Video information processing method and device, electronic equipment and storage medium

Abstract

The invention provides a video information processing method which comprises the following steps: acquiring a target video, and processing the target video to form a multi-level video label matched with the target video; determining a corresponding text generation framework in response to the target video and a multi-level video label matched with the target video; and generating text descriptioninformation matched with the target video through the text generation framework. The invention further provides a video information processing device, electronic equipment and a storage medium. According to the invention, the content of the target video can be described through the natural language, so that non-technicians can timely and accurately convert the video information content into the text of the corresponding natural language to be output, and a high-quality training sample does not need to be configured for a neural network model in the traditional technology; and therefore, the sharing speed of the video information content is effectively improved.

Description

technical field [0001] The present invention relates to information processing technology, in particular to a video information processing method, device, electronic equipment and storage medium. Background technique [0002] Under traditional technical conditions, the demand for multimedia information has shown explosive growth, and traditional information processing technology has been unable to meet the needs of multimedia data in labeling, description and other tasks. In related technologies, before a video is shown to users, it is usually necessary to create a description text of the video in advance to describe the events in the video in general and add it to the video. The added titles (for example, avatars continuously killing hostile avatars) help users to understand the video content in a timely and accurate manner, but related technologies generate video text description information through artificial intelligence neural network models. High-quality training samp...

AI Technical Summary

Problems solved by technology

[0002] Under traditional technical conditions, the demand for multimedia information has shown explosive growth, and traditional information processing technology has been unable to meet the needs of multimedia data in labeling, description and other tasks

In related technologies, before a video is shown to users, it is usually necessary to create a description text of the video in advance to describe the events in the video in general and add it to the video. The added titles (for example, avatars continuously killing hostile avatars) help users to understand the video content in a timely and accurate manner, but related technologies generate video text description information through artificial intelligence neural network models. High-quality training samples also require specialized technicians to supervise the learning and deployment of the neural network model, which is not conducive to the use of ordinary users. At the same time, the description of text information generated by the neural network model is relatively blunt, which is not conducive to the user experience , affecting the sharing speed of video content

Images