Use Tegaki API OCR engine

Use the Tegaki API OCR engine with IQ Bot to improve the accuracy of the optical character recognition (OCR) results that is used for training documents in Japanese and Korean languages. You can configure it for use with Automation 360 IQ Bot On-Premises.

Prerequisites

Important: From Automation 360 v .30, we have deprecated the use of Tegaki API OCR engine for data extraction in Automation 360 IQ Bot. We recommend using the Google Vision API OCR engine instead. For details, see Feature deprecations affecting Automation Anywhere products.
Review the following prerequisites for setting up Tegaki API OCR engine:
  • Only Automation 360 IQ Bot On-Premises supports Tegaki API OCR.
  • You must have a dedicated server that meets the requirements set by Cogent Labs. For more information, contact your Customer Success Manager.
  • IQ Bot provides Tegaki API as a built-in plug-in. Set Tegaki API as your default OCR engine in the settings.txt file available in the following folder:

    C:\Program Files (x86)\Automation 360 IQ Bot <version>\Configurations

  • Set the communication for the API endpoint on default port = 443, using TCP protocol.
Important: Not available in Automation 360 IQ Bot Cloud.
Tegaki API OCR supports documents in the following languages:
  • Japanese
  • Korean
  • Japanese- English
  • Korean- English

Procedure

  1. Run the IQ Bot installer.
  2. Configure the Tegaki API OCR engine for the On-Premises version on your machine based on instructions received from your Automation Anywhere representative.
  3. Input your license key in the Tegaki OCR settings.json file.
    As IQ Bot does not provide you with the license to use the Tegaki API OCR engine, you must use your own license key. Follow the steps to install your own license key:
    1. Navigate to the following location:

      C:\Program Files (x86)\Automation 360 IQ Bot\Configurations

    2. Set up the Tegaki API endpoint where you have installed the On-Premises version. Set APIKey = <your key here> and configure the TegakiOCREngineSettings.json file.
      {
  "APIKey": "<ensure your key meets UUID format (https://www.uuidgenerator.net)>”,
  "RestEndpointURL": "<your Tegaki Server URL here>”,
  "RestEndpointPort": <80>,
  "EngineType": 3,
  "EnableFieldMerging": false,
  "EnableFieldRegions": false,
  "DebuggingFolder": "C:\\Users\\Public\\Documents\\Automation Anywhere IQBot Platform\\Logs\\Engine\\Tegaki"
}

      See How to change OCR Settings in IQ Bot (A-People login required).

  4. Navigate to ..\Automation 360 IQ Bot\Configurations\Settings.txt, and modify the following value: OCREngine=TegakiAPI.
    The TegakiOCREngineSettings.json file is available after IQ Bot installation.

Next steps

  1. Create a new learning instance with the Asian language document you want to train.
  2. Train the document and set your learning instance to production.
  3. Upload Asian language files and run the bot.
  4. Download and view the accuracy of the extraction results.