Como extrair dados de formulários

Importante:

The aim of this page is to help first time users get familiar with Document Understanding^TM.

For scalable production deployments, we strongly recommend using the Document Understanding Process available in UiPath® Studio under the Templates section.

This quickstart guides you through the steps required to extract information from W-9 forms using the Intelligent Form Extractor. The W-9 forms are used as an example, but the procedure is similar for other types of documents where the data is structured.

Começando do zero, estas são as etapas que precisam ser seguidas:

1. Crie um processo em branco
2. Instale os pacotes de atividades exigidos
3. Crie uma taxonomia
4. Digitalize o documento
5. Extraia os dados usando o Intelligent Form Extractor
6. Valide os resultados usando o Validation Station
7. Exportar Resultados da Extração

1. Crie um processo em branco

Execute o UiPath Studio.

In the HOME backstage view, select Process to create a new project.

A janela Novo processo em branco é exibida. Nesta janela, insira um nome para o novo projeto. Se desejar, você também pode adicionar uma descrição para classificar seus projetos com mais facilidade.

Select Create. The new project is opened in Studio.

2. Instale os pacotes de atividades exigidos

From the Manage Packages button in the ribbon, besides the core activities packages (UiPath.Excel.Activities,UiPath.Mail.Activities,UiPath.System.Activities,UiPath.UIAutomation.Activities) that are added to the project by default, install the following activities packages:

• UiPath.IntelligentOCR.Activities
• UiPath.OCR.Activities

3. Crie uma taxonomia

Após os Pacotes estarem instalados, liste os campos necessários. Faremos a extração de dados para os seguintes campos:

• 1_Name - Text
• 2_BusinessName - Text
• 3a_Individual - Boolean
• 3b_CCorp - Boolean
• 3c_SCorp - Boolean
• 3d_Partnership - Boolean
• 3e_TrustEstate - Boolean
• 3f_LLC - Boolean
• 3f_LLCTaxClassification - Boolean
• 3g_Other - Boolean
• 3g_OtherDetail - Boolean
• 5_Address - Text
• 6_CityStateZip - Text
• 7_AcctNumber - Text
• TIN_SSN - Text
• TIN_ETN - Text
• Certification_Signature - Boolean
• Certification_SignatureDate - Date

Open Taxonomy Manager and create a group named Structured Documents, a category named Lending Forms, and a document type named W-9. Createlisted fields with user friendly names along with respective data types.

4. Digitalize o documento

In the Main.xaml file, add a Load Taxonomy activity and create a variable for the taxonomy output.

Add a Digitize Document activity with UiPath Document OCR. Provide the input property Document Path and create output variables for Document Text and Document Object Model.

Lembre-se de adicionar a Chave de API do Document Understanding na atividade UiPath Document OCR.

5. Extraia os dados usando o Intelligent Form Extractor

Add a Data Extraction Scope activity and fill in the properties.

Drag and drop the Intelligent Form Extractor within it. The endpoint should be auto-populated with the Intelligent Form Extractor endpoint, namely https://du.uipath.com/svc/intelligentforms. Provide the Document Understanding API key.

Once that is done, to create a new template, select Manage Templates > Create Template. A pop-up window opens.

Em Tipo de documento, selecione o tipo de documento W-9 criado anteriormente.

Em Nome do documento, insira um nome para o seu modelo.

Under Template document (native PDF if possible), attach a template document where you are going to map the field positions.

Under OCR Engine, select again the UiPath Document OCR. Just like before, the endpoint should be auto-populated, namely https://du.uipath.com/ocr, and you just need to provide the API Key.

Select Configure to move to the next step. The Template Manager pop-up window opens.

Here, we will need to select the areas where we want Intelligent Form Extractor to search for our fields. Configure them by following the steps detailed here. You also have the option of using anchors for your fields. More information on anchors here.

O resultado deve ser parecido com:

Select Save. In this screen, you can define the handwritten or signature fields, where applicable. You can also define synonyms for Boolean fields. Close the window after you are done.

O próximo passo é configurar o extrator, ou seja, fazer com que o Intelligent Form Extractor processe todos os documentos do tipo W-9.

6. Valide os resultados usando o Validation Station

To check the results through Validation Station, drag and drop the Present Validation Station activity and provide the input details.

7. Exporte os resultados da extração

To export the extraction results, validated or not, drag and drop an Export Extraction Results activity to the end of your workflow. This outputs the results into a DataSet that contains multiple tables, which could then be written to an Excel file or be used directly in a downstream process.

Baixe o exemplo

Download this sample project to execute the W-9 with Intelligent Form Extractor workflow using this link.