User behavior-based log filtering method

Abstract

The invention discloses a user behavior-based log filtering method. The method comprises the following steps of 1, dividing a user behavior into multiple sub-behaviors, allocating corresponding weights, obtaining and storing log information of the user behavior through a distributed log collection tool, and extracting and filtering the log information of the corresponding sub-behaviors with the weights lower than a weight threshold; and 2, performing parallel processing on the reserved log information of the sub-behaviors through a utility function, establishing a mapping relationship between user interest degrees and sub-behavior indicators by the utility function, extracting and filtering the corresponding log information of the sub-behaviors with interest degrees lower than an interest degree threshold, reserving the log information of the sub-behaviors preferred by a user, forming an optimized data source of a recommendation result, and storing the optimized data source in a data cluster. According to the method, massive log information can be subjected to secondary filtration, and current demands and interested information of the user can be responded in time, so that the processing efficiency is improved; and the method is easy to expand and has fault tolerance to a certain extent.

Description

technical field [0001] The present invention relates to the field of information technology. More specifically, the present invention relates to a log filtering method based on user behavior. Background technique [0002] With the rapid development of the Internet, users generate massive log information in the process of using the network. When users are faced with massive Internet information, they cannot obtain the information they are interested in, resulting in the problem of information overload. Therefore, various recommendation methods have become research hotspots, enabling user groups to obtain information they are interested in in real time and effectively (such as interesting Weibo recommendations, product recommendations, movie recommendations, etc.). Log filtering is an essential link in recommendation. However, the current log filtering technology has many deficiencies, such as missing data (incomplete data, missing ID, time, product ID, etc.) such as only fo...

AI Technical Summary

Problems solved by technology

Log filtering is an essential link in recommendation. However, the current log filtering technology has many deficiencies, such as missing data (incomplete data, missing ID, time, product ID, etc.) such as only for noise, missing values ​​( For example, the data of the picture lacking light) is filtered

Moreover, different recommendation systems use different filtering methods, which cannot achieve universality.

Images