How to extract text from materials in JPG or PDF format using AI and send the content via email

STEP2 Set a Trigger to Activate When a Specific Email is Received

1. Select "When you receive the email".

‍

‍

2. Set the address for receiving. Forward incoming emails to the address entered here to activate the email trigger.
   Next, set the search criteria. This time, we set the condition to include the word "photo" in the subject, but you can also set the condition to the body or sender.
   After entering, select "Next".

‍

‍

3. Send an email that matches the conditions set to the email address entered earlier.
   (Please also attach files such as PDFs. This time, a business card PDF file was attached.)
   After sending, select "Test".
   * It may take some time for the email to be received after sending. If the test fails, please check the conditions again.
   If the test is successful, select "Save".

‍

STEP3 Set an Action to Read Text from Images and PDFs

1. Select the operation "Read text from images and PDFs".

‍

‍

2. Select any read action and click "Next".

‍

‍

3. Set the details. For the attachment method, select "Use obtained value" and "Attachment 1" to use the email attachment sent in STEP2.
   Enter the items from which you want to extract text data. (Since business card data was attached in STEP2, "Name", "Company Name", and "Email Address" were set.) After entering
  After entering, select "Test".

‍

‍

  If the test is successful, the read content will be displayed in the output.
  Check if it was read accurately and select "Save".

For operations to read text information from images and PDFs, please also check this page.

STEP4 Set an Action to Send the Read Text via Gmail

1.  Select the operation. To send an email to Gmail, select "Send Email".

‍

‍

2. Set up the email. Select "Account information to link with Gmail".

‍

‍

3. Set the content of the email. Enter the recipient's email address in "To". (Cc and Bcc can also be set.)
   Enter the "Subject". Set the output extracted in STEP3 in the "Body".

‍

After entering, select "Next".

4. Test the email sending. Select "Test". If the test is successful, select "Save".

‍

‍

5. Finally, turn the trigger "ON" to complete.

‍

‍

Other Automation Examples with AI-OCR and Gmail

In addition to the flow introduced this time, by using AI-OCR and Gmail's API, you can automate various tasks.
All of them can be used with simple settings, so if there's anything you're interested in, please give it a try!

This is a flow bot that reads Gmail attachments with OCR and adds them to a database tool.
It automatically registers information, potentially eliminating the hassle of switching between tools.

This is a flow bot that reads document data posted on Gmail using OCR, updates the file name, and stores it in a storage service.
It may help reduce the tasks of checking document data and storing files.

This is a flow bot that reads business card images received in Gmail using OCR, adds the data to an information management tool, and sends a thank-you email using an email tool.
The automation flow is expected to speed up follow-ups.

This is a flow bot that reads contracts received in Gmail using OCR, adds them to kintone, and notifies you via a chat tool.
You will be able to confirm the receipt of contracts and the registration of data from the messages.

Other automation examples using Gmail

An example of automation in conjunction with Yoom's schedule trigger

It will start at a set date and time, and automatically send emails to specific addresses to inform team goals and provide reminders.

Get customer information at the specified date and time and send a standard message via Gmail

Gmail standard messages are automatically sent on the specified schedule, eliminating the need to manually get information or create and send emails, and preventing emails from being sent to the wrong address or forgotten.

Upload attachments received via Gmail

It will automatically upload to a specified folder, which is useful for sharing files received via email.

Benefits of Automating Image Data and PDFs with OCR

What are the benefits of automating image data and PDF files with OCR?

1. Digitization of Documents‍

By converting data saved as images or PDFs into text data, such data can also be digitized as document data. As a result, document management may become significantly more efficient.

2. Easy Information Retrieval‍

Since the data is converted into text data with OCR, keyword searching and filtering become easier, and it is expected that search efficiency will greatly improve.

3. Streamlining Data Entry‍

By automatically converting paper documents into digital data, the need for manual data entry is eliminated, potentially reducing the burden of input tasks. Additionally, using OCR allows for the digitization of large volumes of documents in a short time, significantly reducing the time and effort required for data entry.

4. Integration with Other Systems‍

Digitizing documents enables workflow automation and integration with existing systems, allowing data to be utilized in other systems.

Conclusion

What do you think? The automation of image data and PDF files with OCR can lead to various efficiencies and accuracy improvements in operations. The digitization of documents plays an important role in business scenes, including from the perspective of the Electronic Book Storage Act.

The applications are limitless, including the application flows introduced earlier!