentioned transceiver circuit, interface or interface circuit can be used for reading and writing code/data, or the above-mentioned transceiver circuit, interface or interface circuit can be used for transmitting or transferring signals.

In one implementation, the processor may store a computer program, and the computer program runs on the processor, which can enable the communication device to perform the method described in the above method embodiment. The computer program may be fixed in the processor, in which case the processor may be implemented by hardware.

In one implementation, the communication device may include a circuit that can implement the functions of sending or receiving or communicating in the aforementioned method embodiments. The processor and transceiver described in the present disclosure may be implemented in an integrated circuit (IC), an analog IC, a radio frequency integrated circuit RFIC, a mixed signal IC, an application specific integrated circuit (ASIC), a printed circuit board (PCB), an electronic device, etc. The processor and transceiver may also be manufactured using various IC process technologies, such as complementary metal oxide semiconductor (CMOS), N-type metal oxide semiconductor (NMOS), P-type metal oxide semiconductor (positive channel metal oxide semiconductor, PMOS), bipolar junction transistor (BJT), bipolar CMOS (BiCMOS), silicon germanium (SiGe), gallium arsenide (GaAs), etc.

The communication device described in the above embodiments may be a network device or a terminal device (such as the terminal device in the aforementioned method embodiment), but the scope of the communication device described in the present disclosure is not limited thereto, and the structure of the communication device may not be limited thereto. The communication device may be an independent device or may be part of a larger device. For example, the communication device may be:

(1) Independent integrated circuit IC, or chip, or chip system or subsystem;

(2) having a set of one or more ICs, and optionally, the IC set may also include a storage component for storing data and computer programs;

(3) ASIC, such as modem;

(4) Modules that can be embedded in other devices;

(5) Receivers, terminal devices, intelligent terminal devices, cellular phones, wireless devices, handheld devices, mobile units, vehicle-mounted devices, network devices, cloud devices, artificial intelligence devices, etc.;

(6)Others

In the case where the communication device may be a chip or a chip system, the chip includes a processor and an interface, wherein the number of the processors may be one or more, and the number of the interfaces may be multiple.

Optionally, the chip also includes a memory for storing necessary computer programs and data.

Those skilled in the art may also understand that the various illustrative logical blocks and steps listed in the embodiments of the present disclosure may be implemented by electronic hardware, computer software, or a combination of both. Whether such functions are implemented by hardware or software depends on the specific application and the design requirements of the entire system. Those skilled in the art may use various methods to implement the described functions for each specific application, but such implementation should not be understood as exceeding the scope of protection of the embodiments of the present disclosure.

The present disclosure also provides a readable storage medium having instructions stored thereon, which implement the functions of any of the above method embodiments when executed by a computer.

The present disclosure also provides a computer program product, which implements the functions of any of the above method embodiments when executed by a computer.

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

Those skilled in the art can understand that the various numerical numbers such as first and second involved in the present disclosure are only used for the convenience of description and are not used to limit the scope of the embodiments of the present disclosure, but also indicate the order of precedence.

At least one in the present disclosure may also be described as one or more, and a plurality may be two, three, four or more, which is not limited in the present disclosure. In the embodiments of the present disclosure, for a technical feature, the technical features in the technical feature are distinguished by "first", "second", "third", "A", "B", "C" and "D", etc., and there is no order of precedence or size between the technical features described by the "first", "second", "third", "A", "B", "C" and "D".

Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

An algorithm updating method, characterized in that the method is executed by a unified data management function UDM, and the method comprises:

Receive AI algorithm update query requests sent by the artificial intelligence service function AISF;

In response to the AI algorithm corresponding to the AI algorithm update query request not existing in the UDM, sending a Nudm AI algorithm authentication update request Nudm_Algorithm_Update_Request to the application function AF;

Receive a Nudm AI algorithm authentication update response Nudm_Algorithm_Update_Response message sent by the AF, wherein the Nudm_Algorithm_Update_Response message includes an AI algorithm corresponding to the AI algorithm update query request;

Sending the AI algorithm corresponding to the AI algorithm update query request to the AISF.
The method according to claim 1, characterized in that the method further comprises:

Sending an authorization request for the AF to a network opening function NEF;

Receive authorization information sent by the NEF in response to the authorization request.
The method according to claim 1, characterized in that the method further comprises:

Receive the AI session AISession registration request sent by the session management function SMF;

Sending the contract information for the AISession registration request to the SMF, wherein the contract information includes the authorization information of the AI session, the functions supported by the AI session, and the prohibited services.
An algorithm updating method, characterized in that the method is executed by an AISF, and the method comprises:

Determine the AI algorithms that correspond to the AI service requirements;

Sending an AI algorithm update query request for the AI algorithm to the UDM;

Receive an AI algorithm corresponding to the AI algorithm update query request sent by the UDM.
The method according to claim 4, characterized in that the method further comprises:

Receive the data set sent by the user data register UDR;

Acquire an AI recognition result corresponding to the AI service requirement according to the data set and the updated AI algorithm;

Send the AI identification result to the access and mobility management function AMF.
The method according to claim 4, characterized in that the method further comprises:

Receive AI service requirements sent by AMF via AI session.
An algorithm update method, characterized in that the method is executed by AMF, and the method comprises:

Receiving a service request message sent by a terminal device via a radio access network RAN, wherein the service request message is used to request to establish the AI session;

Send a network slice management function AI session establishment short message context Nsmf_AISession_CreateSMContext request to SMF, wherein the Nsmf_AISession_CreateSMContext request is used to establish the AI session;

Receive the AI Session create session context request result sent by the SMF, wherein the AI Session create session context request result includes the AI session identifier;

The session establishment result is sent to the terminal device.
The method according to claim 7, characterized in that the method further comprises:

In response to the session establishment result being that the session establishment process is completed, receiving session establishment confirmation information sent by the terminal device;

Establish an AI session connection with the selected AISF, and obtain services provided by the AISF, wherein the function type of the AISF corresponds to the service request message.
The method according to claim 7, wherein the Nsmf_AISession_CreateSMContext request includes at least one of the following:

Subscriber Permanent Identification SUPI;

AI Session ID

Request TypeRequest Type;

AI informationAI info.
The method according to claim 7, characterized in that the method further comprises:

AI service requirements sent via AI sessions to AISF;

Receive an AI recognition result sent by the AISF, wherein the AI recognition result is obtained according to an updated AI algorithm corresponding to the AI service requirement.
An algorithm updating method, characterized in that the method is executed by a terminal device, and the method comprises:

Sending a service request message to an access and mobility management function AMF via a radio access network RAN, wherein the service request message is used to request establishment of an artificial intelligence AI session, wherein the AI session includes an AI service requirement;

Receive the AI recognition result sent by the AMF, where the AI recognition result is obtained according to the updated AI algorithm corresponding to the AI service requirement.
The method according to claim 11, characterized in that, wherein the service request message is AISession_CreateSMContext Request, and the AISession_CreateSMContext Request includes at least one of the following:

AI Session ID

Request TypeRequest Type;

AI informationAI info.
The method according to claim 11, characterized in that the method further comprises:

Receiving a session establishment result sent by the AMF in response to the service request message;

In response to the session establishment result being that the session establishment process is completed, a confirmation message for establishing the session is sent to the AMF.
An algorithm updating device, characterized in that the device is arranged on the UDM side, and the device comprises:

A receiving module, used to receive an AI algorithm update query request sent by an artificial intelligence service function AISF;

A sending module, configured to send a Nudm AI algorithm authentication update request Nudm_Algorithm_Update_Request to an application function AF in response to the AI algorithm corresponding to the AI algorithm update query request not existing in the UDM;

The receiving module is further used to receive a Nudm AI algorithm authentication update response Nudm_Algorithm_Update_Response message sent by the AF, wherein the Nudm_Algorithm_Update_Response message includes an AI algorithm corresponding to the AI algorithm update query request;

The sending module is further used to send the AI algorithm corresponding to the AI algorithm update query request to the AISF.
An algorithm updating device, characterized in that the device is arranged on the AISF side, and the device comprises:

A determination module, used to determine the AI algorithm corresponding to the AI service requirements;

A sending module, used for sending an AI algorithm update query request for the AI algorithm to the UDM;

The receiving module is used to receive the AI algorithm corresponding to the AI algorithm update query request sent by the UDM.
An algorithm updating device, characterized in that the device is arranged on the AMF side, and the device comprises:

A receiving module, configured to receive a service request message sent by a terminal device via a radio access network RAN, wherein the service request message is used to request to establish the AI session;

A sending module, used for sending an Nsmf AI session establishment short message context Nsmf_AISession_CreateSMContext request to SMF, wherein the Nsmf_AISession_CreateSMContext request is used to establish the AI session;

A receiving module, used for receiving an AI Session creation context request result sent by the SMF, wherein the AI Session creation context request result includes an AI session identifier;

The sending module is used to send the session establishment result to the terminal device.
An algorithm updating device, characterized in that the device is arranged on a terminal device side, and the device comprises:

A sending module, configured to send a service request message to an access and mobility management function AMF via a radio access network RAN, wherein the service request message is used to request establishment of an artificial intelligence AI session, wherein the AI session includes an AI service requirement;

A receiving module is used to receive the AI recognition result sent by the AMF, where the AI recognition result is obtained according to the updated AI algorithm corresponding to the AI service requirement.
A UDM, characterized in that the device comprises a processor and a memory, wherein a computer program is stored in the memory, and the processor executes the computer program stored in the memory so that the device performs the method as described in any one of claims 1 to 3.
An AISF, characterized in that the device includes a processor and a memory, wherein a computer program is stored in the memory, and the processor executes the computer program stored in the memory so that the device performs the method as described in any one of claims 4 to 6.
An AMF, characterized in that the device includes a processor and a memory, wherein a computer program is stored in the memory, and the processor executes the computer program stored in the memory so that the device performs the method as described in any one of claims 7 to 10.
A terminal device, characterized in that the device includes a processor and a memory, wherein a computer program is stored in the memory, and the processor executes the computer program stored in the memory so that the device performs the method as described in any one of claims 11 to 13.
A communication device, comprising: a processor and an interface circuit, wherein:

The interface circuit is used to receive code instructions and transmit them to the processor;

The processor is configured to execute the code instructions to perform the method according to any one of claims 1 to 3 or 4 to 6 or 7 to 10 or 11 to 13.
A computer-readable storage medium, characterized in that it is used to store instructions, and when the instructions are executed, the method as described in any one of claims 1 to 3 or 4 to 6 or 7 to 10 or 11 to 13 is implemented.
An algorithm updating system, characterized in that the system comprises:

The AISF is used to respond to an AI service demand in an AI session and determine an AI algorithm corresponding to the AI service demand;

The AISF is used to send an AI algorithm update query request for the AI algorithm to the UDM;

The UDM is used to send a Nudm AI algorithm authentication update request Nudm_Algorithm_Update_Request to the application function AF in response to the AI algorithm corresponding to the AI algorithm update query request not existing in the UDM;

The UDM is used to receive a Nudm AI algorithm authentication update response Nudm_Algorithm_Update_Response message sent by the AF, wherein the Nudm_Algorithm_Update_Response message includes an AI algorithm corresponding to the AI algorithm update query request;

The UDM is used to send the AI algorithm corresponding to the AI algorithm update query request to the AISF.