Communication method and system, core network equipment, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a communication method and system, core network equipment, electronic equipment and a storage medium, and relates to the technical field of communication. The method comprises the steps that an artificial intelligence AI network function calling request is sent, AI network function registration information is stored in core network equipment, the AI network function registration information comprises information of an AI network function registered in the core network equipment, and the AI network function is a network function which is provided by network side equipment and relates to the AI technology. Compared with the prior art, the AI network function is registered in the core network equipment, namely, under the condition that the core network equipment is endowed with the AI network function, the AI network function calling request is directly sent to the core network equipment by the UE, so that the transmission cost of obtaining the AI network function service by the UE is remarkably reduced, and meanwhile, the flexibility is greatly improved.

Description

Communication method, system, core network device, electronic device and storage medium Technical Field

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

[0002] Artificial Intelligence (AI) has become a key technology in the communications sector, and typical application scenarios for 5G communications and AI overlap significantly. Furthermore, the massive coverage of 5G networks provides a ubiquitous platform for AI, addressing the significant pain point of a lack of carriers and channels for AI implementation and significantly promoting the development and prosperity of the AI ​​industry.

[0003] Since AI technology was applied to 5G networks relatively late, relevant research was only carried out after the 5G architecture was determined. Network intelligent applications in the 5G stage are optimized and transformed on the traditional network architecture, and are generally plug-in applications. AI network functions are simply superimposed on existing network processes, and cross-domain and cross-layer intelligent applications are difficult to coordinate.

[0004] Summary of the Invention

[0005] The embodiments of the present disclosure provide a communication method, system, core network device, electronic device, and storage medium that can solve the above-mentioned problems of the prior art. The technical solution is as follows:

[0006] According to a first aspect of an embodiment of the present disclosure, a communication method is provided, which is performed by a user equipment (UE). The method includes:

[0007] Send an artificial intelligence (AI) network function call request, which is used to instruct the core network device to provide the AI ​​network function service to the UE;

[0008] Among them, the core network device stores AI network function registration information, which includes information about AI network functions registered in the core network device; AI network functions are network functions involving AI technology provided by network-side devices.

[0009] According to a second aspect of an embodiment of the present disclosure, a communication method is provided, which is performed by a core network device, and the method includes:

[0010] In response to obtaining the AI ​​network function call request, determine target policy control and charging PCC rules based on the AI ​​network function call request and the AI ​​network function registration information;

[0011] Among them, the AI ​​network function call request is used to instruct the core network device to provide the AI ​​network function service to the UE; the AI ​​network function registration information includes information about the AI ​​network function registered in the core network device, and the target PCC rule is related to the AI ​​network function requested by the UE; the AI ​​network function is a network function involving AI technology provided by the network side device.

[0012] According to a third aspect of an embodiment of the present disclosure, a communication method is provided, which is performed by an access and mobility management function (AMF) in a core network device. The method includes:

[0013] In response to obtaining the AI ​​network function call request, forwarding the AI ​​network function call request to the session management function SMF in the core network device;

[0014] Among them, the AI ​​network function call request is used to instruct the core network device to provide AI network function services to the UE; the AI ​​network function is a network function involving AI technology provided by the network side device.

[0015] According to a fourth aspect of an embodiment of the present disclosure, a communication method is provided, which is performed by a session management function SMF in a core network device, and the method includes:

[0016] In response to the AI ​​network function call request, obtain AI network function registration information;

[0017] Send the AI ​​network function call request and AI network function registration information to the policy control function (PCF) in the core network device;

[0018] Among them, the AI ​​network function call request is used to instruct the core network device to provide AI network function services to the UE, and the AI ​​network function registration information includes information about the AI ​​network function registered in the core network device; the AI ​​network function is a network function involving AI technology provided by the network side device.

[0019] According to a fifth aspect of an embodiment of the present disclosure, a communication method is provided, which is performed by a policy control function (PCF) in a core network device. The method includes:

[0020] In response to obtaining the AI ​​network function call request and the AI ​​network function registration information, determining a target PCC rule;

[0021] Among them, the AI ​​network function call request is used to instruct the core network device to provide the AI ​​network function service to the UE, the AI ​​network function registration information includes information about the AI ​​network function registered in the core network device, and the target PCC rule is related to the AI ​​network function requested by the UE; the AI ​​network function is a network function involving AI technology provided by the network side device.

[0022] According to a sixth aspect of an embodiment of the present disclosure, a communication method is provided, which is performed by a user plane function (UPF) in a core network device. The method includes:

[0023] In response to obtaining the target PCC rule, establishing a connection with a target network element and issuing the PCC rule; the target network element is used to implement the AI ​​network function requested by the UE;

[0024] Invoke the AI ​​network function requested by the UE according to the target PCC rules;

[0025] Among them, the target PCC rule is determined based on the AI ​​network function call request sent by the UE. The target PCC rule is related to the AI ​​network function requested by the UE; the AI ​​network function is a network function involving AI technology provided by the network side device.

[0026] According to a seventh aspect of the embodiments of the present disclosure, there is provided a communication method, including:

[0027] The AMF receives an AI network function call request sent by the UE. The AI ​​network function call request is used to instruct the core network device to provide the AI ​​network function service to the UE. The AI ​​network function is a network function involving AI technology provided by the network-side device.

[0028] AMF forwards the AI ​​network function call request to SMF;

[0029] The SMF obtains the AI ​​network function call request and the AI ​​network function registration information in response to the AI ​​network function call request, and sends the AI ​​network function call request and the AI ​​network function registration information to the policy control function PCF; the AI ​​network function registration information includes information about the AI ​​network function registered in the core network device;

[0030] In response to obtaining the AI ​​network function call request and the AI ​​network function registration information, the PCF determines the target PCC rule of the AI ​​network function requested by the UE and sends the target PCC rule to the SMF;

[0031] In response to obtaining the target PCC rule, the SMF sends the target PCC rule to the UPF;

[0032] In response to obtaining the target PCC rule, the UPF establishes a connection with the target network element and issues the PCC rule. Based on the target PCC rule, the UPF invokes the AI ​​network function requested by the UE. In response to obtaining the service result of the AI ​​network function, the UPF sends the service result to the SMF. The target network element is used to implement the AI ​​network function requested by the UE. The service result of the AI ​​network function is the result returned by the core network device after processing the AI ​​network function call request.

[0033] The SMF sends the service result to the AMF, which then sends the service result to the UE.

[0034] The AMF receives a confirmation message sent by the UE in response to receiving the service result. The confirmation message is used to instruct the SMF to release the resources of the AI ​​network function requested by the UE;

[0035] The AMF instructs the SMF to release the resources of the AI ​​network function requested by the UE.

[0036] According to an eighth aspect of an embodiment of the present disclosure, a UE is provided, including:

[0037] A call request sending module is used to send an artificial intelligence (AI) network function call request, which is used to instruct the core network device to provide the AI ​​network function service to the UE;

[0038] Among them, the core network device stores AI network function registration information, which includes information about AI network functions registered in the core network device; AI network functions are network functions involving AI technology provided by network-side devices.

[0039] According to a ninth aspect of an embodiment of the present disclosure, a core network device is provided, including:

[0040] A rule determination module is configured to, in response to obtaining an AI network function call request, determine a target policy control and charging PCC rule based on the AI ​​network function call request and the AI ​​network function registration information;

[0041] Among them, the AI ​​network function call request is used to instruct the core network device to provide the AI ​​network function service to the UE; the AI ​​network function registration information includes information about the AI ​​network function registered in the core network device, and the target PCC rule is related to the AI ​​network function requested by the UE; the AI ​​network function is a network function involving AI technology provided by the network side device.

[0042] According to a tenth aspect of an embodiment of the present disclosure, an access and mobility management function (AMF) is provided, including:

[0043] A forwarding module, configured to, in response to obtaining the AI ​​network function call request, forward the AI ​​network function call request to a session management function SMF in a core network device;

[0044] The AI ​​network function call request is used to instruct the core network device to provide the AI ​​network function service to the UE and store data in the unstructured data storage function UDSF in the core network device; the AI ​​network function is a network function involving AI technology provided by the network side device.

[0045] According to an eleventh aspect of an embodiment of the present disclosure, a session management function (SMF) is provided, including:

[0046] A registration information acquisition module, configured to obtain AI network function registration information in response to an AI network function call request;

[0047] The integrated sending module is used to send AI network function call requests and AI network function registration information to the policy control function (PCF) in the core network device;

[0048] Among them, the AI ​​network function call request is used to instruct the core network device to provide AI network function services to the UE, and the AI ​​network function registration information includes information about the AI ​​network function registered in the core network device; the AI ​​network function is a network function involving AI technology provided by the network side device.

[0049] According to a twelfth aspect of an embodiment of the present disclosure, a policy control function (PCF) is provided, including:

[0050] A rule formulation module, configured to determine a target PCC rule in response to obtaining an AI network function call request and AI network function registration information;

[0051] Among them, the AI ​​network function call request is used to instruct the core network device to provide the AI ​​network function service to the UE, the AI ​​network function registration information includes information about the AI ​​network function registered in the core network device, and the target PCC rule is related to the AI ​​network function requested by the UE; the AI ​​network function is a network function involving AI technology provided by the network side device.

[0052] According to a thirteenth aspect of an embodiment of the present disclosure, a user plane function (UPF) is provided, including:

[0053] A connection module is configured to establish a connection with a target network element and issue the target PCC rule in response to obtaining the target PCC rule; the target network element is configured to implement the AI ​​network function requested by the UE;

[0054] A calling module, configured to call the AI ​​network function requested by the UE according to the target PCC rule;

[0055] Among them, the target PCC rule is determined based on the AI ​​network function call request sent by the UE. The target PCC rule is related to the AI ​​network function requested by the UE; the AI ​​network function is a network function involving AI technology provided by the network side device.

[0056] According to a fourteenth aspect of an embodiment of the present disclosure, a communication system is provided, which is used to execute the method of the second aspect.

[0057] According to a fifteenth aspect of an embodiment of the present disclosure, a communication system is provided, comprising:

[0058] Access and mobility management function AMF for performing the method of the third aspect;

[0059] Access and session management function SMF for executing the method according to the fourth aspect;

[0060] A policy control function PCF for executing the method of the fifth aspect;

[0061] Used to execute the user plane function UPF as described in the sixth aspect.

[0062] According to the sixteenth aspect of an embodiment of the present disclosure, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and runnable on the processor, and when the processor executes the program, it implements the communication method of any one of the first to seventh aspects.

[0063] According to the seventeenth aspect of the embodiment of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, a communication method including any one of the first to seventh aspects is implemented.

[0064] The technical solutions provided by the embodiments of the present disclosure have the following beneficial effects:

[0065] In the prior art, when a UE needs to invoke an AI network function, it sends a call request to a third party that provides the AI ​​network function. The third party then interacts with the core network device to implement the AI ​​network function call. The technical solution disclosed in this disclosure is to register the AI ​​network function in the core network device. That is, when the core network device is endowed with the AI ​​network function, the UE directly sends the AI ​​network function call request to the core network device. This significantly reduces the transmission cost for the UE to obtain the AI ​​network function service while greatly improving flexibility. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following briefly introduces the drawings required for describing the embodiments of the present disclosure.

[0067] FIG1 is a flow chart of a communication method performed by a UE according to an embodiment of the present disclosure;

[0068] FIG2 is a flow chart of a communication method performed by a core network device according to an embodiment of the present disclosure;

[0069] FIG3 is a schematic diagram of interaction between a UE and a core network device provided by an embodiment of the present disclosure;

[0070] FIG4 is a flow chart of a communication method performed by an AMF according to an embodiment of the present disclosure;

[0071] FIG5 is a flow chart of a communication method performed by SMF according to an embodiment of the present disclosure;

[0072] FIG6 is a flow chart of a communication method performed by a PCF according to an embodiment of the present disclosure;

[0073] FIG7 is a flow chart of a communication method performed by a UPF according to an embodiment of the present disclosure;

[0074] FIG8 is a flow chart of a communication method provided by an embodiment of the present disclosure;

[0075] FIG9 is a schematic structural diagram of a UE provided in an embodiment of the present disclosure;

[0076] FIG10 is a schematic structural diagram of a core network device provided in an embodiment of the present disclosure;

[0077] FIG11 is a schematic structural diagram of an AMF provided in an embodiment of the present disclosure;

[0078] FIG12 is a schematic structural diagram of an SMF provided in an embodiment of the present disclosure;

[0079] FIG13 is a schematic structural diagram of a PCF provided in an embodiment of the present disclosure;

[0080] FIG14 is a schematic structural diagram of a UPF provided by an embodiment of the present disclosure;

[0081] FIG15 is a schematic structural diagram of a communication system provided by an embodiment of the present disclosure;

[0082] FIG16 is a schematic structural diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0083] The following describes embodiments of the present disclosure in conjunction with the accompanying drawings. It should be understood that the embodiments described below in conjunction with the accompanying drawings are exemplary descriptions for explaining the technical solutions of the embodiments of the present disclosure and do not constitute a limitation on the technical solutions of the embodiments of the present disclosure.

[0084] Those skilled in the art will understand that, unless otherwise stated, the singular forms "a", "an" and "the" used herein may also include plural forms. It should be further understood that the terms "including" and "comprising" used in the embodiments of the present disclosure mean that the corresponding features can be implemented as the presented features, information, data, steps, operations, elements and / or components, but do not exclude implementation as other features, information, data, steps, operations, elements, components and / or combinations thereof supported by the present technical field. It should be understood that when we say that an element is "connected" or "coupled" to another element, the element can be directly connected or coupled to the other element, or it can refer to the element and the other element establishing a connection relationship through an intermediate element. In addition, the "connection" or "coupling" used here can include wireless connection or wireless coupling. The term "and / or" used here indicates at least one of the items defined by the term, for example, "A and / or B" can be implemented as "A", or as "B", or as "A and B".

[0085] In order to make the objectives, technical solutions and advantages of the present disclosure more clear, the embodiments of the present disclosure will be further described in detail below with reference to the accompanying drawings.

[0086] The communication method, system, core network device, electronic device, and computer-readable storage medium provided in the present disclosure are intended to solve the above technical problems in the prior art.

[0087] Among them, the method and the device are based on the same application concept. Since the principles of solving problems by the method and the device are similar, the implementation of the device and the method can refer to each other, and the repeated parts will not be repeated.

[0088] In addition, the technical solution provided by the embodiment of the present disclosure can be applicable to a variety of systems, especially 5G systems. For example, applicable systems can be Global System Of Mobile Communication (GSM) systems, Code Division Multiple Access (CDMA) systems, Wideband Code Division Multiple Access (WCDMA) General Packet Radio Service (GPRS) systems, Long Term Evolution (LTE) systems, LTE Frequency Division Duplex (FDD) systems, LTE Time Division Duplex (TDD) systems, Long Term Evolution Advanced (LTE-A) systems, Universal Mobile Telecommunication System (UMTS), Worldwide Interoperability For Microwave Access (WiMAX) systems, 5G New Radio (NR) systems, etc. These various systems include terminal devices and network devices. The system may also include core network equipment, such as the Evolved Packet System (EPS), 5G System (5GS), etc.

[0089] The terminal (device) involved in the embodiments of the present disclosure may refer to a device that provides voice and / or data connectivity to a user, a handheld device with wireless connection function, or other processing devices connected to a wireless modem. In different systems, the name of the terminal device may also be different. For example, in a 5G system, the terminal device may be called User Equipment (UE). A wireless terminal device can communicate with one or more core network devices (CN) via a radio access network (RAN). The wireless terminal device can be a mobile terminal device, such as a mobile phone (or "cellular" phone) and a computer with a mobile terminal device. For example, it can be a portable, pocket-sized, handheld, computer-built-in or vehicle-mounted mobile device that exchanges voice and / or data with a radio access network. For example, Personal Communication Service (PCS) phones, cordless phones, Session Initiated Protocol (SIP) phones, Wireless Local Loop (WLL) stations, Personal Digital Assistants (PDAs), and other devices. The wireless terminal device may also be referred to as a system, a subscriber unit (Subscriber Unit), a subscriber station (Subscriber Station), a mobile station (Mobile Station), a mobile station (Mobile), a remote station (Remote Station), an access point (Access Point), a remote terminal device (Remote Terminal), an access terminal device (Access Terminal), a user terminal device (User Terminal), a user agent (User Agent), or a user device (User Device), but is not limited in the embodiments of the present disclosure.

[0090] The following describes several exemplary embodiments to illustrate the technical solutions of the embodiments of the present disclosure and the technical effects produced by the technical solutions of the present disclosure. It should be noted that the following embodiments can refer to, draw on, or combine with each other, and the same terms, similar features, and similar implementation steps in different embodiments will not be repeated.

[0091] An embodiment of the present disclosure provides a communication method, which is executed by a UE. As shown in FIG1 , the method includes:

[0092] Step S101: Send an AI network function call request, where the AI ​​network function call request is used to instruct the core network device to provide AI network function services to the UE.

[0093] In one embodiment, an AI network function is a network function involving AI technology provided by a network-side device; wherein the network function is a function implemented by a network element; a core network may include multiple network elements and multiple network functions, wherein one network element may implement one or more network functions, and a network function may be implemented by one network element or multiple network elements.

[0094] In one embodiment, the AI ​​network function is at least one of a network function that performs AI processing through an AI model (also referred to as a neural network model) and a network function that outputs an AI model.

[0095] The network function for performing AI processing through an AI model may illustratively include at least one of the following: a network function for performing data processing on audio data through an AI model, a network function for performing data processing on video data through an AI model, a network function for performing data processing on text through an AI model, etc. The network function for outputting an AI model may illustratively include at least one of the following: a network function for outputting an AI model for performing AI processing on audio data, a network function for outputting an AI model for performing AI processing on video data, a network function for outputting an AI model for performing AI processing on text, etc. It should be understood that, before performing AI processing through an AI model or outputting an AI model, the embodiments of the present disclosure may further train the AI ​​model, so that AI processing can be performed through the trained AI model, or the trained AI model can be output.

[0096] Of course, the above exemplary description of the AI ​​network function is intended only to facilitate understanding and does not limit the scope of the embodiments of the present disclosure. Specifically, an AI network function invocation request can include sending data to be processed to a core network device and receiving a service result of the AI ​​network function from the core network device. The service result of the AI ​​network function can be data returned after the corresponding AI network function processes the data to be processed, or it can be the AI ​​model corresponding to the AI ​​network function. In one embodiment, the AI ​​network function has been registered with the core network device, meaning that the core network device is able to determine the AI ​​network function currently available for the UE. In one possible implementation, the AI ​​network function may include an AI network function provided by a third party; the third party referred to in this disclosure is an entity that is neither a UE nor a core network device, for example, a network element or network entity that provides AI technology services. In another possible implementation, the AI ​​network function may include an AI network function provided by a core network device; for example, it may be a network function, network element, or network entity provided in the core network that provides AI technology services. In another possible implementation, the AI ​​network function may include an AI network function provided by a core network device and an AI network function provided by a third party; thereby enabling the core network to schedule multiple AI network functions.

[0097] In one embodiment, a core network device stores AI network function registration information, which includes information about AI network functions registered in the core network device. In some embodiments, the AI ​​network function registration information may include at least one of the following information: a unique identifier of the AI ​​network function, capabilities of the AI ​​network function, information about the provider of the AI ​​network function, a calling address for the AI ​​network function, parameters required when calling the AI ​​network function, etc.

[0098] In some embodiments, the capability of an AI network function is used to characterize the data type of data to be processed that the AI ​​network function is applicable to, or the accuracy, processing precision, etc. of the AI ​​network function. For example, the capability of an AI network function that performs AI processing on audio indicates that the data type to be processed is audio; the capability of an AI network function that outputs an AI model that performs AI processing on text indicates that the data type to be processed is text.

[0099] By including the capability of the AI ​​network function in the AI ​​network function registration information, the UE includes the capability of the AI ​​network function in the AI ​​network function call request accordingly, and the core network device can determine the AI ​​network function requested by the UE in combination with the capabilities of each registered AI network function. For example, if the capability of the AI ​​network function included in the AI ​​network function call request is that the data to be processed by the AI ​​network function is video, then the subsequent core network device determines that the AI ​​network function requested by the UE is an AI network function that is at least applicable to AI processing of videos. For another example, if the capability of the AI ​​network function included in the AI ​​network function call request is high-precision AI processing or low-precision AI processing of images, then the subsequent core network device determines that the AI ​​network function requested by the UE is an AI network function that is applicable to high-precision AI processing or low-precision AI processing of images. In one embodiment, the AI ​​network function registration information is stored in the network repository function (NRF) of the core network device.

[0100] In one embodiment, the core network device stores policy control and charging (PCC) rules for calling each registered AI network function.

[0101] In some embodiments, the PCC rules for invoking each registered AI network function are stored in a Policy Control Function (PCF).

[0102] In some embodiments, the AI ​​network function call request may include a service identifier, the capabilities of the AI ​​network function, and data to be processed indicated by the UE.

[0103] In other embodiments, at least one of the service identifier, the capability of the AI ​​network function, and the AI ​​network function call request including the data to be processed indicated by the UE may also be recorded in the AI ​​network function call request.

[0104] The service identifier is used to identify the UE. In one embodiment, the core network device determines the AI ​​network function requested by the UE based on the capabilities of the AI ​​network function indicated in the AI ​​network function call request, and then establishes a correspondence between the AI ​​network function requested by the UE and the service identifier in the AI ​​network function call request. In this way, when the AI ​​network function is updated in some cases, the core network device can search for the corresponding service identifier based on the updated AI network function to determine which UEs are involved in the updated AI network function. For those UEs that request the updated AI network function, the core network device can provide the service of the updated AI network function to those UEs.

[0105] In some embodiments, the data to be processed indicated by the UE may be provided by the UE itself, or may not be provided by the UE itself, or may be partly provided by the UE itself and partly provided by the UE itself. For data to be processed that is not provided by the UE itself, the UE may instruct the core network device to obtain it by carrying the network data name (DNN) in the AI ​​network function call request, that is, the data to be processed indicated by the UE may be provided by the DNN.

[0106] For example, when a UE requests to beautify a selfie using AI technology, the AI ​​network function call request sent by the UE includes a selfie from the UE and the network data name corresponding to the special effects material required for the beautification process. After receiving the AI ​​network function call request, the core network device obtains the corresponding special effects material according to the DNN in the AI ​​network function call request, and then performs beautification on the obtained special effects material and selfie.

[0107] In the related art, when a UE needs to call an AI network function, it sends a call request to a third party that provides the AI ​​network function, and then the third party and the core network device interact to implement the AI ​​network function call. The technical solution disclosed in the present disclosure stores AI network function registration information in the core network device, and the AI ​​network function registered in the core network device can be determined through the AI ​​network function registration information; therefore, the UE can directly send an AI network function call request to the core network device, so that the transmission cost for the UE to obtain the AI ​​network function service is significantly reduced, and the flexibility is greatly improved. In some embodiments, the AI ​​network function may include the AI ​​network function that can be provided by the core network device and / or the AI ​​network function that can be provided by a third party, so that the AI ​​network function requested by the UE can be scheduled through the core network device. In some embodiments, the AI ​​network function may include the AI ​​network function that can be provided by a third party, so that the AI ​​network function requested by the UE can be scheduled through the core network. In an optional embodiment, the communication method of the embodiment of the present disclosure includes:

[0108] Step S201: In response to obtaining the service result of the AI ​​network function, the UE sends a confirmation message to the core network device, where the confirmation message is used to instruct the core network device to release the resources of the AI ​​network function requested by the UE.

[0109] The service result of the AI ​​network function is the result returned by the core network device after processing the AI ​​network function call request. The service result of the AI ​​network function can be the data returned after the corresponding AI network function processes the data to be processed indicated by the UE, or it can be the AI ​​model corresponding to the AI ​​network function.

[0110] In one embodiment, the service result of the AI ​​network function includes at least one of the following:

[0111] The result of processing the data to be processed indicated by the UE through the corresponding AI model;

[0112] A neural network model capable of performing AI processing on data to be processed as indicated by the UE. For example, when the AI ​​network function call request sent by the UE includes a photo to be AI-repaired (the photo can be provided by the UE or by a network data provider), the service result can be the AI-repaired photo or the neural network model used to perform AI-repair on the photo.

[0113] For another example, when the AI ​​network function call request sent by the UE includes the capability of the AI ​​network function that the AI ​​network function is applicable to, and the data to be processed is a photo to be AI repaired, the service result can be a photo after AI repair, or it can be a neural network model with the ability to perform AI repair on the image.

[0114] After obtaining the service result of the AI ​​network function, the UE of the embodiment of the present disclosure instructs the core network device to release the resources of the AI ​​network function requested by the UE to ensure the performance of the core network device.

[0115] In one embodiment, the resources of the AI ​​network function requested by the UE may include various data in the AI ​​network function call request and at least one of the PPC rules related to the AI ​​network function requested by the UE. Those skilled in the art will appreciate that step S201 may be performed alone or in combination with step S101, or in combination with the steps of any other embodiment of the present disclosure.

[0116] An embodiment of the present disclosure provides a communication method, which is executed by a core network device. As shown in FIG2 , the method includes:

[0117] Step S301: In response to obtaining an AI network function call request, determine a target PCC rule according to the AI ​​network function call request and AI network function registration information.

[0118] In some embodiments, the AI ​​network function provided by a third party has been registered in the core network device, so the core network device can generate AI network function registration information based on the registered AI network function, and the AI ​​network function registration information includes information about the AI ​​network function registered in the core network device.

[0119] In some embodiments, the AI ​​network function registration information may include at least one of the following information:

[0120] The unique identifier of the AI ​​network function, the capabilities of the AI ​​network function, the information of the provider of the AI ​​network function, and the calling address of the AI ​​network function. The target PCC rule of the embodiment of the present disclosure is related to the AI ​​network function requested by the UE. The core network device can pre-define PCC rules for calling each AI network function. After determining that the UE requests the AI ​​network function, the target PCC rules that match the AI ​​network function requested by the UE can be determined from the pre-defined PCC rules for calling each AI network function.

[0121] In some embodiments, the AI ​​network function, the AI ​​network function call request, and the AI ​​network function registration information may refer to the embodiment corresponding to step S101.

[0122] In some embodiments, the target PPC rule may include a unique identifier of the target PCC rule, a unique identifier of the AI ​​network function requested by the UE, and task allocation information of the AI ​​network function requested by the UE.

[0123] In other embodiments, the target PCC rule may also include at least one of a unique identifier of the target PCC rule, a unique identifier of the AI ​​network function requested by the UE, and task allocation information of the AI ​​network function requested by the UE.

[0124] In some embodiments, the task allocation information is used to indicate the execution steps and rules of each AI network function requested by the UE during the AI ​​processing process.

[0125] In some embodiments, the core network device can determine the AI ​​network function requested by the UE based on the capabilities of the AI ​​network function indicated in the AI ​​network function call request and the capabilities of each registered AI network function recorded in the AI ​​network function registration information. The core network device can further use the PCC rules for calling each AI network function predefined in the core network device to determine the AI ​​network function requested by the UE and the target PCC rules related to the AI ​​network function requested by the UE.

[0126] The core network device of the embodiment of the present disclosure determines the AI ​​network function requested by the UE and the target PCC rule related to the AI ​​network function requested by the UE based on the AI ​​network function call request and the AI ​​network function registration information in response to obtaining the AI ​​network function call request sent by the UE, thereby providing the UE with reliable and systematic AI services and laying the foundation for an AI-based intelligent network system.

[0127] As an optional embodiment, the communication method of the embodiment of the present disclosure further includes:

[0128] Step S401: The core network device establishes a connection with a target network element and issues a target PCC rule; the target network element is used to implement the AI ​​network function requested by the UE.

[0129] Step S402: Call the AI ​​network function requested by the UE based on the target PCC rule.

[0130] The core network device of the embodiment of the present disclosure includes a target network element for implementing the AI ​​network function requested by the UE. After determining the AI ​​network function requested by the UE, the core network device establishes a connection with the target network element for implementing the AI ​​network function requested by the UE. In the embodiment of the present disclosure, the number of AI network functions implemented by a target network element can be one or more.

[0131] By establishing a connection with the target network element that implements the AI ​​network function requested by the UE and issuing the target PCC rule, the AI ​​network function requested by the UE can provide the AI ​​network function service to the UE based on the target PCC rule.

[0132] As an optional embodiment, the communication method of the embodiment of the present disclosure further includes:

[0133] The core network device responds to obtaining the service result of the AI ​​network function, which is the result returned after the core network device processes the AI ​​network function call request, and sends the service result to the UE.

[0134] The core network device of the disclosed embodiment may send all service results to the UE at once after obtaining all service results, or may send a portion of the service results to the UE each time a portion of the service results is obtained. For example, when the data to be processed by the AI ​​network function is a video, the AI ​​processing result of the entire video may be obtained and then sent to the UE as the service result; or the AI ​​processing result of a portion of the video frame may be obtained each time and then sent to the UE as the portion of the service result.

[0135] In some embodiments, the service result of the AI ​​network function may refer to the embodiment corresponding to step S201. For example, the service result of the AI ​​network function is any one of the following:

[0136] The result of processing the data to be processed indicated by the UE through the corresponding AI model;

[0137] A neural network model capable of performing AI processing on data to be processed indicated by the UE.

[0138] The data to be processed indicated by the UE may refer to the embodiment corresponding to step S101.

[0139] As an optional embodiment, the communication method of the embodiment of the present disclosure further includes:

[0140] The core network device releases the resources of the AI ​​network function requested by the UE in response to the confirmation message returned after obtaining the result of the UE receiving the service.

[0141] Please refer to FIG3 , which exemplarily shows a schematic diagram of interaction between a UE and a core network device according to an embodiment of the present disclosure. As shown in the figure, the interaction process includes:

[0142] Step S501: Complete registration of the AI ​​network function in the core network device, store the AI ​​network function registration information in the core network device, and define PCC rules for calling each registered AI network function.

[0143] Step S502: The UE sends an AI network function call request to the core network device;

[0144] Step S503: In response to obtaining the AI ​​network function call request, the core network device determines a target PCC rule related to the AI ​​network function requested by the UE according to the AI ​​network function call request and the AI ​​network function registration information.

[0145] Step S504: The core network device establishes a connection with the target network element and issues a target PCC rule. Based on the target PCC rule, the AI ​​network function requested by the UE is invoked. The target network element is used to implement the AI ​​network function requested by the UE.

[0146] Step S505: In response to obtaining the service result of the AI ​​network function, the core network device sends the service result to the UE;

[0147] Step S506: In response to obtaining the service result of the AI ​​network function, the UE sends a confirmation message to the core network device;

[0148] Step S507: In response to the confirmation message returned by the UE after receiving the service result, the core network device releases the resources of the AI ​​network function requested by the UE.

[0149] An embodiment of the present disclosure provides a communication method, which is performed by an access and mobility management function (AMF) in a core network device. As shown in FIG4 , the method includes:

[0150] Step S601: In response to obtaining an AI network function call request, forward the AI ​​network function call request to a session management function (SMF) in a core network device.

[0151] In one embodiment, the AI ​​network function call request may refer to the embodiment corresponding to step S101.

[0152] In one embodiment, the UE may forward the AI ​​network function call request to the AMF via the (R)AN. The AMF in the embodiment of the present disclosure forwards the AI ​​network function call request to the SMF, so that the SMF can send the AI ​​network function call request to the PCF, laying the foundation for the PCF to specify the PCC rules of the UE.

[0153] As an optional embodiment, if the AI ​​network function call request includes the data to be processed indicated by the UE, the AMF responds to obtaining the AI ​​network function call request, further including: storing the data to be processed indicated by the UE in the unstructured data storage function (UDSF) in the core network device.

[0154] In some embodiments, the data to be processed indicated by the UE may refer to the embodiment corresponding to step S101. The AMF of the embodiment of the present disclosure stores the data to be processed indicated by the UE in the UDSF in the core network device, thereby laying the foundation for other functional entities in the subsequent core network device, such as the user plane function (UPF), to call the AI ​​network function to provide AI services for the UE.

[0155] As an optional embodiment, the communication method on the AMF side also includes: in response to obtaining the service result of the AI ​​network function, sending the service result to the UE.

[0156] In some embodiments, the AMF may obtain the service result of the AI ​​network function from the SMF. The service result of the AI ​​network function may refer to the embodiment corresponding to step S201.

[0157] In some embodiments, the service result of the AI ​​network function may be obtained by the UPF and sent by the UPF to the SMF.

[0158] In some embodiments, the AMF may transmit the service result to the UE via the (R)AN.

[0159] In response to obtaining the service result of the AI ​​network function, the AMF of the present disclosure sends the service result to the UE so that the UE can obtain the service result.

[0160] As an optional embodiment, the communication method on the AMF side further includes:

[0161] In response to the confirmation message returned by the UE after receiving the service result, the SMF is instructed to release the resources of the AI ​​network function requested by the UE.

[0162] In some embodiments, the AMF may receive the confirmation message sent by the UE via the (R)AN.

[0163] In some embodiments, the UE generates a confirmation message upon receiving the service result of the AI ​​network function.

[0164] After learning that the UE has obtained the service result, the AMF in the embodiment of the present disclosure instructs the SMF to promptly release the resources of the AI ​​network function requested by the UE to maintain the normal operation of the core network equipment.

[0165] The present disclosure provides a communication method, which is executed by an SMF in a core network device. As shown in FIG5 , the method includes:

[0166] Step S701: In response to obtaining an AI network function call request, obtain AI network function registration information;

[0167] Step S702: Send the AI ​​network function call request and AI network function registration information to the PCF.

[0168] In some embodiments, the SMF may obtain an AI network function call request from the AMF in the core network device. The AI ​​network function call request and the AI ​​network function registration information may refer to the embodiment corresponding to step S101.

[0169] In some embodiments, the SMF may obtain the AI ​​network function registration information from the NRF.

[0170] The SMF of the embodiment of the present disclosure responds to obtaining the AI ​​network function call request of the UE and the AI ​​network function registration information containing information of the AI ​​network function registered in the core network device, and sends the AI ​​network function call request and the AI ​​network function registration information to the policy control function PCF, laying the foundation for the PCF to generate PCC rules.

[0171] As an optional embodiment, the communication method on the SMF side further includes:

[0172] In response to obtaining the PCC rules, the PCC rules are sent to a user plane function (UPF).

[0173] In some embodiments, the SMF may obtain target PCC rules from the PCF.

[0174] The target PCC rule in the embodiment of the present disclosure is related to the AI ​​network function requested by the UE, that is, the target PCC rule is the PCC rule that calls the AI ​​network function requested by the UE.

[0175] As an optional embodiment, the communication method on the SMF side further includes:

[0176] In response to obtaining the service result of the AI ​​network function, the service result is sent to the AMF in the core network device.

[0177] In some embodiments, the SMF may obtain the service result of the AI ​​network function from the UPF. For the service result of the AI ​​network function, reference may be made to the embodiment corresponding to step S201.

[0178] As an optional embodiment, the communication method on the SMF side further includes:

[0179] Receive an indication from the AMF to release the resources of the AI ​​network function requested by the UE according to the indication.

[0180] In some embodiments, when the UE receives the service result, it sends a confirmation message. The confirmation message is used to instruct the SMF to release the resources of the AI ​​network function requested by the UE. After receiving the confirmation message, the AMF forwards the confirmation message to the SMF, so that the SMF releases the resources of the AI ​​network function requested by the UE according to the received confirmation message.

[0181] The present disclosure provides a communication method, which is executed by a PCF in a core network device. As shown in FIG6 , the method includes:

[0182] Step S801: In response to obtaining an AI network function call request and AI network function registration information, determine a target PCC rule.

[0183] The AI ​​network function call request is used to instruct the core network device to provide the AI ​​network function service to the UE. The AI ​​network function registration information includes information about the AI ​​network function registered in the core network device. The target PCC rule is related to the AI ​​network function requested by the UE.

[0184] In some embodiments, the PCF may obtain the AI ​​network function call request and the AI ​​network function registration information from the SMF. The AI ​​network function call request and the AI ​​network function registration information may refer to the embodiment corresponding to step S101.

[0185] As an optional embodiment, the communication method on the PCF side further includes:

[0186] Send the target PCC rules to the SMF in the core network device.

[0187] The present disclosure sends the target PCC rule to the SMF, so that the SMF forwards the target PCC rule to the UPF, and calls the AI ​​network function requested by the UE through the UPF, thereby giving the core network the service capability of the AI ​​network function.

[0188] As an optional embodiment, the communication method on the PCF side further includes:

[0189] The target PCC rules are stored in the user data register UDR in the core network device.

[0190] The present disclosure provides a communication method, which is executed by a UPF in a core network device. As shown in FIG7 , the method includes:

[0191] S901. In response to obtaining a target PCC rule, establish a connection with a target network element and issue the PCC rule; the target network element is used to implement the AI ​​network function requested by the UE;

[0192] S902: Call the AI ​​network function requested by the UE according to the target PCC rule.

[0193] In the embodiment of the present disclosure, the UPF invokes the AI ​​network function requested by the UE to grant the core network the service capability of the AI ​​network function. The AI ​​network function can refer to the embodiment corresponding to step S101.

[0194] As an optional embodiment, calling the AI ​​network function requested by the UE according to the target PCC rule includes:

[0195] The data to be processed indicated by the UE and stored in the UDSF in the core network device is obtained, and the data to be processed indicated by the UE is shared with the target network element.

[0196] In some embodiments, the AI ​​network function can interact with the DNN through the UPF.

[0197] As an optional embodiment, the AI ​​network function requested by the UE is called according to the PCC rule, and then the following steps are further included:

[0198] In response to obtaining the service result of the AI ​​network function, the service result is sent to the SMF.

[0199] Among them, the service results of the AI ​​network function can refer to the embodiment corresponding to step S201.

[0200] An embodiment of the present disclosure provides a communication method, as shown in FIG8 , which includes the following steps:

[0201] 1) When the UE pre-invokes the service of the AI ​​network function, it sends an AI network function invocation request to the AMF to start the invocation process. The AI ​​network function invocation request is forwarded to the AMF by the (R)AN. The AI ​​network function invocation request includes the data to be processed by the AI ​​network function;

[0202] 2a)AMF forwards the AI ​​network function call request to SMF;

[0203] 2b) The AMF stores the data to be processed indicated by the UE in the UDSF;

[0204] 3) In response to the AI ​​network function call request, the SMF queries the NRF to obtain the AI ​​network function registration information;

[0205] 4) The SMF sends the AI ​​network function call request and AI network function registration information to the PCF; the AI ​​network function registration information includes information about the AI ​​network function registered in the core network device. In response to obtaining the AI ​​network function call request and the AI ​​network function registration information, the PCF determines the target PCC rule for calling the AI ​​network function requested by the UE;

[0206] 5a) PCF stores the target PCC rules in UDR;

[0207] 5b) The PCF sends the target PCC rule to the SMF. In response to obtaining the target PCC rule, the SMF sends the target PCC rule to the UPF.

[0208] 6) In response to obtaining the target PCC rule, the UPF establishes a connection with the target network element and issues the PCC rule. Based on the PCC rule, the AI ​​network function requested by the UE is called, and the target network element is used to implement the AI ​​network function requested by the UE.

[0209] 7) During the execution of the AI ​​network function service, the target network element can exchange data with the DNN (not shown in the figure) and UDSF through the UPF to achieve data sharing between multiple AI network functions;

[0210] 8) The UPF sends the service result to the SMF in response to obtaining the service result of the AI ​​network function;

[0211] 9) SMF sends the service result to AMF, which then sends the service result to UE via (R)AN;

[0212] 10) In response to obtaining the service result, the UE sends a confirmation message to the AMF. The confirmation message is used to instruct the SMF to release the resources of the AI ​​network function requested by the UE. The AMF forwards the confirmation information to the SMF;

[0213] 11) In response to the Acknowledge message, the SMF releases the resources of the AI ​​network function requested by the UE.

[0214] An embodiment of the present disclosure provides a UE, as shown in FIG9 , including:

[0215] The call request sending module 101 is used to send an artificial intelligence (AI) network function call request, where the AI ​​network function call request is used to instruct the core network device to provide the AI ​​network function service to the UE;

[0216] Among them, AI network functions are network functions involving AI technology provided by network-side devices; AI network function registration information is stored in the core network device, and the AI ​​network function registration information includes information about AI network functions registered in the core network device.

[0217] The UE of the embodiments of the present disclosure can execute the method provided on the UE side of the embodiments of the present disclosure, and the implementation principles are similar. The actions performed by each module in the UE of each embodiment of the present disclosure correspond to the steps in the communication method on the UE side of each embodiment of the present disclosure. For the detailed functional description of each module of the UE, please refer to the description in the corresponding method shown in the previous text, and will not be repeated here.

[0218] The present disclosure provides a core network device, as shown in FIG10 , including:

[0219] A rule determination module 201 is configured to, in response to obtaining an AI network function call request, determine a target policy control and charging PCC rule based on the AI ​​network function call request and the AI ​​network function registration information;

[0220] Among them, the AI ​​network function call request is used to instruct the core network device to provide the AI ​​network function service to the UE; the AI ​​network function registration information includes information about the AI ​​network function registered in the core network device, and the target PCC rule is related to the AI ​​network function requested by the UE; the AI ​​network function is a network function involving AI technology provided by the network side device.

[0221] The core network device of the embodiment of the present disclosure can execute the method provided by the core network device side of the embodiment of the present disclosure, and the implementation principle is similar. The actions performed by each module in the core network device of each embodiment of the present disclosure correspond to the steps in the communication method on the core network device side of each embodiment of the present disclosure. For the detailed functional description of each module of the core network device, please refer to the description in the corresponding method shown in the previous text, and will not be repeated here.

[0222] The present disclosure provides an AMF, as shown in FIG11 , including:

[0223] The forwarding module 301 is configured to forward the AI ​​network function call request to the session management function SMF in the core network device in response to obtaining the AI ​​network function call request;

[0224] The AI ​​network function call request is used to instruct the core network device to provide the AI ​​network function service to the UE; the AI ​​network function is a network function involving AI technology provided by the network side device.

[0225] The AMF of the embodiments of the present disclosure can execute the method provided by the AMF side of the embodiments of the present disclosure, and the implementation principles are similar. The actions performed by each module in the AMF of each embodiment of the present disclosure correspond to the steps in the communication method on the AMF side of each embodiment of the present disclosure. For the detailed functional description of each module of the AMF, please refer to the description in the corresponding method shown in the previous text, which will not be repeated here.

[0226] The present disclosure provides an SMF, as shown in FIG12 , including:

[0227] A registration information acquisition module 401 is configured to obtain AI network function registration information in response to an AI network function call request;

[0228] The integrated sending module 402 is configured to send the AI ​​network function call request and the AI ​​network function registration information to the policy control function PCF in the core network device;

[0229] Among them, the AI ​​network function call request is used to instruct the core network device to provide AI network function services to the UE, and the AI ​​network function registration information includes information about the AI ​​network function registered in the core network device; the AI ​​network function is a network function involving AI technology provided by the network side device.

[0230] The SMF of the embodiment of the present disclosure can execute the method provided by the SMF side of the embodiment of the present disclosure, and the implementation principle is similar. The actions performed by each module in the SMF of each embodiment of the present disclosure correspond to the steps in the communication method on the SMF side of each embodiment of the present disclosure. For the detailed functional description of each module of the SMF, please refer to the description in the corresponding method shown in the previous text, which will not be repeated here.

[0231] The present disclosure provides a PCF, as shown in FIG13 , including:

[0232] A rule formulation module 501 is configured to determine a target PCC rule in response to obtaining an AI network function call request and AI network function registration information;

[0233] Among them, the AI ​​network function call request is used to instruct the core network device to provide the AI ​​network function service to the UE, the AI ​​network function registration information includes information about the AI ​​network function registered in the core network device, and the target PCC rule is related to the AI ​​network function requested by the UE; the AI ​​network function is a network function involving AI technology provided by the network side device.

[0234] The PCF of the embodiments of the present disclosure can execute the method provided by the PCF side of the embodiments of the present disclosure, and the implementation principles are similar. The actions performed by each module in the PCF of each embodiment of the present disclosure correspond to the steps in the communication method on the PCF side of each embodiment of the present disclosure. For the detailed functional description of each module of the PCF, please refer to the description in the corresponding method shown in the previous text, which will not be repeated here.

[0235] The present disclosure provides a UPF, as shown in FIG14 , including:

[0236] The connection module 601 is configured to establish a connection with a target network element and issue the PCC rule in response to obtaining the target PCC rule; the target network element is configured to implement the AI ​​network function requested by the UE;

[0237] A calling module 602 is configured to call the AI ​​network function requested by the UE according to the target PCC rule;

[0238] Among them, the target PCC rule is determined based on the AI ​​network function call request sent by the UE. The target PCC rule is related to the AI ​​network function requested by the UE; the AI ​​network function is a network function involving AI technology provided by the network side device.

[0239] The UPF of the embodiments of the present disclosure can execute the method provided by the UPF side of the embodiments of the present disclosure, and the implementation principle is similar. The actions performed by each module in the UPF of each embodiment of the present disclosure correspond to the steps in the communication method on the UPF side of each embodiment of the present disclosure. For the detailed functional description of each module of the UPF, please refer to the description in the corresponding method shown in the previous text, which will not be repeated here.

[0240] An embodiment of the present disclosure provides a communication system, which is used to execute the method executed by the core network device in the above embodiment.

[0241] A communication system is provided in an embodiment of the present disclosure, as shown in FIG15 , including an access and mobility management function AMF 701 , a session management function SMF 702 , a policy control function PCF 703 and a user plane function UPF 704 .

[0242] An embodiment of the present disclosure provides an electronic device, including a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the steps of a communication method. Compared with related technologies, this method can achieve: in the prior art, when a UE needs to call an AI network function, it sends a call request to a third party that provides the AI ​​network function, and the third party and the core network device interact to implement the AI ​​network function call. The technical solution disclosed in the present disclosure is to register the AI ​​network function in the core network device, that is, when the core network device is endowed with the AI ​​network function, the UE directly sends the AI ​​network function call request to the core network device, so that the transmission cost of the UE obtaining the AI ​​network function service is significantly reduced, while the flexibility is greatly improved.

[0243] In an optional embodiment, an electronic device is provided, as shown in FIG16 , wherein the electronic device 4000 shown in FIG16 includes: a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, such as via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which may be used for data interaction between the electronic device and other electronic devices, such as data transmission and / or data reception. It should be noted that in actual applications, the transceiver 4004 is not limited to one, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present disclosure.

[0244] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the present disclosure. Processor 4001 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0245] Bus 4002 may include a path for transmitting information between the aforementioned components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, for example. Bus 4002 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, FIG16 shows only one thick line, but this does not imply that there is only one bus or only one type of bus.

[0246] The memory 4003 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, other magnetic storage devices, or any other medium that can be used to carry or store computer programs and can be read by a computer, without limitation herein.

[0247] The memory 4003 is used to store the computer program for executing the embodiments of the present disclosure, and the execution is controlled by the processor 4001. The processor 4001 is used to execute the computer program stored in the memory 4003 to implement the steps shown in the above method embodiments.

[0248] An embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps and corresponding contents of the aforementioned method embodiment can be implemented.

[0249] The embodiments of the present disclosure further provide a computer program product, including a computer program, which can implement the steps and corresponding contents of the aforementioned method embodiments when executed by a processor.

[0250] The terms "first," "second," "third," "fourth," "1," "2," and the like (if any) in the description and claims of the present disclosure and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or sequential sequence. It should be understood that the terms used in this manner are interchangeable where appropriate, such that the embodiments of the present disclosure described herein can be practiced in an order other than that shown or described.

[0251] It should be understood that, although the flowcharts of the embodiments of the present disclosure indicate the various operation steps by arrows, the order of implementation of these steps is not limited to the order indicated by the arrows. Unless otherwise clearly stated herein, in some implementation scenarios of the embodiments of the present disclosure, the implementation steps in each flowchart can be performed in other orders as required. In addition, some or all of the steps in each flowchart may include multiple sub-steps or multiple stages based on the actual implementation scenario. Some or all of these sub-steps or stages can be executed at the same time, and each sub-step or stage in these sub-steps or stages can also be executed at different times. In scenarios where the execution times are different, the order of execution of these sub-steps or stages can be flexibly configured as required, and the embodiments of the present disclosure do not limit this.

[0252] The above are only optional implementation methods for some implementation scenarios of the present disclosure. It should be pointed out that for ordinary technicians in this technical field, without departing from the technical concept of the solution of the present disclosure, other similar implementation methods based on the technical ideas of the present disclosure are also within the protection scope of the embodiments of the present disclosure.

Claims

1. A communication method, characterized in that: Executed by user equipment UE, the method includes: Sending an artificial intelligence (AI) network function call request, where the AI ​​network function call request is used to instruct the core network device to provide the AI ​​network function service to the UE; the AI ​​network function is a network function involving AI technology provided by the network side device; The core network device stores AI network function registration information, and the AI ​​network function registration information includes information of the AI ​​network function registered in the core network device.

2. The method according to claim 1, characterized in that Also includes: In response to obtaining the service result of the AI ​​network function, sending a confirmation message to the core network device, where the confirmation message is used to instruct the core network device to release the resources of the AI ​​network function requested by the UE; the service result of the AI ​​network function is the result returned by the core network device after processing the AI ​​network function call request.

3. The method according to claim 2, characterized in that The service result of the AI ​​network function is any of the following: The result of processing the data to be processed indicated by the UE through the corresponding AI model; A neural network model capable of performing AI processing on data to be processed indicated by the UE.

4. A communication method, characterized in that: Executed by a core network device, the method includes: In response to obtaining the AI ​​network function call request, determining a target policy control and charging PCC rule based on the AI ​​network function call request and the AI ​​network function registration information; The AI ​​network function call request is used to instruct the core network device to provide the AI ​​network function service to the UE; the AI ​​network function registration information includes information about the AI ​​network function registered in the core network device, and the target PCC rule is related to the AI ​​network function requested by the UE; the AI ​​network function is a network function involving AI technology provided by the network side device.

5. The method according to claim 4, characterized in that Also includes: Establishing a connection with a target network element and issuing the target PCC rule; the target network element is used to implement the AI ​​network function requested by the UE; The AI ​​network function requested by the UE is called based on the target PCC rule.

6. The method according to claim 4, characterized in that Also includes: In response to obtaining the service result of the AI ​​network function, the service result is sent to the UE; the service result of the AI ​​network function is the result returned after the core network device processes the AI ​​network function call request.

7. The method according to claim 6, characterized in that Also includes: In response to obtaining a confirmation message returned by the UE after receiving the service result, releasing the resources of the AI ​​network function requested by the UE.

8. The method according to claim 6, characterized in that The service result of the AI ​​network function is any of the following: The result of processing the data to be processed indicated by the UE through the corresponding AI model; A neural network model capable of performing AI processing on data to be processed indicated by the UE.

9. A communication method, characterized in that: The method is performed by the access and mobility management function AMF in the core network device, and includes: In response to obtaining the AI ​​network function call request, forwarding the AI ​​network function call request to the session management function SMF in the core network device; Among them, the AI ​​network function call request is used to instruct the core network device to provide AI network function services to the UE; the AI ​​network function is a network function involving AI technology provided by the network side device.

10. The method according to claim 9, characterized in that If the AI ​​network function call request includes data to be processed indicated by the UE, then in response to obtaining the AI ​​network function call request, the method further includes: The data to be processed indicated by the UE is stored in an unstructured data storage function UDSF in the core network device.

11. The method according to claim 9, characterized in that Also includes: In response to obtaining a service result of the AI ​​network function, the service result is sent to the UE; the service result of the AI ​​network function is a result returned by the core network device after processing the AI ​​network function call request.

12. The method according to claim 11, characterized in that Also includes: In response to obtaining a confirmation message returned by the UE after receiving the service result, instruct the SMF to release the resources of the AI ​​network function requested by the UE.

13. The method according to claim 11, characterized in that The service result of the AI ​​network function is any of the following: The result of processing the data to be processed indicated by the UE through the corresponding AI model; A neural network model capable of performing AI processing on data to be processed indicated by the UE.

14. A communication method, characterized in that: Executed by a session management function SMF in a core network device, the method includes: In response to the AI ​​network function call request, obtain AI network function registration information; Sending the AI ​​network function call request and the AI ​​network function registration information to the policy control function PCF in the core network device; The AI ​​network function call request is used to instruct the core network device to provide the AI ​​network function service to the UE, and the AI ​​network function registration information includes information about the AI ​​network function registered in the core network device; the AI ​​network function is a network function involving AI technology provided by the network side device.

15. The method according to claim 14, characterized in that The method further comprises: In response to obtaining the target PCC rule, sending the target PCC rule to a user plane function (UPF) in a core network device; The target PCC rule is related to the AI ​​network function requested by the UE.

16. The method according to claim 14, characterized in that Also includes: In response to obtaining the service result of the AI ​​network function, the service result is sent to the AMF in the core network device, where the service result of the AI ​​network function is the result returned by the core network device after processing the AI ​​network function call request.

17. The method according to claim 14, characterized in that Also includes: Receive an indication from the AMF to release resources of the AI ​​network function requested by the UE according to the indication.

18. The method according to claim 16, characterized in that The service result of the AI ​​network function is any of the following: The result of processing the data to be processed indicated by the UE through the corresponding AI model; A neural network model capable of performing AI processing on data to be processed indicated by the UE.

19. A communication method, characterized in that: Executed by a policy control function (PCF) in a core network device, the method includes: In response to obtaining the AI ​​network function call request and the AI ​​network function registration information, determining a target PCC rule; The AI ​​network function call request is used to instruct the core network device to provide the AI ​​network function service to the UE, the AI ​​network function registration information includes information about the AI ​​network function registered in the core network device, and the target PCC rule is related to the AI ​​network function requested by the UE; the AI ​​network function is a network function involving AI technology provided by the network side device.

20. The method according to claim 19, wherein Also includes: The target PCC rule is sent to the SMF in the core network device.

21. The method according to claim 19, wherein Also includes: The target PCC rule is stored in a user data register UDR in a core network device.

22. A communication method, characterized in that: Executed by a user plane function (UPF) in a core network device, the method includes: In response to obtaining the target PCC rule, establishing a connection with a target network element and issuing the target PCC rule; the target network element is used to implement the AI ​​network function requested by the UE; the AI ​​network function is a network function involving AI technology provided by a network-side device; Invoking the AI ​​network function requested by the UE according to the target PCC rule; The target PCC rule is determined according to the AI ​​network function call request sent by the UE, and the target PCC rule is related to the AI ​​network function requested by the UE.

23. The method according to claim 22, characterized in that The calling of the AI ​​network function requested by the UE according to the target PCC rule includes: The data to be processed indicated by the UE and stored in the UDSF in the core network device is obtained, and the data to be processed indicated by the UE is shared with the target network element.

24. The method according to claim 22, characterized in that The calling of the AI ​​network function requested by the UE according to the PCC rule further includes: In response to obtaining the service result of the AI ​​network function, the service result is sent to the SMF; the service result of the AI ​​network function is the result returned after the core network device processes the AI ​​network function call request.

25. The method according to claim 24, characterized in that The service result of the AI ​​network function is any of the following: The result of processing the data to be processed indicated by the UE through the corresponding AI model; A neural network model capable of performing AI processing on data to be processed indicated by the UE.

26. A communication method, characterized in that: include: The AMF receives an AI network function call request sent by the UE, where the AI ​​network function call request is used to instruct the core network device to provide the UE with an AI network function service; the AI ​​network function is a network function involving AI technology provided by the network-side device; The AMF forwards the AI ​​network function call request to the SMF; The SMF obtains the AI ​​network function call request in response to the AI ​​network function call request, obtains the AI ​​network function registration information, and sends the AI ​​network function call request and the AI ​​network function registration information to the policy control function PCF; the AI ​​network function registration information includes information about the AI ​​network function registered in the core network device; The PCF determines, in response to obtaining the AI ​​network function call request and the AI ​​network function registration information, a target PCC rule of the AI ​​network function requested by the UE, and sends the target PCC rule to the SMF; In response to obtaining the target PCC rule, the SMF sends the target PCC rule to the UPF; In response to obtaining the target PCC rule, the UPF establishes a connection with the target network element and issues the target PCC rule, calls the AI ​​network function requested by the UE based on the target PCC rule, and in response to obtaining a service result of the AI ​​network function, sends the service result to the SMF; the target network element is used to implement the AI ​​network function requested by the UE; the service result of the AI ​​network function is the result returned by the core network device after processing the AI ​​network function call request; The SMF sends the service result to the AMF, and the AMF sends the service result to the UE; The AMF receives a confirmation message sent by the UE in response to receiving the service result, where the confirmation message is used to instruct the SMF to release resources of the AI ​​network function requested by the UE; The AMF instructs the SMF to release the resources of the AI ​​network function requested by the UE.

27. A UE, characterized in that: include: A call request sending module, configured to send an artificial intelligence (AI) network function call request, wherein the AI ​​network function call request is used to instruct the core network device to provide the AI ​​network function service to the UE; The AI ​​network function is a network function involving AI technology provided by a network-side device; the core network device stores AI network function registration information, and the AI ​​network function registration information includes information about the AI ​​network function registered in the core network device.

28. A core network device, characterized in that: include: a rule determination module, configured to, in response to obtaining an AI network function call request, determine a target policy control and charging PCC rule based on the AI ​​network function call request and the AI ​​network function registration information; The AI ​​network function call request is used to instruct the core network device to provide the AI ​​network function service to the UE; the AI ​​network function registration information includes information about the AI ​​network function registered in the core network device, and the target PCC rule is related to the AI ​​network function requested by the UE; the AI ​​network function is a network function involving AI technology provided by the network side device.

29. An access and mobility management function AMF, characterized in that include: a forwarding module, configured to, in response to obtaining the AI ​​network function call request, forward the AI ​​network function call request to a session management function SMF in a core network device; The AI ​​network function call request is used to instruct the core network device to provide the AI ​​network function service to the UE; the AI ​​network function is a network function involving AI technology provided by the network side device.

30. A session management function SMF, characterized in that include: A registration information acquisition module, configured to obtain AI network function registration information in response to an AI network function call request; A comprehensive sending module, configured to send the AI ​​network function call request and the AI ​​network function registration information to the policy control function PCF in the core network device; The AI ​​network function call request is used to instruct the core network device to provide the AI ​​network function service to the UE, and the AI ​​network function registration information includes information about the AI ​​network function registered in the core network device; the AI ​​network function is a network function involving AI technology provided by the network side device.

31. A policy control function PCF, characterized in that include: a rule formulation module, configured to determine a target PCC rule in response to obtaining an AI network function call request and the AI ​​network function registration information; The AI ​​network function call request is used to instruct the core network device to provide the AI ​​network function service to the UE, the AI ​​network function registration information includes information about the AI ​​network function registered in the core network device, and the target PCC rule is related to the AI ​​network function requested by the UE; the AI ​​network function is a network function involving AI technology provided by the network side device.

32. A user plane function UPF, characterized in that include: a connection module, configured to, in response to obtaining a target PCC rule, establish a connection with a target network element and issue the PCC rule; the target network element is configured to implement the AI ​​network function requested by the UE; a calling module, configured to call the AI ​​network function requested by the UE according to the target PCC rule; The target PCC rule is determined according to the AI ​​network function call request sent by the UE, and the target PCC rule is related to the AI ​​network function requested by the UE; the AI ​​network function is a network function involving AI technology provided by the network side device.

33. A communication system, characterized in that: The system is used to execute the method according to any one of claims 3 to 6.

34. A communication system, characterized in that Includes at least one of the following network elements: Access and mobility management function AMF for performing the method according to any one of claims 7 to 10; A session management function SMF for executing the method according to any one of claims 11 to 14; A policy control function PCF for executing the method according to any one of claims 15 to 17; A user plane function UPF for executing the method according to any one of claims 18 to 20.

35. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the communication method according to any one of claims 1 to 21 is implemented.

36. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the communication method according to any one of claims 1 to 21 is implemented.

Images