Semantic interaction method and device and electronic device

Abstract

The invention provides a semantic interaction method and device and an electronic device. The method comprises the steps that initial interaction contents input by users are input into a preset classification model, so that application scenes corresponding to the initial interaction contents are obtained, and response core elements corresponding to the application scenes are obtained; whether the initial interaction contents comprise all response core elements or not is judged, if not, inquiries of supplying the lacking response core elements are generated, continuous interaction contents of the users responding to the inquiries are received, and when the received continuous interaction contents complement the response core elements completely, responses required by the users are generated according to the contents of the response core elements. According to the semantic interaction method, the initial interaction contents of the users are classified to the corresponding application scenes according to the classification model, interaction is conducted in the specific application scenes, and the interaction accuracy is improved. In addition, when the interaction contents are not complete, the inquiries of supplying complete information are given, the device guides the users to improve the information, and the responses are more accurate and humanized.

Description

technical field [0001] The present invention relates to the field of semantic interaction, in particular to a semantic interaction method, device and electronic equipment. Background technique [0002] In the existing semantic interaction products, for the semantic content input by the user, syntactic analysis or word segmentation is used to determine which field the interactive content input by the user belongs to. The disadvantage of this method is that some semantic content input by the user may include Multiple word segmentations belonging to different fields, or there is no preset target word segmentation in the semantic content, resulting in errors in field identification, or inaccurate field positioning, resulting in unnecessary responses for users, and poor user experience. Contents of the invention [0003] In view of this, the purpose of the embodiments of the present invention is to provide a semantic interaction method, device and electronic equipment to improv...

AI Technical Summary

Problems solved by technology

[0002] In the existing semantic interaction products, for the semantic content input by the user, syntactic analysis or word segmentation is used to determine which field the interactive content input by the user belongs to. The disadvantage of this method is that some semantic content input by the user may include Multiple word segmentations belonging to different fields, or there is no preset target word segmentation in the semantic content, resulting in errors when identifying domains, or inaccurate domain positioning, resulting in unnecessary responses for users, and poor user experience

Images