Model registration method and device, and model access method and device

Abstract

The present application provides a model registration method and device, and a model access method and device, which enhance the security of providing services by models. The method comprises: a first model proxy network element receives first model registration information, the first model registration information comprising model information of a first model and function information of the first model; the first model proxy network element sends test information to a model providing network element corresponding to the first model, the test information being related to the first model registration information, and the test information being used for the model providing network element to test the first model; the first model proxy network element receives a first model test result, the first model test result being a result of the model providing network element testing the first model on the basis of the test information; and the first model proxy network element determines a first model registration result, the first model registration result being related to the first model test result.

Description

Method and apparatus for model registration and access

[0001] The present application claims priority to the Chinese patent application No. 202411332999.X, filed on September 23, 2024, and entitled "Method and apparatus for model registration and access", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the technical field of wireless communication, and more particularly, to a method and apparatus for model registration and access. BACKGROUND

[0003] The artificial intelligence (AI) models associated with the AI services provided by the future network can be provided by multiple different vendors worldwide, which can include operators, device vendors, and over-the-top media services (OTT) vendors, etc. The security of the models, as the core assets of the model-providing network elements, cannot be ignored. The model-providing network elements can wish to shield the models from the outside or limit them in a private network to provide services to terminals. Similarly, from the perspective of terminal privacy protection, the terminal can wish to use personal data after security processing to avoid the occurrence of personal privacy leakage or personal data abuse problems. Therefore, how to effectively isolate the terminal and the model-providing network element to protect the security of the models and data is a problem that needs to be solved at present. SUMMARY

[0004] The present application provides a method and apparatus for model registration and access, which enhances the security of model-providing services.

[0005] In a first aspect, an embodiment of the present application provides a method for registering a model. The method is applied to a first model agent network element. For example, the method can be executed by the first model agent network element, or implemented by a component (for example, a circuit, a processor, a chip, or a chip system) in the first model agent network element, or can be a logic module or software capable of realizing all or part of the function of the first model agent network element. The present application does not limit this. The following takes the first model agent network element as an example. The method comprises the following steps: the first model agent network element receives first model registration information, wherein the first model registration information comprises model information of a first model and function information of the first model; the first model agent network element sends test information to a model providing network element corresponding to the first model, wherein the test information is related to the first model registration information, and the test information is used for testing the first model by the model providing network element; the first model agent network element receives a first model test result, wherein the first model test result is a result of testing the first model by the model providing network element based on the test information; and the first model agent network element determines a first model registration result, wherein the first model registration result is related to the first model test result.

[0006] Based on the above technical solution, the method for registering a model provided by the embodiment of the present application can filter out a model with a performance meeting the requirements and register the model in the first model agent network element to provide the model for a terminal by sending test information to a model providing network element to obtain a model test result. The method can solve the security problem of the model providing service by isolating the direct contact between the terminal and the model providing network element.

[0007] In combination with the first aspect, in some implementations of the first aspect, the determining the first model registration result comprises: the first model test result passes the verification, the first model agent network element allocates a first model identifier to the first model, and registers the first model registration information and the first model test result; and the first model identifier is used for associating the first model. In this way, when the first model test result passes the verification, the first model agent network element can efficiently manage the first model passing the verification by using the first model identifier.

[0008] In combination with the first aspect, in some implementations of the first aspect, the first model agent network element sends first registration result indication information, and / or the first model agent network element sends the first model identifier, and the first registration result indication information indicates the first model registration result.

[0009] Based on the above technical solution, the first model agent network element can timely notify the model providing network element of the model registration result, so as to avoid the model providing network element continuously waiting for obtaining the model registration result.

[0010] With reference to the first aspect, in some implementations of the first aspect, the first model agent network element obtains subscription information of the first model, and the subscription information comprises service information of the first model. In this way, the first model agent network element and the model providing network element can align the manner in which the first model provides services.

[0011] With reference to the first aspect, in some implementations of the first aspect, the first model agent network element deregisters the first model when a first condition is met. Based on the above technical solution, the first model agent network element can deregister the failed first model, thereby avoiding providing the failed model to the terminal for use and reducing the storage overhead of the first model registration information.

[0012] With reference to the first aspect, in some implementations of the first aspect, the first condition is met when, within a first time period, the first model agent network element does not receive a re-registration request from the model providing network element; or the first model agent network element receives deregistration information from the model providing network element, the deregistration information indicating that the first model agent network element deregisters the first model; or the first model agent network element determines that the first model is failed. Based on the above technical solution, the first model agent network element can identify the failed model, thereby avoiding providing the failed model to the terminal for use and reducing the storage overhead of the first model registration information.

[0013] With reference to the first aspect, in some implementations of the first aspect, the deregistering the first model comprises deleting the first model registration information. Based on the above technical solution, the first model agent network element can delete the registration information of the failed model, thereby avoiding providing the failed model to the terminal for use and reducing the storage overhead of the first model registration information.

[0014] In a second aspect, an embodiment of the present application provides a method for registering a model. The method is applied to a model providing network element, for example, the method can be executed by the model providing network element, or implemented by a component (for example, a circuit, a processor, a chip or a chip system) inside the model providing network element, or can also be a logic module or software capable of realizing all or part of the function of the model providing network element, and the present application does not make any limitation in this regard. The following takes the model providing network element as an example for description, and the method comprises the following steps: the model providing network element sends first model registration information, wherein the first model registration information comprises model information of the first model and function information of the first model; the model providing network element receives test information, wherein the test information is related to the first model registration information, and the test information is used for testing the first model by the model providing network element; and the model providing network element sends a first model test result, wherein the first model test result is a result of testing the first model by the model providing network element based on the test information.

[0015] Based on the technical solution, the method for registering a model provided by the embodiment of the present application sends the first model test result to the first model agent network element, thereby screening a model meeting the performance requirement and registering the model in the first model agent network element to provide the model for a terminal. The method solves the security problem of the model providing service by isolating the direct contact between the terminal and the model providing network element.

[0016] In combination with the second aspect, in some implementations of the second aspect, the model providing network element receives first registration result indication information, and / or the model providing network element receives a first model identifier allocated to the first model; the first result indication information indicates a first model registration result of the first model, and the first model registration result is related to the first model test result; and the first model identifier is used to associate the first model. In this way, the model providing network element can learn the registration result of the first model in time, thereby avoiding continuous waiting.

[0017] In combination with the second aspect, in some implementations of the second aspect, the model providing network element and the first model agent network element negotiate to determine the subscription information of the first model, and the subscription information includes service information of the first model. In this way, the first model agent network element and the model providing network element can align the service providing mode of the first model.

[0018] In combination with the second aspect, in some implementations of the second aspect, the model providing network element sends deregistration information to the first model agent network element, the deregistration information indicates that the first model agent network element deregisters the first model, and the deregistration includes deleting the first model registration information. Based on the technical solution, the first model agent network element can identify and delete the registration information of the invalid model, thereby avoiding providing the invalid model for the terminal, and also reducing the storage cost of the first model registration information.

[0019] Optionally, the test information includes test configuration, and the test configuration can include test cases. In addition, the test information can also include test data sets. The type and content of the test information are related to the received first model registration information from the model providing network element. In this way, by sending the test configuration or sending the test configuration and the test data set, the model providing network element can be instructed to test the first model, thereby ensuring the validity of the test result.

[0020] Optionally, the first model registration information further includes one or more of scenario information of the first model, network element information of the first model, and access information of the first model. In this way, after receiving the first model registration information, the first model agent network element can register the scenario information of the first model, and / or the network element information of the first model, and / or the access information of the first model.

[0021] Optionally, the subscription information further comprises registration information publishing range of the first model and / or charging information of the first model. In this way, the first model agent network element and the model providing network element can perform subscription negotiation on the registration information publishing range of the first model and / or the charging mode of the first model.

[0022] In a third aspect, an embodiment of the present application provides a method for publishing information, which is applied to a first model agent network element. For example, the method can be executed by the first model agent network element, or implemented by a component (for example, a circuit, a processor, a chip or a chip system) in the first model agent network element, or a logic module or software capable of realizing all or part of the function of the first model agent network element. The present application does not make any limitation in this regard. The following takes the first model agent network element as an example. The method comprises: the first model agent network element publishes a first model publishing information set to a terminal, wherein the first model publishing information set comprises first model publishing information, and the first model publishing information corresponds to a first model registered in the first model agent network element; and / or the first model agent network element publishes a second model publishing information set to a second model agent network element, wherein the second model publishing information set comprises second model publishing information, and the second model publishing information corresponds to a first model registered in the first model agent network element.

[0023] Based on the above technical solution, the information publishing method provided by the embodiment of the present application realizes the perception of the model providing service in a region by publishing the registered model information in the region. In addition, the registered model information is diffused among other model agents to realize the registered model information publishing in a wider region, which can provide service for more terminals.

[0024] In combination with the third aspect, in some implementation manners of the third aspect, the first model agent network element receives third model publishing information from the second model agent network element, and the third model publishing information corresponds to a second model registered in the second model agent network element. Based on the above technical solution, the first model agent network element can perceive the model registration in other model agents, obtain the registration information of the model registered in other model agents, and provide more diverse and comprehensive model services for terminals.

[0025] With reference to the third aspect, in some implementations of the third aspect, the first model publishing information set includes fourth model publishing information, the fourth model publishing information corresponding to at least one piece of the third model publishing information. In this way, when the content or format of the received third model publishing information does not meet the publishing requirements, the first model agent network element can generate fourth model publishing information that meets the requirements based on the third model publishing information and then publish the fourth model publishing information to the terminal. In addition, at least one piece of third model publishing information included in the third model publishing information set can be combined into one piece of fourth model publishing information and then published, thereby reducing the cost of information publishing.

[0026] With reference to the third aspect, in some implementations of the third aspect, the fourth model publishing information includes second model information and second function information corresponding to the second model, or the fourth model publishing information includes a second public identifier corresponding to the second model. In this way, the terminal can determine whether the second model corresponding to the received fourth model publishing information can meet its own needs.

[0027] With reference to the third aspect, in some implementations of the third aspect, the first model publishing information includes first model information and first function information corresponding to the first model, or the first model publishing information includes a first public identifier corresponding to the first model. In this way, the terminal can determine whether the first model corresponding to the received first model publishing information can meet its own needs.

[0028] With reference to the third aspect, in some implementations of the third aspect, the first model agent network element publishes a first mapping relationship table to the terminal, the first mapping relationship table including association information of the first public identifier and the first model, and / or the first mapping relationship table including association information of the second public identifier and the second model. Based on the above technical solution, the terminal can determine the information of the model that can provide services based on the received first mapping relationship table and the first public identifier or the second public identifier.

[0029] With reference to the third aspect, in some implementations of the third aspect, the first model agent network element receives a model information query request; and determines the content of the first model publishing information set based on the model information query request. Based on the above technical solution, the first model agent network element can adjust the content of the first model publishing information set based on the model information query request of the terminal, thereby improving the efficiency of publishing the first model publishing information set.

[0030] With reference to the third aspect, in some implementations of the third aspect, the first model publishing information set further includes fifth model publishing information, the fifth model publishing information and the first model publishing information have different publishing frequencies. In this way, the first model agent network element can publish the first model publishing information corresponding to the first model with high priority at a higher frequency, so as to guide the terminal to select the first model with high priority to provide services.

[0031] With reference to the third aspect, in some implementations of the third aspect, the first model agent network element sends first identity matching information to the terminal, the first identity matching information indicates that the first model and the second model correspond to the same model providing network element. In this way, the terminal can know that the first model registered in the first model agent network element and the second model registered in the second model agent network element are the same model according to the first identity matching information.

[0032] With reference to the third aspect, in some implementations of the third aspect, the second model publishing information includes sixth model publishing information, the sixth model publishing information is a conversion of one or more of the model identifier, the function identifier, the model access entry, and the second public identifier corresponding to at least one of the first models. In this way, the first model agent network element can effectively ensure the security of information transmission when transmitting the information corresponding to the first model to the second model agent network element in a different network.

[0033] With reference to the third aspect, in some implementations of the third aspect, the first model agent network element performs inverse conversion on the third model publishing information received from the second model agent network element, the inverse conversion is used to obtain one or more of the model identifier, the function identifier, the model access entry, and the second public identifier corresponding to at least one of the second models. In this way, the first model agent network element can correctly interpret the content of one or more of the model identifier, the function identifier, and the model access entry of the second model corresponding to the third model publishing information.

[0034] The fourth aspect, the embodiments of the present application provide a method for obtaining information, the method is applied to the terminal, for example, the method can be executed by the terminal, or implemented by components (such as circuits, processors, chips or chip systems) contained in the terminal, or it can also be a logic module or software capable of realizing all or part of the terminal function, the present application does not limit this. As follows, the terminal is taken as an example for description, and the method comprises: the terminal receives a first model publishing information set, the first model publishing information set includes first model publishing information, and the first model publishing information corresponds to a first model registered in a first model agent network element.

[0035] Based on the technical solution, the method for acquiring information provided by the embodiment of the application realizes the perception of the terminal to the model providing services in the region through the publishing of the registration model information in a certain region.

[0036] In combination with the fourth aspect, in some implementation manners of the fourth aspect, the first model publishing information set further includes second model publishing information, and the second model publishing information corresponds to a second model registered in a second model agent network element. Based on the technical solution, the terminal can perceive the information of the models registered in multiple different model agent network elements through receiving the first model publishing information set, and can obtain more diverse and comprehensive model services.

[0037] In combination with the fourth aspect, in some implementation manners of the fourth aspect, the second model publishing information includes second model information and second function information corresponding to the second model, or the second model publishing information includes a second public identifier corresponding to the second model. In this way, the terminal can determine whether the corresponding second model can meet its own demand according to the received second model publishing information.

[0038] In combination with the fourth aspect, in some implementation manners of the fourth aspect, the first model publishing information includes first model information and first function information corresponding to the first model, or the first model publishing information includes a first public identifier corresponding to the first model. In this way, the terminal can determine whether the corresponding first model can meet its own demand according to the received first model publishing information.

[0039] In combination with the fourth aspect, in some implementation manners of the fourth aspect, the terminal receives a first mapping relationship table from the first model agent network element, and the first mapping relationship table includes the association information between the first public identifier and the first model, and / or the first mapping relationship table includes the association information between the second public identifier and the second model. Based on the technical solution, the terminal can determine the information of the model that can provide services based on the received first mapping relationship table and the first public identifier or the second public identifier.

[0040] In combination with the fourth aspect, in some implementation manners of the fourth aspect, the terminal sends a model information query request to the first model agent network element, and the model information query request is used to determine the content of the first model publishing information set. Based on the technical solution, the first model agent network element can adjust the content of the first model publishing information set according to the model information query request of the terminal, and improve the effectiveness of the first model publishing information set acquired by the terminal.

[0041] With reference to the fourth aspect, in some implementations of the fourth aspect, the terminal receives first identity matching information from the first model proxy network element, the first identity matching information indicating that the first model and the second model correspond to the same model providing network element. In this way, the terminal can know that the first model registered at the first model proxy network element and the second model registered at the second model proxy network element are the same model according to the first identity matching information.

[0042] In a fifth aspect, an embodiment of the present application provides a method for providing model access, which is applied to a first model proxy network element. For example, the method can be executed by the first model proxy network element, or implemented by a component (such as a circuit, a processor, a chip or a chip system) in the first model proxy network element, or a logic module or software capable of realizing all or part of the function of the first model proxy network element, which is not limited in the present application. The following takes the first model proxy network element as an example. The method comprises: the first model proxy network element receives a service request, the service request comprising first information of a model to be accessed; in response to the service request, sending response information, the response information comprising related information of a first service model matched with the first information; and the first deployment network element providing access service to the first service model based on the related information of the first service model. Based on the above technical solution, the method for providing model access provided by an embodiment of the present application builds a channel between a terminal and a model providing network element through the first model proxy network element, and realizes secure access of the terminal to the model.

[0043] With reference to the fifth aspect, in some implementations of the fifth aspect, the related information of the first service model comprises a first model access portal corresponding to the first service model, or the related information of the first service model comprises the first model access portal corresponding to the first service model and an identifier of the first model proxy network element or an identifier of a second model proxy network element where the first service model is registered. In this way, the first model proxy network element or the second model proxy network element can provide model access service for the terminal through the first model access portal.

[0044] With reference to the fifth aspect, in some implementations of the fifth aspect, the first deployment network element indicates that the first model access portal is deployed in the first model proxy network element or the second model proxy network element, or the first deployment network element indicates that the first model access portal is deployed in a first anchor network element corresponding to the first model proxy network element or a second anchor network element corresponding to the second model proxy network element. Based on the above technical solution, the first model access portal can be arranged at the model proxy or arranged on an independent network element, and flexible deployment of the model access portal can be realized.

[0045] With reference to the fifth aspect, in some implementations of the fifth aspect, the providing, by the first deployment network element, of the access service to the first service model based on the related information of the first service model comprises: forwarding, by the first deployment network element, first data from the terminal to a model providing network element through the first model access portal; and forwarding, by the first deployment network element, a data processing result from the model providing network element to the terminal through the first model access portal, the data processing result indicating a result of processing of the first data by the first service model. Based on the above technical solution, the first deployment network element can realize secure access of the terminal to the model by forwarding data and data processing results between the terminal and the model providing network element.

[0046] With reference to the fifth aspect, in some implementations of the fifth aspect, the providing, by the first deployment network element, of the access service to the first service model based on the related information of the first service model further comprises: performing, by the first deployment network element, charging based on a charging policy corresponding to the first service model. In this way, the first deployment network element can perform charging according to the charging policy, thereby realizing revenue.

[0047] With reference to the fifth aspect, in some implementations of the fifth aspect, before the performing, by the first deployment network element, of the charging based on the charging policy corresponding to the first service model, the method further comprises: sending, by the first model agent network element, the charging policy to the first deployment network element. In this way, when the model access portal is deployed on the second model agent network element or the anchor network element, charging can still be performed according to the correct charging policy, thereby realizing revenue.

[0048] With reference to the fifth aspect, in some implementations of the fifth aspect, the service request comprises regional information of the terminal, the regional information of the terminal indicating that the terminal is subscribed to the first model agent network element or the second model agent network element. In this way, the first model agent network element can determine whether to obtain the subscription policy of the terminal from the second model agent network element to serve the terminal.

[0049] With reference to the fifth aspect, in some implementations of the fifth aspect, before the determining of the response information, the first model agent network element obtains the subscription policy of the terminal from the second model agent network element. In this way, the first model agent network element can serve the terminal that is subscribed to the second model agent network element.

[0050] In a sixth aspect, an embodiment of the present application provides a method for providing model access, which is applied to a model providing network element. For example, the method can be executed by the model providing network element, or implemented by a component (for example, a circuit, a processor, a chip or a chip system) in the model providing network element, or can be a logic module or software capable of realizing all or part of the function of the model providing network element, which is not limited in the present application. The following is described by taking the model providing network element as an example. The method comprises the following steps: the model providing network element receives first data from a first deployment network element; and the model providing network element sends a data processing result to the first deployment network element, wherein the data processing result indicates a result of processing the first data by a first service model. Based on the above technical solution, the model access method provided by the embodiment of the present application builds a channel between a terminal and a model providing network element through a first model agent network element, and realizes safe access of the terminal to the model.

[0051] In combination with the sixth aspect, in some implementations of the sixth aspect, the first deployment network element indicates that a first model access portal corresponding to the first service model is deployed in a first model agent network element or a second model agent network element; or the first deployment network element indicates that the first model access portal corresponding to the first service model is deployed in a first anchor network element corresponding to the first model agent network element or a second anchor network element corresponding to the second model agent network element. Based on the above technical solution, the first model access portal can be arranged at the model agent or arranged on a separate network element, and flexible deployment of the model access portal can be realized.

[0052] In a seventh aspect, an embodiment of the present application provides a method for accessing a model, which is applied to a terminal. For example, the method can be executed by the terminal, or implemented by a component (for example, a circuit, a processor, a chip or a chip system) included in the terminal, or can be a logic module or software capable of realizing all or part of the function of the terminal, which is not limited in the present application. The following is described by taking the terminal as an example. The method comprises the following steps: the terminal sends a service request to a first model agent network element, wherein the service request comprises first information of a model to be accessed; the terminal receives response information, wherein the response information comprises related information of a first service model matched with the first information; and the terminal accesses the first service model through a first deployment network element based on the related information of the first service model. Based on the above technical solution, the model access method provided by the embodiment of the present application enables the terminal to build a channel between the first model agent network element and a model providing network element, and realize safe access to the model.

[0053] In some implementations of the seventh aspect, in conjunction with the seventh aspect, the related information of the first service model includes a first model access entry corresponding to the first service model, or the related information of the first service model includes the first model access entry corresponding to the first service model and an identifier of the first model agent network element or an identifier of a second model agent network element in which the first service model is registered. In this way, the terminal can obtain the model access service provided by the first model agent network element or the second model agent network element through the first model access entry.

[0054] In some implementations of the seventh aspect, in conjunction with the seventh aspect, the first deployment network element indicates the first model agent network element or the second model agent network element in which the first model access entry is deployed, or the first deployment network element indicates a first anchor network element corresponding to the first model agent network element or a second anchor network element corresponding to the second model agent network element in which the first model access entry is deployed. Based on the above technical solution, the first model access entry can be arranged at the model agent or arranged on an independent network element, and flexible deployment of the model access entry can be implemented.

[0055] In some implementations of the seventh aspect, in conjunction with the seventh aspect, the accessing the first service model based on the related information of the first service model through the first deployment network element includes: the terminal sending first data to the first deployment network element; and the terminal receiving a data processing result from the first deployment network element, the data processing result indicating a result of processing the first data by the first service model. Based on the above technical solution, the first deployment network element can forward data and data processing results between the terminal and the model providing network element, and secure access of the terminal to the model can be implemented.

[0056] In some implementations of the seventh aspect, in conjunction with the seventh aspect, the service request includes regional information of the terminal, and the regional information of the terminal indicates that the terminal is subscribed to the first model agent network element or the second model agent network element. In this way, the first model agent network element can determine whether to obtain the subscription policy of the terminal from the second model agent network element to serve the terminal.

[0057] In an eighth aspect, an electronic device is provided. The electronic device is configured to perform the method provided in the first aspect or the second aspect or the third aspect or the fourth aspect or the fifth aspect or the sixth aspect or the seventh aspect. Specifically, the electronic device can include units and / or modules for performing the method provided in the first aspect or any of the implementation manners of the first aspect, such as a processing unit and an obtaining unit. Alternatively, the electronic device can include units and / or modules for performing the method provided in the second aspect or any of the implementation manners of the second aspect, such as a processing unit and an obtaining unit. Alternatively, the electronic device can include units and / or modules for performing the method provided in the third aspect or any of the implementation manners of the third aspect, such as a processing unit and an obtaining unit. Alternatively, the electronic device can include units and / or modules for performing the method provided in the fourth aspect or any of the implementation manners of the fourth aspect, such as a processing unit and an obtaining unit. Alternatively, the electronic device can include units and / or modules for performing the method provided in the fifth aspect or any of the implementation manners of the fifth aspect, such as a processing unit and an obtaining unit. Alternatively, the electronic device can include units and / or modules for performing the method provided in the sixth aspect or any of the implementation manners of the sixth aspect, such as a processing unit and an obtaining unit. Alternatively, the electronic device can include units and / or modules for performing the method provided in the seventh aspect or any of the implementation manners of the seventh aspect, such as a processing unit and an obtaining unit.

[0058] In conjunction with the eighth aspect, in some implementations of the eighth aspect, the electronic device is a model agent network element. The obtaining unit can be a transceiver, or an input / output interface. The processing unit can be at least one processor. Optionally, the transceiver can be a transceiver circuit. Optionally, the input / output interface can be an input / output circuit.

[0059] In conjunction with the eighth aspect, in some implementations of the eighth aspect, the electronic device is a chip, a chip system, or a circuit in the model agent network element. The obtaining unit can be an input / output interface, an interface circuit, an output circuit, an input circuit, a pin, or related circuitry, etc. on the chip, the chip system, or the circuit. The processing unit can be at least one processor, a processing circuit, or a logic circuit, etc.

[0060] In conjunction with the eighth aspect, in some implementations of the eighth aspect, the electronic device is a model provision network element. The obtaining unit can be a transceiver, or an input / output interface. The processing unit can be at least one processor. Optionally, the transceiver can be a transceiver circuit. Optionally, the input / output interface can be an input / output circuit.

[0061] In some implementations of the eighth aspect, the electronic device is a chip, chip system or circuit in the network element. The obtaining unit can be an input / output interface, interface circuit, output circuit, input circuit, pin or related circuit on the chip, chip system or circuit; and the processing unit can be at least one processor, processing circuit or logic circuit.

[0062] In some implementations of the eighth aspect, the electronic device is a terminal. The obtaining unit can be a transceiver or an input / output interface; and the processing unit can be at least one processor. Optionally, the transceiver can be a transceiver circuit. Optionally, the input / output interface can be an input / output circuit.

[0063] In some implementations of the eighth aspect, the electronic device is a chip, chip system or circuit in the terminal. The obtaining unit can be an input / output interface, interface circuit, output circuit, input circuit, pin or related circuit on the chip, chip system or circuit; and the processing unit can be at least one processor, processing circuit or logic circuit.

[0064] In the ninth aspect, an embodiment of the present application provides a processor for executing the method provided in the above aspects. For the sending and obtaining / receiving operations of the processor, if no special description is given, or if it does not contradict the actual role or inherent logic in the related description, it can be understood as the processor output and receive, input, etc. operations, or it can be understood as the sending and receiving operations performed by the radio frequency circuit and the antenna, and the present application does not limit this.

[0065] In the tenth aspect, an embodiment of the present application provides a computer readable storage medium. The computer readable storage medium stores program code for execution by a device, and the program code includes a method for executing any one of the above first aspect to seventh aspect, and any one of the implementation manners of any one of the first aspect to seventh aspect.

[0066] In the eleventh aspect, an embodiment of the present application provides a computer program product containing instructions. When the computer program product runs on a computer, the computer is caused to execute the method provided in any one of the above first aspect to seventh aspect, and any one of the implementation manners of any one of the first aspect to seventh aspect.

[0067] In the twelfth aspect, an embodiment of the present application provides a chip. The chip includes a processor and a communication interface. The processor reads instructions stored on a memory through the communication interface, and executes the method provided in any one of the above first aspect to seventh aspect, and any one of the implementation manners of any one of the first aspect to seventh aspect.

[0068] Optionally, as an implementation form, the chip further comprises a memory, the memory storing a computer program or instructions, and the processor is configured to execute the computer program or instructions stored in the memory, and when the computer program or instructions are executed, the processor is configured to execute the method provided in any one of the first aspect to the seventh aspect and any one of the implementation forms of any one of the first aspect to the seventh aspect.

[0069] In a thirteenth aspect, an embodiment of the present application provides a system for providing a model service, the system comprising the electronic device of the eighth aspect.

[0070] In addition, the technical effects of the eighth aspect to the thirteenth aspect can refer to the technical effects of the method of the first aspect to the seventh aspect, which will not be described here. BRIEF DESCRIPTION OF DRAWINGS

[0071] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the background art, the drawings needed to be used in the embodiments of the present application or the background art will be described below.

[0072] FIG. 1 is a schematic diagram of an AI module suitable for the embodiments of the present application;

[0073] FIG. 2 is a schematic flowchart of a model registration method 200 provided by an embodiment of the present application;

[0074] FIG. 3 is a schematic flowchart of a release information method 300 provided by an embodiment of the present application;

[0075] FIG. 4 is a schematic flowchart of a model access providing method 400 provided by an embodiment of the present application;

[0076] FIG. 5 is a schematic block diagram of an electronic device 500 provided by an embodiment of the present application;

[0077] FIG. 6 is a schematic block diagram of an electronic device 600 provided by an embodiment of the present application;

[0078] FIG. 7 is a structural schematic diagram of an electronic device 700 provided by an embodiment of the present application;

[0079] FIG. 8 is a structural schematic diagram of an electronic device 800 provided by an embodiment of the present application. DETAILED DESCRIPTION

[0080] The technical solutions in the embodiments of the present application will be described below with reference to the drawings.

[0081] The terminology used in the following embodiments is for the purpose of describing specific embodiments only and is not intended to be limiting of this application. As used in the specification and appended claims of this application, the singular expressions “a,” “an,” and “the” are intended to include expressions such as “one or more,” unless the context clearly indicates otherwise. It should also be understood that in the following embodiments of this application, “at least one,” “at least one,” and “one or more” refer to one, two, or more than two. “First,” “second,” and various numerical designations are merely distinctions for descriptive convenience and are not intended to limit the scope of the embodiments of this application. “And / or” is used to describe the correspondence between corresponding objects, indicating that three relationships can exist. For example, “A and / or B” can represent: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character “ / ” generally indicates that the preceding and following related objects are in an “or” relationship. The order of the process numbers below does not imply the order of execution. The execution order of each process should be determined by its function and internal logic and should not constitute any limitation on the implementation process of the embodiments of this application. For example, in the embodiments of this application, the words "201", "301", "401" etc. are merely identifiers made for the convenience of description and do not limit the order of execution steps.

[0082] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. In this application, the words "exemplary" or "for example" are used to indicate that something is illustrative, exemplary, or descriptive. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized. In the embodiments of this application, descriptions such as "when," "in the case of," "if," and "if" all refer to the fact that the device will perform a corresponding processing under certain objective circumstances, and are not a limitation on time, nor do they require the device to perform a judgment action during implementation, nor do they imply any other limitations.

[0083] The technical solutions of the embodiments of the present application can be applied to various communication systems, for example: a long-term evolution (LTE) system, an LTE frequency division duplex (FDD) system, an LTE time division duplex (TDD), a universal mobile telecommunication system (UMTS), a worldwide interoperability for microwave access (Wi-MAX) communication system, a 5th generation (5G) system or new radio (NR), a future 6th generation (6G) system, a narrow band-Internet of things (NB-IoT) system, a global system for mobile communications (GSM), an enhanced data rate for GSM evolution (EDGE), a wideband code division multiple access (WCDMA) system, a code division multiple access 2000 (CDMA2000) system, a time division-synchronization code division multiple access (TD-SCDMA) system, an inter-satellite communication and a satellite communication, and a non-terrestrial network (NTN) system such as a non-terrestrial communication network. The satellite communication system includes a satellite base station and a terminal. The satellite base station provides communication services for the terminal. The satellite base station can also communicate with a base station. The satellite can act as a base station or a terminal. The satellite can be an unmanned aerial vehicle, a hot air balloon, a low-orbit satellite, a medium-orbit satellite, a high-orbit satellite, or the like. The satellite can also be a non-ground base station or a non-ground device.

[0084] Embodiments of the present application can be applied to a terminal. The terminal can be a wireless terminal or a wired terminal. The wireless terminal can be a device that provides voice and / or data connectivity to a user, a handheld device having wireless connection capability, a wearable device, a computing device, or other processing device connected to a wireless modem. The wireless terminal can communicate with one or more core networks via a radio access network (RAN). The wireless terminal can be a mobile terminal, such as a mobile telephone (also known as a "cellular" telephone) and a computer with a mobile termination, e.g., a portable, pocket, handheld, computer-embedded, or car-mounted mobile apparatus that exchanges language and / or data with a radio access network. For example, the wireless terminal can be a personal communication service (PCS) phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), a subscriber unit, a smart phone, a wireless data card, a computer, a tablet computer, a wireless modem, a handset, a laptop computer, a machine type communication (MTC) terminal, or the like. The wireless terminal can also be referred to as a system, a subscriber unit (SU), a subscriber station (SS), a mobile station (MS), a mobile, a remote station (RS), an access point (AP), a remote terminal (RT), an access terminal (AT), a user terminal (UT), a user agent (UA), a user device (UD), or a user equipment (UE).

[0085] The apparatus for implementing the functions of the terminal in the embodiments of the present application can be a terminal, or can be an apparatus capable of supporting the terminal to implement the functions, such as a chip system. The apparatus can be installed in the terminal or used in matching with the terminal. In the embodiments of the present application, the chip system can be composed of a chip, or can include a chip and other discrete devices.

[0086] The technical solutions in the embodiments of the present application can also be applied to an access network device. The access network device can be a device capable of accessing a terminal to a wireless network. The access network device can also be referred to as a radio access network (RAN) node, a radio access network device, a network device. For example, the access network device can be a base station.

[0087] The base station in the embodiments of the present application can cover various names in the following or replace the names in the following, such as: Node B (NodeB), evolved Node B (eNB), base station gNB in 5G network, relay station, access point, transmission reception point, transmitting point (TP), master eNodeB (MeNB), secondary eNodeB (SeNB), multi-standard radio (MSR) node, home base station, network controller, access node, wireless node, AP, transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), positioning node, etc. The base station can be a macro base station, a micro base station, a relay node, a donor node or the like, or a combination thereof. The base station can also refer to a communication module, modem or chip used in the foregoing devices or apparatuses. The base station can also be a network side device in a 6G network, a device assuming a base station function in a future communication system, etc. The base station can support networks of the same or different access technologies.

[0088] The base station can be a central unit (CU) and distributed unit (DU) separation architecture. The RAN can be connected with a core network (for example, a core network of Long Term Evolution (LTE), a core network of 5G, etc.). The CU and the DU can be understood as a division of the base station from a logical function perspective. The CU and the DU can be physically separated or deployed together. Multiple DUs can share one CU. One DU can also connect to multiple CUs. The CU and the DU can be connected through an interface, for example, an F1 interface. The CU and the DU can be divided according to a protocol layer of a wireless network. For example, in one possible division, the CU is configured to perform functions of a radio resource control (RRC) layer, a service data adaptation protocol (SDAP) layer, and a packet data convergence protocol (PDCP) layer, and the DU is configured to perform functions of a radio link control (RLC) layer, a media access control (MAC) layer, a physical (PHY) layer, and the like. It can be understood that the division of the processing functions of the CU and the DU according to the protocol layer is only an example, and the CU and the DU can also be divided in other manners. For example, the CU or the DU can be divided into more protocol layers. For example, the CU or the DU can also be divided into partial processing functions of the protocol layers. In one design, partial functions of the RLC layer and functions of the protocol layers above the RLC layer are arranged in the CU, and the remaining functions of the RLC layer and functions of the protocol layers below the RLC layer are arranged in the DU. In another design, the functions of the CU or the DU can also be divided according to a service type or other system requirements. For example, according to a delay, functions requiring a delay requirement to be met are arranged in the DU, and functions not requiring the delay requirement to be met are arranged in the CU. In another design, the CU can also have one or more functions of a core network. One or more CUs can be centrally arranged or separately arranged. For example, the CU can be arranged at a network side for centralized management. The DU can have multiple radio frequency functions, or the radio frequency functions can be remotely arranged.

[0089] The functions of the CU can be implemented by one entity or by different entities. For example, the functions of the CU can be further divided, for example, the control plane (CP) and the user plane (UP) are separated, i.e., the control plane of the CU (CU-CP) and the user plane of the CU (CU-UP). For example, the CU-CP and the CU-UP can be implemented by different functional entities and are connected through an E1 interface. The CU-CP and the CU-UP can be coupled with the DU to jointly complete the functions of the base station. The control plane of the CU CU-CP also includes a further divided architecture, i.e., the existing CU-CP is further divided into CU-CP1 and CU-CP2. The CU-CP1 includes various radio resource management functions, and the CU-CP2 only includes RRC functions and PDCP-C functions (i.e., basic functions of control plane signaling at the PDCP layer).

[0090] The base station can be fixed or mobile. For example, a helicopter or a drone can be configured to act as a mobile base station, and one or more cells can move according to the location of the mobile base station. In other examples, the helicopter or the drone can be configured to act as a device that communicates with another base station.

[0091] The technical solutions in the embodiments of the present application can also be applied to operation administration and maintenance (OAM). OAM refers to the actual needs of the operation of the operator network, and the management of the network is usually divided into three categories: operation, administration, and maintenance, which are collectively referred to as OAM. OAM can also be referred to as an OAM entity or function. Operation mainly completes the analysis, prediction, planning, and configuration of daily network and services; maintenance mainly includes the daily operation activities of testing and fault management of the network and services, and OAM can detect the running state of the network, optimize network connection and performance, improve network running stability, and reduce network maintenance costs.

[0092] The technical solutions in the embodiments of the present application can also be applied to third-party application services, for example, over the top (OTT). OTT refers to providing various application services to users through the Internet. Such applications are different from the communication services currently provided by operators, which only use the network of the operator, and the services are provided by a third party outside the operator. At present, typical OTT services include Internet television services, application stores, etc.

[0093] The technical solutions in the embodiments of the present application can be applied to network equipment. The network equipment can be a base station or a core network device. The core network device can include a mobility management module (MME), an access and mobility management function (AMF) network element, a network data analytics function (NWDAF) network element, a session management function (SMF) network element, or other core network network elements.

[0094] An AI model, that is, an AI algorithm (or an AI operator), is a general term for a mathematical algorithm constructed based on the principle of artificial intelligence, and is also the basis for solving specific problems using AI. The type of AI model is not limited in the embodiments of the present application. For example, the AI model can be a machine learning model, a deep learning model, a reinforcement learning model, or a federated learning, etc.

[0095] Machine learning is a method for realizing artificial intelligence, and the goal of the method is to design and analyze some algorithms (that is, models) that can be automatically "learned" by a computer. The designed algorithm is called a machine learning model. A machine learning model is a kind of algorithm that automatically analyzes rules from data and uses the rules to predict unknown data. Machine learning models are diverse, and according to whether the model needs to rely on the corresponding label of the training data during training, the machine learning model can be divided into: 1, a supervised learning model; 2, an unsupervised learning model.

[0096] Deep learning is a new technical field in the process of machine learning research. Specifically, deep learning is a method for learning deep features based on data in machine learning. Deep learning explains data by establishing a neural network that simulates the analysis and learning of the human brain. In the machine learning method, almost all features need to be determined by industry experts and then encoded. However, the deep learning algorithm attempts to learn features from data itself. The algorithm designed according to the deep learning idea is called a deep learning model.

[0097] Reinforcement learning is a special field in machine learning, which is a process of constantly learning the optimal strategy through the interaction between an agent and an environment, making sequential decisions, and obtaining the maximum return. In simple terms, reinforcement learning is learning "what to do (i.e., how to map the current situation into an action) to maximize the numerical reward signal". The agent will not be told what action to take, but must discover for itself which actions will yield the most generous rewards through trial and error. Reinforcement learning is different from supervised learning and unsupervised learning in the field of machine learning. Supervised learning is a process of learning from externally provided labeled training data (task-driven), and unsupervised learning is a process of finding the implicit structure in unlabeled data (data-driven). Reinforcement learning is a process of finding better solutions through "trial and error". The agent must develop existing experience to obtain rewards, while also exploring so that better action selection space can be obtained in the future (i.e., learning from mistakes). The algorithm designed according to reinforcement learning is called a reinforcement learning model.

[0098] Federated learning (also known as collaborative learning) is a machine learning technique that can train algorithms on multiple decentralized edge devices or servers holding local data samples without exchanging them. This approach is in sharp contrast to traditional centralized machine learning techniques, where all local data sets are uploaded to a server to complete training. Federated learning enables multiple participants to build a common, robust machine learning model without sharing data, thus allowing the solution of key problems such as data privacy, data security, data access permissions, and access to heterogeneous data.

[0099] Any AI model needs to be trained before it is used to solve a specific technical problem. The training of an AI model refers to the process of using a specified initial model to calculate training data, adjusting the parameters in the initial model according to the results of the calculation, and gradually learning certain rules to the model so that it has a specific function. The AI model with stable function after training can be used for inference. The inference of an AI model is the process of using a trained AI model to calculate input data and obtain the predicted inference result (also known as output data).

[0100] The AI module is a module with AI learning and computing capability. In a wireless communication system, the AI module can be located in an OAM, or in a gNB (separated architecture located in a CU), or in part of a UE, or as a separate network element entity. The main function of the AI module in a wireless communication system is to perform a series of AI calculations such as model establishment, training approximation, and reinforcement learning according to input data (for example, in a wireless communication system, the input data can be network operation data provided by the RAN side or monitored by the OAM, such as network load, channel quality, etc.). The trained model provided by the AI module has the function of predicting changes in the RAN network, and can be used for load prediction, UE trajectory prediction, etc. In addition, the AI module can also infer strategies from the perspective of network energy saving and mobility optimization based on the prediction results of the trained model of the RAN network performance, to obtain reasonable and efficient energy saving strategies, mobility optimization strategies, etc. When the AI module is located in the OAM, its communication with the gNB of the RAN side can reuse the current northbound interface; when the AI module is located in the gNB or CU, it can reuse the current F1, Xn, Uu, etc. interface; when the AI module is independent as a network entity, it needs to re-establish a communication link to the OAM and RAN side, for example, based on a wired link or a wireless link.

[0101] FIG. 1 is a schematic diagram of an AI module applicable to the embodiments of the present application. As shown in FIG. 1, the AI module 100 includes a database module 101, a training module 102, a model module 103, and an execution module 104.

[0102] The database module 101 can store training data. The training data can also come from a terminal. The training data can come from a network device. For example, the training data can come from a base station (such as a gNB) or a functional unit (such as a CU or a DU) that makes up the base station. For another example, the training data can come from a network device other than a base station. For example, a gateway, a management entity (such as an MME or other core network device, etc.

[0103] The training module 102 analyzes the training data provided by the database module 101 to obtain an AI model. The training module 102 can send the trained AI model to the model module 103. After completing the training of the AI model, the training module 102 can also update the trained model and send the update parameters for updating the model to the model module 103. The model module 103 can also collect some running data of the model in the process of running the AI model, and send these running data to the training module 102. The training module 102 can update the AI model according to these running data.

[0104] The model module 103 can determine output data according to the AI model and the input data. The output data can include a prediction result of network operation based on the input data and the AI model. The output data can also include an adjustment strategy determined according to the input data and the AI model. In some embodiments, the network device and / or the terminal can directly send the input data to the model module 103. In other embodiments, the database module 101 can also collect data from the network device and / or the terminal, determine the input data, and send the input data to the model module 103.

[0105] The execution module 104 can be used to execute the adjustment strategy determined by the model module 103. The execution module 104 can also collect the specific performance of the network after the adjustment strategy is applied, such as performance parameters in the network, and feed back the information to the database module 101. The database module 101 can store the feedback information. The feedback information can be used for subsequent model training or improvement of the AI model.

[0106] The following introduces the application in the AI mobile communication system. In the mobile communication system, the AI model can be used to intelligently collect and analyze data, and improve network performance and user experience.

[0107] For example, AI can be applied to CSI feedback enhancement. CSI is the channel property of a communication link, and is the channel quality information reported by a terminal to a base station. The terminal reports the downlink channel quality information to the base station, so as to select a more suitable modulation and coding scheme (MCS) for the terminal, so as to better adapt to the changing wireless channel.

[0108] For another example, AI can also be applied to beam management (BM). BM is mainly used to find the strongest beam pair. AI-based beam prediction can improve prediction accuracy.

[0109] For another example, AI can also be applied to positioning accuracy enhancements. Positioning accuracy is related to the number of total radiated power antennas. Generally speaking, the more the number of total radiated power antennas, the higher the positioning accuracy. With AI models, higher positioning accuracy can be achieved with fewer total radiated power antennas. For example, traditional positioning methods, such as time difference of arrival (TDOA), round trip time (RTT), etc., rely on information collection of line of sight (LOS) paths between terminals and total radiated power antennas. For indoor scenarios, there can not be enough number of LOS paths, and traditional positioning methods can not work well. Therefore, AI-based positioning can improve positioning accuracy in scenarios with less LOS paths.

[0110] For another example, AI can also be applied to network energy saving. Network energy saving can be through cell activation / deactivation, reducing load, improving coverage, or other RAN setting adjustment. Optimal energy saving decisions depend on factors such as load conditions of different RAN nodes, RAN node capabilities, key performance indicator (KPI) requirements, quality of service (QoS) requirements, number of activated users and mobility of terminals, cell utilization, etc. However, improving network energy efficiency is a complex process, and incorrect cell shutdown and incorrect traffic offloading operations, etc. can cause network performance to decline or even energy efficiency to decline. AI technology can be used to optimize energy saving decisions by utilizing data collected in the RAN network. AI algorithms can predict the energy efficiency and load status of the next period, which can be used to better decide cell activation / deactivation to save energy. Based on the predicted load, the system can dynamically configure energy saving strategies to maintain a balance between system performance and energy efficiency, and reduce energy consumption.

[0111] For another example, AI can also be applied to load balancing. The purpose of load balancing is to evenly distribute the load among cells and among areas within a cell, or to transfer part of the traffic from a congested cell, or to split the terminal on one cell, carrier or access mode, to improve network performance. This can be achieved by optimizing handover parameters and handover actions. The automation of such optimization can provide a high-quality user experience, while improving system capacity and minimizing manual intervention for network management and optimization tasks. Currently, load balancing decisions that rely on the current / past moment of cell load state are not enough. In addition, the overall network and service performance is difficult to guarantee when load balancing. Therefore, AI model-based solutions can be introduced to improve load balancing performance, such as inputting various measurements and feedbacks of users and network nodes, historical data, etc. into the AI model to improve load balancing performance, to provide a higher quality of user experience and improve system capacity.

[0112] For another example, AI can also be applied to mobility optimization. Mobility management is a scheme to ensure service continuity during terminal movement by minimizing dropped calls, radio link failure (RLF), unnecessary handovers, and ping-pong effects. For future high-frequency networks, as the coverage area of a single node decreases, the frequency of terminal handover between nodes will become high, especially for high-mobility terminals. In addition, for applications with strict QoS requirements such as reliability, latency, etc., the quality of experience (QoE) is sensitive to handover performance, so mobility management should avoid handover failures and reduce latency during handover. However, for traditional methods, it is challenging to achieve almost zero-failure handover based on trial-and-error solutions. Therefore, AI-based solutions can be used to enhance mobility management in the following aspects: 1) reduce the probability of unexpected events, 2) terminal location / mobility / performance prediction, 3) traffic steering.

[0113] The following describes in detail the method of registering a model (corresponding to method 200 below), the method of publishing information (corresponding to method 300 below), and the method of providing model access (corresponding to method 400 below) provided by the embodiments of the present application in conjunction with the accompanying drawings.

[0114] It should be noted that in the embodiments of the present application, the model agent network element (including the first model agent network element and the second model agent network element) can be located in different network devices (such as base stations, core network devices, etc.) in the wireless communication system constituted with the terminal, or located in the OAM, or located in the application service OTT provided by the third party, or the model agent network element as a stand-alone network element, etc. to realize the functions of registering the model, publishing the information, and accessing the model. Among them, the core network device can include at least one of MME, AMF, NWDAF, SMF, or other network devices. It should be understood that any one network element or entity or application service mentioned above in which the first model agent network element is located and the model providing network element can interact with the first model agent network element based on the method of registering the model provided by the present application; any one network element or entity or application service mentioned above in which the first model agent network element is located and the terminal, and / or the second model agent network element can interact with the terminal and / or the second model agent network element based on the method of publishing the information provided by the present application; any one network element or entity or application service mentioned above in which the first model agent network element is located and the model providing network element and the terminal can interact with the model providing network element and the terminal based on the method of accessing the model provided by the present application.

[0115] It should be further noted that in the embodiments of the present application, the model providing network element can be located in the terminal, or located in different network devices (such as base stations, core network devices, etc.) in the wireless communication system constituted with the terminal, or located in the OAM, or located in the application service OTT provided by the third party, or the model providing network element as a stand-alone network element, etc. to realize the functions of registering the model and accessing the model. Among them, the core network device can include at least one of MME, AMF, NWDAF, SMF, or other network devices. It should be understood that any one network element or entity or application service mentioned above in which the model providing network element is located and the model agent network element can interact with the first model agent network element based on the method of registering the model provided by the present application; any one network element or entity or application service mentioned above in which the model providing network element is located and the first model agent network element and the terminal can interact with the model agent network element and the terminal based on the method of accessing the model provided by the present application.

[0116] In addition, in the embodiments of the present application, the model information, the function information, the scenario information, the network element information, the access information, the subscription information, the information of the model providing network element, the model charging policy, the model usage policy, and the subscribed area information are involved. The subscription information involves the registration information publishing range, the service information, and the charging information. It should be understood that the names of the above information are only names used for conveniently explaining the embodiments of the present application, and do not affect the protection scope of the present application. In the future development of technology, the names of the information can be changed, but if the functions of the information are the same as those described in the embodiments of the present application, the information should be within the protection scope of the present application.

[0117] FIG. 2 is a schematic flowchart of a method 200 for registering a model from the perspective of device interaction, according to an embodiment of the present application. As shown in FIG. 2, the method 200 can include S201 to S204. The steps of the method 200 will be explained in detail below.

[0118] S201, the model providing network element sends first model registration information to the first model agent network element, the first model registration information being used for requesting registration of a first model.

[0119] Specifically, the first model registration information includes the model information of the first model and the function information of the first model. The model information includes, but is not limited to, at least one of the input and output data types of the model, the model structure information, and the data type of the model parameter. The function information is used for indicating the function of the model, and the function of the model includes part or all of channel estimation, beam management, and mobility management. When the model providing network element wants to register the model, the model providing network element sends the first model registration information to the first model agent network element, the first model registration information being used for requesting registration of the first model. Correspondingly, the first model agent network element receives the first model registration information of the model providing network element.

[0120] It should be understood that the first model registration information can include at least one of the above-mentioned model information. Similarly, the first model registration information can include at least one of the above-mentioned function information.

[0121] Optionally, the first model registration information can further include one or more of the scenario information of the first model, the network element information of the first model, and the access information of the first model. The scenario information is used for indicating the scenario in which the model can be applied, and the scenario information can include one or more of the service type, the environmental parameter, and the geographic location. The network element information is used for indicating the type and the location of the model providing network element. The access information can include the access entry and / or the access permission of the first model.

[0122] Optionally, the first model registration information further includes the subscription information of the first model, and the subscription information includes the service information of the first model.

[0123] Specifically, the subscription information of the first model can be carried in the first model registration information and sent by the model providing network element to the first model agent network element. The service information is used to indicate the user type and scenario that can access the model.

[0124] Optionally, the subscription information of the first model can further include the registration information publishing range of the first model and / or the charging information of the first model.

[0125] Specifically, the registration information publishing range is used to indicate the network and regional range in which the model can publish the registration information. The charging information is used to indicate the charging policy of the model providing network element when providing the model service to the outside.

[0126] S202, the first model agent network element sends test information to the model providing network element, the test information being related to the first model registration information, and the test information being used for the model providing network element to test the first model.

[0127] Optionally, in the embodiment of the present application, the test information includes test configuration. The test configuration can include test case. The test configuration indicates the method and parameter of the model configuration during the test, and can include the structure of the model, the size of the model, and the value of the hyperparameter. The test case indicates the scenario, flow and method of the model test. The test information can be used to test the first model to obtain the first model test result. For example, the model providing network element can configure the model according to the obtained test configuration information, and test the model based on the standard data set downloaded / obtained locally to obtain the model test result.

[0128] Optionally, the test information further includes test data set, and the test data set indicates a set of data used for model test. The test data set can include input data of the model, and / or output verification data / output verification label of the model. The test data set can be used in combination with the test configuration described above to test the first model to obtain the first model test result. For example, the model providing network element can configure the model according to the obtained test configuration information, and test the model based on the received test data set to obtain the model test result.

[0129] It should be understood that the test information sent by the first model agent network element to the model agent network element is related to the first model registration information, which indicates that the test information sent by the first model agent network element to the model agent network element is determined according to the first model registration information. For example, when the first model registration information includes the function information of the first model, and the function information indicates that the first model is used for beam management, the test information can include beam-related input information and beam-related output verification information to test the performance of the first model.

[0130] It should also be understood that the model providing network element providing the test indication of the first model assesses or verifies the performance of the first model.

[0131] S203, the first model agent network element receives the first model test result from the model providing network element, the first model test result being the result of the test of the first model by the model providing network element based on the test information.

[0132] It should be noted that the first model test result in the embodiments of the present application is used to describe the performance of the model, which can be the evaluation result of the accuracy, stability and efficiency of the model. For example, when the first model is used for channel information compression feedback, the first model test result can be squared generalized cosine similarity (SGCS), which measures the similarity between the model output result and the output verification label, indicating the accuracy of the channel information compression feedback. The value of the squared generalized cosine similarity is between 0 and 1, and the closer the value is to 1, the higher the similarity between the model output result and the output verification label. When they are completely the same, the value reaches the maximum value 1. The process of obtaining the squared generalized cosine similarity is as follows: the first model obtains the output vector b according to the input vector a, and the output verification label corresponding to the input vector a is the vector c. The squared generalized cosine similarity can be calculated according to the following formula: where n is the dimension of the vector b and the vector c, b i and c i are the i-th elements in the vector b and the vector c, respectively.

[0133] It should be understood that the first model test result being the result of the test of the first model by the model providing network element based on the test information indicates that the first model test result is the corresponding test result of the first model, and the first model test result is related to the test information.

[0134] S204, the first model agent network element determines the first model registration result, which is related to the first model test result.

[0135] It should be noted that the determination of the first model registration result by the first model agent network element can be understood as the determination of whether the first model is registered successfully or failed. In addition, the first model registration result being related to the first model test result can be understood as the determination of the first model registration result by the first model agent network element according to the first model test result.

[0136] In a possible implementation, the process in which the first model agent network element determines the first model registration result is as follows: if the first model test result meets the requirements of the first model agent network element, the first model agent network element determines that the first model can be registered, at this time, the first model agent network element determines that the first model registration provided by the model providing network element is successful. Or if the first model test result cannot meet the requirements of the first model agent network element, the first model agent network element determines that the first model cannot be registered, at this time, the first model agent network element determines that the first model registration provided by the model providing network element fails.

[0137] It should be noted that the first model test result meeting the requirements of the first model agent network element can be understood as that the first model agent network element verifies that the first model test result meets the requirements. Exemplarily, the first model test result is the square generalized cosine similarity, and the threshold value of the first model test result set by the first model agent network element is 0.99. The first model agent network element compares the size of the first model test result and the threshold value, when the first model test result is greater than or equal to 0.99, the first model passes the verification of the first model agent network element, which indicates that the first model can meet the requirements of the first model agent network element and can be successfully registered in the first model agent network element. Conversely, when the first model test result is lower than 0.99, the first model fails to pass the verification of the first model agent network element, which indicates that the first model cannot meet the requirements of the first model agent network element and fails to be registered in the first model agent network element.

[0138] Optionally, the method 200 further includes the following steps:

[0139] S205, the first model agent network element allocates a first model identifier to the first model, registers the first model registration information and the first model test result; wherein the first model identifier is used to associate the first model.

[0140] Specifically, when the first model test result passes the verification, the first model agent network element allocates a first model identifier to the first model, which is different from the identifiers of other models registered in the first model agent network element, and the purpose is to facilitate the management of the first model. In addition, the first model agent network element also registers the first model registration information and the first model test result, which facilitates the publication of relevant information to terminal users. The first model agent network element registering the first model registration information and the first model test result can be understood as that the first model agent network element stores / records the first model registration information and the first model test result. Exemplarily, the first model agent network element can register and manage the first model in the manner described in the following Table 1:

[0141] Table 1

[0142] Optionally, S206, the first model agent network element sends a first registration result indication information to the model providing network element, and / or the first model agent network element sends a first model identifier to the model providing network element.

[0143] Specifically, when the first model test result passes the verification, the first model agent network element sends a first registration result indication information to the model providing network element, the first registration result indication information indicating that the model registration is successful. Alternatively, when the first model test result passes the verification, the first model agent network element sends a first model identifier assigned to the first model to the model providing network element. Alternatively, when the first model test result passes the verification, the first model agent network element sends a first registration result indication information and a first model identifier assigned to the first model to the model providing network element, wherein the first registration result indication information indicates that the model registration is successful. When the first model test result fails the verification, the first model agent network element sends a first registration result indication information to the model providing network element, the first registration result indication information indicating that the model registration fails. Illustratively, the indication field occupied by the registration result indication information includes a number of bits equal to 1, if the value of the indication field is 1, it indicates that the first model registration is successful; if the value of the indication field is 0, it indicates that the first model registration fails; it can also be the opposite, if the value of the indication field is 0, it indicates that the first model registration is successful; if the value of the indication field is 1, it indicates that the first model registration fails.

[0144] Optionally, S207, the first model agent network element and the model providing network element negotiate to determine the subscription information of the first model, the subscription information including service information of the first model.

[0145] Specifically, when the first model registration is successful, the first model agent network element and the model providing network element negotiate to determine the subscription information of the first model, the subscription information including service information of the first model. Wherein, the service information is used to represent the user type and scenario that can access the model.

[0146] Optionally, the subscription information of the first model further includes registration information publishing range of the first model and / or charging information of the first model.

[0147] Specifically, the registration information publishing range is used to represent the network and regional range in which the model can publish the registration information. The charging information is used to represent the charging policy of the model providing network element when providing the model service to the outside.

[0148] It should be understood that the first model agent network element and the model providing network element negotiate to determine the subscription information of the first model, which can include the first model agent network element indicating the subscription information of the first model to the model providing network element, can also include the model providing network element indicating the subscription information of the first model to the first model agent network element, and can also include the first model agent network element and the model providing network element agreeing on the subscription information of the first model through at least one round of interaction information, which is not limited in the embodiments of the present application.

[0149] Optionally, the first model agent network element deregisters the first model in S208.

[0150] In a possible implementation, the first model agent deregisters the first model if the first model agent does not receive a re-registration request from the model providing network element within a first time period, and the deregistration includes deleting the registration information of the first model. For example, the first model agent network element starts a registration update timer when the registration of the first model is successful, and provides timing information to the model providing network element, which is used by the model providing network element to update the registration of the first model before the timer expires. When the timer expires, the first model agent network element still does not receive a re-registration request from the model providing network element, and the first model agent network element starts a deregistration process, which includes deleting the registration information of the first model from the model list.

[0151] In another possible implementation, the first model agent network element receives deregistration information from the model providing network element, which indicates that the first model agent network element deregisters the first model, and the deregistration includes deleting the registration information of the first model. For example, when the model providing network element cannot provide services due to its own reasons such as location movement or function update, the model providing network element sends deregistration information to the first model agent network element, which indicates that the first model agent network element deregisters the first model, and the deregistration includes deleting the registration information of the first model. For example, the indication field occupied by the deregistration information includes a number of bits equal to 1, and if the value of the indication field is 0, it indicates deregistration of the first model; or conversely, if the value of the indication field is 1, it indicates deregistration of the first model.

[0152] In yet another possible implementation, when the first model agent network element determines that the first model is invalid, the first model is deregistered, which includes deleting the first model registration information. Specifically, the first model invalidity indicates that the first model can no longer provide services for the terminal, or the first model invalidity indicates that the first model can no longer meet the requirements of the first model agent network element. Exemplarily, when the SGCS value corresponding to the first model registered in the first model agent network element is lower than the standard value 0.99 set by the first model agent network element, the first model agent network element considers that the first model can no longer provide services for the terminal, and then starts a deregistration process, which includes deleting the first model registration information from the model list.

[0153] FIG. 3 is a schematic flowchart of a method 300 of publishing information provided by an embodiment of the present application, shown from the perspective of device interaction. As shown in FIG. 3, the method 300 can include S301. The steps of the method 300 are described in detail below.

[0154] S301, the first model agent network element sends a first model publishing information set to the terminal, the first model publishing information set being used to indicate information of a first model registered in the first model agent network element. And / or, the first model agent network element sends a second model publishing information set to a second model agent network element, the second model publishing information set being used to indicate information of the first model registered in the first model agent network element.

[0155] Specifically, the first model agent network element can send the first model publishing information set to the terminal, so that the terminal learns the information of the registered model. The first model publishing information set includes first model publishing information, which corresponds to the first model registered in the first model agent network element. The first model agent network element can also send the second model publishing information set to the second model agent network element, so that the second model agent network element learns the information of the first model registered in the first model agent network element. The second model publishing information set includes second model publishing information, which corresponds to the first model registered in the first model agent network element.

[0156] It should be noted that the first model agent network element can send both the first model publishing information set to the terminal and the second model publishing information set to the second model agent network element, or only send the first model publishing information set to the terminal, or only send the second model publishing information set to the second model agent network element.

[0157] Optionally, the first model publishing information set is published to the terminal by a system information block (SIB) of a radio access network (RAN) or by a non-access stratum (NAS) message of an access and mobility management function (AMF).

[0158] Optionally, the first model publishing information includes first model information corresponding to the first model and first function information, or the first model publishing information includes a first public identity corresponding to the first model.

[0159] Specifically, the first model information includes one or more of input and output data types, model structure information, and data types of model parameters of the first model. The first function information is used to represent a function of the first model, where the function of the first model includes one or more of channel estimation, beam management, and mobility management. The first public identity is used to represent a common feature of the first model and at least one other model registered at the first model agent. For example, when the first model and the at least one other model registered at the first model agent are both applicable to beam management, the first public identity is beam management, indicating that the first model is one of the models belonging to the beam management category.

[0160] Optionally, the first model publishing information can further include one or more of information of a first model providing network element corresponding to the first model, a first model charging policy, and a first model usage policy. The information of the first model providing network element is used to represent an identity of the model providing network element corresponding to the first model. The first model charging policy is used to represent a charging policy of the model providing network element corresponding to the first model when providing model services to the outside. The first model usage policy is used to represent a usage method of the first model.

[0161] It should be understood that the first model publishing information set can further include seventh model publishing information, and when the first model publishing information set includes the first model publishing information and the seventh model publishing information, the model corresponding to the seventh model publishing information and the model corresponding to the first model publishing information are different models.

[0162] It should also be understood that when the first model publishing information includes the first public identity, the first model publishing information corresponds to at least one model registered at the first model agent network element, including the first model.

[0163] Optionally, the first model publishing information sent by the first model agent network element to the terminal is different from the first model registration information received by the first model agent network element from the model providing network element. For example, the first model publishing information sent by the first model agent network element to the terminal can include part of the content of the first model registration information; or the first model publishing information sent by the first model agent network element to the terminal can be a conversion of the first model registration information; or the first model publishing information sent by the first model agent network element to the terminal can be a combination of the first model registration information and the second model registration information.

[0164] Optionally, the second model publishing information includes a model identifier and a function identifier corresponding to the first model, or the second model publishing information includes a third public identifier corresponding to the first model.

[0165] Specifically, the model identifier indicates an identifier for identifying a model, which can be a model number, a model code, and any other identifier information that can be used to identify a model. The function identifier is used to indicate the function of the model. After the function of the model is identified, the function identifier can be used to indicate the function information of the model. For example, function 1, function 2, and function 3 can be used to indicate channel estimation, beam management, and mobility management, respectively. Channel estimation, beam management, and mobility management can also be used to indicate channel estimation, beam management, and mobility management, respectively. The third public identifier is used to represent the common characteristics of the first model and at least one other model registered in the first model agent. For example, when the first model and at least one other model registered in the first model agent are both used for beam management, the first public identifier is beam management, which is used to represent that the first model belongs to one of the models in the beam management category.

[0166] Optionally, the second model publishing information includes a model access entry corresponding to the first model.

[0167] Specifically, the model access entry is used to indicate the location information for the terminal to interact with or access the first model. The terminal can use the function and service provided by the first model through the model access entry. The model access entry can be an IP address for access.

[0168] It should be understood that the second model publishing information set can also include eighth model publishing information. When the second model publishing information set includes the second model publishing information and the eighth model publishing information, the model corresponding to the eighth model publishing information and the model corresponding to the second model publishing information are different models.

[0169] It should also be understood that when the second model publishing information includes the third public identifier, the second model publishing information corresponds to at least one model registered in the first model agent network element, which includes the first model.

[0170] Optionally, the second model publishing information includes sixth model publishing information, the sixth model publishing information is a conversion of the model identifier corresponding to the first model, the function identifier, the model access entry, or the sixth model publishing information is a conversion of the third public identifier corresponding to the first model.

[0171] It should be understood that the conversion can be an encryption operation, which has the effect of protecting information. Exemplarily, the first model proxy network element can convert the real model access IP address into a pseudo address before sending it to the second model proxy network element.

[0172] Optionally, the first model proxy network element and the second model proxy network element can discover each other through a network storage function (NRF) network element and a discovery process.

[0173] Optionally, the first model proxy network element and the second model proxy network element can be interconnected by a point-to-point interface and directly communicate.

[0174] Optionally, the method 300 further includes the following steps:

[0175] S302, the first model proxy network element receives third model publishing information from the second model proxy network element, the third model publishing information corresponding to the second model registered in the second model proxy network element.

[0176] Optionally, the third model publishing information includes the model identifier and the function identifier corresponding to the second model, or the third model publishing information includes the second public identifier corresponding to the second model.

[0177] Specifically, the model identifier indicates an identifier for identifying a model, which can be a model number, a model code, and any kind of identification information that can be used to identify a model. The function identifier is used to indicate the function of the model. After the function of the model is identified, the function identifier can be used to indicate the function information of the model. Exemplarily, function 1, function 2, and function 3 can be used to indicate channel estimation, beam management, and mobility management, respectively. Channel estimation, beam management, and mobility management can also be used to indicate channel estimation, beam management, and mobility management, respectively. The second public identifier is used to represent the common characteristics of the second model and at least one other model registered in the second model proxy. Exemplarily, when the second model and at least one other model registered in the second model proxy are both applicable to beam management, the second public identifier is beam management, which is used to represent that the second model belongs to one of the models of the beam management category.

[0178] Optionally, the third model publishing information includes the model access entry corresponding to the second model.

[0179] Specifically, the model access portal is used to indicate the location information of the terminal and the second model interaction or access, and the terminal can use the functions and services provided by the second model through the model access portal. The model access portal can be an IP address of access.

[0180] Optionally, the first model publishing information set includes fourth model publishing information, and the fourth model publishing information corresponds to at least one piece of third model publishing information.

[0181] Specifically, when the first model publishing information set includes the fourth model publishing information, the terminal can be indicated the information of the second model registered in the second model agent network element. The fourth model publishing information can correspond to at least one piece of third model publishing information. When one piece of fourth model publishing information corresponds to one piece of third model publishing information, the fourth model publishing information can include all or part of the content of the third model publishing information. For example, the third model publishing information includes the model identifier, the function identifier and the model access portal of the second model registered in the second model agent network element, and the fourth model publishing information only includes the model identifier and the function identifier of the second model. When one piece of fourth model publishing information corresponds to multiple pieces of third model publishing information, the fourth model publishing information can include the common identifier of the multiple models corresponding to the multiple pieces of third model publishing information.

[0182] Optionally, the first model agent network element needs to obtain the third model publishing information from the second model agent network element before sending the first model publishing information set including the fourth model publishing information to the terminal.

[0183] Optionally, the fourth model publishing information is obtained by inverse conversion of at least one piece of third model publishing information. The inverse conversion is the reverse operation of the conversion. For example, when the third model publishing information includes a pseudo address obtained by processing the IP address of model access, the fourth model publishing information obtained by reverse processing of the pseudo address can indicate the IP address of model access.

[0184] Optionally, the first model publishing information set further includes fifth model publishing information, and the fifth model publishing information has a different publishing frequency from the first model publishing information.

[0185] It should be understood that the first model agent network element can publish the first model publishing information at a higher publishing frequency and publish the fifth model publishing information at a lower publishing frequency. The publishing frequency indicates the publishing period of the first model publishing information or the fifth model publishing information or indicates the number of publications in a fixed period. For example, the first model publishing information can be published at a frequency of three times per hour, and the fifth model publishing information can be published at a frequency of one time per hour.

[0186] S303, the first model agent network element publishes a first mapping relationship table to the terminal, which is used to indicate the association information between the public identity and the model.

[0187] Specifically, the first model agent network element publishes a first mapping relationship table to the terminal, which includes the association information between the first public identity and the first model, and / or which includes the association information between the second public identity and the second model.

[0188] It should be noted that the first mapping relationship table including the association information between the first public identity and the first model indicates that the terminal can learn the information of the first model corresponding to the first public identity through the first mapping relationship table. Or the terminal determines that the first model corresponding to the same first public identity and other models registered in the first model agent network element are equivalent or similar through the first mapping relationship table. Similarly, the first mapping relationship table including the association information between the second public identity and the second model indicates that the terminal can learn the information of the second model corresponding to the second public identity through the first mapping relationship table. Or the terminal determines that the second model corresponding to the same second public identity and other models registered in the second model agent network element are equivalent or similar through the first mapping relationship table. Exemplarily, the first model agent network element generates the first mapping relationship table in the manner described in Table 2.

[0189] Table 2

[0190] It should be understood that the first mapping relationship table can include both the association information between the first public identity and the first model and the association information between the second public identity and the second model, or can only include the association information between the first public identity and at least one first model, or can only include the association information between the second public identity and at least one second model.

[0191] It should also be understood that similar indicates that the first model corresponding to the same first public identity and other models registered in the first model agent network element can both provide services for a same service request and can both meet the requirements of a same service request.

[0192] S304, the terminal sends a model information query request to the first model agent network element, which is used to determine the content of the first model publishing information set.

[0193] It should be noted that the model information query request is used to determine the content of the first model publishing information set, which can be understood as that the first model agent network element determines the content of the first model publishing information set according to the model information query request, and can also be understood as that the content of the first model publishing information set published by the first model agent network element is related to the received model information query request from the terminal.

[0194] Optionally, the model information query request carries a description about the model, such as function information and / or scenario information of the model.

[0195] Optionally, the first model publishing information set includes first model publishing information containing all or part of the information of the first model associated with the model information query request, and / or the first model publishing information set includes fourth model publishing information containing all or part of the information of the second model associated with the model information query request. For example, the model information query request sent by the terminal to the first model agent network element includes information of a model capable of beam management required by the first model agent network element to feed back, and the first model agent network element can send the model information of the model E and the model F having the function of beam management, the information of the model providing network element, and the model charging policy to the terminal according to Table 3.

[0196] Table 3

[0197] S305, the first model agent network element sends the first identification matching information to the terminal, which is used to indicate that the first model registered in the first model agent network element and the second model registered in the second model agent network element correspond to the same model providing network element.

[0198] It should be understood that the model identifier of the first model registered by a model providing network element in the first model agent network element and the model identifier of the second model registered by the model providing network element in the second model agent network element can be different. The first model agent network element sends the model identifier of the first model and the model identifier of the second model corresponding to the same model providing network element to the terminal through the first identification matching information, so that the terminal can identify the first model or the second model corresponding to the same model providing network element when moving between the area managed by the first model agent network element and the area managed by the second model agent network element. For example, when the terminal hopes that the model providing network element Y continues to serve it, the first model agent network element can send the model identifier information of the same model providing network element Y registered in different model agent network elements shown in Table 4 to the terminal, so that the terminal selects the model I to provide services for it in the area managed by the first model agent network element, and when the terminal moves from the area managed by the first model agent network element to the area managed by the second model agent network element, it selects the model J to provide services for it in the area managed by the second model agent network element.

[0199] Table 4

[0200] FIG. 4 is a schematic flow diagram of a method 400 for providing model access provided by an embodiment of the present application from the perspective of device interaction. As shown in FIG. 4, the method 400 can include S401 to S403. The steps of the method 400 are described in detail below.

[0201] S401, the first model agent network element receives a service request from a terminal, for determining response information.

[0202] Specifically, when the terminal needs the first model agent network element to provide model service for it, the terminal sends a service request to the first model agent network element, the service request including first information of a model to be accessed. The first model agent network element determines response information according to the first information.

[0203] It should be noted that the above first information can include at least one of model function information, model structure information, input and output data type information, and scene information of the model to be accessed. The model to be accessed indicates a model that can match the first information. The first model agent network element can determine the response information after performing local retrieval according to the first information.

[0204] Optionally, the first model agent network element determines the response information according to the first information and a subscription policy of the terminal. The subscription policy of the terminal for determining the response information can be subscription data, subscription scheme, and subscription manner of a terminal user. The subscription policy can include service level of the terminal and inference accuracy in different service scenarios. The first model agent network element can determine the response information after performing local retrieval according to the first information and the subscription policy of the terminal.

[0205] Optionally, the service request of the terminal further includes regional information of the terminal, for the first model agent network element to identify whether the terminal is subscribed to the first model agent network element or the second model agent network element.

[0206] Optionally, when the terminal is located in a service area of the first model agent network element but is subscribed to the second model agent network element, the first model agent network element receives a subscription policy of the terminal from the second model agent network element for determining the response information.

[0207] S402, the first model agent network element sends the response information to the terminal, for responding to the service request.

[0208] Specifically, in response to the above service request, the first model agent network element sends response information to the terminal, the response information including related information of a first service model matching the received first information.

[0209] It should be understood that the first service model indicates a model that can meet the service request of the terminal user or can match the first information. The first service model is a first model registered in the first model agent network element or a second model registered in the second model agent network element.

[0210] Optionally, the relevant information of the first service model may include the first model access entry corresponding to the first service model, or the relevant information of the first service model may include the first model access entry corresponding to the first service model and the identifier of the first model proxy network element or the identifier of the second model proxy network element to which the first service model is registered.

[0211] It should be understood that the first model access entry indicates the location information of the interaction or access between the terminal and the first service model. The terminal can use the functions and services provided by the first service model through the first model access entry. The first model access entry can be the accessed IP address or its corresponding pseudo address.

[0212] It should also be understood that the identification indication of the model proxy network element can be used to distinguish the identification information of the model proxy network element. For example, the number of bits included in the indication field occupied by the identification information of the model proxy network element is equal to 1. If the value of the indication field is 0, it indicates that the first service model is registered in the first model proxy network element, and the first model proxy network element provides services to the terminal; if the value of the indication field is 1, it indicates that the first service model is registered in the second model proxy network element, and the second model proxy network element provides services to the terminal; or conversely, if the value of the indication field is 1, it indicates that the first service model is registered in the first model proxy network element, and the first model proxy network element provides services to the terminal; if the value of the indication field is 0, it indicates that the first service model is registered in the second model proxy network element, and the second model proxy network element provides services to the terminal.

[0213] S403, the first deployed network element provides access services to the first service model based on the relevant information of the first service model.

[0214] Optionally, the first deployment network element indicates the first model proxy network element or the second model proxy network element on which the first model access entry is deployed, or the first deployment network element indicates the first anchor network element corresponding to the first model proxy network element or the second anchor network element corresponding to the second model proxy network element on which the first model access entry is deployed.

[0215] Specifically, when the first model access entry is deployed on the first model proxy network element or the second model proxy network element, the first model proxy network element or the second model proxy network element provides the terminal with access services to the first service model. When the first model access entry is deployed on the first anchor network element corresponding to the first model proxy network element or the second anchor network element corresponding to the second model proxy network element, the first anchor network element or the second anchor network element provides the terminal with access services to the first service model. Here, the first anchor network element indicates an independent network element decoupled from the first model proxy network element, and the second anchor network element indicates an independent network element decoupled from the second model proxy network element.

[0216] Optionally, the step S404 that the first deployment network element provides an access service for the first service model based on the related information of the first service model comprises: the first deployment network element forwards first data from the terminal to the model providing network element through the first model access portal; and the first deployment network element forwards a data processing result from the model providing network element to the terminal through the first model access portal, the data processing result indicating a result of processing the first data by the first service model.

[0217] Specifically, the terminal establishes a session with the first model access portal, and the first model access portal establishes a session with the model providing network element corresponding to the first service model. The first deployment network element receives the first data from the terminal through the first model access portal, and forwards the first data to the model providing network element through the first model access portal. The first service model included in the model providing network element processes the first data to obtain a data processing result. The first deployment network element receives the data processing result from the model providing network element through the first model access portal, and forwards the data processing result to the terminal through the first model access portal.

[0218] It should be understood that the session established between the terminal and the first model access portal indicates a process of establishing a communication connection between the terminal and the first deployment network element in which the first model access portal is deployed. The terminal can send first data to the first deployment network element through the first model access portal, the first data indicating data that needs to be processed / used by the first service model. The terminal can also receive a data processing result from the first deployment network element through the first model access portal, the data processing result being an output result or output data of the first service model, or a result of processing the received first data by the model providing network element.

[0219] It should also be understood that the session established between the first model access portal and the model providing network element corresponding to the first service model indicates a process of establishing a communication connection between the first deployment network element in which the first model access portal is deployed and the model providing network element. The first deployment network element can send first data to the model providing network element through the first model access portal, the first data indicating data that needs to be processed / used by the first service model. The first deployment network element can also receive a data processing result from the model providing network element through the first model access portal, the data processing result being an output result or output data of the first service model, or a result of processing the received first data by the model providing network element.

[0220] Optionally, the method 400 further comprises the following steps:

[0221] The first deployment network element performs charging, S405.

[0222] Specifically, the first deployment network element performs charging statistics on service conditions of the terminal according to a charging policy of the first service model.

[0223] In a possible implementation, the first model access portal is deployed on the first model agent network element or the second model agent network element, and charging is performed by the first model agent network element or the second model agent network element on the terminal or on the terminal and the model providing network element.

[0224] In another possible implementation, the first model access portal is deployed on the first anchor network element corresponding to the first model agent network element or the second anchor network element corresponding to the second model agent network element, that is, the first model access portal is decoupled from the first model agent network element or the second model agent network element, and charging is performed by the first anchor network element or the second anchor network element. The first anchor network element or the second anchor network element needs to obtain a charging policy from the corresponding model agent network element to perform charging on the terminal or on the terminal and the model providing network element.

[0225] Optionally, the charging policy can be charging by service data volume, charging by service result output volume, or charging by model occupation time.

[0226] FIG. 5 is a schematic block diagram of an electronic device 500 provided by an embodiment of the present application. The device 500 includes a receiving module 501, which can be configured to implement a corresponding receiving function. The receiving module 501 can also be referred to as a receiving unit.

[0227] The device 500 further includes a processing module 502, which can be configured to implement a corresponding processing function.

[0228] The device 500 further includes a sending module 503, which can be configured to implement a corresponding sending function. The sending module 503 can also be referred to as a sending unit.

[0229] Optionally, the device 500 further includes a storage unit, which can be configured to store instructions and / or data. The processing module 502 can read the instructions and / or data in the storage unit, so that the device implements the actions of the related device in each of the foregoing method embodiments.

[0230] The device 500 can be configured to perform the actions performed by the terminal or the first model agent network element or the model providing network element in each of the foregoing method embodiments. In this case, the device 500 can be a component of the terminal or the first model agent network element or the model providing network element. The receiving module 501 is configured to perform the receiving-related operations of the terminal or the first model agent network element or the model providing network element in the foregoing method embodiments. The processing module 502 is configured to perform the processing-related operations of the terminal or the first model agent network element or the model providing network element in the foregoing method embodiments. The sending module 503 is configured to perform the sending-related operations of the terminal or the first model agent network element or the model providing network element in the foregoing method embodiments.

[0231] As a design, the apparatus 500 is configured to perform actions performed by any of the devices in the various method embodiments (the method 300 to the method 400). In one embodiment, the electronic apparatus can be configured to perform operations of the terminal in FIGS. 3 to 4. For example:

[0232] The sending module 503 is configured to send a service request, the service request being used to determine the response information.

[0233] The receiving module 501 is configured to receive the response information, the response information being used to respond to the service request.

[0234] It should be understood that the specific processes in which the modules perform the corresponding steps are described in the above method embodiments, and thus will not be repeated here for brevity.

[0235] In addition, the receiving module 501, the processing module 502, and the sending module 503 in the electronic apparatus 500 can also implement other operations or functions of the terminal in the above method, which will not be repeated here.

[0236] Optionally, the electronic apparatus 500 can be a device including the terminal. Alternatively, the electronic apparatus 500 can be a component configured in the terminal, for example, a chip in the terminal. In this case, the receiving module 501 and the sending module 503 can be interface circuits, pins, etc. Specifically, the interface circuits can include input circuits and output circuits, wherein the receiving module 501 can include the input circuits, the sending module 503 can include the output circuits, and the processing module 502 can include processing circuits.

[0237] In another embodiment, the electronic apparatus can be configured to perform operations of the first model agent network element in FIGS. 2 to 4. For example:

[0238] The sending module 503 is configured to send test information, the test information being used for the model providing network element to test the first model.

[0239] The receiving module 501 is configured to receive a first model test result, the first model test result being a result of the model providing network element testing the first model based on the test information.

[0240] The processing module 502 is configured to determine a first model registration result, the first model registration result being related to the first model test result.

[0241] In addition, the receiving module 501, the processing module 502, and the sending module 503 in the electronic apparatus 500 can also implement other operations or functions of the first model agent network element in the above method, which will not be repeated here.

[0242] Optionally, the electronic device 500 can be a device comprising the first model agent network element. Alternatively, the electronic device 500 can be a component configured in the first model agent network element, for example, a chip in the first model agent network element. In this case, the receiving module 501 and the sending module 503 can be interface circuits, pins, etc. Specifically, the interface circuits can comprise input circuits and output circuits, wherein the receiving module 501 can comprise the input circuits, the sending module 503 can comprise the output circuits, and the processing module 502 can comprise processing circuits.

[0243] In another embodiment, the electronic device can be configured to perform the operations of the model providing network element in FIG. 2 or FIG. 4. For example:

[0244] The sending module 503 is configured to send first model registration information, the first model registration information being used to request registration of the first model.

[0245] The receiving module 501 is configured to receive test information, the test information being used to test the first model.

[0246] In addition, the receiving module 501, the processing module 502, and the sending module 503 in the electronic device 500 can also implement other operations or functions of the model providing network element in the above method, which will not be described here.

[0247] Optionally, the electronic device 500 can be a device comprising the model providing network element. Alternatively, the electronic device 500 can be a component configured in the model providing network element, for example, a chip in the model providing network element. In this case, the receiving module 501 and the sending module 503 can be interface circuits, pins, etc. Specifically, the interface circuits can comprise input circuits and output circuits, wherein the receiving module 501 can comprise the input circuits, the sending module 503 can comprise the output circuits, and the processing module 502 can comprise processing circuits.

[0248] It should be understood that the specific processes of each module performing the above corresponding steps have been described in detail in the above method embodiments, and for the sake of brevity, will not be described here.

[0249] Fig. 6 is a schematic structural diagram of an electronic device 600 according to an embodiment of the present application. The electronic device 600 comprises a processor 601. As shown in Fig. 6, the device for processing a model can further comprise at least one memory 602 for storing computer programs or instructions and / or data. The memory 602 is coupled to the processor 601, and the processor 601 is configured to execute the computer programs or instructions and / or data stored in the memory 602, so that the method (the method 200 to the method 400) in the above method embodiments is executed. The coupling in the embodiments of the present application is indirect coupling or communication connection between devices, units or modules, which can be electrical, mechanical or other forms, and is used for information interaction between devices, units or modules. The processor 601 can operate in cooperation with the memory 602. At least one of the at least one memory 602 can be included in the processor 601.

[0250] Optionally, the processor 601 included in the electronic device 600 is one or more.

[0251] Optionally, the memory 602 can be integrated with the processor 601 or separately arranged.

[0252] The electronic device 600 can further comprise a transceiver 603 for registering a model / publishing information / providing model access through a transmission medium and other devices, so that the device can register a model / publish information / provide model access with other devices. Optionally, the transceiver 603 can be an interface, a bus, a circuit or a device capable of realizing the receiving and transmitting functions.

[0253] Optionally, the device for realizing the receiving function in the transceiver 603 can be regarded as a receiving module, and the device for realizing the transmitting function in the transceiver 603 can be regarded as a transmitting module, that is, the transceiver 603 comprises a receiver and a transmitter.

[0254] The specific connection medium between the processor 601, the memory 602 and the transceiver 603 is not limited in the embodiments of the present application. In Fig. 6, the processor 601, the memory 602 and the transceiver 603 are connected through a bus, and the bus is represented by a thick line in Fig. 6. The connection mode between other components is only schematically illustrated and is not limited. The bus can be divided into an address bus, a data bus, a control bus and the like.

[0255] It should be understood that, in Fig. 6, only one thick line is used for representation, but it does not mean that there is only one bus or only one type of bus.

[0256] Optionally, as shown in FIG. 6, the electronic device 600 can further include a transceiver 603 and / or a communication interface for receiving and / or sending signals. For example, the processor 601 is configured to control the transceiver 603 and / or the communication interface to receive and / or send data.

[0257] The transceiver can also be referred to as a transceiver, a transceiver module, or a transceiver circuit, etc. from time to time. The receiver can also be referred to as a receiver, a receiving module, or a receiving circuit, etc. from time to time. The transmitter can also be referred to as a transmitter, a transmitter, a transmitter module, or a transmitter circuit, etc.

[0258] For example, in one embodiment, the processor 601 is configured for other operations or functions of the terminal. The transceiver 603 is used to realize the acquisition of information / access to the model between the electronic device and the first model agent network element or the model providing network element.

[0259] In another embodiment, the processor 601 is configured for other operations or functions of the first model agent network element. The transceiver 603 is used to realize the registration of the model / provision of information / provision of model access between the electronic device and the terminal or the model providing network element.

[0260] In another embodiment, the processor 601 is configured for other operations or functions of the model providing network element. The transceiver 603 is used to realize the registration of the model / provision of model access between the electronic device and the terminal or the first model agent network element.

[0261] One or more of the above modules or units can be implemented in software, hardware, or a combination of both. When any of the above modules or units is implemented in software, the software exists in the form of computer program instructions and is stored in a memory. A processor can be used to execute the program instructions and implement the above method flows. The processor can include, but is not limited to, at least one of the following: a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a microcontroller unit (MCU), or an artificial intelligence processor, and the like computing devices that run software, each of which can include one or more cores for executing software instructions to perform computations or processing. The processor can be built into a system on chip (SoC) or an application specific integrated circuit (ASIC), or can be a standalone semiconductor chip. In addition to the cores for executing software instructions to perform computations or processing, the processor can further include necessary hardware accelerators, such as a field programmable gate array (FPGA), a programmable logic device (PLD), or a logic circuit that implements specialized logic operations.

[0262] When any of the above modules or units is implemented in hardware, the hardware can be any one or any combination of a CPU, a microprocessor, a DSP, an MCU, an artificial intelligence processor, an ASIC, an SoC, an FPGA, a PLD, a dedicated digital circuit, a hardware accelerator, or a non-integrated discrete device, which can run necessary software or be independent of software to execute the above method flows.

[0263] When the above modules or units are implemented using software, they can be implemented in whole or in part as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0264] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of this application. It should be understood that the above description is only a specific embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solution of this application should be included within the scope of protection of this application.

[0265] This application provides an electronic device 700, which may be a first model proxy network element / model providing network element or a chip. The electronic device 700 can be used to perform the operations executed by the first model proxy network element / model providing network element in the above-described method embodiments (methods 200 to 400).

[0266] When the electronic device 700 is a first model agent network element / model providing network element, FIG. 7 shows a simplified structural diagram of the first model agent network element / model providing network element. The first model agent network element / model providing network element includes a 710 part and a 720 part. The 710 part includes an antenna and a radio frequency circuit, the antenna is mainly used for transceiving radio frequency signals, and the radio frequency circuit is mainly used for converting radio frequency signals and baseband signals. The 720 part includes a memory and a processor, which are mainly used for baseband processing, controlling the model management network element, etc. The 710 part can be commonly referred to as a transceiving unit, a transceiver, a transceiving circuit, or a transceiver, etc. The 720 part is usually the control center of the first model agent network element / model providing network element, and can be commonly referred to as a processing unit, which is used to control the first model agent network element / model providing network element to perform the processing operations on the side of the first model agent network element / model providing network element in the above method embodiments.

[0267] Optionally, the devices in the 710 part for implementing the receiving function can be regarded as a receiving unit, and the devices for implementing the sending function can be regarded as a sending unit, that is, the 710 part includes a receiving unit and a sending unit. The receiving unit can also be referred to as a receiver, a receiver, or a receiving circuit, etc., and the sending unit can be referred to as a transmitter, a transmitter, or a transmitting circuit, etc.

[0268] When data needs to be sent, the processor performs baseband processing on the data to be sent, and then outputs the baseband signal to the radio frequency circuit. The radio frequency circuit performs radio frequency processing on the baseband signal, and then sends the radio frequency signal in the form of electromagnetic waves to the outside through the antenna. When data is sent to the model management network element, the radio frequency circuit receives the radio frequency signal through the antenna, converts the radio frequency signal into a baseband signal, and outputs the baseband signal to the processor. The processor converts the baseband signal into data and processes the data.

[0269] The 720 part can include one or more single boards, and each single board can include one or more processors and one or more memories. For the convenience of description, only one memory and one processor are shown in FIG. 7. The processor is used to read and execute the program in the memory to realize the baseband processing function and the control of the model management network element. If there are multiple single boards, the single boards can be interconnected to enhance the processing capability. As an optional implementation, multiple single boards can share one or more processors, or multiple single boards can share one or more memories.

[0270] It should be understood that FIG. 7 is only an example and not a limitation, and the above-mentioned first model agent network element / model providing network element including a transceiving unit and a processing unit can not depend on the structure shown in FIG. 7.

[0271] When the apparatus 700 is a chip, the chip comprises a transceiver unit and a processing unit. The transceiver unit can be an input / output circuit, a communication interface; and the processing unit is a processor or a microprocessor integrated on the chip or an integrated circuit.

[0272] The embodiment of the present application further provides another electronic device 800, which can be a terminal / model providing network element or a chip. The electronic device 800 can be used to perform the operations performed by the terminal / model providing network element in the above method embodiments (the method 200 to the method 400).

[0273] When the electronic device 800 is a terminal / model providing network element, FIG. 8 shows a simplified structural schematic diagram of the terminal / model providing network element. As shown in FIG. 8, the terminal / model providing network element comprises a processor, a memory, a radio frequency circuit, an antenna and an input / output device. The processor is mainly used for processing communication protocols and communication data, controlling the terminal / model providing network element, executing software programs, processing data of the software programs and the like. The memory is mainly used for storing software programs and data. The radio frequency circuit is mainly used for conversion between a baseband signal and a radio frequency signal and processing of the radio frequency signal. The antenna is mainly used for transceiving a radio frequency signal in the form of an electromagnetic wave. The input / output device, such as a touch screen, a display screen, a keyboard and the like, is mainly used for receiving data input by a user and outputting data to the user. It should be noted that some kinds of terminal / model providing network elements can not have the input / output device.

[0274] When data needs to be sent, the processor performs baseband processing on the data to be sent, and outputs a baseband signal to the radio frequency circuit. The radio frequency circuit performs radio frequency processing on the baseband signal, and transmits a radio frequency signal in the form of an electromagnetic wave through the antenna. When data is sent to the terminal / model providing network element, the radio frequency circuit receives a radio frequency signal through the antenna, converts the radio frequency signal into a baseband signal, and outputs the baseband signal to the processor. The processor converts the baseband signal into data and processes the data. For the convenience of description, only one memory and one processor are shown in FIG. 8. In actual terminal products, there can be one or more processors and one or more memories. The memory can also be referred to as a storage medium or a storage device, etc. The memory can be arranged independently of the processor or integrated with the processor. The embodiment of the present application does not limit this.

[0275] In the embodiment of the present application, the antenna and the radio frequency circuit with the transceiving function can be regarded as a transceiver unit of the terminal / model providing network element, and the processor with the processing function can be regarded as a processing unit of the terminal / model providing network element.

[0276] As shown in FIG. 8, the terminal / model providing network element includes a transceiver unit 10 and a processing unit 20. The transceiver unit 10 can also be referred to as a transceiver, a transceiver machine, a transceiver device, or a transceiver circuit, etc. The processing unit 20 can also be referred to as a processor, a processing board, a processing module, a processing device, etc.

[0277] Optionally, the device for implementing the receiving function in the transceiver unit 10 can be regarded as a receiving unit, and the device for implementing the sending function in the transceiver unit 10 can be regarded as a sending unit, that is, the transceiver unit 10 includes a receiving unit and a sending unit. The receiving unit can also be referred to as a receiver, a receiver device, a receiver circuit, etc. from time to time. The sending unit can also be referred to as a transmitter, a transmitter device, a transmitter circuit, etc. from time to time.

[0278] It should be understood that FIG. 8 is only an example and not a limitation, and the terminal / model providing network element described above including a transceiver unit and a processing unit can not depend on the structure shown in FIG. 8.

[0279] When the apparatus 800 is a chip, the chip includes a transceiver unit and a processing unit. The transceiver unit can be an input / output circuit or a communication interface; and the processing unit can be a processor or a microprocessor integrated on the chip or an integrated circuit.

[0280] According to the method provided in the embodiments of the present application, the present application further provides a computer program product, which includes computer program codes, and when the computer program codes run on a computer, the computer executes the method of the terminal in the foregoing method embodiments.

[0281] According to the method provided in the embodiments of the present application, the present application further provides a computer program product, which includes computer program codes, and when the computer program codes run on a computer, the computer executes the method of the first model agent network element in the foregoing method embodiments.

[0282] According to the method provided in the embodiments of the present application, the present application further provides a computer program product, which includes computer program codes, and when the computer program codes run on a computer, the computer executes the method of the model providing network element in the foregoing method embodiments.

[0283] According to the method provided in the embodiments of the present application, the present application further provides a computer readable medium, which stores program codes, and when the program codes run on a computer, the computer executes the method of the terminal in the foregoing method embodiments.

[0284] According to the method provided in the embodiments of the present application, the present application further provides a computer readable medium storing program codes, which, when executed on a computer, cause the computer to perform the method of the first model agent network element in the foregoing method embodiments.

[0285] According to the method provided in the embodiments of the present application, the present application further provides a computer readable medium storing program codes, which, when executed on a computer, cause the computer to perform the method of the model providing network element in the foregoing method embodiments.

[0286] The embodiments of the present application further provide a processing apparatus, including a processor and an interface; the processor is configured to execute the method of registering a model / publishing information / providing model access in any of the foregoing method embodiments.

[0287] The embodiments of the present application further provide a system of registering a model / publishing information / providing model access, which includes at least one model agent network element in the foregoing embodiments, and / or, a terminal, and / or, at least one model providing network element.

[0288] The terms "component", "module", "system", and the like used in the present specification are used to represent computer-related entities, hardware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and / or a computer. By way of illustration, both an application running on a computing device and the computing device can be a component. One or more components can reside within a process and / or thread of execution, and a component can be localized on one computer and / or distributed between two or more computers. In addition, these components can execute from various computer readable media having various data structures stored thereon. The components can communicate by way of local and / or remote processes such as in accordance with a signal having one or more data packets (e.g., data from one component interacting with another component in a local system, distributed system, and / or across a network such as the Internet with other systems via the signal), software, and / or other means in accordance with the teachings herein.

[0289] Those of ordinary skill in the art can realize that the various illustrative logical blocks and steps described in connection with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. The particular methods of implementation, whether in hardware or software, are not limiting to the scope of the present application. Those of ordinary skill in the art can use different methods to implement the described functions for each particular application, but such implementation will not be considered to be beyond the scope of the present application.

[0290] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0291] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0292] It should be understood that "at least one" in the embodiments of the present application means one or more, and "multiple" means two or more. The "and / or" describes the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after it. "At least one of the following" or similar expressions means any combination of these items, including any combination of single item or multiple items. For example, at least one of a, b and c can represent: a, or b, or c, or a and b, or a and c, or b and c, or a, b and c. Where a, b and c can be single or multiple.

[0293] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are only schematic. For example, the division of the units is only a logical function division, and actual implementation can have another division manner. For example, multiple units or components can be combined or 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 units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0294] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, i.e. they can be located in one place or distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0295] In addition, the various functional units in the embodiments of the present application can be integrated in one processing unit, or each can exist physically as a separate unit, or two or more units can be integrated in one unit.

Claims

1. A method of registering a model, characterized by, The method applied to a first model agent network element comprises: receiving first model registration information, the first model registration information comprising model information of a first model and function information of the first model; sending test information to a model providing network element corresponding to the first model, the test information being related to the first model registration information, and the test information being used for testing the first model by the model providing network element; receiving a first model test result, the first model test result being a result of testing the first model by the model providing network element based on the test information; determining a first model registration result, the first model registration result being related to the first model test result.

2. The method of claim 1, wherein, The determination of the first model registration result comprises: when the first model test result passes verification, assigning a first model identifier to the first model, registering the first model registration information and the first model test result, and the first model identifier being used for associating the first model.

3. The method according to claim 1 or 2, characterized in that, The method further comprises: sending first registration result indication information and / or sending the first model identifier, the first registration result indication information indicating the first model registration result.

4. The method according to any one of claims 1-3, characterized in that, The method further comprises: obtaining subscription information of the first model, the subscription information comprising service information of the first model.

5. The method according to any one of claims 1-4, characterized in that, The method further comprises: when a first condition is met, deregistering the first model.

6. The method of claim 5, wherein, The first condition comprises: within a first time period, no re-registration request is received from the model providing network element; or, receiving deregistration information from the model providing network element, the deregistration information indicating that the first model agent network element deregisters the first model; or, determining that the first model is invalid.

7. The method according to claim 5 or 6, characterized in that, The deregistration of the first model comprises: deleting the first model registration information.

8. A method of registering a model, characterized by, The method applied to a model providing network element comprises: sending first model registration information, the first model registration information comprising model information of a first model and function information of the first model; receiving test information, the test information being related to the first model registration information, and the test information being used for testing the first model by the model providing network element; sending a first model test result, the first model test result being a result of testing the first model by the model providing network element based on the test information.

9. The method of claim 8, wherein, The method further comprises: receiving first registration result indication information and / or receiving a first model identifier assigned to the first model; the first result indication information indicating a first model registration result of the first model, the first model registration result being related to the first model test result; and the first model identifier being used for associating the first model.

10. The method according to claim 8 or 9, characterized in that, The method further comprises: negotiating and determining subscription information of the first model, the subscription information comprising service information of the first model.

11. The method according to any one of claims 8-10, characterized in that, The method further comprises: sending deregistration information, the deregistration information indicating that the first model agent network element deregisters the first model, and the deregistration comprising deleting the first model registration information.

12. A method of publishing information, characterized by The method applied to a first model agent network element comprises: publishing a first model publishing information set to a terminal, the first model publishing information set comprising first model publishing information corresponding to a first model registered at the first model agent network element; and / or, publishing a second model publishing information set to a second model agent network element, the second model publishing information set comprising second model publishing information corresponding to the first model registered at the first model agent network element.

13. The method of claim 12, wherein, The method further comprises: receiving third model publishing information from the second model agent network element, the third model publishing information corresponding to a second model registered at the second model agent network element.

14. The method of claim 13, wherein, The first model publishing information set comprises fourth model publishing information corresponding to at least one piece of the third model publishing information.

15. The method of claim 14, wherein, The fourth model publishing information comprises second model information and second function information corresponding to the second model, or the fourth model publishing information comprises a second public identity corresponding to the second model.

16. The method according to any one of claims 12-15, characterized by, The first model publishing information comprises first model information and first function information corresponding to the first model, or the first model publishing information comprises a first public identity corresponding to the first model.

17. The method according to any one of claims 12-16, characterized by, The method further comprises: publishing a first mapping relationship table, the first mapping relationship table comprising association information between the first public identity and the first model, and / or comprising association information between the second public identity and the second model.

18. The method according to any one of claims 12-17, characterized by, The method further comprises: receiving a model information query request; determining the content of the first model publishing information set based on the model information query request.

19. The method of any one of claims 12-18, wherein The first model publishing information set further comprises fifth model publishing information, the fifth model publishing information having a different publishing frequency than the first model publishing information.

20. The method of any one of claims 12-19, wherein, The method further comprises: sending first identity matching information to a terminal, the first identity matching information indicating that the first model and the second model correspond to the same model providing network element.

21. A method of obtaining information, characterized by, Applied to a terminal, the method comprises: receiving a first model publishing information set, the first model publishing information set comprising first model publishing information corresponding to a first model registered at a first model agent network element.

22. The method of claim 21, wherein, The first model publishing information set further comprises second model publishing information corresponding to a second model registered at a second model agent network element.

23. The method of claim 22, wherein, The second model publishing information comprises second model information and second function information corresponding to the second model, or the second model publishing information comprises a second public identity corresponding to the second model.

24. The method of any one of claims 21-23, wherein, The first model publishing information comprises first model information and first function information corresponding to the first model, or the first model publishing information comprises a first public identity corresponding to the first model.

25. The method of any one of claims 21-24, wherein, The method further comprises: receive a first mapping relationship table, the first mapping relationship table comprising association information of the first public identifier and the first model, and / or the first mapping relationship table comprising association information of the second public identifier and the second model.

26. The method of any one of claims 21-25, wherein, The method further comprises: sending a model information query request, the model information query request being used to determine content of the first model publishing information set.

27. The method of any one of claims 21-26, wherein, The method further comprises: receiving first identifier matching information, the first identifier matching information indicating that the first model and the second model correspond to a same model providing network element.

28. An electronic device, comprising: The electronic device comprises a processor, the processor being configured to execute one or more computer programs or instructions, so that the electronic device performs the method of any one of claims 1 to 7; or, so that the electronic device performs the method of any one of claims 8 to 11; or, so that the electronic device performs the method of any one of claims 12 to 20; or, so that the electronic device performs the method of any one of claims 21 to 27. 29.The electronic device of claim 28, wherein, The electronic device further comprises a memory, the memory being configured to store the computer programs or instructions.

30. An electronic device, comprising: The device comprises a logic circuit and an input / output interface, the logic circuit being configured to be coupled with the input / output interface, and transmit data through the input / output interface, The electronic device is configured to perform the method of any one of claims 1 to 7; or, The electronic device is configured to perform the method of any one of claims 8 to 11; or, The electronic device is configured to perform the method of any one of claims 12 to 20; or, The electronic device is configured to perform the method of any one of claims 21 to 27.

31. A computer readable storage medium, characterized in that, The computer readable storage medium comprises computer programs or instructions, when the computer programs or instructions are run on a computer, so that the method of any one of claims 1 to 7 is performed; or, so that the method of any one of claims 8 to 11 is performed; or, so that the method of any one of claims 12 to 20 is performed; or, so that the method of any one of claims 21 to 27 is performed.

32. A computer program product, characterised in that, The computer program product comprises: computer programs or instructions, when the computer programs or instructions are run on a computer, so that the method of any one of claims 1 to 7 is performed; or, so that the method of any one of claims 8 to 11 is performed; or, so that the method of any one of claims 12 to 20 is performed; or, so that the method of any one of claims 21 to 27 is performed.

33. A chip system, characterized by comprises: a processor, the processor being configured to execute computer programs or instructions in the memory, so that the chip system implements the method of any one of claims 1 to 7, or so that the chip system implements the method of any one of claims 8 to 11, or so that the chip system implements the method of any one of claims 12 to 20, or so that the chip system implements the method of any one of claims 21 to 27.

Images