Customized recommendation method based on user interest

Abstract

The invention discloses a customized recommendation method based on user interest. The method comprises that dishes are classified; users are divided into different expert user classes in each restaurant; an interest model is established for each user; a candidate expert user with authority in a present restaurant in the aspect of user interest is selected, a preliminary recommendation dish of the candidate expert user is obtained; the similarity between the user and a candidate expert is calculated; and a final dish is recommended. According to the method, user interest, suggestions of expert users of the restaurant and dining time of the user are combined, dishes that satisfy customized demands are recommended for the user, the dish recommending efficiency and accuracy are improved, the dishes are recommended for the user in real time, and a time factor is introduce to improve an interest sensing algorithm and a dish preference prediction effect and further to improve the recommendation accuracy.

Description

technical field [0001] The invention specifically relates to a personalized recommendation method based on user interests. Background technique [0002] With the development of economy and technology and the improvement of people's living standards, consumers' pursuit of a higher quality of life is becoming more and more obvious. [0003] As a big catering country in China, the types and styles of dishes continue to increase and enrich with the development of the economy, and there are more and more restaurants, restaurants and other catering service places. Online catering service platforms have also sprung up like mushrooms after rain. However, with the emergence of various catering service platforms, more and more users spend more time and energy on the selection of dishes when dining. [0004] Recommendation systems are widely used in the field of e-commerce, and there are also recommendation systems for food and restaurants, but there is no recommendation system for d...

AI Technical Summary

Problems solved by technology

[0005] However, the collaborative filtering recommendation algorithm has problems such as cold start, data sparseness, and system scalability: the problems in the traditional collaborative filtering algorithm are particularly prominent when recommending dishes, and new users often need recommendations when dining, but new users have not yet been generated. Dining records; the number of dishes ordered by users is relatively small, resulting in a sparse matrix of user dishes; the number of users and dishes in restaurants will gradually increase over time, the amount of data in the recommendation system will increase sharply, and the coping ability of traditional algorithms will also increase accordingly. decline

In addition, even though traditional algorithms can handle massive amounts of data, since the "nearest neighbor search" process in user-based collaborative filtering increases linearly with the increase in the number of users, how to provide recommendations for tens of millions of users in real time? , and being able to cope with the registration of new users and the addition of new products is a serious problem that most recommendation systems are facing now; finally, most of the collaborative filtering recommendation systems now require users to display input rating information to provide services, although in The active participation of users in obtaining information can improve the accuracy of information, but it also brings inconvenience to users in using the system

Images