5 results about "Recommender system" patented technology

The system and method of the present invention automatically extracts the top k recommendations of objects, such as topics, items, products, books, movies, food, drinks, etc., from a local probabilistic recommendation system. Unlike prior systems, the present invention accomplishes the extraction of the top k recommendations of objects without examining a probability for every object that can be recommended. Further, the system and method of the present invention is capable of being implemented using probabilistic recommendation systems based on any conventional type of probabilistic distribution or machine learning technique, including, for example, decision trees and Bayesian networks.

Disclosed are a natural person information setting method, an account information providing method and an electronic device. The natural person information setting method includes the steps of: according to an association degree index and an exclusive degree index of each account and other accounts, determining an associated set of each account; performing convergence processing on all associated sets, so as to allow the associated accounts in any two associated sets subjected to the convergence processing not to be repeated; and setting the same natural person information for the associated accounts in one and the same associated set subjected to the convergence processing, and performing one and the same natural person setting on the associated accounts in one and the same associated set according to the natural person information. Also disclosed are an account information providing method and an electronic device.

The embodiment of the invention provides a cross-platform AI model recommendation system and method, and the system is used for carrying out AI model recommendation according to the demands of a user, and comprises an obtaining module which is used for obtaining a model description text of an AI model from a plurality of AI open platforms; the user module is used for acquiring a demand description text of a user for the required AI model; the recommendation module is used for matching the demand description text of the user for the required AI model with the acquired model description text of the AI model, and generating an AI model recommendation list according to the matching degree; according to the method, the model description text of the AI model is obtained from the multiple AI open platforms, the demand description text of the user for the needed AI model is matched with the obtained model description text of the AI model, and the AI model recommendation list is generated according to the matching degree, so that cross-platform AI model recommendation can be efficiently and accurately realized.

The invention discloses a tourism destination recommendation system and method based on tourism big data, and the system comprises a recommendation information collection module, a database, an internal factor analysis module, an external factor analysis module and a destination screening module. All collected information is stored through a database, data of a user is analyzed and internal parameters are set through an internal factor analysis module, external information is analyzed and external parameters are set through an external factor analysis module, and destinations are screened through a destination screening module in combination with the internal parameters and the external parameters. Different screening functions are set for screening destinations according to single-person and multi-person tourism conditions, the application range of the recommendation mode is expanded, and tourism experience feelings of different users are improved.