Method and device for pushing online playing entry objects based on video retrieval

Abstract

The invention discloses a method and device for pushing online playing entry objects based on video retrieval. The method includes the steps that video retrieval character strings are received; the video retrieval character strings are mapped to one or more first word segments; relevant second word segments are looked up, wherein the co-occurrence rate of the second word segments and the first word segments is higher than a preset threshold value; the co-occurrence rate is the probability that the current one or more first word segments and the second word segments co-occur in same video resource data; network addresses of one or more video data resources matched with the one or more first word segments and the relevant second word segments are acquired; the entry objects for online playing the video data resources are constructed according to the network addresses of the one or more video data resources; the entry objects for online playing the one or more video data resources are pushed. According to the method and device, good resources in a video database are deeply excavated, efficiency for excavating the resources is improved, and the recall rate is beneficially increased.

Description

technical field [0001] The present invention relates to the technical field of the Internet, in particular to a video search-based online play entry object pushing method and a video search-based online play entry object push device. Background technique [0002] Video search engine is a vertical search technology different from comprehensive search. A video search engine crawls and indexes video results on the Internet, and since it can provide pure video results to searchers, it can greatly save Internet users' time in searching for videos. [0003] According to the relevant statistical data of video search, entertainment, games, film and television, news, animation and other types of videos are the main search objects of users. This shows that users have a general demand for video search itself. Users often do not have a strong purpose, and the search results are not "necessary", but have a certain degree of scalability, as long as the target is within the user's favori...

AI Technical Summary

Problems solved by technology

[0004] However, the existing video search engines are not enough in terms of relevant recommendations: some video search engines do not have relevant recommendations, and video search engines with relevant recommendations are only based on the user's search history data, through manual sorting to obtain the correlation system and other simple methods achieve recommendation

For example, when you search for "square dance" on a certain search engine, you will get recommended words such as "ballroom dance", "belly dance", and "aerobics", and when you search for "dota", you will get "Cross Fire", "World of Warcraft", etc. recommended words, but the recall rate of this system is low, and it is generally impossible to give recommendations in long-tail searches

Images