Patent
Personalized news recommendation device and method based on news content and theme feature
TLDR
In this article, a personalized news recommendation device and method based on news content and theme feature was proposed. But the authors did not reveal the model used to build the personalized user model with the theme model and a relevant named entity noun sequence.Abstract:
The invention discloses a personalized news recommendation device and method based on news content and theme feature The recommendation device is equipped with seven modules, namely a news capturing module, a pre-treatment module, a theme model training module, a theme model predicting module, a user model building module, a news recommendation module and a recommendation treatment module The recommendation method comprises the following steps: building an personalized user model with the theme model and a relevant named entity noun sequence to express the interest preference of the user reading news, and calculating weight and converting the theme feature vector of users so as to reduce the influence of hot themes and single news content on the user interest, thereby effectively overcoming the defects of concentrated user interest and insufficient diversity of recommendation results In a recommendation output stage, an initial recommendation news list is treated, a theme grouping process based on the personalized user model is added on the basis of currently repeating data deleting and redundancy filtering, and news texts are reordered again according to the aging weight so as to recommend the accurate, diversified and novel personalized newsread more
Citations
More filters
Patent
Artificial intelligence-based object pushing method and apparatus
TL;DR: In this article, an artificial intelligence-based object pushing method and apparatus is presented, which comprises the steps of inputting historical click behaviors of a target user to a built user model for performing learning to obtain multi-dimensional preference eigenvectors of the target user, and pushing the to-be-pushed objects according to the obtained prediction probabilities.
Patent
News recommendation system and method based on FOLFM model
TL;DR: In this paper, a news recommendation system and method based on an FOLFM model is proposed, where a news content model is expressed abstractly through a latent class model and content characteristics, and an individual latent class preference model is built for each user.
Patent
Personalized research direction recommending system and method based on themes
TL;DR: In this paper, a personalized research direction recommendation system and method based on themes is proposed, which is based on a three-layer graph model to calculate preference values of the users for the themes according to the three layer graph model, to obtain a user-theme preference weight matrix, and to calculate similar user set between the users and other users based on the weight matrix.
Patent
Individual service recommendation system and method based on topic model
TL;DR: In this paper, an individual service recommendation system based on a topic model is proposed, which consists of a social data acquisition module, topic model construction and analysis module, user interest modeling module, service recommendation module, a user interaction module and a system management control module.
Patent
News recommendation method and system
TL;DR: In this article, the authors proposed a news recommendation method and system that aims to push news to different types of users who are interested in the news by extracting features of search and query data, according to behaviors of a certain type of users.
References
More filters
Patent
Automatic recommendation of vertical search engines
TL;DR: The automatic search engine recommendation technique described in this paper automatically recommends topic-specific search engines for user queries, and automatically matches each query submitted to a non-topic specific or general search engine with one or more vertical search engines using a recommendation model and a set of features.
Patent
Method for establishing user interest model
TL;DR: In this article, a method for establishing a user interest model based on constructing an user individual interest model is presented, where a social coordination relationship among users is calculated by utilizing behavior characteristics of the users, and a group interest model of users is established by taking a quantization value of the relationship as a weight.
Patent
Personalized user tag modeling and recommendation method based on unified probability model
Jie Tang,Ning Zhang +1 more
TL;DR: In this article, a personalized user tag modeling and recommendation method based on a unified probability model was proposed, comprising the following steps: S1, carrying out statistics on tagging behaviors of users on a social tagging site; S2, carrying a formal definition on questions tagged by the users; S3, establishing a topic model based on user tagging, wherein the topic model is a unified probabilistic model and called a UdT model, and S4, establishing the frame of a tag recommendation system based on the UdT, where the frame is recommended through learning the interest of
Patent
Decision fusion of recommender scores through fuzzy aggregation connectives
TL;DR: In this article, a method of fusing recommender scores includes the steps of: (a) providing a first recommender score for a topic of interest based on a first set of information; (b) providing an additional score for the same topic by compensatory fuzzy aggregation connectives; and (c) making a final recommendation for the topic based on the fusion in step (c).