Configure an Amount Group Locator

Use the procedure in this topic to configure the Amount Group Locator settings.

Before you begin

Before you can configure the settings for an Amount Group Locator verify that the following steps are complete:

  • You have added a Amount Group Locator method.

Procedure
  1. Open the Amount Group Locator Properties icon Properties.

    The properties for the Amount Group Locator are displayed.

  2. Select the General tab and configure the following settings.

    Setting

    Description

    Formatting group

    Amount formatter

    Select an Amount Formatter from the list. The available formatters in this list are configured on the Project Settings - Formatting tab. (Default: Default amount formatter)

    Percentage formatter

    Select a Percentage Formatter from the list. The available formatters in this list are configured on the Project Settings - Formatting tab. (Default: Use amount formatter)

    Results group

    Min. confidence

    Enter a value or use the slider to adjust the minimum confidence value that alternatives must meet to be returned. (Default: 40)

    Activate VAT-based amount location group

    Activate VAT-based amount location

    Enables VAT-based amount location. (Default: Selected)

    Select one or more countries from the list. By default, the list of available countries consists only of Germany, the United States, France, Spain, and the United Kingdom. Additional countries can be added by selecting the Countries button.

    Countries

    Displays the Project Settings - Country Settings tab where you can add countries and configure VAT amounts.

  3. Select the Document Type tab and configure the following settings.

    Setting

    Description

    Enable

    Selecting this setting enables the you to add keywords to help identify the correct document class. (Default: Cleared)

    When selected, the Keywords table is enabled.

    Keywords

    Use the Add icon Add and Delete icon Delete buttons along with the following settings to configure keywords.

    Invoice:

    Enter or edit the keyword present on documents that identify them as invoices. (Default: Invoice)

    Credit:

    Enter or edit the keyword present on documents that identify them as credit notes. (Default: Credit)

    Unknown:

    Enter or edit the keyword present on documents that identify them as neither invoices nor credit notes. (Default: ~)

    Min. confidence:

    Enter a value or use the slider to adjust the minimum confidence needed for an alternative to be returned. (Default: 50)

  4. Select the Validation tab and configure the following settings.

    Setting

    Description

    Please select a method for the amount validation

    Select the desired validation method from the list. (Default: No Validation Method)

    If you have created your own Multi-field Script Validation or an Invoice Validation, you may need to manually assign a validation method subfield to each locator subfield.

    Field Mapping

    This table lists all fields and their corresponding validation methods. (Default: No Validation Method)

    For each field, select a relevant validation method. If necessary, create new validation methods on the Project Settings - Validation tab.

  5. Select the Advanced tab and configure the following settings.

    Setting

    Description

    Training Type

    The training type defines the algorithm that is used during the training of the locator and therefore how documents are extracted. Changes you make to the locator training type become effective after you retrain the project. The locator training type does not affect or restrict the used knowledge bases. You can select the algorithm for the creation of the knowledge base when you create the knowledge base. For the best result, use generic knowledge bases and restrict the training type for newly trained documents to specific training. This combination enables the use of certified generic knowledge bases that you can then improve with specific document training during online learning.

    The different training types include:

    Generic:

    This type is mainly based on keywords and keyword location in relation to an alternative or field. As a result, this setting requires good OCR quality to extract data from documents. Generic training can also extract values from unknown documents that use similar keywords as some of the trained sample documents.

    Specific:

    This type learns the layout of a sample document and only applies the extraction to another document with the same layout. This is typically true for invoices from the same vendor. Because of the trained layout, specific training can use a combination of restricted keywords, fixed positions and a known field format. In combination, these provide significantly better recognition and accuracy than generic extraction. However, this type of training only works for trained layouts.

    Both:

    If you use both training types, a field is trained for the generic and specific search method. During extraction, the results for specific search are executed first, and if a result is found, the locator returns only the results for the specific search method. If no result is found, the generic search method is executed and if a result is found, the locator returns those results.

    Specific is performed first and if no field is located in a specific location, the entire page is searched for that field.

    Search Confidence

    Available only if the Training Type is set to Generic or Both. Enter a value or use the slider to adjust the minimum confidence required for an alternative to be returned as a search result. (Default: 40)

    Because this group locator returns more than one piece of information, the locator searches a document for each individual field. The locator looks at each alternative field on a document, compares the field with the extraction training document set, and assigns a confidence level to the field based on location and surrounding keywords. An alternative must have a confidence level equal to or higher than the search confidence level for the alternative to be included in the results.

    Evaluation Confidence

    Available only if the Training Type is set to Generic or Both. Enter a value or use the slider to adjust the minimum confidence required for a group of combined alternatives to be returned as a result. (Default: 60)

    When you use the generic training type, the confidence level works in two steps. In the first step, the locator searches fields that are distributed over the document separately (Search Confidence). In the second step, the locator tries to combine all fields that belong to that locator into a single alternative. These grouped alternatives are only returned if the confidence level is equal to or higher than the specified evaluation confidence level.

    Weak Keyword Dictionary

    Available only if the Training Type value is set to either Generic or Both. Select a dictionary from the list that contains a list of words that can negatively affect extraction results. (Default: no dictionary)

    For each group locator, a predefined dictionary of weak keywords is installed. The dictionary contains keywords for US English, UK English, German, Spanish and French. For additional languages, update the dictionaries with keywords for those languages.

    Currencies

    Use the Add icon Add and Delete icon Delete buttons along with the following settings to manage the list of currency abbreviations:

    Currency abbreviation:

    Enter a common currency abbreviation that can be mistaken for the incorrect currency type.

    Result:

    Enter the value for the corresponding Currency abbreviation that you want displayed in the output.

  6. Open a test document and select Test to test your settings.
  7. Optional. Select Close to close the locator properties window.
  8. Save the changes to your project.