A Collaborative Filtering Recommendation System and Method Using EEG Signal Assisted Preference Acquisition

Abstract

A collaborative filtering recommendation system and method using EEG signal-assisted preference acquisition, which calculates the user's emotional tendency through EEG signal data and applies this implicit feedback to the preference score of the product browsed by the user. In the recommendation process, The classification results of EEG signal data are included in the calculation category, thereby improving the recommendation accuracy of the recommendation system. By adopting the recommendation method for deeply digging user preferences of the present invention, users can quickly find what they need from overloaded information data. On the other hand, with the miniaturization and commercialization of EEG equipment, the recommendation method proposed in the present invention combines the professional knowledge in the field of brain-computer interface, and proposes a new direction for the next development of the recommendation system.

Description

technical field [0001] The invention belongs to the technical field of information recommendation and pattern recognition, and in particular relates to a collaborative filtering recommendation system and method for assisting preference acquisition by using electroencephalogram signals. Background technique [0002] Emotions often involve people's immediate needs and subjective attitudes, often have complex interrelationships with other psychological processes, and are a comprehensive state of thinking, feeling, and behavior. Since ancient times, China has said the seven emotions of "joy, anger, sorrow, joy, sorrow, and fear". Lange et al. proposed an emotion classification model based on two-dimensional space based on pleasure and arousal, so that people's different emotional experiences can be mapped to a two-dimensional emotional space through these two dimensions. [0003] The brain is the most complex part of human organs, it contains a wealth of physiological and psych...

AI Technical Summary

Problems solved by technology

[0006] The existing collaborative filtering system only uses the known preference data of the current user or other users for some items to predict the potential preference of the current user for other items, and does not take into account the emotional changes of the user when browsing products and the similarity relationship between items. , the user's demand for recommended content often changes in different emotional states

Images