Extract Patent Information from PDFs to Google Sheets Using Pabbly Connect

Learn how to extract patent information like numbers and expiry dates from PDFs to Google Sheets using Pabbly Connect in this detailed tutorial. Follow this definitive guide to creating powerful automated workflows with straightforward, efficiency-focused solutions that save valuable time.

Watch Step By Step Video Tutorial Below

1. Accessing Pabbly Connect for Patent Information Extraction

To begin extracting patent information using Pabbly Connect, first, navigate to the Pabbly Connect website. You need to sign in to your account or create a new one if you’re a first-time user. Pabbly Connect offers 100 free tasks every month, which is great for testing the integration.

Once logged in, you will see the Pabbly Connect dashboard. Click on the ‘Create Workflow’ button located in the top right corner. This action will allow you to set up a new workflow specifically for extracting patent data from PDFs to Google Sheets.

2. Creating a Workflow in Pabbly Connect

After you click on ‘Create Workflow’, a dialog box will prompt you to name your workflow. Name it ‘Extract Patent Information with AI Agent from PDFs to Google Sheets’ and select a folder to store this workflow. For this example, select the folder named ‘AI Agent Automations’. using Pabbly Connect

With the workflow created, you will see two main sections: the trigger and action windows. The trigger window is where you set the event that will start the workflow, while the action window defines what happens next. In this case, the trigger will be a new file uploaded to a specific folder in Google Drive.

• Select Google Drive as the trigger application.
• Choose the event as ‘New File in Specific Folder’.
• Connect your Google Drive account to Pabbly Connect.

After setting up the trigger, you will be ready to capture the uploaded patent document details automatically.

3. Uploading PDFs to Google Drive

Next, you will upload your PDF documents containing patent details to the designated folder in Google Drive. This is critical because the trigger in Pabbly Connect will monitor this folder for new files. Once a new file is detected, it will initiate the extraction process.

To upload a file, simply go to your Google Drive, select the appropriate folder, and upload the PDF. Ensure that the folder’s sharing settings allow access to the AI agent, as it needs to read the documents for data extraction.

• Click on the folder name, then select ‘Share’ to adjust permissions.
• Change the sharing settings to ‘Anyone with the link’ for accessibility.

Once your document is uploaded and the sharing settings are configured, Pabbly Connect will capture the file details and prepare for the extraction process.

4. Extracting Patent Data Using Pabbly Connect

With the PDF uploaded, the next step is to set up the action in Pabbly Connect. You will select OpenAI as your action application to extract content from the PDF. Choose the action event as ‘Extract Content from PDF Image’.

Connect your OpenAI account by providing the required API token. After setting up the connection, map the PDF URL from the previous step into the action field. This allows OpenAI to access the document for data extraction.

Select the appropriate AI model (e.g., GPT-4 Mini). Enter a prompt for the AI to extract the required patent details. Use structured output in JSON format to organize the extracted data.

After configuring these settings, run a test to ensure that the AI agent successfully extracts the patent information from the uploaded PDF.

5. Saving Extracted Data to Google Sheets

The final step involves storing the extracted patent data into Google Sheets. In this action step, select Google Sheets as the application and choose the action event ‘Add Row’ to create a new entry for each extracted patent.

Connect your Google Sheets account in Pabbly Connect and specify the spreadsheet and sheet where you want to save the data. Map the fields from the previous extraction step to the corresponding columns in your Google Sheet.

Map the inventor’s name, patent number, status, and expiry date fields. Ensure all required fields in your Google Sheet are filled correctly.

After completing this setup, run another test to confirm that the extracted data is accurately recorded in your Google Sheets. This automation streamlines your workflow and ensures all patent information is organized and easily accessible.

Conclusion

By following these steps, you can effectively extract patent information from PDFs to Google Sheets using Pabbly Connect. This integration not only saves time but also enhances data accuracy and accessibility for your legal tech firm.