Our new Receipt and Invoice AI is now available in Public Preview!
Note: The Receipt and Invoice AI Extraction ML model is a Cloud Platform offering and is currently not available for on-premise ML model deployments.
This new AI capability gives your UiPath Robots the ability to read both invoices and receipts and will help streamline your automations around accounts payable and expense compliance processes.
All the details you’ll need to get started are below, including an overview of this new activity, how it works, and how to install and use.
How to provide feedback
Have suggestions, questions, or issues? We want to hear it!
- Simply go to the Receipt and Invoice AI category
- And then click New Topic
- Templateless approach to processing invoices and receipts - Our AI can automatically determine the location of critical information that needs to be extracted from the document, even if the format changes. It is no longer necessary to create multiple layouts manually.
- High accuracy for even ‘noisy’ documents - We are continuously improving our AI to handle the complexities found in real world documents that make them hard to read, such as noise or low resolution from printing and scanning.
- Integrated with our IntelligentOCR Solution - Drag-and-drop our new Machine Learning Extractor seamlessly into our existing document processing infrastructure provided by the IntelligentOCR activity package. Same infrastructure, new supercharged brain.
How to Install in Studio
Note that starting Aug. 28th 2019, you need to create an account in cloud.uipath.com and use a License key from the Licenses page for these features to work. The key must be pasted in API-Key property of the activities.
To get started in minutes with almost no configuration, use the Extract Semi-structured document activity available in UiPath Go! This activity integrates well with Taxonomy Manager and Validation Station, but will work without them if you don’t need them.
For advanced or complex scenarios, you may also use UiPath.MachineLearningExtractor activity via the Beta feed. In order to do this, please follow the instructions below.
You must first install the UiPath.IntelligentOCR.Activities activity package:
- Open the ‘Manage Packages’ window
- Click ‘All Packages’ in the left navigation, then search for “UiPath.IntelligentOCR.Activities”
- Select the result, make sure version 2.2 is selected, then click the ‘Install’ button in the right pane
Next, you need to install the UiPath.MachineLearningExtractor activity via the Beta feed:
- If you haven’t already, add the UiPath Beta Feed (See instructions to add feed) to your Manage Packages window
- In the Beta feed, check ‘Include Prerelease’, then search for “ UiPath.MachineLearningExtractor”
- Select the result and click the ‘Install’ button in the right pane
* Important - We must reiterate, make sure you check the ‘Include Prerelease’ checkbox
The Machine Learning Extractor activity should be visible now in UiPath Studio, as shown below:
How to Use
Please watch our demo video here:
Additionally, here are step-by-step instructions to help you get started:
- If you haven’t yet defined a taxonomy for the documents you intend to process, you can do so using the Taxonomy Manager
- Drag in the Load Taxonomy activity and store the taxonomy in a variable
- Drag in the Digitize Document activity
- Drag-and-drop an OCR Engine inside the Digitize Document activity
- Define variables for both outputs: DocumentObjectModel and DocumentText
- Drag in the Data Extraction Scope activity
- Populate input variables DocumentObjectModel, DocumentText, Taxonomy and DocumentTypeId. The DocumentTypeId is a string you can see in TaxonomyManager if you click on the Document Type you need to extract.
- Define variable for output: ExtractionResults
- Drag in Machine Learning Extractor and drop it inside the Data Extraction Scope
- Populate Endpoint input property with the URL of the endpoint you would like to use:
- Click the “Configure Extractors” link within the Data Extraction Scope activity
- Expand the Document Type you are interested in and populate, on the right side column, the names of the fields which correspond to the fields in your taxonomy. See below for the full field names you need to fill in on the right side.
Invoice available field names:
Receipt model available field names:
Invoices model supports English and Spanish languages.
Receipts model supports English and Romanian languages.
Maximum request size: 4MB or 2 document pages. Maximum 10 requests per minute.
Models cannot be customized/optimized/retrained, they are pre-trained.