Gateway personalized recommendation service method and system introduced yuan recommendation engine

Abstract

The invention discloses a personalized portal recommendation services method and system using Yuan recommendation engine, and provides portal users interested models construction, including the initial creation and the follow update of portal users' interested model. It provides Personalized Recommendation Service Architecture independent to the portal platform by using Yuan recommendation engine, and Yuan recommendation engine can analyze the association of users and user groups, and personal interest changes, and unified control information resources and recommended algorithm to reasonable choice, and optimized push and produce more comprehensive variety personalized recommendations. In resources display, the system with personalized portal recommendation services can package a variety of Web content objects predicted to be recommended into portal component, give the portal users vivid and direct personal display, and provide a higher level of personalized control. Comprehensive utilization of the existing personalized resources and technical means of the portal platform provides independent and flexible services middleware or services agency, to complete the personalized recommendation services.

Description

technical field [0001] The present invention relates to portal technology, in particular to a portal personalized recommendation service method and system using a meta-recommendation engine. Background technique [0002] Personalized recommendation service can actively provide Internet (Internet) users with diversified and intelligent personalized services, displayed in the fastest way, and assist users to efficiently and comprehensively obtain useful World Wide Web (Web) resource information. At present, the system that can realize the personalized recommendation service has become an important part of the network information system, especially in the large-scale portal application fields such as e-commerce, digital library, distance education and so on. With the advent of the Web 2.0 era, resource integration and personalized service means based on portal platforms are becoming more and more abundant. At present, there is a method that uses a central database to store all...

AI Technical Summary

Problems solved by technology

In the current existing methods that use a central database to store all recommendation algorithms and provide dynamic and flexible choices for users to make recommendations, the meta-recommendation system architecture mode generally emphasizes the data layer integration of heterogeneous processing of various recommendation systems, which is about to disperse independent recommendation systems The integration is relatively opaque, so it still tends to system integration, does not consider the details of the recommended algorithm combination selection strategy, and is not suitable for lightweight general requirements that are easy to deploy and not restricted by platforms and resources

Images