Configuring email signature parsing for contacts
Pega Sales Automation uses natural language processing (NLP) on a contact's email signature to create default contact values.
Pega Sales Automation
Implementation Guide
Pega Sales Automation
Implementation Guide
Pega Sales Automation
Implementation Guide
Pega Sales Automation
Implementation Guide
For example, NLP can extract the first and last name, title, and phone number from
a contact in Outlook add-in based on the email signature and add these values to a Pega
Sales Automation contact.
- Integrating Pega Sales Automation with Microsoft Outlook by using the Pega for Outlook Office add-in.
- Configuring Intelligent Virtual Assistant.
After you configure the integration between Microsoft Outlook and Pega Sales Automation, configure signature parsing to use NLP to fill out contact information. Perform all the procedures in this section.
- "Configuring signature parsing"
- "Configuring signature parsing after upgrading to current release"
- "Further customizing the shipped models"
Configuring signature parsing
- In the header of Dev Studio, click .
- Optional: If you have not created an Email channel as part of the Intelligent Virtual
Assistant configuration, create an Email channel.
For more information, see Configuring Intelligent Virtual Assistant for Pega Sales Automation.
- Open the Email channel and perform the following steps:
- On the Behavior tab, in the Text Analyzer section, select the Record training data check box.
- Click Save.
- In the Text Analyzer section, click Open text analyzer rule.
- In the Text extraction section, verify that the pySystemEntities and SASystemEntities models are on the list.
- Optional: If these models are not listed, add them by clicking Add extraction model.
- Click Save.
Configuring signature parsing after upgrading to current release
- In the header of Dev Studio, click .
- Open an existing email channel that you want to associate with signature parsing.
- On the Behavior tab, in the Text Analyzer section, select the Record training data and Use advanced configuration check boxes.
- In the Text Analyzer section, click the Switch
to edit more icon on the right side of the iNLP text
analyzer.
- In the Text Analyzer type field, select iNLP.
- Select the Enable model training check box.
- Click Submit.
- In the Text Analyzer section, delete the existing pyNER model by clicking the trash icon on the right side of this extraction model.
- Add the pySystemEntities and SASystemEntities models by clicking Add text analyzer.
- Click Save.
Further customizing the shipped models
You can further customize the
pySystemEntities and SASystemEntities
models to fit your business needs.
- In the navigation pane of Dev Studio, click .
- Search for and open the pyAllowedNLPShippableRulesets decision table.
- Save the pyAllowedNLPShippableRulesets decision table into your implementation layer.
- In the table, perform the following steps:
- Add your rulesets under the Ruleset column.
- Set the return value under the Actions column to true.
- Click Save.
- In the navigation pane of Dev Studio, click .
- Search for and open the SASystemEntities data model.
- On the Data tab, in the Entity analysis section, download the training data in every language by clicking Download.
- Create a binary file for each model for each language that you want to use, by
clicking .
- In the Label field, enter NLPDefault.
- In the App Name (Directory) field, enter information in the following format: Rule purpose>_<language>, for example, pyNER_English.
- In the File Type (extension) field, enter zip.
- Save the file in the implementation ruleset.
- Open the binary file and upload the training data .zip file for each language
by clicking Upload file.
Previous topic Configuring Intelligent Virtual Assistant Next topic Artificial intelligence-based opportunity insights