Patent · US Active

Chatbot with self-correction on response generation

US11855934B2 · kind B2 · utility

1Cited by
2References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 9, 2021
Grant dateDec 26, 2023
Priority date
Expiry dateFeb 25, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N20/00
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method and system for generating and correcting chatbot responses based on reinforcement learning (RL) are disclosed. In some embodiments, the method includes receiving user data associated with a user in a chatbot conversation. The method includes providing a first recommendation to the user. The method includes detecting user feedback to the first recommendation in the chatbot conversation. The method then includes determining whether to assign a positive reward or a negative reward to the user feedback based on sentiment analysis performed on the user feedback. If the negative reward is assigned to the user feedback, the method further includes calculating a negative reward score for the first recommendation; retraining the one or more of RL models using one or more of the negative reward score, the user data, the first recommendation, and the user feedback; and determining a second recommendation using the one or more retrained RL models.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.