Video keyword processing method and device

Abstract

The invention discloses a video keyword processing method and device, and the method comprises the steps: carrying out the conversion processing of a video, and obtaining at least one video frame image; performing character recognition processing on the subtitle area of the at least one video frame image to obtain a subtitle text contained in the at least one video frame image; performing word segmentation processing on the subtitle text to obtain at least one text entry; determining a sorting weight of the at least one text entry according to the position attribute information and the word frequency information of the at least one text entry; and according to the sorting weight of the at least one text entry, screening out at least one target entry from the at least one text entry, and storing the at least one target entry in a database as a keyword of a video. Through the mode, the keyword of the video is extracted from the subtitles of the video, the accuracy of the keyword of the video is improved, the keyword of the video is enriched, a user can search the video through the more accurate keyword, and the video search accuracy is improved.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a video keyword processing method and device. Background technique [0002] Nowadays, the development of the Internet industry is in full swing, and various Internet products have penetrated into various fields of contemporary social and economic life, providing great convenience for people's daily work, study and life. With the rapid development of the Internet, the content of the network is extremely rich, and various video collection platforms have been born. The video platform combines a large number of video resources, but it makes it difficult for people to search for the target video when using it. In the prior art, videos are retrieved through simple methods such as video titles and video classifications, and users mainly classify desired target videos through title keywords and video classifications. [0003] However, the inventor found that the prior art has at least...

AI Technical Summary

Problems solved by technology

[0003] However, the inventor found that the prior art has at least the following deficiencies in the process of realizing the present invention: However, in the face of massive videos, especially many similar videos, video titles and video classifications often cannot accurately express the key information of the videos, It is difficult to allow users to conduct more accurate searches through video titles and video classifications. For example, training videos developed by JAVA, due to different training institutions and different lecturers, the knowledge points explained are different. Based on existing technologies, through titles, It is difficult to distinguish them by category search, and it is difficult for users to search for titles or categories to find suitable videos

Images