Video Quality Score

Prerequisites

• To use the workflow feature, you must first purchase the unstructured data feature on the current instance.

• An existing workflow is required. For more information, see Create a workflow.

Permissions

Project administrators, developers, and analysts of a Basic project, as well as custom project roles with the Dataset - Use permission, can use any dataset in the project for the operator's input and output.

Supported file formats

The Video Quality Score operator supports the following file formats: mp4, avi, mkv, mov, webm, flv, ts, wmv, 3gp, and mpeg.

Procedure

1. In the top navigation bar of the Dataphin home page, choose Develop > Data Development.

2. On the Develop page, select a project from the top menu bar.

3. In the left-side navigation pane, choose Data Processing > Workflow. In the Workflow list, click the target workflow to open its canvas. From the Operator Library on the left, drag the Video Quality Score operator to the canvas. In the Video Quality Score panel that appears on the right, configure the following parameters.

   Parameter		Description
   Step name		Enter a name for the operator. The name can contain any characters and be up to 256 characters long.
   Input configuration	Dataset	The dataset to process. You can select only a hybrid dataset. After you select a dataset, you must also select its Version. The first version in ascending order is selected by default. If this operator is downstream of another, this is typically the output dataset of the upstream operator.
   	Input field	The field from the input dataset that contains the storage URL of the video file. You can select only fields for which the Is URL parameter is set to Yes.
   	Filter condition (Optional)	Specify the filter condition by using SQL syntax. You need to enter only the clause that follows the WHERE keyword. You can use system-level global variables, such as ${bizdate}.
   Operator configuration	Processing model	You can select a Built-in model (CLIP-IQA) or a multimodal large model. If you select a multimodal large model, you must also specify the Model to use. You can select only models of the Vision (Images and Videos) type with an Enabled status on the Intelligent Application Management > Model Configuration page.
   Output configuration	Dataset	You can select the source dataset or other datasets. If the source dataset's metadata table lacks a primary key, the output dataset setting defaults to other datasets. If you select to use other datasets, you must also specify a hybrid dataset or a table dataset and its Version as the output dataset. By default, the first version of the dataset in ascending order is selected. You can also select a different version of the source dataset. If you select the source dataset, the operator writes the generated metadata to the metadata table of the same version.
   	Loading strategy	If a primary key exists in the metadata table of the selected output dataset, update on primary key conflict is selected by default. Otherwise, append data is selected by default. Append Data: Appends new data to the target table. An error is reported if a primary key or constraint conflict occurs. Update on Primary Key Conflict: If a primary key or constraint conflict occurs, the system deletes the conflicting row before inserting the new data. Overwrite: Deletes all existing data from the target table before writing the new data. Note If you select the source dataset as the output dataset, only the Update on Primary Key Conflict loading strategy is supported.
   	Field mapping	The Video Quality Score operator generates one fixed output field: visual_quality_score: The video quality score. The score ranges from 0 to 1. A higher score indicates better quality. By default, the operator's output fields are mapped to fields with the same names in the output dataset. You can also manually select target fields for custom mapping. In addition, you can map passthrough fields from the source dataset to the target dataset. You can manage field mappings in the following ways: Add output field: Adds a blank field mapping row. This feature is available only when you select other datasets as the output dataset. Batch mapping: Provides options for batch mapping: manual, by name, or same-row. This feature is available only when you select other datasets as the output dataset. Delete mapping: Click the Delete icon to delete the field mapping for the corresponding row. However, mappings for the fixed output fields of an operator cannot be deleted.

4. After you configure the parameters, click Save in the top navigation bar of the canvas.

   After configuring an operator, you can continue building the workflow by adding upstream or downstream operators.