A data source matching method and device

Abstract

The embodiments of the present invention disclose a data source matching method and device, which are used to improve the efficiency and accuracy of video data source fusion, and can be completed automatically without manual participation. In this method, the meta information of the first item is obtained from the first data source, and the meta information of the second item is obtained from the second data source, and the meta information includes: a plurality of data attributes of the corresponding items; The matching decision model finds the base entry in the base entry repository that matches the meta information of the first entry, and the entry matching decision model finds the base entry in the base entry repository that matches the meta information of the second entry. The entry matching decision model uses The sample data of the historical data source is obtained by training and testing the decision tree model; when the first item and the second item match the same basic item from the base item repository, the first data source and the second data source are associated. to the same base entry in the base entry repository.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a data source matching method and device. Background technique [0002] In order to facilitate users to choose a video data source that can meet user needs, it is necessary to be able to aggregate video links from multiple video data sources. At this time, a fusion method of video data sources is produced. [0003] In the prior art, currently commonly used video data source fusion methods mainly include the following two types: 1), the mode of manual addition, that is, manually judge by a large number of editors, and then link multiple videos according to the manual judgment results Aggregation; 2) Aggregating multiple video links with the same title through keyword matching, for example, matching title content. [0004] For the video data source fusion method of the above-mentioned prior art, these two methods have their own defects: [0005] 1) For the method of manual addi...

AI Technical Summary

Problems solved by technology

[0005] 1) For the method of manual addition, this requires a large amount of manual input from editors and continuous operation. At present, major video websites have editorial teams of nearly 100 people to aggregate video data sources. This method is not only time-consuming and labor-intensive , and each editor has inconsistent understanding of video content, so the efficiency and accuracy of video data source fusion cannot be guaranteed;

[0006] 2) For the method of keyword matching, this method can only solve the situation where the naming methods of the title content are very standardized, so the matching success rate is low

Images