Information recommendation effect evaluation method and mobile phone based on facial expression images

Abstract

The invention relates to an information recommendation effect evaluation method and mobile phone based on facial expression images. The method comprises the steps that recommendation information such as pictures, characters, videos and games are read and watched by users, facial expression images of users are collected in the reading process, features of facial expression images are extracted, the emotional situations of users are judged through a facial expression classifier, and the emotional states serve as evaluation effects of information recommendation. The invention further discloses the information recommendation effect evaluation mobile phone based on facial expression images. The information recommendation effect evaluation mobile phone based on facial expression images comprises a recommendation information reading module, a facial expression image collection module, a facial expression image feature vector structuring module, a facial expression classification module, an information recommendation effect evaluation module and a facial expression training sample database. The information recommendation effect evaluation method and mobile phone based on facial expression images have the effects that facial expressions are collected more naturally, evaluation is more real, use is more convenient, and the method can be applied to improvement on an advertisement putting method, a video recommendation method, a game design strategy and the like.

Description

technical field [0001] The invention relates to an evaluation method of information recommendation effect based on facial expression images and a mobile phone, belonging to the fields of information recommendation and pattern recognition. Background technique [0002] Information recommendation is a popular field in recent years, such as e-commerce, social networking sites, etc. It solves the problem of information overload for users and undertakes the burden of avoiding information "overload" on the basis of identifying customer consumption preferences. trouble. Precise advertising is another kind of special information recommendation. At present, many merchants spend huge sums of money on advertising, hoping to use the huge user base to promote advertising on a large scale. This kind of information recommendation reduces the troubles for users. Another type of information recommendation is used to improve marketing strategies and develop new businesses. For example, in te...

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is: the existing information recommendation system lacks the problem of automatic evaluation of recommended information, especially does not consider the user's psychological reflection on recommended information, and it is difficult to obtain a satisfactory recommendation effect

Images