BEHAVIOR PREDICTION ON SOCIAL MEDIA USING NEURAL N

专利名称：BEHAVIOR PREDICTION ON SOCIAL MEDIA

USING NEURAL NETWORKS

发明人：Mandy Barrett Korpusik,Francine

Chen,Shigeyuki Sakaki,Yin-Ying Chen

申请号：US149638申请日：20151211

公开号：US20170169475A1公开日：20170615

专利附图：

摘要：Example implementations include a system and method of recognizing behaviorof a user. In example implementations, a first post and at least one subsequent post

indicative of a product and associated with a first social media account is obtained. Arelevance probability is calculated for each of the obtained first post and the at least onesubsequent post. The obtained first post and the at least one subsequent post aresequentially analyzed by a second neural network to determine output values relevantto probability of purchasing the product. A probability of purchasing the product iscalculated based on the determined output values associated with each post and thecalculated relevance probabilities. Product-related information is transmitted to the userassociated with the obtained first post based on the determined probability ofpurchasing the product.

申请人：FUJI XEROX CO., LTD.

地址：Tokyo JP

国籍：JP

更多信息请下载全文后查看