# Intelligent Document Processing

After a document is uploaded to ProcessMaker IDP, it undergoes the following steps for analysis and data extraction:

1. **Metadata Extraction:** Metadata such as the author, creation date, and media type is extracted from the document. This metadata helps in organizing and managing the documents efficiently.
2. **OCR Processing:** The OCR service processes every uploaded document to extract text from it. This step involves recognizing and digitizing text from images or scanned documents.
3. **Classification:** The classification service analyzes the document and classifies it into one or more predefined document types based on the model being used.
4. **Model Analysis:** The document is processed using a trained model to generate a Model Result. This result provides further insights and structured data extracted from the document.
   * **Object Detection:** The Model also identifies Objects in the document.
   * **NER (Named Entity Recognition):** Static models are to used to identify information (address, organization, etc.) in the document. Anonymization also occurs at this step.
   * **AI Model Gateway:** If configured, custom AI Models can also be used for processing documents.
5. **Store Metadata:** The extracted metadata is then stored in the database for further processing and easy retrieval.

Watch the following product tour to get a quick overview of how IDP processes documents. 

{% embed url="<https://demos.processmaker.com/demo/clydew6oh0pkrthf7zx87e0fn>" %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://processmaker.gitbook.io/idp/idp-user/intelligent-document-processing.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.