Personalized human-computer emotional session system

Abstract

The invention discloses a personalized human-computer emotional session system. The personalized human-computer emotional session system comprises a personalized personality modeling and dynamic analysis module, a session management module and an answer comfort detection and answer strategy adjustment module, wherein the personalized personality modeling and dynamic analysis module includes a session knowledge base and a psychological knowledge base, and a personalized personality modeling and dynamic analysis method; the session management module includes the following steps of 1, performingsemantic analysis on user input; 2, performing semantic inference on the basis of the semantic analysis; 3, formulating an answer strategy according to an inference result; and 4, generating a sessioncontent with the answer strategy as a guidance; and the answer comfort detection and answer strategy adjustment module includes emotional dynamic and psychological knowledge bases and an answer comfort detection and answer strategy adjustment method. The personalized human-computer emotional session system is suitable for a human-computer interaction task, and the personalized personality modeling analysis and an emotional session service are fused, thus the personalized natural interaction experience of the human-computer session system is improved.

Description

technical field [0001] The invention relates to the technical fields of artificial intelligence, natural language understanding, emotional computing and human-computer interaction, in particular to a personalized human-computer emotional conversation system. Background technique [0002] Artificial intelligence tries to understand the essence of intelligence. By simulating human consciousness and thinking, it endows machines with similar capabilities to human intelligence to extend and expand human intelligence, so that machines can complete tasks that usually require human intelligence. Natural language processing is the "crown jewel" of artificial intelligence. It mainly studies various theories and methods that can realize effective communication between humans and computers using natural language. Affective computing takes emotion as the research object, aims at endowing computers with the ability to perceive, understand and express emotions, and aims at building a harmo...

AI Technical Summary

Problems solved by technology

[0003] Traditional human-machine conversational systems ignore the relationship between emotional factors and conversational responses during conversations, and often only focus on factual conversations; and do not consider user personalization factors, and cannot generate personalized responses based on user personality characteristics; Generalization between domains can only complete specific tasks in specific domains; and the generation of conversational responses mainly relies on information retrieval technology, which cannot generate conversational responses that have never appeared in the knowledge base

Images