Chat expression reply method and device and storage medium

Abstract

The invention relates to the technical field of network application, and provides a chat expression reply method and device, and a storage medium, and the method comprises the steps: S10, receiving achat message sent by a user; wherein the chat message comprises any one of a text message, a picture message and a voice message; S20, analyzing the chat message to obtain effective information; S30,judging the effective information, and matching an expression reply strategy according to a judgment result to obtain an expression reply result; and S40, sending the expression reply result to the user. In addition, the invention also provides a chat expression reply device and a storage medium. According to the technical scheme provided by the invention, the chat message sent by the user is automatically recognized, the optimized expression reply is intelligently matched, and the expression reply is accurate and reasonable, has diversity and interestingness, and is rich in expressive force.

Description

technical field [0001] The present invention relates to the technical field of network applications, in particular to a chat expression reply method, device and storage medium. Background technique [0002] Chatting is a common function of network applications, such as WeChat, QQ, Weibo, Baidu Tieba and other social network applications. In social network applications, the use of network emoticons greatly enriches the expression of people's daily emotions. Compared with traditional text and voice, It shows more fun and friendliness, and with the emergence of various emoticon input methods in network media, the use of emoticons has become more widespread. Especially in the pan-entertainment social scene, the use of emoticons undoubtedly shortens the distance between people and creates a relaxed and active atmosphere. In some two-dimensional network groups, you can even see loyal users who only use emoticons for communication. It can be seen that expression communication has ...

AI Technical Summary

Problems solved by technology

[0003] With the emergence of chatbots, it is becoming more and more common to imitate human beings as chat objects by adding chatbots in social network applications, but chatbots in the prior art are mostly in the form of text or voice, and are not good at intelligent replies to network picture emoticons. Too ideal, mainly manifested in: first, the reply is not accurate and reasonable; second, there is a lack of chat data for emoticon interaction; third, only existing emoji replies can be used, and emoticons cannot be automatically synthesized or generated; fourth, emoticon replies are not diverse and interesting enough sex, expressiveness is not rich enough

Images