Information recommendation method and device and server

Abstract

The embodiment of the invention discloses an information recommendation method and device and a server. The method comprises the steps: analyzing retrieval information input by a user, obtaining target reference information matched with the retrieval information, and enabling the similarity between the retrieval information and the target reference information to be greater than a preset similarity threshold; Obtaining historical calling times of the target reference information, wherein the historical calling times are times of matching the target reference information with retrieval information input by at least one user within a first preset time period; Determining recommendation information according to the historical calling times; And sending the recommendation information to the client. By implementing the method, the content which the user may be interested in can be analyzed by combining the historical statistical data, so that more accurate portraying is performed on the user, and the accuracy of the recommendation result is improved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to an information recommendation method, device and server. Background technique [0002] Intelligent question and answer is to organize the accumulated unordered corpus questions in an orderly and scientific manner, and establish knowledge-based classification models; these classification models can guide newly added corpus consultation and service questions, save human resources, and improve the automaticity of problem processing. and reduce website operating costs. [0003] Relevant question recommendation is one of the core functions of the intelligent question answering system. When a user asks a question to the intelligent question answering system, the system not only pushes the answer to the question, but also pushes out the knowledge related to the question for the user to query. When you ask a question, you can fully grasp all the problems. A commonly used rela...

AI Technical Summary

Problems solved by technology

However, for new knowledge bases or new users, this method cannot make accurate portraits of users, which leads to users not being interested in the recommended related issues, and the purpose of the recommendation function is not achieved.

Images