Individualized recommendation method and device

Abstract

The invention provides a method and a device for carrying out individualized recommendation in terminal equipment. The method comprises the following steps: obtaining related information of any user; recommending a territory entity related to an ordered recommendation topic and recommendation evidences of the territory entity to the user; receiving interactive feedback operation of the user aiming at the recommendation evidences in a recommendation result; and based on the received interactive feedback operation, updating the territory entity related to the ordered recommendation topic and the recommendation evidences of the territory entity, which are recommended to the user. With the adoption of the method and the device provided by the invention, not only can an individualized recommendation result and the corresponding recommendation evidences be automatically obtained, but also the present demands of the user can be obtained through an interactive feedback mechanism with the user, so that the recommendation result can be adjusted correspondingly aiming at the present demands of the user, the recommendation result further fits with the demands of the user and the user experience is enhanced.

Description

technical field [0001] The present application relates to a personalized recommendation method and device, in particular to a technology capable of adjusting recommendation results in real time according to the current needs of users. Background technique [0002] With the rapid development of the Internet, major websites have launched personalized life recommendation services one after another. Although these personalized recommendation services can also recommend to users information that is most likely to meet their interests (such as: positions, travel locations, etc.), however, these recommended data are often very sparse and single, and can only describe and understand a user from a small number of dimensions, and it is difficult to fully judge the user's attributes, consumption level and hobbies etc., so the recommended results are not sufficient or even accurate enough; in addition, since the user's needs are changing in real time, these personalized services can onl...

AI Technical Summary

Problems solved by technology

[0002] With the rapid development of the Internet, major websites have launched personalized life recommendation services one after another. Although these personalized recommendation services can also recommend to users information that is most likely to meet their interests (such as: positions, travel locations, etc.), however, these recommended data are often very sparse and single, and can only describe and understand a user from a small number of dimensions, and it is difficult to fully judge the user's attributes, consumption level and hobbies etc., so the recommended results are not sufficient or even accurate enough; in addition, since the user's needs are changing in real time, these personalized services can only predict the user's interest and status based on the user's historical behavior, and cannot The recommendation strategy is adjusted according to the current needs of the user, so the recommended results cannot accurately reflect the current needs of the user

Images