Expression recommendation method and device based on user social relation

Abstract

The invention relates to an instant messaging technology, and discloses an expression recommendation method based on a user social relationship, which is used for improving the accuracy of expressionrecommendation and improving the screening efficiency when a user screens expressions. The method comprises the following steps of: based on traditional expression recommendation based on semantic recognition, based on the chat object identity and intimacy embodied by each expression, refining and classifying each expression. In this way, when the user interacts with the chat object, expressions which better accord with the identity and intimacy of the chat object can be recommended, the recommendation results are more accurate and more in line with the user's psychological needs. Compared with a traditional expression recommendation method, the expression recommendation method has the advantages that the range of the to-be-recommended expressions can be further narrowed, the expression selection time and energy of the user are saved, the recommendation result is more accurate, and the social demands of the user and chat objects are better met.

Description

technical field [0001] The present invention relates to instant communication technology, in particular to an emoticon recommendation method and device based on user social relations. Background technique [0002] At present, instant messaging services are increasingly becoming an indispensable tool for people's daily communication. With the increase of people's communication needs, the current mainstream instant messaging services not only provide chat content such as text and voice, but also provide expression-based The chat function of the chat, through a variety of emoticons that reflect different moods, users can not only express their emotions more vividly, but also activate the chat atmosphere, and sometimes even send some emoticons when they have nothing to say. Resolve embarrassment and give users a better product experience. However, with the continuous increase of the emoticon library, users need to search and select emoticons when they want to send emoticons dur...

AI Technical Summary

Problems solved by technology

Therefore, the traditional emoticon recommendation method does not consider the relationship between the user and the chat object when recommending, and cannot meet the user's needs for different styles of emoticons when facing different relationship chat objects, resulting in inaccurate recommendation results.

Images