Web Content Recommendation Research And Optimization Based On Personalized

Developing very rapidly, the Internet has become the largest distributed database ofinformation. On one hand, the information contribute greatly to the efficiency of people’daily life; on the other hand, as a result of the overwhelmingly redundant information, ithas become increasingly more difficult to exact useful information quickly and efficiently.Traditional search is based on the keyword search, but this method can not effectivelyextract and retrieve the association between semantic content and implicit information,besides，it also performs not well on the knowledge discovery and the recall rate. Theemergence of Semantic Web search technology, can effectively alleviate such problems. Itis able to provide the users with more sophisticated, accurate and automatic service.In this paper, we discuss Web content recommendation system and its optimization,which is based on interest learning. We add user interest areas to the user ontologyaccording to the area ontology that involved in user search. We calculate the weight ofuser interest from the relationship between the concept and the semantic. The ontology isreal-time updated by the user browsing behavior. Then we can get a more accurate userinterest model. Because the user interest is added to search statement as the searchrestriction, it will increase the system response time. In this paper, we study the graphtheory algorithms and re-sort the search criteria, reduce the intermediate result sets byselecting the valuation, choose an efficient implementation plan to improve the connectionsearch efficiency. Then the search response time is reduced and a faster and more accurateresult returns to the user.In this paper, we first introduce the core technology of the Web contentrecommendation, which is based on interest learning. Then we study the user interestlearning algorithm to improve the accuracy of the user search. As the user interestincreases the complexity of the search condition, we optimize the search time by thesearch optimization strategy to improve the efficiency of the user search. Experiments aredone to contrast the search optimization strategy and search engine using other methods.The result shows that the method in this paper can improve the search efficiencyeffectively. By the research and the optimization, improved interest-learning-based Webcontent recommendation system meets users’ interest better on recommending informationfor users, and the search efficiency is also improved.By the experiment, the search results are reordered according to the user interestmodel and return to the user. The users’ satisfaction has increased. We can see that theimproved user interest model is closer to the real user interest. It can reduce the time of searching and turning pages and bring the user a more pleasant user experience. A searchsystem that user interest is added to the query statement as a constraint will increase thequery time. After the query optimization in this paper, the query efficiency has increasedthan former. Especially for the complex case of the query conditions and the statementrelationship, the optimization is more effective.