CN-122003845-A - Method and apparatus for applying data analysis enabled artificial intelligence/machine learning enabled functions

Abstract

Methods, apparatus, and systems are described for managing Artificial Intelligence (AI)/Machine Learning (ML) resources and capabilities available to an application and service enablement layer, and coordinating AI/ML enabled analytics services. According to some aspects, an Application Data Analytics Enabling (ADAE) service may be enhanced to support AI/ML enabled analytics services.

Inventors

• LIU LU
• D. Sid
• Q.LI
• C nurse Latin

Assignees

• 交互数字专利控股公司

Dates

Publication Date

20260508

Application Date

20240808

Priority Date

20230811

Claims (20)

1. 1. A method for providing an artificial intelligence/machine learning (AI/ML) enabled service, the method comprising: Receiving one or more provider messages from one or more AI/ML resource/capability providers, the one or more provider messages including one or more descriptions of one or more AI/ML resources or capabilities of the one or more AI/ML resource/capability providers; storing, by the AI/ML enabled service and based on the one or more provider messages, the one or more descriptions of the one or more AI/ML resources or capabilities; Receiving a consumer request from an AI/ML service consumer, the consumer request including an identifier of the AI/ML service consumer, one or more notification conditions and objectives, a desired analysis type, or one or more service requirements; Determining a service action based on processing information associated with the one or more descriptions of the one or more AI/ML resources or capabilities and the consumer request, the service action comprising selecting an AI/ML resource/capability provider from the one or more AI/ML resource/capability providers to perform an AI/ML operation; sending a request to the selected AI/ML resource/capability provider to perform one or more AI/ML operations; receiving a response message from the selected AI/ML resource/capability provider, the response message indicating that the one or more AI/ML operations have been performed and including one or more results of the performed AI/ML operations, and A notification message including the one or more results of the performed AI/ML operation is sent to the AI/ML service consumer.
2. 2. The method of claim 1, wherein the provider message is a registration request or a message in response to a query/request from the AI/ML-enabled service.
3. 3. The method of claim 1, wherein the one or more AI/ML resource/capability providers comprise at least one of an AI/ML enabled service, a Vertical Application Layer (VAL) entity, an application/service enabled layer entity, or a core network function.
4. 4. The method of claim 1, wherein the one or more descriptions of the one or more AI/ML resources or capabilities comprise at least one of AI/ML data descriptions, AI/ML model descriptions, or AI/ML training/reasoning capabilities descriptions.
5. 5. The method of claim 1, further comprising: Receiving a consumer message from an AI/ML service consumer, the consumer message including filter criteria for AI/ML resources or capabilities of interest to the AI/ML service consumer, wherein the consumer message is a discovery request or a query/subscription request; A response is sent to the AI/ML service consumer, the response including information associated with AI/ML resources or capabilities of interest to the AI/ML service consumer, wherein the response includes one or more descriptions of one or more AI/ML resources or capabilities of the one or more AI/ML resource/capability providers.
6. 6. The method of claim 1, wherein the AI/ML service consumer is an AI/ML enabled service, a Vertical Application Layer (VAL) entity, or an application/service enabled layer entity.
7. 7. The method of claim 1, wherein the service action comprises reselecting a training entity or combining training procedures associated with a plurality of service instances and reconfiguring the training entity or training data.
8. 8. The method of claim 1, wherein the service action comprises reselecting an inference entity or combining a list of notification targets associated with a plurality of service instances at the inference entity.
9. 9. The method of claim 1, wherein the one or more AI/ML operations comprise one or more of collecting AI/ML data, training an AI/ML model, updating an AI/ML model, or using an AI/ML model for a inference.
10. 10. The method of claim 1, wherein the storing further comprises storing information associated with a service instance that is using or will use the one or more AI/ML resources/capabilities of the one or more AI/ML resources/capabilities providers.
11. 11. The method of claim 1, wherein the consumer request further comprises information associated with the AI/ML resource/capability provider of the one or more AI/ML resource/capability providers, a model, or training data specified by the AI/ML service consumer.
12. 12. The method of claim 1, further comprising: Based on the consumer request, an AI/ML service instance profile is generated that includes information associated with the consumer request, instance state, context information of the AI/ML service consumer, or information associated with training data, an AI/ML model, or an AI/ML resource/capability provider of the one or more AI/ML resource/capability providers.
13. 13. An apparatus for providing artificial intelligence/machine learning (AI/ML) enabled services, the apparatus comprising one or more processors and a memory storing instructions that when executed by the one or more processors cause the apparatus to: Receiving one or more provider messages from one or more AI/ML resource/capability providers, the one or more provider messages including one or more descriptions of one or more AI/ML resources or capabilities of the one or more AI/ML resource/capability providers; storing, by the AI/ML enabled service and based on the one or more provider messages, the one or more descriptions of the one or more AI/ML resources or capabilities; Receiving a consumer request from an AI/ML service consumer, the consumer request including an identifier of the AI/ML service consumer, one or more notification conditions and objectives, a desired analysis type, or one or more service requirements; Determining a service action based on processing information associated with the one or more descriptions of the one or more AI/ML resources or capabilities and the consumer request, the service action comprising selecting an AI/ML resource/capability provider from the one or more AI/ML resource/capability providers to perform an AI/ML operation; sending a request to the selected AI/ML resource/capability provider to perform one or more AI/ML operations; receiving a response message from the selected AI/ML resource/capability provider, the response message indicating that the one or more AI/ML operations have been performed and including one or more results of the performed AI/ML operations, and A notification message including the one or more results of the performed AI/ML operation is sent to the AI/ML service consumer.
14. 14. The apparatus of claim 13, wherein the provider message is a registration request or a message in response to a query/request from the AI/ML-enabled service.
15. 15. The apparatus of claim 13, wherein the one or more AI/ML resource/capability providers comprise at least one of an AI/ML enabled service, a Vertical Application Layer (VAL) entity, an application/service enabled layer entity, or a core network function.
16. 16. The apparatus of claim 13, wherein the one or more descriptions of the one or more AI/ML resources or capabilities comprise at least one of AI/ML data descriptions, AI/ML model descriptions, or AI/ML training/reasoning capabilities descriptions.
17. 17. The apparatus of claim 13, wherein the AI/ML service consumer is an AI/ML enabled service, a Vertical Application Layer (VAL) entity, or an application/service enabled layer entity.
18. 18. The apparatus of claim 13, wherein the service action comprises a reselection: Training entities or combining training processes associated with multiple service instances and reconfiguring the training entities or training data, or Reselecting an inference entity or combining at the inference entity a list of notification targets associated with a plurality of service instances.
19. 19. The apparatus of claim 13, wherein the one or more AI/ML operations comprise one or more of collecting AI/ML data, training AI/ML models, updating AI/ML models, or using AI/ML models for a inference.
20. 20. The apparatus of claim 13, wherein the storing further comprises storing information associated with a service instance that is using or will use the one or more AI/ML resources or capabilities of the one or more AI/ML resources/capabilities providers.

Description

Method and apparatus for applying data analysis enabled artificial intelligence/machine learning enabled functions Cross Reference to Related Applications The present application claims the benefit of U.S. provisional patent application No. 63/518,905 filed on 8/11 of 2023, which is incorporated herein by reference in its entirety. Background Machine Learning (ML) is a branch of Artificial Intelligence (AI) that aims to build a method of improving performance with data about a set of tasks. For example, one or more ML algorithms may be used to construct a model based on sample data (e.g., training data) to make predictions or decisions without explicit programming. The process of training the ML model may include data collection, data preparation/processing, model construction/training, model evaluation, model deployment, monitoring, and updating, etc. After training, the ML model can be deployed and used for the intended purpose, such as performing inference tasks and generating inference results. To support the deployed models and reasoning tasks, access to hardware resources (e.g., computing power, communication bandwidth, etc.) and reasoning data may be required. The 3GPP defines a network data analysis function (NWDAF) and an Application Data Analysis Enable (ADAE) service to provide analysis services to various consumers in the network. The analytics service provided by NWDAF (e.g., TS 23.288) is intended to support network data analytics services in a 5G core network. Such analysis may collect data from other NFs, AFs, or OAM and may be open to third party AFs to provide statistics and predictions related to various types of analysis, such as slice load levels, observed service experiences, NF load, network performance, UE-related analysis (mobility, communications), user data congestion, qoS sustainability, DN performance, and so forth. For example, 3gpp TS 23.288 sets forth architectural enhancements to 5G systems (5 GS) to support network data analysis services. ADAE services (e.g., TS 23.436) provide functionality to support opening data analysis services from different 3GPP domains to a vertical ASP in a unified manner. For example, 3gpp TS 23.436 sets forth the functional architecture and information flow of application data analysis enabled services. ADAE services define value added application data analysis services at the general level, which cover statistics and predictions of end-to-end application services. The primary consumers of ADAE services may include vertical specific applications and edge applications. Disclosure of Invention Methods, apparatus, and systems are described herein that manage AI/ML resources and capabilities available to applications and service enablement layers and coordinate analysis services of AI/ML enablement. According to some examples, ADAE services may be enhanced to support AI/ML-enabled analytics services. According to some examples, AI/ML resources and capabilities management is provided, wherein ADAE services maintain a profile of AI/ML resources and capabilities and support registration and discovery procedures for AI/ML resources and capabilities. According to some examples, coordination of AI/ML-enabled analytics services is provided, wherein ADAE services maintain and monitor the state of AI/ML service instances, coordinate AI/ML service requests received from different consumers, and dynamically determine service actions based on the service instances and AI/ML resource/capability information. According to some examples, enhancements to ADAE services may support AI/ML enabled analytics services at the 3GPP application and service enablement layer. Enhanced ADAE services may support management of AI/ML resources and capabilities, as well as coordination of AI/ML enabled analytics services. According to some examples, a message may be received from an AI/ML resource/capability provider. The message may include a description of the resources or capabilities of the analytics service that may be provided by the provider to support AI/ML enablement. The message may be a registration request or a message in response to a query/request from ADAE. The AI/ML resources or capabilities can include AI/ML data, AI/ML models, training capabilities, reasoning capabilities, and the like. The AI/ML resource/capability provider may be ADAE services, VAL entities (VAL servers, VAL clients), application/service-enabling layer entities (e.g., SEAL, EES, etc.), or core network functions (e.g., NWDAF, DCCF, ADRF). The description of the AI/ML resources or capabilities may include (1) AI/ML data descriptions, data formats, data usage, data characteristics, data locations, data sources, access policies, etc., (2) AI/ML model descriptions, model requirements, model locations, associated training entities and training data, access policies, etc., or (3) AI/ML training/reasoning capability descriptions, supported features, supported resources, capability schedules (schedules),