Semantic recognition method and device

Abstract

The embodiment of the invention provides a semantic recognition method and device. The semantic recognition method and device are applicable to inferencing and understanding the acting styles, the personality hints and the psychological characteristics of figures and organizations. According to the embodiment of the invention, a computer obtains text data corresponding to the character expression about behavior facts. The method comprises the steps: firstly, according to a predetermined near-synonymous relationship corresponding model and an antisense relationship corresponding model, computing the standard character expression of the behavior facts; then, according to the standard character expression of the behavior facts, searching in a predetermined database of the corresponding relationship of the behavior facts and the personality hints to obtain the standard character expression of the personality hints corresponding to the behavior facts. Through the adoption of the semantic recognition method and device, disclosed by the embodiment of the invention, the computer can obtain the personality hints beyond the character expression according to the character expression of the behavior facts, and judges the personality characteristics or the acting styles of the figures and the organizations according to the personality hints, and the demands for artificial intelligence and personification can be further satisfied.

Description

technical field [0001] Embodiments of the present invention relate to the field of pattern recognition, in particular, to a method and device for semantic recognition. Background technique [0002] Semantic recognition is a kind of pattern recognition. It further analyzes and mines the obtained objective character text data, and then extracts the user's subjective intention contained in it. The purpose is to enable computers to understand human language to meet the needs of artificial intelligence. needs. In the prior art, a computer can usually only recognize the direct or literal meaning of words or sentences in a written expression. In this case, the computer can only simply copy or copy other expressions that are the same or similar to the written expression, while It is impossible to further understand the personality, psychological characteristics, tendencies, and behavioral motivations of the actors involved behind the text expressions, and it is difficult to meet th...

AI Technical Summary

Problems solved by technology

In the prior art, computers usually can only recognize the direct meaning or literal meaning of the words or sentences in the written expression. In this case, the computer can only simply copy or copy other expressions that are the same or similar to the written expression, while It is impossible to further understand the character, psychological characteristics, tendencies, and behavioral motivations of the actors involved behind the text expressions, and it is difficult to meet the needs of artificial intelligence and anthropomorphism

Images