Communication method, first function, second function, and storage medium

Abstract

The application discloses a communication method, which comprises the following steps: a second function sends first information to a first function; wherein the first information comprises relevant information of at least one network function service consumer or supplier which is authorized to access the second function; the first function receives the first information sent by the second function; and the first function determines the way in which the first network function service consumer obtains a target model according to the first information. The application also discloses a first function, a second function and a computer readable storage medium.

Description

TECHNICAL FIELD

[0001] The present application relates to, but is not limited to, the field of communication, and in particular to a communication method, a first function, a second function and a computer readable storage medium. BACKGROUND

[0002] In the field of communication, a machine learning (ML) model combined with a network data analytics function (NWDAF) can provide prediction services in different scenarios.

[0003] Under the existing technical solution of the 5th generation mobile communication technology (5G), the 3rd Generation Partnership Project (3GPP) Standalone (SA) 2 standard solution defines a method for obtaining an ML model based on the NWDAF, that is, a consumer (Consumer) sends an ML model obtaining request to the NWDAF including a model training logic function (MTLF); then, the MTLF determines whether the Consumer directly obtains the ML model from an analytic data repository function (ADRF) or indirectly obtains the ML model based on the MTLF. Here, indirect acquisition means that the ADRF first transmits the ML model to the MTLF, and then the MTLF transmits the ML model to the Consumer. Finally, after the MTLF makes a determination, the ADRF returns the ML model directly or indirectly to the Consumer. It should be noted that since some Consumers do not have the ability to directly access some ADRFs, SA2 hopes to determine by the MTLF which Consumers can access the ADRF.

[0004] However, at present, the access permission processing method based on the ML model acquisition of the NWDAF is proposed in the 3GPP SA3, in which the ADRF updates the access list locally of the ADRF according to the received MTLF local list, so that the list of the ADRF does not work, and further, all network function consumers (NFc) that can access the ML model judged by the MTLF can directly acquire the ML model from the ADRF. Obviously, in the method currently described in the SA3, there is a logical contradiction with the method defined in the SA2 standard scheme. Therefore, it is urgent to provide a new scheme to solve the contradiction between the SA2 and the SA3 schemes. SUMMARY

[0005] Embodiments of the present application provide a communication method, a first function, a second function and a computer readable storage medium, and provide a new method for judging the ML model acquisition based on the NWDAF.

[0006] In a first aspect, embodiments of the present application provide a communication method applied to a first function, comprising:

[0007] receiving first information sent by a second function; wherein the first information comprises related information of at least one network function service consumer or supplier authorized to access the second function;

[0008] determining a way for a first network function service consumer to acquire a target model according to the first information.

[0009] In a second aspect, embodiments of the present application provide a communication method applied to a second function, comprising:

[0010] sending first information to a first function; wherein the first information comprises related information of at least one network function service consumer or supplier authorized to access the second function.

[0011] In a third aspect, a first function is provided, comprising:

[0012] a first receiving module configured to receive first information sent by a second function; wherein the first information comprises related information of at least one network function service consumer or supplier authorized to access the second function;

[0013] a first processing module configured to determine a way for a first network function service consumer to acquire a target model according to the first information.

[0014] In a fourth aspect, a second function is provided, comprising:

[0015] The second sending module is configured to send first information to the first function, wherein the first information comprises relevant information of at least one network function service consumer or provider authorized to access the second function.

[0016] In a fifth aspect, a first function comprises:

[0017] A first memory configured to store executable instructions.

[0018] A first processor configured to execute the executable instructions stored in the first memory to implement the communication method.

[0019] In a sixth aspect, a second function comprises:

[0020] A second memory configured to store executable instructions.

[0021] A second processor configured to execute the executable instructions stored in the second memory to implement the communication method.

[0022] In a seventh aspect, an embodiment of the present application provides a chip for implementing the communication method; the chip comprises a processor configured to call and run a computer program from a memory, so that a device installed with the chip executes the communication method.

[0023] In an eighth aspect, an embodiment of the present application provides a computer readable storage medium for storing a computer program, the computer program causing a computer to execute the communication method.

[0024] In a ninth aspect, an embodiment of the present application provides a computer program product comprising computer program instructions, the computer program instructions causing a computer to execute the communication method.

[0025] In a tenth aspect, an embodiment of the present application provides a computer program which, when running on a computer, causes the computer to execute the communication method.

[0026] This application, by sending the first information of the second function, namely the ADRF (Advanced Access RF), namely the list of authorized access NFs or vendors, to the first function, namely the MTLF, enables the MTLF to understand the ADRF's permissions. After determining that the first NFc has permission to access the ML model, the MTLF can compare the information corresponding to the first NFc with the NF or vendor list when it receives subsequent ML model retrieval requests from the first NFc to confirm whether the first NFc has permission to access the ADRF. This allows the MTLF to determine whether the first NFc directly or indirectly retrieves the ML model. This resolves the logical contradiction between the method proposed in SA3 and the method defined in the SA2 standard scheme mentioned in related technologies. Furthermore, the approach in this application, where the MTLF determines whether the first NFc directly or indirectly retrieves the ML model based on the authorized access NF or vendor list, compared to the SA3 scheme where the MTLF determines that any NFc with access to the ML model can directly retrieve it from the ADRF, ensures the security of certain ADRFs that need to conceal their addresses and avoids information leakage caused by cross-vendor functions. Attached Figure Description

[0027] Figure 1 This is a schematic diagram of the network architecture applicable to the embodiments of this application;

[0028] Figure 2 This is a flowchart illustrating the methods for obtaining ML models provided by related technologies. Figure 1 ;

[0029] Figure 3 This is a flowchart illustrating the methods for obtaining ML models provided by related technologies. Figure 2 ;

[0030] Figure 4 Flowchart of the communication method provided in the embodiments of this application Figure 1 ;

[0031] Figure 2 Flowchart of the communication method provided in the embodiments of this application Figure 6 ;

[0032] Figure 7 A schematic block diagram illustrating a first function provided in an embodiment of this application;

[0033] Figure 8 A schematic block diagram illustrating a second function provided in an embodiment of this application;

[0034] Figure 9 A schematic structural diagram of a communication device provided in an embodiment of this application;

[0035] Figure 10 A schematic structural diagram of a chip provided by an embodiment of the present application is shown in FIG. 1.

[0036] Figure 1 A schematic block diagram of a communication system provided by an embodiment of the present application is shown in FIG. 2. DETAILED DESCRIPTION

[0037] The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0038] The technical solutions in the embodiments of the present application can be applied to various communication systems, for example, a 5G system or new radio (NR), a long term evolution (LTE) system, an LTE frequency division duplex (FDD) system, an LTE time division duplex (TDD), and the like. The technical solutions provided by the present application can also be applied to future communication systems, such as a sixth generation mobile communication system. The technical solutions in the embodiments of the present application can also be applied to device to device (D2D) communication, vehicle-to-everything (V2X) communication, machine to machine (M2M) communication, machine type communication (MTC), and internet of things (IoT) communication systems or other communication systems.

[0039] For the convenience of description, the 5G network will be taken as an example for description in the embodiments of the present application.

[0040] Figure 1 FIG. 1 is a schematic diagram of a network architecture 100 to which the embodiments of the present application are applicable. As shown in FIG. 1, the network architecture specifically can include three parts, which are a terminal device part, a data network (DN), and a public land mobile network (PLMN) part of an operator network. The functions of network elements of each part will be briefly described below. Figure 1

[0041] ​The terminal device part can include a terminal device 110, which can also be referred to as a user equipment (UE). The terminal device 110 in this application is a device with wireless transceiver function, which can communicate with one or more core network (CN) devices through an access network device (or also referred to as an access device) in a radio access network (RAN). The terminal device 110 can also be referred to as an access terminal, a terminal, a user unit, a user station, a mobile station, a mobile station, a remote station, a remote terminal, a mobile device, a user terminal, a user agent, or a user device, etc. The terminal device 110 can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; can also be deployed on water (such as ships, etc.); can also be deployed in the air (such as airplanes, balloons and satellites, etc.). The terminal device 110 can be a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a smart phone, a mobile phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), etc. Alternatively, the terminal device 110 can also be a handheld device, a computing device or other device connected to a wireless modem with wireless communication function, a vehicle-mounted device, a wearable device, a unmanned aerial vehicle device, or a terminal in Internet of Things, Internet of Vehicles, 5G network and future network, any form of terminal in future network, relay user equipment or terminal in future evolved 6G network, etc. Among them, the relay user equipment can be, for example, a 5G residential gateway (RG). For example, the terminal device 110 can be a virtual reality (VR) terminal, an augmented reality (AR) terminal, a wireless terminal in industrial control, a wireless terminal in unmanned driving, a wireless terminal in remote medical treatment, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, etc. The terminal device here refers to a 3GPP terminal. The embodiments of this application do not limit the type or category of terminal device. For ease of description, the following embodiments of this application take the UE as an example to illustrate the terminal device.

[0042] The operator network PLMN part can include, but is not limited to, a (radio) access network ((R)AN) 120 and a core network (CN) part.

[0043] The (R)AN 120 can be regarded as a sub-network of the operator network, and is an implementation system between a service node of the operator network and the terminal device 110. To access the operator network, the terminal device 110 first passes through the (R)AN 120, and then can be connected with the service node of the operator network through the (R)AN 120. The access network device (RAN device) in the embodiments of the present application is a device for providing wireless communication function for the terminal device 110, and can also be referred to as a network device. The RAN device includes, but is not limited to, a next generation node base station (gNB) in a 5G system, an evolved node B (eNB) in a long term evolution (LTE), a radio network controller (RNC), a node B (NB), a base station controller (BSC), a base transceiver station (BTS), a home base station (for example, a home evolved node B, or a home node B, HNB), a base band unit (BBU), a transmitting and receiving point (TRP), a transmitting point (TP), a small base station device, a mobile switching center, or a network device in a future network, etc. In systems using different wireless access technologies, the names of devices with the function of access network devices can be different. For the convenience of description, in all embodiments of the present application, the above-mentioned devices for providing wireless communication function for the terminal device 110 are collectively referred to as access network devices or simply referred to as RAN or AN. It should be understood that the specific types of access network devices are not limited herein.

[0044] The CN part can include, but is not limited to, the following network functions (NFs): user plane function (UPF), access and mobility management function (AMF), session management function (SMF), NWDAF, unified data management (UDM), network function repository function (NRF).

[0045] A data network (DN) 130, which can also be referred to as a packet data network (PDN), is usually a network located outside the operator network, for example, a third-party network. Of course, in some implementations, the DN can also be deployed by the operator, that is, the DN belongs to a part of the PLMN. The present application does not limit whether the DN belongs to the PLMN. The operator network PLMN can access multiple DNs 130, and multiple services can be deployed on the DN 130, which can provide data and / or voice services for the terminal device 110. For example, the DN 130 can be a private network of a certain smart factory, and the sensors installed in the workshop of the smart factory can be terminal devices 110. A control server of the sensors is deployed in the DN 130, and the control server can provide services for the sensors. The sensors can communicate with the control server, obtain instructions from the control server, and transmit the collected sensor data to the control server according to the instructions, and the like. For another example, the DN 130 can be an internal office network of a certain company, and the mobile phones or computers of the employees of the company can be terminal devices 110. The mobile phones or computers of the employees can access information and data resources on the internal office network of the company. The terminal device 110 can establish a connection with the operator network through an interface (for example, N1, etc.) provided by the operator network, and use the data and / or voice services provided by the operator network. The terminal device 110 can also access the DN 130 through the operator network, use the operator services and / or third-party services deployed on the DN 130.

[0046] The NF functions included in the CN are further briefly described below.

[0047] The UPF is a gateway provided by an operator and is a gateway for the operator network to communicate with the DN 130. The UPF includes functions related to the user plane, such as data packet routing and transmission, data packet detection, service usage reporting, quality of service (QoS) processing, lawful interception, uplink data packet detection, downlink data packet storage, and the like.

[0048] The AMF is a control plane network function provided by an operator network and is responsible for access control and mobility management of terminal devices 110 accessing the operator network, such as functions including mobile state management, allocation of a user temporary identity, authentication and authorization of a user, and the like.

[0049] The SMF is a control plane network function provided by an operator network and is responsible for managing protocol data unit (PDU) sessions of terminal devices 110. A PDU session is a channel for transmitting PDUs, and terminal devices need to transmit PDUs to and from the DN 130 through the PDU session. The SMF is responsible for establishing, maintaining, and deleting the PDU session, and the like. The SMF includes functions related to the session, such as session management (e.g., session establishment, modification, and release, including maintenance of tunnels between a user plane function (UPF) and a (R)AN 120), selection and control of the UPF, selection of a service and session continuity (SSC) mode, roaming, and the like.

[0050] The NRF is a control plane function provided by an operator and can be used to maintain real-time information of network functions and services in a network. For example, the NRF supports network service discovery, maintains NF profile supported services of NF instances, supports service discovery of a service communication proxy (SCP), maintains an SCP profile of an SCP instance, sends notifications about newly registered, deregistered, and updated NFs and SCPs, maintains health states of NFs and SCPs running, and the like.

[0051] The UDM is a control plane function provided by an operator, responsible for storing the user permanent identifier (SUPI) of a subscription user in an operator network, the generic public subscription identifier (GPSI) of the subscription user, credentials, and the like. Among them, the SUPI will be encrypted first in the transmission process, and the encrypted SUPI is called the subscription concealed identifier (SUCI). The information stored by the UDM can be used for authentication and authorization of the terminal device 110 accessing the operator network. Among them, the subscription user of the operator network can be a user using the services provided by the operator network, for example, a user using a China Telecom mobile phone core card (subscriber identity module, SIM) card, or a user using a China Mobile mobile phone core card, and the like. The credentials of the subscription user can be a long-term key stored in the mobile phone core card or a small file stored in the information related to the encryption of the mobile phone core card, used for authentication and / or authorization. It should be noted that the permanent identifier, the credentials, the security context, the authentication data (cookie), and the token and the like are related to the same verification / authentication, authorization information, which are not distinguished or limited for the sake of convenience in the description of the embodiments of the present application.

[0052] The NWDAF is a control plane function provided by an operator, and its main function is to collect data from NFs, external application functions (AFs), and operations, administration and maintenance (OAM) systems, and the like, and provide NWDAF service registration, data exposure, and analysis data to NFs and AFs.

[0053] Specifically, the NWDAF can include the following logical functions:

[0054] Analysis logical function (AnLF): a logical function in the NWDAF, used to perform reasoning, derive analysis information (i.e., derive statistics and / or predictions according to analysis consumer requests), and expose analysis services.

[0055] Model training logical function (MTLF): a logical function in the NWDAF, which trains machine learning (ML) models and exposes new training services, for example, provides trained ML models.

[0056] It should be understood that a NWDAF can contain either MTLF or AnLF or both logical functions. Among them, the NWDAF containing AnLF is locally configured with the identity document (ID) of the NWDAF containing MTLF and the analysis ID (s) supported by each NWDAF containing MTLF to retrieve the trained ML model. If necessary, the NWDAF containing AnLF uses NWDAF discovery for the NWDAF containing MTLF in the configured ID set of the NWDAF containing MTLF.

[0057] It should be understood that in order to ensure the accuracy of the analysis output of the analysis ID, based on the UE abnormal behavior analysis from itself or other NWDAFs, including the abnormal UE list and the observed time window, the NWDAF is used to detect and can delete the input data from the abnormal UE, and then can generate a new ML model and / or analysis output for the analysis ID during the observed time window without input data related to the abnormal UE list, and then send / update the ML model information and / or analysis output to the subscribed NWDAF service consumer.

[0058] In order to support NF discovery and selection of NWDAF instances containing MTLF, AnLF or both, which are capable of providing required services (e.g. analytics exposure or ML model deployment) for the required type of analytics, each NWDAF instance, when registering to the NRF, shall provide the list of supported analytics IDs (possibly per supported service) along with other NRF registration elements of the NF profile. NFs that need to discover NWDAF instances that support certain specific services for a specific type of analytics can query the NRF for NWDAFs that support the required services and the required analytics IDs.

[0059] The NWDAF architecture allows arranging multiple NWDAF instances in a hierarchy / tree with a flexible number of layers / branches. The number and organization of the hierarchy layers and the functionality of each NWDAF instance remain deployment choices.

[0060] In a hierarchical deployment, when a data collection coordination function (DCCF) network element is not present in the network, the NWDAF can provide data collection exposure capabilities for generating analytics based on data collected by other NWDAFs.

[0061] In order to make the NWDAF discoverable in some network deployments, the NWDAF can be configured (e.g. for UE mobility analytics) to register in the UDM (Nudm_UECM_Registration service operation) the UEs it serves and the related analytics ID. The registration in the UDM should happen when the NWDAF starts to serve a UE or to collect data for a UE. The deregistration in the UDM happens when the NWDAF deletes the analytics context for a UE of the related analytics ID.

[0062] In future communication systems, the network data analytics function network element can still be the NWDAF network element, or, there can be other names, which are not limited by the present application.

[0063] Optionally, the network architecture can further include a DCCF network element and an analytics data repository function (ADRF) network element. The ADRF provides storage and retrieval services for data and analytics for consumers. For example, a consumer sends a data management storage request (NadrfDataManagementStorageRequest) to the ADRF containing data or analytics to be stored; or, the consumer sends a data management storage subscription request (NadrfDataManagementStorageSubscriptionRequest) to the ADRF, requesting the ADRF to subscribe to receive data or analytics for storage, and then the ADRF subscribes to the NWDAF or the DCCF to obtain the data or analytics, providing an ADRF notification address (or notification association ID). The analytics or data are then provided as notifications using the DCCF data management (NdccfDataManagement) service, the NWDAF data management (NnwdafDataManagement) service, or the MFAF data management (Nmfaf_3caDataManagement) service.

[0064] Exemplarily, the consumer sends a data management retrieval request (NadrfDataManagementRetrievalRequest) to the ADRF to retrieve data or analytics for a specified data or analytics collection time window. The ADRF determines the availability of data or analytics in its repository and sends data or analytics, or a description of the data or analytics, to the consumer in a response; or the consumer sends a data management retrieval subscribe request (NadrfDataManagementRetrievalSubscribe) to the ADRF to retrieve data or analytics for a specified data or analytics collection time window. If the time window includes the future, and the ADRF has subscribed to receive data or analytics, the ADRF receives subsequent notifications that are sent by the ADRF to the notification endpoint. The ADRF determines the availability of data or analytics and sends a success / failure indication to the consumer in a response. The ADRF then sends one or more notifications to the consumer specified notification address (or notification association ID) using a data management retrieval notification (NadrfDataManagementRetrievalNotify). The notification provides data or analytics, or provides the endpoint with instructions to obtain data or analytics using a data management retrieval request (NadrfDataManagementRetrievalRequest).

[0065] It can be understood that the above-mentioned network elements or functions can be either physical entities in hardware devices, or software instances running on special hardware, or virtualized functions instantiated on a shared platform (for example, a cloud platform). In short, an NF can be implemented by hardware or software.

[0066] Figure 1 The Nudm, Nnwdaf, Nausf, Namf, Nsmf, N1, N2, N3, N4, and N6 are interface sequence numbers. Exemplarily, the meanings of the above-mentioned interface sequence numbers can be referred to the meanings defined in the 3GPP standard protocol, and the meanings of the above-mentioned interface sequence numbers are not limited in the present application. It should be noted that, Figure 1 The interface names between the various network functions in the above-mentioned system architecture are only examples, and the interface names of the system architecture in the specific implementation can also be other names, which are not limited in the present application. In addition, the names of the messages (or signaling) transmitted between the above-mentioned various network elements are also only examples, and do not constitute any limitation on the functions of the messages themselves.

[0067] It should be noted that the interfaces between the various control plane network elements can also be point-to-point interfaces, which are not described here again.

[0068] It should be understood that the network architecture to which the above embodiments of the present application can be applied is only illustratively described, and the network architecture to which the embodiments of the present application are applicable is not limited thereto, and any network architecture including the functions of the above-mentioned network elements is applicable to the embodiments of the present application.

[0069] It should also be understood that Figure 1 The illustrated NRF, UDM, etc. can be understood as network elements for implementing different functions, which can be combined into network slices as needed, for example. These network elements can be independent devices, or can be integrated into the same device to implement different functions, or can be network elements in a hardware device, or can be software functions running on a dedicated hardware, or can be virtualized functions instantiated on a platform (e.g., a cloud platform), and the specific form of the network elements is not limited in the present application.

[0070] It should also be understood that the above naming is only defined for the convenience of distinguishing different functions and should not constitute any limitation on the present application. The present application does not exclude the possibility of using other names in 5G networks and other future networks. For example, in a 6G network, some or all of the above-mentioned network elements can use the terms in 5G, or other names, etc.

[0071] It should also be understood that Figure 2 The interface names between the various network elements of the above-mentioned are only an example, and the names of the interfaces in the specific implementation can be other names, which are not limited in the present application. In addition, the names of the messages (or signaling) transmitted between the above-mentioned network elements are also only an example, and do not constitute any limitation on the functions of the messages themselves.

[0072] The network architecture and service scenarios described in the embodiments of the present application are for more clearly illustrating the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. It is known to those skilled in the art that, with the evolution of network architecture and the appearance of new service scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0073] In the service-oriented system architecture of 5G, the two parties communicating based on service-oriented interfaces are called service consumer and service producer. Among them, the party requesting the service is the service consumer, and the party providing the service is the service producer. The service consumer can also be called consumer, consumer network element, user, requestor, or service consumer network element, etc. The service producer can also be called provider network element, service provider network element, provider, producer, or responder, etc., which is not limited in the present application.

[0074] Before explaining the present application, the related art ML model acquisition method is explained: the scheme in 3GPP Technical Specification (TS) 23.288 standard, the current NWDAF-based ML model acquisition method is defined by 3GPP SA2. Figure 2 is a flowchart of a method for acquiring an ML model provided by the related art. As shown in Figure 3 , the method includes the following steps:

[0075] S201. The consumer sends a network data analytics function machine learning model acquisition request (Nnwdaf_MLModelProvision Request) to the NWDAF including the MTLF function.

[0076] S202. The NWDAF including the MTLF function determines whether to retrieve the machine learning model from the ADRF (NWDAF determines whether ML model is to be retrieved from ADRF). Further, S203 is performed, or S206 is performed.

[0077] S203. If the MTLF decides to acquire indirectly between MTLFs, the NWDAF including the MTLF function sends an analytics data storage function machine learning model management retrieval request (Nadrf_MLModelManagement_Retrieve Request) to the ADRF.

[0078] S204. The ADRF sends an analytics data storage function machine learning model management retrieval response (Nadrf_MLModelManagement_Retrieve Response) to the NWDAF including the MTLF function.

[0079] S205. The NWDAF including the MTLF function sends a network data analytics function machine learning model acquisition response (Nnwdaf_MLModelProvision Response) to the consumer.

[0080] S206. If the MTLF decides to acquire directly from the ADRF, the consumer sends an analytics data storage function machine learning model management retrieval request (Nadrf_MLModelManagement_Retrieve Request) to the ADRF.

[0081] S207. The ADRF sends the consumer a Nadrf_MLModelManagement_Retrieve Response.

[0082] It should be noted that the current SA2 defines the NWDAF-based ML model acquisition method, and does not clearly define how the MTLF decides to acquire directly or indirectly.

[0083] It should be noted that the permission problem of the NWDAF-based ML model acquisition is solved in the scheme proposed by 3GPP SA3. Figure 3 is another flowchart of the method for acquiring the ML model provided by the related art. As shown in Figure 4 , the method comprises the following steps:

[0084] S301. A network function service provider (NF service producer, NFp) (for example, a NWDAF MTLF) sends an Nadrf_MLModelManagement_Storage Request to the ADRF.

[0085] Among them, the Nadrf_MLModelManagement_Storage Request includes the MTLF ID, the Model ID, the Model Address in MTLF, for example, Uniform Resource Locator (URL) 1, the allowed NFc list.

[0086] It should be noted that before step 301 is executed, it also includes:

[0087] The NFp (for example, the NWDAF MTLF) is registered in the NRF, that is, Register NWDAF / MTLF; wherein, when registering, the registration request includes Analytics ID, Interoperability ID.

[0088] The NFc (for example, the NWDAF AnLF) is registered in the NRF, that is, Register NWDAF / AnLF; wherein, when registering, the registration request includes Analytics ID, Vendor ID.

[0089] The NFp conditionally encrypts the ML model.

[0090] S302, the ADRF sends a response to the NFp.

[0091] The response includes a Model ID, a Model Address in ADRF, for example, a URL2.

[0092] S303, the NFc discovers the MTLF in the NRF.

[0093] Here, the MTLF can be discovered based on the Analytics ID.

[0094] S304, the NFc sends a Network Repository Function_Access Token_Get Request to the NRF.

[0095] The Nnrf_AccessToken_Get Request includes an Analytics ID, a Vendor ID, and information of a target NF, for example, the ADRF.

[0096] S305, the NRF sends a Network Repository Function_Access Token_Get Response to the NFc.

[0097] The Nnrf_AccessToken_Get Response includes information of a token 1.

[0098] S306, the NFc sends a Network Data Analytics Function's Machine Learning's Model Get Request to the NFp.

[0099] The Nnwdaf_MLModelProvision Request includes an Analytics ID, a Vendor ID, and information of the token 1.

[0100] S307, the NRF and the NFp perform authorization of the NFc and store an NFc ID.

[0101] S308. The NFp sends an analysis data storage function_ml model management storage update (Nadrf_MLModelManagement_Storage Update) to the ADRF.

[0102] Wherein, the Nadrf_MLModelManagement_Storage Update includes MTLF ID, Model ID, allowed NFc list.

[0103] S309. The ADRF sends a response (Response) to the NFp.

[0104] Wherein, the Model ID is included in the response.

[0105] S310. The NFp sends a network data analytics function_ml model provision response (Nnwdaf_MLModelProvision Response) to the NFc.

[0106] Wherein, the Nnwdaf_MLModelProvision Response includes Model ID, Model address, [ADRF ID, Storage Transaction ID].

[0107] It should be noted that if the ML model is to be retrieved from the ADRF, the following S311 to S315 are performed.

[0108] S311. The NFc sends a network storage function_access token_get (Nnrf_AccessToken_Get) to the NRF.

[0109] Wherein, the Nnrf_AccessToken_Get includes identification information related to the target NF (ADRF).

[0110] S312. The NRF sends a network storage function_access token_get response (Nnrf_AccessToken_Get Response) to the NFc.

[0111] Wherein, the Nnrf_AccessToken_Get Response includes token 2.

[0112] S313, the NFc sends an analytics data storage function_ machine learning model management_ retrieval request (Nadrf_MLModelManagement_Retrieval Request) to the ADRF.

[0113] The Nadrf_MLModelManagement_Retrieval Request includes an Analytics ID, token2.

[0114] S314, the ADRF sends an analytics data storage function_ machine learning model management_ retrieval response (Nadrf_MLModelManagement_Retrieval Response) to the NFc.

[0115] The Nadrf_MLModelManagement_Retrieval Response includes a model address in the ADRF (Model Address in ADRF).

[0116] S315, the NFc conditionally decrypts the ML model.

[0117] It should be noted that the access permission processing method of the NWDAF-based ML model acquisition defined by the current SA3 judges that the NFc has the permission to obtain the model after the MTLF verification token, stores the NFc ID, and transmits the list of NFcs allowed to access locally by the MTLF to the ADRF. The ADRF updates the access list locally according to the NFc ID allowed by the MTLF after receiving it. Then, the information of the ADRF is transmitted to the NFc, so that the NFc can directly obtain the model from the ADRF.

[0118] Figure 4 A flowchart of a communication method provided by an embodiment of the present application is shown in FIG. 1. Figure 1 The method is applied to the network architecture 100 shown in FIG. 1. Figure 5 The method includes the following steps.

[0119] Step 401, the second function sends first information to the first function.

[0120] The first information includes related information of at least one network function service consumer or provider authorized to access the second function.

[0121] In the embodiments of the present application, the first function can be MTLF, or NWDAF including MTLF. Obviously, in the present application, the first function belongs to a network function service provider (NFp).

[0122] In the embodiments of the present application, the second function can be ADRF.

[0123] In the embodiments of the present application, the related information of the at least one network function service consumer includes but is not limited to the NF instance ID of the at least one NF service consumer, the at least one NFc ID, the Analytics ID corresponding to the at least one NFc, and the Vendor ID corresponding to the at least one NFc.

[0124] In the embodiments of the present application, the related information of the at least one vendor includes a vendor ID, which is used to represent the vendor of the NF, and can be the ID of the vendor or the internal implementation of the vendor.

[0125] In the embodiments of the present application, the first information can be sent in the following ways: in-band, out-of-band, media, signaling, data, message, control plane, user plane, etc. Among them, the existing media channel can be used to send the first information, so as to better compatible with the existing system and reduce the cost of system transformation. In addition, when the first function is multi-party, the established media plane communication channel is a one-to-many multicast / broadcast communication channel, so that the first information is sent only once through the established multicast / broadcast communication channel, and other first functions can receive it, effectively reducing the number of information transmission.

[0126] In the embodiments of the present application, the related information of the at least one network function service consumer or vendor authorized to access the second function includes the list of NFcs or Vendors allowed to access the second function. That is, the first information can be implemented in the form of a list.

[0127] In the embodiments of the present application, the first function and the second function can be one function network element. The function network element or function can be a physical entity in a hardware device, a software instance running on a dedicated hardware, or a virtualized function instantiated on a platform. In short, an NF can be implemented by hardware or software.

[0128] Step 402, the first function receives the first information sent by the second function.

[0129] Step 403, the first function determines the way for the first network function service consumer to obtain the target model according to the first information.

[0130] In an embodiment of the present application, the first network function service consumer (NFc) can include the NWDAF of the AnLF.

[0131] In an embodiment of the present application, the target includes but is not limited to an ML model, an Artificial Intelligence (AI) model.

[0132] In an embodiment of the present application, the manner in which the first NFc acquires the target model includes that the first NFc directly acquires the target model from the ADRF, and that the first NFc indirectly acquires the target model from the ADRF through the MTLF.

[0133] It should be noted that this implementation mode is applicable to the case where the NFc and the NFp belong to the same operator, and is also applicable to the case where the NFc and the NFp belong to different operators, which is not limited in the present application.

[0134] An embodiment of the present application provides a communication method, which includes: a second function sends first information to a first function; wherein the first information includes relevant information of at least one network function service consumer or supplier authorized to access the second function; the first function receives the first information sent by the second function; and the first function determines a manner in which a first network function service consumer acquires a target model according to the first information. That is, in the present application, the first information, i.e., the list of authorized NFs or suppliers, of the second function, i.e., the ADRF, is sent to the first function, i.e., the MTLF, so that the MTLF can learn the authority of the ADRF, and after the MTLF judges the authority of the first NFc to access the ML model, the MTLF can compare the information corresponding to the first NFc with the list of NFs or suppliers to confirm whether the first NFc has the authority to access the ADRF, and then determine whether the first NFc directly acquires the ML model or indirectly acquires the ML model. In this way, the problem of logical contradiction between the method proposed in SA3 and the method defined in the SA2 standard scheme mentioned in the related art is solved. Meanwhile, in the present application, the MTLF determines whether the first NFc directly acquires the ML model or indirectly acquires the ML model according to the list of authorized NFs or suppliers, which is relative to the scheme proposed in SA3 that the MTLF determines that the NFc that can access the ML model can directly acquire the ML model from the ADRF, and can guarantee the security of some ADRFs that need to hide their own addresses, and avoids the problem of information leakage caused by the functions corresponding to different manufacturers being able to access each other.

[0135] In some embodiments, the step 401 of the second function sending first information to the first function and the step 402 of the first function receiving the first information sent by the second function can be implemented by the following steps:

[0136] Step A1, the first function sends a model storage request to the second function.

[0137] In some embodiments, the model storage request (e.g., Nadrf_MLModelManagement_StorgeRequest) can include information about at least one network function service consumer or vendor authorized to access the first function; of course, the model storage request can not include information about at least one network function service consumer or vendor authorized to access the first function.

[0138] In the embodiments of the present application, the information about at least one network function service consumer or vendor authorized to access the first function includes a list of NFcs or Vendors allowed to access the MTLF. That is, the information about at least one network function service consumer or vendor authorized to access the first function can be implemented in the form of a list.

[0139] In the embodiments of the present application, the model storage request can be sent in the following ways: in-band, out-of-band, media, signaling, data, message, control plane, user plane, etc.

[0140] Step A2, the second function receives the model storage request sent by the first function.

[0141] In some embodiments, when the second function is registered, the second function configures the first information in the third function; that is, when the ADRF is registered, the NFcs or Vendor list that can access it needs to be configured in the NRF.

[0142] In the embodiments of the present application, after the second function, i.e., the ADRF, receives the information about at least one network function service consumer or vendor authorized to access the first function, i.e., the list of NFcs or Vendors allowed to access the MTLF, the ADRF locally queries whether the list is the same as the first information, i.e., the list of NFcs or Vendors allowed to access the ADRF. After comparison, the ADRF can locally decide whether to update the list of NFcs or Vendors allowed to access the ADRF according to the list of NFcs or Vendors allowed to access the MTLF, and then pass the list of NFcs or Vendors allowed to access the ADRF to the MTLF.

[0143] Step A3, the second function sends a model storage response to the first function.

[0144] The model storage response includes the first information.

[0145] In the embodiments of the present application, the model storage response (Nadrf_MLModelManagement_StorgeResponse) includes the list of NFcs or Vendors allowed to access the ADRF.

[0146] Step A4, the first function receives the model storage response sent by the second function.

[0147] In some embodiments, step 403, the first function determines the way for the first network function service consumer to obtain the target model according to the first information, which can be implemented by the following steps:

[0148] Step B1, the first function receives the second information sent by the first network function service consumer.

[0149] The second information is used to request to obtain the target model, and the second information includes the identification information of the first network function service consumer.

[0150] In the embodiments of the present application, the first network function service consumer sends a model obtaining request (Nadrf_MLModelManagement_Retrieve Request) carrying the second information to the first function. The first function receives the model obtaining request and analyzes the target model expected to be obtained by the first network function service consumer.

[0151] Here, the second information includes the identification information of the first network function service consumer and the identification information of the target model. Each network function service consumer and each model has unique identification information. In some embodiments, the identification information includes color identification, graphic identification, text identification, numerical identification, location identification, etc. Different network function service consumers and different models can use the same type of identification information. Of course, the types of identification information of each network function service consumer and each model can also be not completely the same, or the types of identification information of each network function service consumer and each model are completely different.

[0152] In some embodiments, the identification information includes at least one of the following: the vendor identification of the first network function consumer; the network function instance identification of the first network function consumer; the analytic identification corresponding to the first network function consumer.

[0153] In some embodiments, the analytic ID (Analytic ID) can indicate the type of the target model that the NFc expects to access.

[0154] Step B2, the first function determines the way for the first network function consumer to obtain the target model based on the identification information and the first information.

[0155] In some embodiments, if the identification information matches the first information, it is determined that the first network function consumer obtains the target model in the first way; if the identification information does not match the first information, it is determined that the first network function consumer obtains the target model in the second way.

[0156] It should be noted that the matching indication is a complete match or a partial match; for example, the identification information is completely matched with a certain sub-information in the first information, that is, completely same, which indicates that the identification information is matched with the first information; or the identification information is partially matched with a certain type of sub-information in the first information, that is, partially overlapped, which indicates that the identification information is matched with the first information. It should be noted that if the identification information is not same as any sub-information in the first information, or the identification information is not overlapped with any type of sub-information in the first information, it indicates that the identification information is not matched with the first information.

[0157] For example, the first function compares the first supplier identifier corresponding to the first network function service consumer, the first analysis identifier corresponding to the first network function service consumer, the analysis identifier corresponding to each network function consumer in the first information, and the supplier identifier of each network function consumer in the first information, or compares the first network function instance identifier corresponding to the first network function service consumer, the first analysis identifier corresponding to the first network function service consumer, the analysis identifier corresponding to each network function consumer, and the network function instance identifier of each network function consumer, to obtain a comparison result. If the comparison result indicates that the first supplier identifier and the first analysis identifier are in the first information, or the first network function instance identifier and the first analysis identifier are in the first information, it is determined that the first network function consumer acquires the target model in the first mode; if the comparison result indicates that the first supplier identifier and the first analysis identifier are not in the first information, or the first network function instance identifier and the first analysis identifier are not in the first information, it is determined that the first network function consumer acquires the target model in the second mode.

[0158] It should be noted that in the case that the first network function consumer acquires the target model in the first mode, the first function sends the identifier of the second function to the first network function service consumer; the first network function service consumer sends third information to the second function; wherein the third information is used to request information for acquiring the target model; the second function receives the third information; the second function sends information of the target model to the first network function service consumer; the first network function service consumer receives the information of the target model.

[0159] It should be noted that in the case that the first network function consumer acquires the target model in the second mode, the first function sends third information to the second function; wherein the third information is used to request information for acquiring the target model; the second function receives the third information; the second function sends information of the target model to the first function; the first function receives the information of the target model; the first function sends the information of the target model to the first network function consumer; the first network function service consumer receives the information of the target model.

[0160] In the embodiments of the present application, the information of the target model includes one or more of a target model identifier or a target model address or a hash value of the target model address; wherein the address of the model can be a URL or a Fully Qualified Domain Name (FQDN). Correspondingly, the hash value of the model address can be a hash value of the URL or the FQDN.

[0161] It should be noted that the third information sent by the first function to the second function is different information carried by different messages compared to the third information sent by the first network function service consumer to the second function, but both of the different information are used to request the second function to obtain the target model.

[0162] In the embodiments of the present application, the identifier of the second function includes but is not limited to the ID of the second function, the address of the second function. In some embodiments, the second function has a unique identifier; the identifier includes color identification, graphic identification, text identification, digital identification, location identification, etc.

[0163] The present application proposes a new method for obtaining and determining ML model based on NWDAF. By pre-configuring the list of NFcs authorized to access ADRF by ADRF in NRF, and returning the list of NFcs authorized to access ADRF to MTLF when MTLF stores the model in ADRF, when MTLF receives a model obtaining request, it can compare the list with NFc to confirm whether NFc has the right to access ADRF, and then determine the ML model obtaining method (directly or indirectly).

[0164] In the present application, "communication" can also be described as "data transmission", "information transmission", "data processing", etc. "Transmission" includes "sending" and "receiving".

[0165] In the present application, "first", "second" and various numerical designations indicate differentiation for the sake of description, and are not used to limit the scope of the embodiments of the present application. For example, different messages are differentiated, rather than used to describe a specific order or sequence. It should be understood that the objects thus described can be interchanged under appropriate circumstances in order to describe solutions other than the embodiments of the present application.

[0166] Figure 5 is a flowchart of a communication method provided by the embodiments of the present application. As shown in Figure 4 the method includes the following steps:

[0167] S501, the NFp (for example, NWDAF MTLF) initiates a model storage request (Nadrf_MLModelManagement_StorgeRequest) to the ADRF.

[0168] Wherein, the Model ID and Model address are carried in the Nadrf MLModelManagement StorgeRequest; that is, the MTLF carries the Model ID and Model address to the ADRF through the Nadrf MLModelManagement StorgeRequest.

[0169] It should be noted that before step 501 is executed, it further includes:

[0170] Registering the NWDAF / MTLF, the NWDAF / MTLF, at the time of registration, includes the Analytics ID, the interoperability identifier (Interoperability ID) in the registration request, and needs to pre-configure the interoperability indicator (Interoperability indicator) of the model according to the Analytics ID in the NRF, to indicate that the Vendor or NF that can obtain the above-mentioned model.

[0171] It should be understood that the interoperability identifier is a list of vendor IDs of the NWDAF that allows to obtain the ML model from the NFp.

[0172] Registering the NWDAF / AnLF, the AnLF, at the time of registration, includes the Vendor ID in the registration request 、 Analytics ID.

[0173] Registering the ADRF in the NRF, at the time of registration of the ADRF, the registration request includes the Analytics ID, and the ADRF allowed NFc list (ADRF allowed NFc list) that the ADRF allows to access. Further, the ADRF configures the NFc or Vendor list that can access the ADRF in the NRF; it should be noted that the NFc or Vendor list is determined according to the Analytics ID.

[0174] If the MTLF and the ADRF do not belong to the same manufacturer's device, the model needs to be encrypted and integrity protected before transmission, that is, the NFp conditionally encrypts the ML model.

[0175] S502, the ADRF sends a model storage response (Nadrf MLModelManagement StorgeResponse) to the NFc.

[0176] In some embodiments, after the ADRF receives the Model address, it can selectively decide whether to download the model to local storage ADRF; and the ADRF informs the NFc model has been stored through the Nadrf_MLModelManagement_StorgeResponse, while allowing the NFc or Vendor list that has access to this ADRF to be provided to the MTLF.

[0177] It should be noted that the NFc or Vendor list can be configured according to the Analytics ID and Vendor ID.

[0178] S503, the NFc (for example, NWDAF AnLF) discovers the MTLF according to the Analytics ID.

[0179] S504, the NFc sends a token request (Nnrf_AccessToken_Get Request) to the NRF.

[0180] Among them, AnLF initiates a token request for MTLF to NRF, which should include Vendor ID and Analytics ID in the request.

[0181] S505, the NRF uses the interoperability indicator to check the Analytics ID, Vendor ID and target MTLF

[0182] It should be noted that the NRF compares and checks the received Analytics ID, Vendor ID and the configured Interoperability indicator of the target MTLF (NRF checks the Analytics ID, Vendor ID and Target MTLF with Interoperability indicator). Further, if the check is passed, the token is issued and S506 is executed.

[0183] S506, the NRF sends a token response (Nnrf_AccessToken_Get Response) to the NFc.

[0184] It should be noted that the NRF returns the token to AnLF.

[0185] S507, the NFc initiates a model acquisition request (Nnwdaf_MLModelProvision Request) to the NFp.

[0186] In the embodiments of the present application, in addition to token, Vendor ID and Analytics ID also need to be carried in Nnwdaf_MLModelProvision Request.

[0187] S508, NFp (for example, NWDAF MTLF) compares the Analytic ID, Vendor ID with the list provided by ADRF (MTLF checks the Analytic ID and Vendor ID with the allowed NFc list of ADRF), or compares the Analytic ID, NF instance ID of AnLF with the list provided by ADRF.

[0188] If this NFc is in the list provided by ADRF, then MTLF decides that this AnLF can directly access ADRF for model acquisition (If ML Model needs to be retrieved from ADRF directly), and S511 to S515 are executed.

[0189] If this NFc is not in the list provided by ADRF, then MTLF decides that this AnLF cannot directly access ADRF for model acquisition, since the ML model needs to be retrieved from ADRF and the NF consumer is agnostic to where the ML model is stored (If ML Model needs to be retrieved from ADRF and the NF consumer is agnostic to where the ML model is stored), and model acquisition needs to be performed through MTLF, then S509 to S511, S515 are executed.

[0190] S509, NFp requests ML model acquisition request (Nadrf_MLModelManagement_RetrieveRequest) from ADRF.

[0191] Here, Analytics ID(s), Storage Transaction Identifier, ML model ID are included in Nadrf_MLModelManagement_Retrieve Request.

[0192] S510, the ADRF sends an ML model retrieval response (Nadrf_MLModelManagement_RetrieveResponse) to the NFp; that is, the ADRF returns the model address to the MTLF.

[0193] S511, the NFp sends an ML model provisioning response (Nnwdaf_MLModelProvision Response) to the NFc.

[0194] It should be noted that the MTLF returns the model-related information to the AnLF in S511. The model-related information can be a model address or an ADRF ID, one of the two. And only when the MTLF decides in S508 that the AnLF can directly obtain the model from the ADRF, the ADRF ID will be provided in this step.

[0195] S512, the NFc and the NRF perform token request and response.

[0196] S513, the NFc sends an ML model retrieval request (Nadrf_MLModelManagement_RetrieveRequest) to the ADRF.

[0197] Among them, Analytics ID(s), Storage Transaction Identifier, Model ID in Nadrf_MLModelManagement_Retrieve Request.

[0198] S514, the ADRF sends an ML model retrieval response (Nadrf_MLModelManagement_RetrieveResponse) to the NFc, that is, the ADRF directly returns the model address to the AnLF.

[0199] S515, the NFc conditionally decrypts the ML model.

[0200] Embodiments of the present application provide a first function, which can be used to implement Figure 6 The corresponding embodiment provides a communication method, which refers to Figure 4 As shown in the figure, the first function 60 includes:

[0201] The first receiving module 601 is configured to receive first information sent by a second function; wherein the first information includes related information of at least one network function service consumer or supplier authorized to access the second function;

[0202] The first processing module 602 is configured to determine, according to the first information, a manner in which the first network function service consumer acquires the target model.

[0203] In other embodiments of the present application, the first receiving module 601 is configured to receive second information sent by the first network function service consumer, wherein the second information is used to request acquisition of the target model, and the second information includes identification information of the first network function service consumer.

[0204] The first processing module 602 is configured to determine, based on the identification information and the first information, the manner in which the first network function consumer acquires the target model.

[0205] In other embodiments of the present application, the first processing module 602 is configured to, if the identification information matches the first information, determine that the first network function consumer acquires the target model in the first manner.

[0206] In other embodiments of the present application, the first processing module 602 is configured to, if the identification information does not match the first information, determine that the first network function consumer acquires the target model in the second manner.

[0207] In other embodiments of the present application, the identification information includes at least one of the following: a vendor identifier of the first network function consumer; a network function instance identifier of the first network function consumer; and an analytics identifier corresponding to the first network function consumer.

[0208] In other embodiments of the present application, the first sending module 603 is configured to, in the case where the first network function consumer acquires the target model in the first manner, send, to the first network function service consumer, identification of the second function.

[0209] In other embodiments of the present application, the first sending module 603 is configured to, in the case where the first network function consumer acquires the target model in the second manner, send, to the second function, third information, wherein the third information is used to request acquisition of the target model.

[0210] The first receiving module 601 is configured to receive information of the target model sent by the second function.

[0211] The first sending module 603 is configured to send, to the first network function service consumer, the information of the target model.

[0212] In other embodiments of the present application, the first sending module 603 is configured to send, to the second function, a model storage request.

[0213] The first receiving module 601 is configured to receive a model storage response sent by the second function, wherein the model storage response includes the first information.

[0214] In other embodiments of the present application, the model storage request includes information about at least one network function service consumer or provider that is authorized to access the first function.

[0215] The above device embodiments are described similarly to the above method embodiments, and have similar beneficial effects to the method embodiments. For technical details not disclosed in the device embodiments of the present application, please refer to the description of the method embodiments of the present application.

[0216] It should be noted that, in the embodiments of the present application, if the above-mentioned communication method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for causing an end device to execute all or part of the method embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, ROM, magnetic disk or optical disk, and various storage media that can store program codes. Thus, the embodiments of the present application are not limited to any specific hardware and software combination.

[0217] The embodiments of the present application provide a second function, which can be used to implement Figure 7 The communication method provided by the corresponding embodiments is described with reference to Figure 8 As shown in the figure, the second function 70 includes:

[0218] The second sending module 701 is configured to send first information to the first function; wherein the first information includes information about at least one network function service consumer or provider that is authorized to access the second function.

[0219] In other embodiments of the present application, the second receiving module 702 is configured to receive a model storage request sent by the first function.

[0220] The second sending module 701 is configured to send a model storage response to the first function; wherein the model storage response includes the first information.

[0221] In other embodiments of the present application, the model storage request includes information about at least one network function service consumer or provider that is authorized to access the first function.

[0222] In other embodiments of the present application, the second processing module 703 is configured to configure the first information in the third function when the second function is registered.

[0223] In other embodiments of the present application, the second receiving module 702 is configured to receive third information sent by the first network function service consumer, in the case where the first network function consumer acquires the target model in the first manner; the third information is used to request information for acquiring the target model.

[0224] The second sending module 701 is configured to send information of the target model to the first network function service consumer

[0225] In other embodiments of the present application, the second receiving module 702 is configured to receive third information sent by the first network function service consumer, in the case where the first network function consumer acquires the target model in the second manner; the third information is used to request information for acquiring the target model.

[0226] The second sending module 701 is configured to send information of the target model to the first network function service consumer

[0227] The above device embodiments are similar to the descriptions of the above method embodiments, and have similar beneficial effects to the method embodiments. For technical details not disclosed in the device embodiments of the present application, please refer to the description of the method embodiments of the present application for understanding.

[0228] It should be noted that, in the embodiments of the present application, if the above-mentioned communication method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a terminal device to execute all or part of the method embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a ROM, a magnetic disk or an optical disk, and various storage media that can store program codes. Thus, the embodiments of the present application are not limited to any specific hardware and software combination.

[0229] Figure 8 is a schematic structural diagram of a communication device 800 provided by the embodiments of the present application. The communication device can be a first function or a second function. Figure 8 The communication device 800 shown includes a first processor 810, which can call and run a computer program from a memory to implement the method in the embodiments of the present application.

[0230] Optionally, as shown in Figure 8 The communication device 800 can also include a first memory 820. The first processor 810 can call and run a computer program from the first memory 820 to implement the method in the embodiments of the present application.

[0231] The first memory 820 can be a separate device independent of the first processor 810, or can be integrated in the first processor 810.

[0232] Optionally, as shown in the figure, the communication device 800 can further include a transceiver 830, and the first processor 810 can control the transceiver 830 to communicate with other devices, specifically, can send information or data to other devices, or receive information or data sent by other devices. Figure 9

[0233] The transceiver 830 can include a transmitter and a receiver. The transceiver 830 can further include an antenna, and the number of antennas can be one or more.

[0234] Optionally, the communication device 800 can be a first function / second function of the embodiments of the present application, and the communication device 800 can implement the corresponding processes in the various methods of the embodiments of the present application that are implemented by the first function / second function. For the sake of brevity, they will not be described here.

[0235] Figure 9 The chip 900 shown in the figure includes a second processor 910, which can call and run computer programs from the memory to implement the methods in the embodiments of the present application. Figure 9

[0236] Optionally, as shown in the figure, the chip 900 can further include a second memory 920. The second processor 910 can call and run computer programs from the second memory 920 to implement the methods in the embodiments of the present application. Figure 10

[0237] The second memory 920 can be a separate device independent of the second processor 910, or can be integrated in the second processor 910.

[0238] Optionally, the chip 900 can further include an input interface 930. The second processor 910 can control the input interface 930 to communicate with other devices or chips, specifically, can obtain information or data sent by other devices or chips.

[0239] Optionally, the chip 900 can further include an output interface 940. The second processor 910 can control the output interface 940 to communicate with other devices or chips, specifically, can output information or data to other devices or chips.

[0240] ​​​Optionally, the chip can be applied to the first function / second function in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the first function / second function in the various methods of the embodiments of the present application. For brevity, details are not repeated here.

[0241] It should be understood that the chip mentioned in the embodiments of the present application can also be referred to as a system chip, a system chip, a chip system, or a system on chip, etc.

[0242] Figure 10 is a schematic block diagram of a communication system 1000 provided by the embodiments of the present application. As shown in ​ , the communication system 1000 includes a first function 60 and a second function 70.

[0243] The first function 60 can be used to implement the corresponding functions implemented by the first function in the above-mentioned methods, and the second function 70 can be used to implement the corresponding functions implemented by the second function in the above-mentioned methods. For brevity, details are not repeated here.

[0244] It should be understood that the processor of the embodiments of the present application can be an integrated circuit chip with signal processing capability. In the implementation process, each step of the above-mentioned method embodiments can be completed by integrated logic circuits of hardware in the processor or instructions in the form of software. The processor mentioned above can be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component. The disclosed methods, steps and logic block diagrams in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can be any conventional processor. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly embodied as a hardware coding processor for execution, or a combination of hardware and software modules in the coding processor for execution. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, a register, or other mature storage medium in the art. The storage medium is located in the memory, and the processor reads the information in the memory, and combines the hardware to complete the steps of the above-mentioned method.

[0245] As an example, a processor can include one or more general-purpose Central Processing Units (CPUs). Each of these processors can be a single-CPU processor or a multi-CPU processor. A processor here can refer to one or more devices, circuits, and / or processing cores for processing data, such as computer-executed instructions.

[0246] It is to be appreciated that the memory in the embodiments of this application can be volatile, nonvolatile, or a combination of both. The non-volatile memory can be, for example, read only memory (ROM), programmable ROM (PROM), erasable PROM (EPROM), electrically EPROM (EEPROM), or flash memory. The volatile memory can be, for example, random access memory (RAM), which acts as external cache. By way of example and not limitation, many forms of RAM are available, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DR RAM). It is to be appreciated that the system and method described herein can be implemented with either single type of memory or both types of memory. It is also to be appreciated that the system and method described herein can be implemented on one device or both devices of a system of multiple devices.

[0247] It should be understood that the above-mentioned memory is an example but not a limiting description, for example, the memory in the embodiments of the present application can also be static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct memory bus random access memory (Direct Rambus RAM, DR RAM) and the like. That is, the memory in the embodiments of the present application is intended to include but not limited to these and any other suitable type of memory.

[0248] The embodiments of the present application also provide a computer readable storage medium for storing a computer program.

[0249] Optionally, the computer readable storage medium can be applied to the first function / second function in the embodiments of the present application, and the computer program makes the computer execute the corresponding processes in the respective methods of the embodiments of the present application which are realized by the first function / second function. For brevity, it will not be repeated here.

[0250] In the above-mentioned embodiments, all or part can be realized by software, hardware, firmware or any combination thereof. When realized by software, it can be realized in the form of computer program product in whole or in part.

[0251] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the processes or functions according to the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that the computer can store or be integrated into a data storage device such as a server, data center, etc. containing one or more available media. The available media can be magnetic media (for example, floppy disk, hard disk, magnetic tape), optical media (for example, DVD), or semiconductor media (for example, solid state disk (SSD)) and the like.

[0252] The communication method, the first function, the second function and the storage medium provided by the embodiments of the present application are described in detail above, and the principles and implementation manners of the present application are described by applying specific examples. The above description of the embodiments is only used to help understand the method of the present application and its core idea; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation manner and application range will be changed, and the above description should not be understood as a limitation of the present application.

[0253] It should be understood that the "one embodiment" or "an embodiment" or "the embodiments of the present application" or "the foregoing embodiment" or "some embodiments" or "some embodiments" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiments are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" or "in the embodiments of the present application" or "in the foregoing embodiment" or "in some embodiments" or "in some embodiments" appearing throughout the specification does not necessarily mean the same embodiment. In addition, these specific features, structures or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in various embodiments of the present application, the size of the sequence number of the above processes does not mean the execution order, and the execution order of the processes should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. The above sequence number of the embodiments of the present application is only for description, not representing the advantages and disadvantages of the embodiments.

[0254] Unless otherwise defined, the first function / second function performs any step in the embodiments of the present application, which can be a processor of the first function / second function performing the step. Unless otherwise specified, the embodiments of the present application do not limit the order of the steps performed by the first function / second function. In addition, the way of processing data in different embodiments can be the same or different.

[0255] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, another division manner can be used, such as: a plurality of units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed components can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0256] The units described above as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units; they can be located in one place or distributed on multiple network units; and part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0257] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be realized in the form of hardware or in the form of hardware plus software functional unit.

[0258] The methods disclosed in several method embodiments provided in the present application can be combined arbitrarily without conflict to obtain new method embodiments.

[0259] The features disclosed in several product embodiments provided in the present application can be combined arbitrarily without conflict to obtain new product embodiments.

[0260] The features disclosed in several method or device embodiments provided in the present application can be combined arbitrarily without conflict to obtain new method embodiments or device embodiments.

[0261] Those skilled in the art can understand that all or part of the steps of the above-mentioned method embodiments can be completed by program instruction related hardware, and the foregoing program can be stored in a computer storage medium, and the program executes the steps of the above-mentioned method embodiments when executed; and the foregoing storage medium includes a mobile storage device, a ROM, a magnetic disc or an optical disc and various storage medium that can store program codes.

[0262] Alternatively, the integrated units of the present application can be stored in a computer storage medium if the integrated units are realized in the form of software function modules and sold or used as independent products. Based on such understanding, the technical solutions of the embodiments of the present application can be embodied in the form of software product, and the computer software product is stored in a storage medium, includes several instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the methods described in the embodiments of the present application. The foregoing storage medium includes a mobile storage device, a ROM, a magnetic disc or an optical disc and various storage medium that can store program codes.

[0263] The singular forms "a", "an" and "the" used in the embodiments of the present application and the appended claims are intended to include plural forms, unless the context clearly indicates otherwise.

[0264] It should be noted that in each of the embodiments of the present application, all steps can be executed or part of the steps can be executed, as long as a complete technical solution is formed.

[0265] The above is only the implementation of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical range disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A communication method characterized by comprising: The method applied to the first function comprises: sending a model storage request to a second function; the first function comprises a model training logic function; and the second function comprises an analysis data storage function; receiving a model storage response sent by the second function; wherein the model storage response comprises first information; and the first information comprises relevant information of at least one network function service consumer or supplier authorized to access the second function; determining a manner in which a first network function service consumer acquires a target model according to the first information; the target model comprises a machine learning model or an artificial intelligence model.

2. The method of claim 1, wherein, The determining of the manner in which the first network function service consumer acquires the target model according to the first information comprises: receiving second information sent by the first network function service consumer; wherein the second information is used to request acquisition of the target model; and the second information comprises identification information of the first network function service consumer; determining the manner in which the first network function service consumer acquires the target model based on the identification information and the first information.

3. The method of claim 2, wherein, The determining of the manner in which the first network function service consumer acquires the target model based on the identification information and the first information comprises: if the identification information matches the first information, determining that the first network function service consumer acquires the target model in a first manner.

4. The method of claim 2, wherein, The determining of the manner in which the first network function service consumer acquires the target model based on the identification information and the first information comprises: if the identification information does not match the first information, determining that the first network function service consumer acquires the target model in a second manner.

5. The method of claim 2, wherein, The identification information comprises at least one of the following: a supplier identification of the first network function service consumer; a network function instance identification of the first network function service consumer; an analysis identification corresponding to the first network function service consumer.

6. The method of claim 3, wherein, The method further comprises: in a case where the first network function service consumer acquires the target model in the first manner, sending an identification of the second function to the first network function service consumer.

7. The method of claim 4, wherein, The method further comprises: in a case where the first network function service consumer acquires the target model in the second manner, sending third information to the second function; wherein the third information is used to request acquisition of the target model; receiving information of the target model sent by the second function; sending the information of the target model to the first network function service consumer.

8. The method of claim 7, wherein, The model storage request comprises relevant information of at least one network function service consumer or supplier authorized to access the first function.

9. A communication method characterized by comprising: The method applied to the second function comprises: receiving a model storage request sent by a first function; the first function comprises a model training logic function; and the second function comprises an analysis data storage function; sending a model storage response to the first function; wherein the model storage response comprises first information; and the first information comprises relevant information of at least one network function service consumer or supplier authorized to access the second function.

10. The method of claim 9, wherein, The model storage request includes information about at least one network function service consumer or provider authorized to access the first function.

11. The method of claim 9, wherein, The method further includes: At the time of registration of the second function, the first information is configured in a third function.

12. The method according to any one of claims 9 to 11, characterized in that, The method further includes: In a case where the first network function consumer acquires a target model in a first manner, third information sent by the first network function service consumer is received; the third information is used to request information about the target model; Information about the target model is sent to the first network function service consumer.

13. The method according to any one of claims 9 to 11, characterized in that, The method further includes: In a case where the first network function consumer acquires a target model in a second manner, third information sent by the first function is received; the third information is used to request information about the target model; Information about the target model is sent to the first function.

14. A first communications device, characterized by: The first communication device includes: A first sending module configured to send a model storage request to a second function; the first function includes a model training logic function; the second function includes an analysis data storage function; A first receiving module configured to receive a model storage response sent by the second function; the model storage response includes first information; the first information includes information about at least one network function service consumer or provider authorized to access the second function; A first processing module configured to determine, according to the first information, a manner in which a first network function service consumer acquires a target model; the target model includes a machine learning model or an artificial intelligence model.

15. A second communications device, characterized by The second communication device includes: A second receiving module configured to receive a model storage request sent by a first function; the first function includes a model training logic function; the second function includes an analysis data storage function A second sending module configured to send a model storage response to the first function; the model storage response includes first information; the first information includes information about at least one network function service consumer or provider authorized to access the second function.

16. A first communication device, characterized by The first communication device includes: A first memory configured to store executable instructions; A first processor configured to execute the executable instructions stored in the first memory to implement the communication method of any one of claims 1 to 8.

17. A second communication device, characterized by The second communication device includes: A second memory configured to store executable instructions; A second processor configured to execute the executable instructions stored in the second memory to implement the communication method of any one of claims 9 to 13.

18. A computer-readable storage medium, characterized in that, The computer readable storage medium stores one or more programs executable by one or more processors to implement the communication method of any one of claims 1 to 8, or the communication method of any one of claims 9 to 13.

Images