18662647. EXAMPLE-DRIVEN MACHINE LEARNING SCHEME FOR DIALOG SYSTEM ENGINES simplified abstract (GOOGLE LLC)
EXAMPLE-DRIVEN MACHINE LEARNING SCHEME FOR DIALOG SYSTEM ENGINES
Organization Name
Inventor(s)
Ilya Gennadyevich Gelfenbeyn of Sunnyvale CA (US)
Artem Goncharuk of Arlington VA (US)
Pavel Aleksandrovich Sirotin of Sunnyvale CA (US)
EXAMPLE-DRIVEN MACHINE LEARNING SCHEME FOR DIALOG SYSTEM ENGINES - A simplified explanation of the abstract
This abstract first appeared for US patent application 18662647 titled 'EXAMPLE-DRIVEN MACHINE LEARNING SCHEME FOR DIALOG SYSTEM ENGINES
The patent application discloses a method for example-driven machine learning, involving dialog system rules and a knowledge database containing intent and entity objects associated with the rules.
- The method receives an exemplary phrase and retrieves linguistic elements from it.
- It determines if the linguistic elements are related to intent or entity objects, adding them to the knowledge database in association with dialog system rules.
Potential Applications: - Natural language processing systems - Chatbots and virtual assistants - Customer service automation
Problems Solved: - Enhancing machine learning accuracy - Improving natural language understanding - Streamlining dialog system rule management
Benefits: - Increased efficiency in machine learning processes - Enhanced user interactions with AI systems - Improved customization of dialog systems
Commercial Applications: - AI-powered customer service platforms - Virtual assistant applications for various industries - Data analysis and information retrieval systems
Questions about Example-Driven Machine Learning: 1. How does this method improve the accuracy of machine learning models? 2. What are the potential challenges in implementing this technology in real-world applications?
Frequently Updated Research: - Stay updated on advancements in natural language processing and machine learning algorithms to enhance the performance of example-driven machine learning systems.
Original Abstract Submitted
A method for example-driven machine learning is disclosed herein. The method comprises maintaining a plurality of dialog system rules and a knowledge database including a plurality of intent objects and a plurality of entity objects. The plurality of intent objects and the plurality of entity objects are associated with at least one dialog system rule. An exemplary phrase is received and one or more linguistic elements are retrieved from the exemplary phrase. It is determined that at least one of the linguistic elements is directed to at least one of the plurality of intent objects of the plurality of entity objects and at least one of the linguistic elements in association with the at least one dialog system rule is added to the knowledge database.
