View source for 17766616. RE-RANKING RESULTS FROM SEMANTIC NATURAL LANGUAGE PROCESSING MACHINE LEARNING ALGORITHMS FOR IMPLEMENTATION IN VIDEO GAMES simplified abstract (GOOGLE LLC)

=RE-RANKING RESULTS FROM SEMANTIC NATURAL LANGUAGE PROCESSING MACHINE LEARNING ALGORITHMS FOR IMPLEMENTATION IN VIDEO GAMES=


==Organization Name==

[[:Category:GOOGLE LLC|GOOGLE LLC]]


[[Category:GOOGLE LLC]]

==Inventor(s)==

[[:Category:Anna Kipnis of San Bruno CA (US)|Anna Kipnis of San Bruno CA (US)]][[Category:Anna Kipnis of San Bruno CA (US)]]

[[:Category:Benjamin Pietrzak of San Francisco CA (US)|Benjamin Pietrzak of San Francisco CA (US)]][[Category:Benjamin Pietrzak of San Francisco CA (US)]]

==RE-RANKING RESULTS FROM SEMANTIC NATURAL LANGUAGE PROCESSING MACHINE LEARNING ALGORITHMS FOR IMPLEMENTATION IN VIDEO GAMES - A simplified explanation of the abstract==


This abstract first appeared for US patent application 17766616 titled 'RE-RANKING RESULTS FROM SEMANTIC NATURAL LANGUAGE PROCESSING MACHINE LEARNING ALGORITHMS FOR IMPLEMENTATION IN VIDEO GAMES

==Simplified Explanation==

The abstract describes a patent application for a semantic natural language processing (NLP) machine learning (ML) algorithm stored in memory and executed by a processor to generate scores based on matching candidate responses with user input phrases. The scores are then modified using rules that associate phrases, selected based on semantic similarity, to improve the execution of the program code.

* The patent application involves a semantic NLP ML algorithm stored in memory.
* The algorithm generates scores based on matching candidate responses with user input phrases.
* The scores are modified using rules that associate phrases to improve program execution.
* Rules are selected based on semantic similarity of input and response phrases.

### Potential Applications
- Chatbots
- Virtual assistants
- Customer service automation

### Problems Solved
- Improving accuracy of matching responses to user input
- Enhancing natural language understanding in machines

### Benefits
- Increased efficiency in processing natural language
- Enhanced user experience with AI-powered systems
- Improved automation of tasks requiring language processing


==Original Abstract Submitted==

Program code representing a semantic natural language processing (NLP) machine learning (ML) algorithm is stored in a memory. A processor executes the semantic NLP ML algorithm to generate initial scores that represent a degree of matching between candidate responses and an input phrase provided by a user during execution of program code. The processor also modifies one or more of the initial scores using one or more rules that associate a first phrase with a second phrase. The one or more rules are selected to modify the initial scores based on semantic similarity of the user input phrase and the first phrase determined by the semantic NLP ML algorithm and the semantic similarity of the response phrase with a corresponding candidate response. Execution of the program code is modified based on the modified initial scores. In some cases, the semantic NLP ML algorithm is used to implement a video game.



[[Category:A63F13/424]]
[[Category:G06F40/30]]
[[Category:A63F13/422]]