17959665. CONTINUOUSLY IMPROVING API SERVICE ENDPOINT SELECTIONS VIA ADAPTIVE REINFORCEMENT LEARNING simplified abstract (International Business Machines Corporation)
Contents
- 1 CONTINUOUSLY IMPROVING API SERVICE ENDPOINT SELECTIONS VIA ADAPTIVE REINFORCEMENT LEARNING
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 CONTINUOUSLY IMPROVING API SERVICE ENDPOINT SELECTIONS VIA ADAPTIVE REINFORCEMENT LEARNING - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
CONTINUOUSLY IMPROVING API SERVICE ENDPOINT SELECTIONS VIA ADAPTIVE REINFORCEMENT LEARNING
Organization Name
International Business Machines Corporation
Inventor(s)
Rong Nickle Chang of Pleasantville NY (US)
Nitin Gaur of Round Rock TX (US)
CONTINUOUSLY IMPROVING API SERVICE ENDPOINT SELECTIONS VIA ADAPTIVE REINFORCEMENT LEARNING - A simplified explanation of the abstract
This abstract first appeared for US patent application 17959665 titled 'CONTINUOUSLY IMPROVING API SERVICE ENDPOINT SELECTIONS VIA ADAPTIVE REINFORCEMENT LEARNING
Simplified Explanation
The method described in the abstract involves using a machine learning model to select an endpoint for a web-based service based on a feature vector generated from the request parameters.
- The processor set receives a request for a web-based service.
- The processor set generates a feature vector based on the parameters of the request.
- The processor set generates an endpoint selection vector with probabilities for different endpoints using the feature vector and a machine learning model.
- One of the plural endpoints is selected based on the probabilities.
- The selected endpoint is invoked by the processor set.
Potential Applications
This technology could be applied in various industries such as e-commerce, online services, and cloud computing to optimize endpoint selection for better performance and user experience.
Problems Solved
1. Efficient endpoint selection for web-based services. 2. Improved performance and user experience by selecting the most suitable endpoint based on request parameters.
Benefits
1. Enhanced scalability and reliability of web-based services. 2. Automated endpoint selection process based on machine learning for optimal performance. 3. Streamlined decision-making process for selecting endpoints.
Potential Commercial Applications
Optimizing endpoint selection for cloud services in "Enhancing Cloud Service Performance with Machine Learning Endpoint Selection."
Possible Prior Art
One possible prior art could be the use of load balancing algorithms to distribute incoming requests among multiple endpoints based on factors like server load and response time.
Unanswered Questions
How does this method handle dynamic changes in endpoint performance or availability?
The abstract does not provide information on how the system adapts to changes in endpoint performance or availability to ensure optimal selection.
What types of machine learning models are suitable for generating the endpoint selection vector?
The abstract does not specify the specific machine learning models used for generating the endpoint selection vector.
Original Abstract Submitted
A method includes: receiving, by a processor set, a request for a web-based service; generating, by the processor set, a feature vector including values based on parameters of the request; generating, by the processor set, an endpoint selection vector including plural probabilities corresponding to plural endpoints, wherein the endpoint selection vector is generated using the feature vector with a machine learning model; selecting, by the processor set, one of the plural endpoints based on the plural probabilities; and invoking, by the processor set, the selected endpoint.
