A method and device for emoticon recommendation based on user social relationship

Abstract

The invention relates to instant communication technology, and discloses an emoticon recommendation method based on user social relations, which is used to improve the accuracy of emoticon recommendation and improve the screening efficiency when users screen emoticons. The method is: on the basis of traditional expression recommendation based on semantic recognition, each expression is refined and classified based on the identity and intimacy of the chat object embodied by each expression, so that when the user interacts with the chat object, more recommended The emoticons that meet the identity and intimacy of the chat object make the recommendation results more accurate and more in line with the psychological needs of users. Compared with traditional emoticon recommendation methods, it can further narrow the range of emoticons to be recommended, saving users time and energy in selecting emoticons, and The recommendation results are more accurate and more in line with the social needs of users and chat partners.

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