DQ

Content Review Console

PDF、图片、音频与视频质量及合规审核

OCR Extract
Java V2
Python V1
Multilingual content intelligence

Review every medium.
See the decision clearly.

Upload a PDF, image, audio or video file, choose the Java or Python pipeline, and inspect the result without reading raw JSON.

Files are forwarded in memory and are not stored by this page.
1 · Select media type
2 · Select evaluation service

Enter the service base URL only. The fixed v1/v2 endpoint path is appended automatically.

3 · Upload PDF
Drop a PDF here or click to browse

One file · Up to 100 MB

Advanced request settings
Java · :9324
Evaluating PDFPDF conversion and content analysis are running
0.0s
Evaluation failed

Structured visual extraction

OCR Extract

Test Java V2 category-specific OCR. It extracts only the configured fields and preserves values exactly as printed.

Java V2 · /v2/ocr_extract
Drop an image here or click to browse

JPG, PNG, WEBP, GIF or BMP · Up to 100 MB

Java · /v2/ocr_extract
No extraction yetChoose a document category and upload an image to inspect structured fields.

Extracted fields

Success

Evaluation result

Overall decision

Content abstract

Policy findings

Standard review

Issues

Recommendations

Analysis report

Content profile

Named entities

Audience & child safety

Sentiment

Run history

TimeMediaServiceFileDurationDecisionHTTP