Chat-robot-oriented hybrid strategy type emotional comforting system

Abstract

The invention discloses a chat-robot-oriented hybrid strategy type emotional comforting system and method. The system takes the emotion calculation as a core and has the capability of task completionand automatic question answering, and the defects of existing chat robots in the current market are effectively overcome. According to the technical scheme, the system comprises an emotional calculation-oriented language understanding module for identifying intention label, a keyword slot and an emotion category possibly contained from a user query which is inquired by a current user; an emotionalcalculation-oriented conversation management module, which is used for generating candidate user responses for the user, re-sorting the generated candidate emotion responses according to the dialoguestate determined by the multi-round dialogue, and generating re-ordered user responses; and an emotional calculation-oriented language generation module which generates a final user response according to a robot portrait set by the user according to the re-ordered user responses which are output by emotional calculation-oriented conversation management module.

Description

technical field [0001] The invention relates to a human-computer interaction technology, in particular to a chat robot-oriented mixed-strategy emotional appeasement system. Background technique [0002] Letting machines chat with humans is one of the most challenging tasks in the field of artificial intelligence in recent years, and it has received continuous attention from academia and industry. In 1966, Joseph Weizenbaum of the Massachusetts Institute of Technology (MIT) developed the ELIZA chat system to simulate a psychiatrist. In 2011, IBM developed the in-depth question-answering system Watson, which successfully defeated humans in the "Jeopardy" TV show. In 2014, Microsoft launched the intelligent chatbots "Xiaobing" and "Xiaona", which received widespread attention. Today, smart speaker systems represented by "Little AI Speaker" and "Tmall Genie" have entered thousands of households. It is not difficult to see that the technology of man-machine dialogue has been g...

AI Technical Summary

Problems solved by technology

[0005] 1. Single function and feature: the existing chatbots either focus on task completion, such as "Xiaona", "Watson", etc., or focus on the intelligence of chatting, such as "Xiaobing", "ELIZA", etc. Chatbots with Task Completion and Emotional Computing

[0006] 2. Lack of emotional computing: The chat robot "Xiaobing" with outstanding performance in small talk uses rules or memory banks to allow the machine to respond to users such as "singing" and "writing". type emotional computing module, therefore, it cannot be called a chatbot with emotional comfort function

[0007] 3. Lack of user portraits: the user groups of chatbots are quite different in age, gender, personality and many other dimensions. However, the existing chatbots do not have the ability to give different responses to different user portraits

Successful emotional reassurance is impossible without the ability to model what personas reveal

[0008] 4. Lack of robot portraits: Existing chatbots do not have the function of setting robot avatars

This limits the robot's ability to soothe emotionally

Images