Support analyisis of video media content

### Background on the problem the feature will solve/improved user experience
The TakeTwo web application currently supports only text. However, there is a lot of content in video that could be potentially racially biased.

### Describe the solution you'd like
Support video content as another input.

### Tasks
Description of the development tasks needed to complete this issue, including tests,
- Plan how video content training will happen
- create models cased on video
-
### Acceptance Criteria
Standards we believe this issue must reach to be considered complete and ready for a pull request. E.g precisely all the user should be able to do with this update, performance requirements, security requirements, etc as appropriate.

未指定任何文件、测试或入口点。首先梳理当前 Web 应用如何接收和分析文本，然后明确视频输入、训练和模型的范围；完成的要求包括为受支持的视频分析制定明确的验收标准并提供测试。

由索引模型根据 Issue 内容生成。