Information recommendation method and system

Abstract

The invention discloses an information recommendation method and a system. The information recommendation method comprises the following steps of: inquiring user behavior data in a preset time period; obtaining the user sub type interesting degree and / or user keyword interesting degree according to the inquired user behavior data, and using the obtained sub type interesting degree and / or the user keyword interesting degree for forming a user interesting degree vector; using a vector included angle formula for calculating the similarity of the current user interesting vector and other user interesting degree vector; and selecting at least one user with the highest similarity to the current user interesting degree according to the similarity calculation results, and recommending information to the current users according to the selected user mark information. Through the scheme, more accurate and effective information recommendation can be realized, so the use feeling of the users is improved, the unnecessary information interaction among the users can be reduced, the load of a system server is reduced, and the network bandwidth resource occupation is saved.

Description

technical field [0001] The present application relates to the field of Internet application technology, in particular to an information recommendation method and system. Background technique [0002] With the continuous development of the Internet, it has become a popular trend to meet netizens through websites or instant messaging. At present, many websites or instant messaging tools have the function of recommending friend information. Through friend information recommendation, user groups can be expanded, communication and interaction among netizens can be enhanced, and the stickiness of websites or instant messaging tools to users can also be enhanced. [0003] A commonly used way of recommending friend information in the prior art is to recommend according to the existing friend relationship. For example, currently, user A has a friend relationship with user B, and user B has a friend relationship with user C, then the system will According to the above-mentioned exist...

AI Technical Summary

Problems solved by technology

The realization of this method depends on the completeness and accuracy of user attribute information. However, in practical applications, many users often do not pay attention to filling in this part of information when registering, making this solution difficult to implement.

[0005] To sum up, the existing recommendation schemes cannot achieve accurate and effective friend information recommendation, and once inappropriate friend information is recommended to users, it is likely to reduce the user experience

From a system point of view, inappropriate friend information recommendation will inevitably increase unnecessary information interaction between users, resulting in an additional invalid burden on the website server or instant messaging server, as well as additional waste of network bandwidth resources

Images