A Service Composition Approach Combining Gaussian Processes and Reinforcement Learning
A technology of reinforcement learning and service combination, applied in digital transmission systems, data exchange networks, electrical components, etc., can solve the problems of lack of generalization ability and inaccurate learning results, and achieve the effect of accurate prediction and good generalization ability
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Publication Date
- 2020-04-24
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
Description
technical field
[0001] The invention relates to a method for combining Web services by using a computer, which belongs to the field of artificial intelligence. Background technique
[0002] With the development of computer technology, the requirements of software systems are becoming more and more complex and changeable. Coupled with the development of the Internet and information technology, a service-oriented software architecture (Service-Oriented Architecture) has gradually emerged: it will realize a certain Some functional software or components are placed in the Internet environment as web services, and users can communicate with web services through a certain message protocol to use their functions. Finally, by combining multiple web services, a new software system that meets the needs is constructed. At present, common web services include weather services, map positioning services, and so on.
[0003] For a certain function, there are generally multiple services p...
Examples
Embodiment Construction
[0034] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments.
[0035] The basic model of service composition is as figure 1 As shown, a complex software system can be regarded as a workflow composed of multiple components or subsystems. In the field of service composition, components are web services. Therefore, when performing service composition, user requirements can be modeled with an abstract task workflow diagram, in which each component is an abstract service. For each abstract service, there may be multiple candidate services, these services have similar functions, but have different QoS (Quality of Service), so the appropriate specific service can be selected from the candidate services based on the QoS attributes, and finally the available Service composition system.
[0036] The service combination method combining Gaussian process and reinforcement learning disclosed by the present invention ...