Generation method of video indexing data and system

Abstract

The invention discloses a generation method of video indexing data and a device. The generation method of the video indexing data comprises the following steps: obtaining video content and text content which is relevant to the video content, classifying the text content, selecting a proper pinyin language model and a proper word language model according to a classification result, segmenting voice data of the video content and classifying speakers, selecting a proper acoustic model according to a speaker classification result, generating a pinyin gridding according to the selected acoustic model and the selected word language model and a first pronunciation dictionary according to the text content, obtaining a word gridding according to the pinyin gridding, the word language mode corresponding to the text content, and a second pronunciation dictionary, recalculating a confidence coefficient of the word gridding to obtain a new work gridding according to the pinyin gridding and the word gridding, and finally combining the new gridding with original video content to obtain the video indexing data. According to the video indexing data, a user can conveniently and accurately retrieve the relevant video content through text keywords.

Description

【Technical field】 [0001] The invention relates to the field of search technology, in particular to a method and system for generating video index data. 【Background technique】 [0002] With the development of network technology, the search function has become an indispensable tool for users. Text-based search engines have become very common. Before searching, it is necessary to establish index data for the search target content, which is used to match the text entered by the user to realize the search function. [0003] Video retrieval technology has also been applied in many search engines. The search engines of Baidu and Google basically search according to the name and label of the video file, and retrieve the corresponding text content of the web page where each audio file is located. However, the video and the audio content (Content) in the video are not formally processed, and these contents are used for effective retrieval. [0004] In fact, for many videos, we are...

AI Technical Summary

Problems solved by technology

[0004] In fact, for many videos, we are interested in some specific content, such as a news video (30 minutes of news broadcast), its corresponding file name and the content of the web page (such as news titles, and important news content) It is only a small part of the content of the news video, and if the content to be searched (such as "China Merchants Bank", which is a specific name mentioned in a certain financial news) does not appear in the content of the webpage, but appears in the video or audio, then it will be impossible to find

Images