In today’s fast-evolving multimedia information era, video data has become an essential information carrier, and its collection and processing are receiving increasing attention. Supametas.AI provides users with an easy-to-use local video import feature, making the processing of large-scale video data simple and efficient. This article will walk you through how to import local video data into the Supametas.AI platform, detailing the key steps involved.
1. Create a New Task
In the dataset detail page, select the "Local Video Import" option from the "Import Data Source" menu and click the "New Task" button to start creating a video import task.
- Task Naming:
- Enter a task name of up to 20 characters to make it easy to identify and manage in the task list.
2. Upload Local Video Files
After creating the task, proceed to the video file upload stage:
- Upload Methods:
- You can drag and drop the local video files into the upload area or click the upload button to select files.
- Supported File Formats:
- The platform supports common video formats such as
.mov,.mp4,.mpv, etc.
- The platform supports common video formats such as
- File Limits:
- A maximum of 50 video files can be uploaded per task;
- Each file size must not exceed 200MB.
- Tip:
- Ensure that the videos uploaded within the same task have similar content to improve the accuracy of parameter retrieval and output processing.
3. Task Settings
The task settings stage is similar to other data import tasks, with the goal of ensuring the system can correctly parse and process the uploaded video files:
- Select the appropriate parsing method based on the video file type to ensure the system can accurately extract key information from the video.
4. Retrieve Parameters
In the parameter retrieval step, you need to configure how the system will extract relevant data from the video content:
- Default Fields:
- Timeline: The system will attempt to automatically extract timeline information from the video content.
- Text Details: The system will use speech recognition technology to extract dialogue or descriptive text from the video.
- Text Language: The system will detect and record the language used in the video.
- Custom Fields:
- If you need to capture specific data (e.g., nicknames in the video), you can enable custom fields and provide the corresponding field names and detailed descriptions (it is recommended to use English for better accuracy).
5. Output Settings
After completing the parameter retrieval, you need to configure the output settings to decide how the extracted data will be saved and exported:
- Output Format Selection:
- JSON Format: Suitable for subsequent processing via API program calls.
- Markdown Format: More beneficial for building knowledge bases and document presentation.
6. Save or Execute the Task Immediately
Finally, based on your needs, you can choose how to execute the task:
- Save and Execute Later:
- Save the task configuration to the task list for manual execution later.
- Execute Task Immediately:
- If the configuration is correct and ready, click the "Execute Task Now" button, and the system will start processing the uploaded video files and import the extracted data into the specified dataset.
The local video import feature is not only intuitive and easy to follow but also provides flexible task settings and data output options, helping you efficiently manage and process video data. Whether for bulk processing of promotional videos or extracting text information from videos, it offers reliable support and a convenient user experience.
