A video index classification method and device

Abstract

The embodiment of the invention discloses a video index grading method and device. The method includes the steps that indexes corresponding to videos, meeting a preset rule, in all videos are added into primary indexes, and indexes corresponding to all the videos are added into secondary indexes; feature data for determining whether the indexes of the videos need to be added into the primary indexes or not is extracted from other videos except for the videos corresponding to the indexes included in the primary indexes; a classification model for determining whether the indexes of the videos need to be added into the primary indexes or not is trained according to the feature data; aiming at each video except for the videos corresponding to the indexes included in the primary indexes, whether the indexes of the videos need to be added into the primary indexes or not is determined according to the trained classification model, and the determined indexes are added into the primary indexes. By means of the method and device, the number of online servers is reduced.

Description

technical field [0001] The present invention relates to the technical field of video processing, in particular to a video index classification method and device. Background technique [0002] With the increasing demands of users, video search engines need to provide high-frequency and high-concurrency online services, that is, to allow different users to search for satisfactory videos within a very low response time. The video search engine searches in the index according to the user's video search request. [0003] With the increase in the number of users and visits, the video search engine QPS (Query Per Second, query rate per second) load increases, that is, more requests must be processed simultaneously per second. The generation of video results in a huge number of search engine indexes. In order to ensure the recall rate of video search, all videos need to be indexed, and the server memory space required to accommodate a set of indexes will become larger and larger. ...

AI Technical Summary

Problems solved by technology

[0003] With the increase in the number of users and visits, the video search engine QPS (Query Per Second, query rate per second) load increases, that is, more requests must be processed simultaneously per second. The generation of video results in a huge number of search engine indexes. In order to ensure the recall rate of video search, all videos need to be indexed, and the memory space of the server required to accommodate a set of indexes will become larger and larger.

However, due to the limitations of the server bandwidth, the QPS load that a single server can bear is limited, and the memory space of the server is also limited. In order to meet the continuous growth of QPS load and index volume, the existing method is to increase the number of servers, but This approach results in a huge number of online servers

Images