Method, system and device for providing intelligent service in communication system

Abstract

The invention provides a method, a system and a device for providing an intelligent service in a communication system, and relates to the technical field of communication. The method comprises the following steps: receiving a trained target machine learning model sent by a model training functional entity and description information of intelligent service provided by the target machine learning model; determining input data of the target machine learning model and correct data corresponding to the input data based on the description information; based on the input data, determining output data through a target machine learning model; determining whether the target machine learning model passes the test based on the correct data and the output data; if the target machine learning model passes the inspection, sending the target machine learning model to an analysis function entity so as to provide an intelligent service through the analysis function entity; and if the target machine learning model does not pass the test, feeding back a test result to the model training functional entity to instruct the model training functional entity to retrain the target machine learning model.

Description

Background Art

[0002] With the rapid development of artificial intelligence technology, it has become a major trend in technological development to provide convenient and intelligent services through artificial intelligence technology. To cope with this situation, communication systems have also adapted intelligent services. However, the error rate of intelligent services in current communication systems is relatively high, resulting in waste of data and computing power resources. Summary of the Invention

[0003] The present disclosure provides a method, system, device and related equipment for providing intelligent services in a communication system, which at least improves the quality of intelligent services in the communication system.

[0004] Other features and advantages of the present disclosure will become apparent through the following detailed description, or will be partially learned through the practice of the present disclosure.

[0005] According to one aspect of the present disclosure, there is provided a method for providing an intelligent service in a communication system, which is executed by a model verification functional entity. The method includes: receiving a trained target machine learning model and description information of the intelligent service provided by the target machine learning model sent by a model training functional entity; determining input data of the target machine learning model and correct data corresponding to the input data based on the description information; determining output data through the target machine learning model based on the input data; determining whether the target machine learning model passes the verification based on the correct data and the output data; if the target machine learning model passes the verification, sending the target machine learning model to an analysis functional entity to provide the intelligent service through the analysis functional entity; if the target machine learning model does not pass the verification, feeding back the verification result to the model training functional entity to instruct the model training functional entity to retrain the target machine learning model.

[0006] In some embodiments of the present disclosure, the model training functional entity is configured to execute: receiving a model training request sent by an analysis functional entity, determining description information based on the model training request; determining a target machine learning model from multiple machine learning models stored in a model repository based on the description information; determining training data from a data repository based on the description information; and training the target machine learning model using the training data.

[0007] In an embodiment of the present disclosure, after sending the target machine learning model to the analysis functional entity, the analysis functional entity is configured to register the intelligent service in a service list of a service repository and save the target machine learning model in the service repository, where the service list is used for other network functional entities to discover the intelligent service.

[0008] In an embodiment of the present disclosure, after sending the target machine learning model to the analysis functional entity, the analysis functional entity receives a call instruction through an application programming interface and provides the intelligent service through the application programming interface.

[0009] In one embodiment of the present disclosure, determining whether a target machine learning model passes a test based on correct data and output data includes: extracting a first feature of the correct data and a second feature of the output data; calculating a similarity between the first feature and the second feature; if the similarity is greater than a test threshold, determining that the target machine learning model passes the test; if the similarity is less than or equal to the test threshold, determining that the target machine learning model fails the test.

[0010] According to another aspect of the present disclosure, there is provided a system for providing intelligent services in a communication system, including: an analysis functional entity configured to send a model training request, receive a target machine learning model that passes the test, and provide intelligent services by using the target machine learning model that passes the test; a model training functional entity configured to receive the model training request, determine description information of the intelligent service based on the model training request, train the target machine learning model based on the description information, and send the trained target machine learning model and the description information; a model checking functional entity configured to receive the trained target machine learning model and the description information, check the trained target machine learning model based on the description information, and send the target machine learning model that passes the test.

[0011] In one embodiment of the present disclosure, the model checking functional entity is further configured to, if the target machine learning model fails the test, feedback the test result to the model training functional entity to instruct the model training functional entity to retrain the target machine learning model.

[0012] In one embodiment of the present disclosure, the analysis functional entity is further configured to send a registration request to a service repository to register the intelligent service in a service list, where the service list is used for other network functional entities to discover the intelligent service.

[0013] According to another aspect of the present disclosure, there is provided an apparatus for providing intelligent services in a communication system. The apparatus is configured inside a model verification functional entity and includes: a receiving module configured to receive a trained target machine learning model sent by a model training functional entity and description information of the intelligent services provided by the target machine learning model; a determining module configured to determine input data of the target machine learning model and correct data corresponding to the input data based on the description information; a model module configured to determine output data through the target machine learning model based on the input data; a verification module configured to determine whether the target machine learning model passes verification based on the correct data and the output data; a sending module configured to, if the target machine learning model passes verification, send the target machine learning model to an analysis functional entity to provide intelligent services through the analysis functional entity; and a feedback module configured to, if the target machine learning model does not pass verification, feedback the verification result to the model training functional entity to instruct the model training functional entity to retrain the target machine learning model.

[0014] According to yet another aspect of the present disclosure, there is provided an electronic device, including: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the method for providing intelligent services in the communication system as described above via executing the executable instructions.

[0015] According to yet another aspect of the present disclosure, there is provided a computer-readable storage medium having a computer program stored thereon, and the computer program, when executed by a processor, implements the method for providing intelligent services in the communication system as described above.

[0016] According to yet another aspect of the present disclosure, there is provided a computer program product including computer instructions stored in a computer-readable storage medium, and the computer instructions, when executed by a processor, implement the method for providing intelligent services in the communication system as described above.

[0017] In the embodiments of the present disclosure, by determining whether the target machine learning model passes verification based on the correct data and the output data, and if the target machine learning model passes verification, sending the target machine learning model to the analysis functional entity, the problem of high error rate of intelligent services in the related communication system is solved, thereby improving the quality of intelligent services and avoiding waste of data and computing power resources.

[0018] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure. Obviously, the accompanying drawings in the following description are only some embodiments of the present disclosure, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0020] Figure 1 The flowchart showing a method for providing intelligent services in a communication system in an embodiment of the present disclosure.

[0021] Figure 2 The flowchart showing a method for model training in an embodiment of the present disclosure.

[0022] Figure 3 The flowchart showing a method for model verification in an embodiment of the present disclosure.

[0023] Figure 4 The schematic diagram showing a device for providing intelligent services in a communication system in an embodiment of the present disclosure.

[0024] Figure 5 The schematic structural diagram showing a system for providing intelligent services in a communication system in an embodiment of the present disclosure.

[0025] Figure 6 The schematic structural diagram showing another system for providing intelligent services in a communication system in an embodiment of the present disclosure.

[0026] Figure 7 The schematic structural diagram showing yet another system for providing intelligent services in a communication system in an embodiment of the present disclosure.

[0027] Figure 8 The schematic diagram showing an exposure and coordination framework in an embodiment of the present disclosure.

[0028] Figure 9 The schematic diagram showing an electronic device provided in an embodiment of the present disclosure. Detailed implementation manners

[0029] Now, example embodiments will be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be more thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments.

[0030] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0031] It should be understood that the steps recited in the method embodiments of the present disclosure may be executed in a different order and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this regard.

[0032] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or mutual dependency relationship of the functions performed by these devices, modules or units.

[0033] It should be noted that the modifiers "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly specified in the context, it should be understood as "one or more".

[0034] It should be pointed out that, without conflict, the embodiments of the present disclosure and the technical features in the embodiments may be combined with each other.

[0035] For the convenience of understanding, several terms related to the present disclosure are first explained as follows:

[0036] RAN (Radio Access Network) is a key part connecting user equipment and the core network (CN), and is responsible for the transmission and management of wireless signals.

[0037] CN (Core Network) is a key component in the network architecture.

[0038] CAPIF (Common API Framework for 3GPP Northbound APIs) is a standard capability open architecture defined in the R15 phase and can be regarded as the cornerstone of 5G network capability opening.

[0039] An API (Application Program Interface) is a bridge for interaction and communication between software systems. It defines a set of rules and protocols that allow different software applications or components to call each other and exchange data.

[0040] The following will describe in detail the specific implementation manners of the embodiments of the present disclosure with reference to the accompanying drawings.

[0041] Figure 1 The flowchart shows a method for providing intelligent services in a communication system in an embodiment of the present disclosure. The method is executed by a model verification functional entity (please define what a model verification functional entity is). The method is as follows Figure 1 shown, and includes the following steps:

[0042] S101, receive the trained target machine learning model sent by the model training functional entity and the description information of the intelligent service provided by the target machine learning model.

[0043] S102, determine the input data of the target machine learning model and the correct data corresponding to the input data based on the description information.

[0044] S103, determine the output data through the target machine learning model based on the input data.

[0045] S104, determine whether the target machine learning model passes the verification based on the correct data and the output data.

[0046] S105, if the target machine learning model passes the verification, send the target machine learning model to the analysis functional entity to provide intelligent services through the analysis functional entity.

[0047] S106, if the target machine learning model does not pass the verification, feedback the verification result to the model training functional entity to instruct the model training functional entity to retrain the target machine learning model.

[0048] In the embodiments of the present disclosure, an analysis functional entity, a model verification functional entity, and a model training functional entity are set in the communication system to adapt intelligent services in the communication system. The model training functional entity trains the target machine learning model, and the model verification functional entity verifies the trained target machine learning model. Only when the verification passes, the target machine learning model is sent to the analysis functional entity, solving the problem of high error rate of intelligent services in the related art communication system, thereby improving the quality of intelligent services and avoiding waste of data and computing power resources.

[0049] The description information in the embodiments of the present disclosure is a description of intelligent services, including the types and content descriptions of intelligent services. The types of intelligent services include: communication network optimization, network fault prediction, text generation, text content extraction, image generation, etc.

[0050] Taking communication network optimization as an example, the content description of the intelligent service includes: real-time analysis of network traffic patterns, dynamically adjusting base station power, spectrum allocation, and computing resources. For example, if it is determined according to the description information that the intelligent service is used to dynamically adjust the base station power, then network usage information and base station status, etc. are obtained as input data, and the labeled base station power is used as the correct data.

[0051] Taking text content extraction as an example, the content description of the intelligent service includes: extracting text summaries, generating text content outlines, generating outline schematic diagrams, etc. For example, if it is determined according to the description information that the intelligent service is used to extract text summaries, then a piece of text is obtained as input data, and the labeled summary is used as the correct data. The piece of text is used as the input to the target machine learning model to obtain output data. Finally, based on the correct data and the output data, it is determined whether the target machine learning model passes the test.

[0052] Figure 2 The flowchart of a model training method in an embodiment of the present disclosure is shown. This method is executed by a model training functional entity. The method is as Figure 2 shown and includes the following steps:

[0053] S201, receive a model training request sent by an analysis functional entity, and determine description information based on the model training request;

[0054] S202, determine a target machine learning model from multiple machine learning models stored in a model repository based on the description information;

[0055] S203, determine training data from a data repository based on the description information; use the training data to train the target machine learning model.

[0056] Extract the type and content description of the intelligent service required by the analysis functional entity from the model training request to obtain the description information. The model repository stores multiple machine learning models. The data repository stores training data required for various training tasks. For example, if it is determined according to the description information that the intelligent service is used to extract text summaries, then the model with the best text summary extraction effect is selected from the model repository as the target machine learning model, and the training data for text summary extraction is determined from the data repository. The training data includes text and corresponding summaries (labels). Use the training data to train the target machine learning model for the task of extracting text summaries. Through the above technical means, the efficiency of model training is improved.

[0057] In some embodiments, after the target machine learning model is sent to the analysis functional entity, the analysis functional entity is used to register the intelligent service in the service list of the service repository and save the target machine learning model in the service repository, where the service list is used for other network functional entities to discover the intelligent service.

[0058] Register the intelligent service in the service list of the service repository, and other network functional entities discover the intelligent service by searching the service list. Save the target machine learning model in the service repository, and subsequent other network functional entities can directly call the target machine learning model from the service repository. Through the above technical means, the intelligent service is adapted in the communication network, enhancing the interaction between network functional entities.

[0059] In an embodiment of the present disclosure, after the target machine learning model is sent to the analysis functional entity, the analysis functional entity receives a call instruction through the application programming interface and provides the intelligent service through the application programming interface.

[0060] Other network functional entities send call instructions to the analysis functional entity through CAPIF / API, and the analysis functional entity provides the intelligent service to other network functional entities through CAPIF / API. Other network functional entities include networks of various types of users.

[0061] Figure 3 The flowchart of a model verification method in an embodiment of the present disclosure is shown. The method is executed by a model verification functional entity, and the method is as Figure 3 shown, including the following steps:

[0062] S301, extract the first feature of the correct data and the second feature of the output data;

[0063] S302, calculate the similarity between the first feature and the second feature;

[0064] S303, if the similarity is greater than the verification threshold, determine that the target machine learning model passes the verification;

[0065] S304, if the similarity is less than or equal to the verification threshold, determine that the target machine learning model fails the verification.

[0066] In an exemplary embodiment, the BERT (Bidirectional Encoder Representations from Transformers) model is used to extract the embedding features of the correct data and the output data, as the first feature and the second feature respectively. In some embodiments, the cosine similarity formula is used to calculate the similarity between the first feature and the second feature, but the present disclosure is not limited thereto. If the similarity is greater than the inspection threshold, the inspection is passed; otherwise, the inspection is not passed.

[0067] In some embodiments, the intelligent service provided by the target machine learning model is denoted as the current intelligent service, and the existing intelligent service closest to the current intelligent service is determined; the user experience information and the existing content of the existing intelligent service up to the current moment are obtained; the popularity score corresponding to the current intelligent service is determined according to the user experience information; the content innovation score of the current intelligent service relative to the existing intelligent service is calculated based on the existing content and the content description, where the description information includes the content description and the performance indicators; the inspection benchmark is determined based on the popularity score, the content innovation score and the performance indicators; the inspection threshold is determined based on the inspection benchmark, where the higher the inspection benchmark, the greater the inspection threshold.

[0068] For example, if the type of the current intelligent service is text content extraction, then the existing intelligent service is also selected as text content extraction. For example, the existing content of the existing intelligent service includes extracting text summaries and generating text content contexts. And the content description of the current intelligent service includes: extracting text summaries, generating text content contexts, generating context schematic diagrams, etc. Generating context schematic diagrams belongs to the content innovation item of the current intelligent service. The content innovation score is calculated according to the preset rules (for example, the more the number of content innovation items, the higher the content innovation score).

[0069] In some embodiments, the higher the popularity score, the lower the inspection benchmark; the higher the content innovation score, the lower the inspection benchmark; the higher the performance indicator, the higher the inspection benchmark.

[0070] In some embodiments, the user experience information includes the search times, the usage times and the usage evaluation score; the search score corresponding to the search times and the usage score corresponding to the usage times are determined; the popularity score is calculated based on the search score, the usage score and the usage evaluation score.

[0071] In an exemplary embodiment, the more the search times, the higher the search score. The more the usage times, the higher the usage score. The usage evaluation score is calculated based on the positive and negative reviews. The search score, the usage score and the usage evaluation score are weighted and summed according to the preset weights to obtain the popularity score.

[0072] In some embodiments, the input data includes multiple pieces of data, and each piece of data has corresponding correct data; a target quantity is determined based on a verification criterion, where the verification criterion is obtained based on the current intelligent service and the description information, and the higher the verification criterion, the larger the target quantity; the multiple pieces of data are divided into the target quantity of portions, and each portion is used as a subset; the multiple pieces of data in each subset are input into an artificial intelligence model, and target results corresponding to each piece of data are output; verification scores corresponding to each subset are determined based on the target results and the correct data corresponding to each piece of data in each subset; a total score of the artificial intelligence model (and the relationship description between the machine learning model) is calculated based on the verification scores corresponding to each subset; it is determined whether the artificial intelligence model passes the verification according to the total score.

[0073] In some embodiments, a target score is determined based on the verification criterion, where the higher the verification criterion, the higher the target score; if the total score is greater than the target score, it is determined that the artificial intelligence model passes the verification; if the total score is less than or equal to the target score, it is determined that the artificial intelligence model does not pass the verification.

[0074] Based on the same inventive concept, an apparatus for providing an intelligent service in a communication system is further provided in an embodiment of the present disclosure, as described in the following embodiments. Since the principle of solving problems in this apparatus embodiment is similar to that in the above method embodiment, the implementation of this apparatus embodiment can refer to the implementation of the above method embodiment, and repeated parts will not be elaborated.

[0075] Figure 4 A schematic diagram showing an apparatus for providing an intelligent service in a communication system in an embodiment of the present disclosure, the apparatus is configured inside a model verification functional entity, as Figure 4 shown, the apparatus for providing an intelligent service in the communication system may include:

[0076] A receiving module 401, configured to receive a trained target machine learning model and description information of an intelligent service provided by the target machine learning model sent by a model training functional entity;

[0077] A determining module 402, configured to determine input data of the target machine learning model and correct data corresponding to the input data based on the description information;

[0078] A model module 403, configured to determine output data through the target machine learning model based on the input data;

[0079] A verification module 404, configured to determine whether the target machine learning model passes the verification based on the correct data and the output data;

[0080] A sending module 405, configured to, if the target machine learning model passes the verification, send the target machine learning model to an analysis functional entity to provide an intelligent service through the analysis functional entity;

[0081] A feedback module 406, configured to feed back a test result to a model training functional entity to indicate the model training functional entity to retrain the target machine learning model if the target machine learning model fails the test.

[0082] According to the technical solution provided by the embodiments of the present disclosure, by determining whether the target machine learning model passes the test based on the correct data and the output data, if the target machine learning model passes the test, the target machine learning model is sent to the analysis functional entity, which solves the problem of high error rate of intelligent services in the related art communication system, thereby improving the quality of intelligent services and avoiding waste of data and computing power resources.

[0083] In some embodiments, the test module 404 is further configured to extract a first feature of the correct data and a second feature of the output data; calculate the similarity between the first feature and the second feature; if the similarity is greater than a test threshold, determine that the target machine learning model passes the test; if the similarity is less than or equal to the test threshold, determine that the target machine learning model fails the test.

[0084] In some embodiments, the test module 404 is further configured to record the intelligent service provided by the target machine learning model as the current intelligent service, and determine the existing intelligent service closest to the current intelligent service; obtain the user experience information and existing content of the existing intelligent service up to the current moment; determine the popularity score corresponding to the current intelligent service according to the user experience information; calculate the content innovation score of the current intelligent service relative to the existing intelligent service based on the existing content and the content description, where the description information includes the content description and performance indicators; determine a test benchmark based on the popularity score, the content innovation score, and the performance indicators; determine a test threshold based on the test benchmark, where the higher the test benchmark, the greater the test threshold.

[0085] In some embodiments, the test module 404 is further configured to determine a search score corresponding to the number of searches and a usage score corresponding to the number of usages; calculate the popularity score based on the search score, the usage score, and the usage evaluation score.

[0086] In some embodiments, the test module 404 is further configured to determine a target quantity based on the test benchmark, where the test benchmark is obtained based on the current intelligent service and the description information, and the higher the test benchmark, the greater the target quantity; divide multiple pieces of data into the target quantity of portions, and use each portion as a subset; input the multiple pieces of data in each subset into the artificial intelligence model, and output the target result corresponding to each piece of data; determine the test score corresponding to each subset based on the target result corresponding to each piece of data in each subset and the correct data; calculate the total score of the artificial intelligence model based on the test scores corresponding to each subset; determine whether the artificial intelligence model passes the test according to the total score.

[0087] In some embodiments, the inspection module 404 is further configured to determine a target score based on an inspection benchmark, where the higher the inspection benchmark, the higher the target score; if the total score is greater than the target score, it is determined that the artificial intelligence model passes the inspection; if the total score is less than or equal to the target score, it is determined that the artificial intelligence model fails the inspection.

[0088] Figure 5 The structural schematic diagram of a system for providing intelligent services in a communication system according to an embodiment of the present disclosure is shown as Figure 5 shown. The system for providing intelligent services in this communication system may include:

[0089] An analysis functional entity 501, configured to send a model training request, receive a target machine learning model that has passed the inspection, and provide intelligent services by using the target machine learning model that has passed the inspection;

[0090] A model training functional entity 502, configured to receive a model training request, determine description information of the intelligent service based on the model training request, train the target machine learning model based on the description information, and send the trained target machine learning model and the description information;

[0091] A model inspection functional entity 503, configured to receive the trained target machine learning model and the description information, inspect the trained target machine learning model based on the description information, and send the target machine learning model that has passed the inspection.

[0092] The analysis functional entity sends a model training request to the model training functional entity. The model training functional entity determines the description information of the intelligent service based on the model training request, trains the target machine learning model based on the description information, and finally sends the trained target machine learning model and the description information to the model inspection functional entity. The model inspection functional entity inspects the trained target machine learning model based on the description information, and sends the target machine learning model that has passed the inspection to the analysis functional entity. The analysis functional entity provides intelligent services by using the target machine learning model that has passed the inspection.

[0093] The model inspection functional entity 503 is further configured to, if the target machine learning model fails the inspection, feedback the inspection result to the model training functional entity to instruct the model training functional entity 502 to retrain the target machine learning model.

[0094] Figure 6 The structural schematic diagram of another system for providing intelligent services in a communication system according to an embodiment of the present disclosure is shown as Figure 6 shown. The system for providing intelligent services in this communication system may include:

[0095] The analysis functional entity 501 is further configured to send a registration request to the service repository 504;

[0096] The service repository 504 is configured to register the intelligent service in a service list, where the service list is used for other network functional entities to discover the intelligent service.

[0097] Figure 7 FIG. shows a schematic structural diagram of a system for providing an intelligent service in another communication system according to an embodiment of the present disclosure, as Figure 7 shown, the system for providing an intelligent service in this communication system may include:

[0098] The model training functional entity 502 determines the target machine learning model from a variety of machine learning models saved in the model repository 505 based on the description information;

[0099] The model training functional entity 502 determines training data from the data repository 506 based on the description information;

[0100] Other network functional entities interact with the analysis functional entity 501 and the service repository 504 through CAPIF / API.

[0101] Figure 8 FIG. shows a schematic diagram of an exposure and coordination framework. The exposure and coordination framework is a system architecture for managing and coordinating interactions between different services and frameworks. As Figure 8 shown, it may include:

[0102] API provider domain, which is the domain or scope for providing API services, including: Data Mesh Management: Involves the management and operation of data meshes; Security policies, discovery, etc.: A series of rules and measures for protecting data and networks, and the process of identifying and locating resources and services in a network environment.

[0103] API invoker(s), entities or services that call APIs to use their functions, including: Cross framework conflict management: Manages and resolves potential conflicts between different frameworks; Cross framework CL governance and control: CL refers to Cloud Native Landscape, representing cross framework governance and control.

[0104] API Management core functions: The basic functions of API management, such as monitoring, analysis, security, etc.

[0105] Management interfaces: Interfaces used to manage and configure a system or service. There are management interfaces between the API provider domain and the API management core functions.

[0106] Framework A / B / C: Refers to different framework instances, which may represent different services or technology stacks. Framework A / B / C all include: Mesh Node: A single element or service that constitutes a mesh; AEFs / API provider: AEFs refers to Application Enablement Functions, that is, application enablement functions, representing entities that provide API services; API callers.

[0107] There is a Cross Framework Data Mesh between Framework A / B / C: A data mesh that spans multiple frameworks and is used to integrate and manage data in different frameworks.

[0108] Communication Infra for services: Infrastructure that supports communication between services.

[0109] The exposure and coordination framework provides a unified management and coordination mechanism to effectively manage and use data and services in a multi-framework environment. This framework is used to handle interactions between different service frameworks (such as Framework A, B, C). The core of the framework is data mesh management, which is responsible for tasks such as security policies and service discovery. The framework also includes API providers and callers, which interact through management interfaces and service communication infrastructure. In addition, the framework also involves cross-framework conflict management and governance control to ensure coordination and consistency between different frameworks, and to ensure the stability and reliability of API services.

[0110] All communications involved in this disclosure can be carried out under this exposure and coordination framework.

[0111] Those skilled in the art to which the present disclosure pertains will appreciate that various aspects of the present disclosure can be implemented as a system, a method, or a program product. Accordingly, various aspects of the present disclosure can be embodied in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which can be collectively referred to herein as "circuitry", "module", or "system".

[0112] Reference will now be made to Figure 9 describe the electronic device 900 according to such an embodiment of the present disclosure. Figure 9 The electronic device 900 shown is merely an example and should not impose any limitations on the functions and scope of use of the embodiments of the present disclosure.

[0113] As Figure 9 shown, the electronic device 900 is presented in the form of a general-purpose computing device. The components of the electronic device 900 may include, but are not limited to: at least one of the above-mentioned processing units 910, at least one of the above-mentioned storage units 920, and a bus 930 connecting different system components (including the storage unit 920 and the processing unit 910).

[0114] Among them, the storage unit stores program code, and the program code can be executed by the processing unit 910, so that the processing unit 910 executes the steps according to various exemplary embodiments of the present disclosure described in the above "Exemplary Method" section of this specification. For example, the processing unit 910 may execute the following steps of the above method embodiment: receiving the trained target machine learning model sent by the model training functional entity and the description information of the intelligent service provided by the target machine learning model; determining the input data of the target machine learning model and the correct data corresponding to the input data based on the description information; determining the output data through the target machine learning model based on the input data; determining whether the target machine learning model passes the inspection based on the correct data and the output data; if the target machine learning model passes the inspection, sending the target machine learning model to the analysis functional entity to provide an intelligent service through the analysis functional entity; if the target machine learning model does not pass the inspection, feeding back the inspection result to the model training functional entity to instruct the model training functional entity to retrain the target machine learning model.

[0115] The storage unit 920 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 9201 and / or a cache storage unit 9202, and may further include a read-only storage unit (ROM) 9203.

[0116] The storage unit 920 may also include a program / utilities 9204 having a set (at least one) of program modules 9205. Such program modules 9205 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment.

[0117] The bus 930 may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus structures.

[0118] The electronic device 900 may also communicate with one or more external devices 940 (such as a keyboard, a pointing device, a Bluetooth device, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 900, and / or may communicate with any device that enables the electronic device 900 to communicate with one or more other computing devices (such as a router, a modem, etc.). Such communication may be carried out through an input / output (I / O) interface 950. Moreover, the electronic device 900 may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 960. As shown in the figure, the network adapter 960 communicates with other modules of the electronic device 900 through the bus 930. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0119] Through the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described herein can be implemented by software, or can be implemented by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product. The software product can be stored in a non-volatile storage medium (which may be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which may be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

[0120] In an exemplary embodiment of the disclosure, a computer-readable storage medium is also provided. The computer-readable storage medium may be a readable signal medium or a readable storage medium.

[0121] In some possible embodiments, aspects of the present disclosure can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to cause the terminal device to execute the steps according to various exemplary embodiments of the present disclosure described in the "Specific Embodiments" section of this specification.

[0122] More specific examples of the computer-readable storage medium in the present disclosure may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0123] In the present disclosure, the computer-readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, in which the readable program code is carried. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable signal medium may also be any readable medium other than the readable storage medium, and the readable medium may send, propagate, or transmit a program used by or in conjunction with an instruction execution system, apparatus, or device.

[0124] Optionally, the program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the above.

[0125] In specific implementation, the program code for executing the operations of the present disclosure can be written in any combination of one or more programming languages. The programming languages include object-oriented programming languages - such as Java, C++, etc., and also include conventional procedural programming languages - such as the "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, executed as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, by using an Internet service provider to connect through the Internet).

[0126] Embodiments of the present disclosure provide a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method for providing an intelligent service in a communication system provided in any of the various alternative manners in the present disclosure.

[0127] It should be noted that although several modules or units of a device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of the two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0128] In addition, although the steps of the methods in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be executed in that specific order, or that all the steps shown must be executed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution, etc.

[0129] From the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software, or by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (such as a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the methods according to the embodiments of the present disclosure.

[0130] After considering the specification and practicing the invention disclosed herein, those skilled in the art will readily conceive of other embodiments of the present disclosure. The present disclosure is intended to cover any variations, uses, or adaptations of the present disclosure, which follow the general principles of the present disclosure and include known common knowledge or conventional technical means in the technical field not disclosed in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the true scope of the present disclosure is pointed out by the appended claims.

Claims

1. A method for providing intelligent services in a communication system, characterized in that: The method is performed by a model checking function entity, and the method comprises: Receive information about a trained target machine learning model and intelligent services provided by the target machine learning model sent by a model training functional entity; Determine input data of the target machine learning model and correct data corresponding to the input data based on the description information; Based on the input data, determining output data through the target machine learning model; Determine whether the target machine learning model passes the test based on the correct data and the output data; If the target machine learning model passes the test, the target machine learning model is sent to the analysis function entity so as to provide the intelligent service through the analysis function entity; If the target machine learning model fails the test, the test result is fed back to the model training functional entity to instruct the model training functional entity to retrain the target machine learning model.

2. The method according to claim 1, characterized in that The model training functional entity is used to perform: receiving a model training request sent by the analysis function entity, and determining the description information based on the model training request; Determine the target machine learning model from a plurality of machine learning models stored in a model repository based on the description information; determining training data from a data repository based on the description information; The target machine learning model is trained using the training data.

3. The method according to claim 1, characterized in that After sending the target machine learning model to the analysis functional entity, the analysis functional entity is used to register the intelligent service in a service list of a service repository and save the target machine learning model in the service repository, wherein the service list is used for other network functional entities to discover the intelligent service.

4. The method according to claim 1, characterized in that: After sending the target machine learning model to the analysis function entity, the analysis function entity receives the calling instruction through the application program interface and provides the intelligent service through the application program interface.

5. The method according to claim 1, characterized in that Determining whether the target machine learning model passes the test based on the correct data and the output data includes: Extracting a first feature of the correct data and a second feature of the output data; calculating a similarity between the first feature and the second feature; If the similarity is greater than the test threshold, it is determined that the target machine learning model passes the test; If the similarity is less than or equal to the test threshold, it is determined that the target machine learning model has not passed the test.

6. A system for providing intelligent services in a communication system, characterized in that: include: The analysis function entity is configured to send a model training request, receive a target machine learning model that has passed the verification, and provide an intelligent service using the target machine learning model that has passed the verification; A model training functional entity is configured to receive the model training request, determine the description information of the intelligent service based on the model training request, train the target machine learning model based on the description information, and send the trained target machine learning model and the description information; The model checking functional entity is configured to receive a trained target machine learning model and the description information, verify the trained target machine learning model based on the description information, and send the target machine learning model that has passed the verification.

7. The system according to claim 6, characterized in that The model checking functional entity is also configured to feed back the inspection result to the model training functional entity if the target machine learning model fails the inspection, so as to instruct the model training functional entity to retrain the target machine learning model.

8. The system according to claim 6, characterized in that The analysis function entity is further configured to send a registration request to a service repository to register the intelligent service in a service list, wherein the service list is used for other network function entities to discover the intelligent service.

9. A device for providing intelligent services in a communication system, characterized in that: The device is configured inside the model checking functional entity, and the device includes: A receiving module is configured to receive information about a trained target machine learning model and intelligent services provided by the target machine learning model, sent by a model training function entity; A determination module, configured to determine input data of the target machine learning model and correct data corresponding to the input data based on the description information; A model module, configured to determine output data through the target machine learning model based on the input data; A verification module, configured to determine whether the target machine learning model passes the verification based on the correct data and the output data; A sending module is configured to send the target machine learning model to the analysis function entity if the target machine learning model passes the inspection, so as to provide the intelligent service through the analysis function entity; The feedback module is configured to feed back the inspection result to the model training functional entity if the target machine learning model fails the inspection, so as to instruct the model training functional entity to retrain the target machine learning model.

10. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 5 by executing the executable instructions.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

12. A computer program product, comprising computer instructions, wherein the computer instructions are stored in a computer-readable storage medium, and when the computer instructions are executed by a processor, the operating instructions of the method according to any one of claims 1 to 5 are implemented.

Images