IBM App Connect passes key data between Watson Natural Language Classifier and other apps â€“ automatically, in real time.
You can use App Connect with Watson Natural Language Classifier by configuration and data mapping without a need for coding, and can achieve a return on your investment in minutes/hours, not days/months.
This guide is to show you how…
If you can’t find what you want, or have comments about the “how to” information, please either add comments to the bottom of this page or send us comments by email.
About Watson Natural Language Classifier
IBM Watson Natural Language Classifier helps understand the language of texts and returns a corresponding classification based on a confidence score. In order for Watson to do this, you have to provide sample data which includes representative texts with class labels. Then, you create a classifier and train it to classify the texts you created against your class labels. Once the classifier is trained, you can test it with data it is not trained on, check the results against the confidence scores, and update your training data accordingly.
A typical business scenario
Say youâ€™re leading a team thatâ€™s part of a large international customer services department. Thereâ€™s so much to do, and your team is spread across several locations. Customer queries are coming in through lots of channels and it’s difficult to priorities and direct each customer case to the correct department. You need a way to classify each case efficiently so that it is dealt with quickly.
How App Connect can help
As soon as a new ticket is created in a support app, for instance Atlassian JIRA Service Desk, you can use the Natural Language Classifier to analyze the subject header for a classification, then assign a priority based on the classification. Or, when a message is received in a support channel in Slack, you can categorize the message using the Natural Language Classifier and then send an email to a different functional ID based on the classification.
What should I consider first?
To use Watson Natural Language Classifier with App Connect, you must have provisioned a Watson Natural Language Classifier service in IBM Cloud.
You can connect App Connect to the Watson Natural Language Classifier application either from the Applications tab on the App Connect Catalog page, or when you add the application to a flow. You’ll need to provide the following connection details:
- Base URL: Specify the base URL for the Watson Natural Language Classifier service endpoint; for example:
- API key: If your service instance supports token-based Identity and Access Management (IAM) authentication, specify the API key for that instance. (Leave the User name and Password fields blank.)
- User name: If your service instance uses Cloud Foundry service credentials for authentication, specify your user name for that instance. (Leave the API key field blank.)
- Password: If your service instance uses Cloud Foundry service credentials for authentication, enter the password for the specified user name. (Leave the API key field blank.)
Example of completed fields for connecting from App Connect using IAM authentication
You can find the connection values on the “Service credentials” page for the service instance in IBM Cloud:
- Log in to IBM Cloud.
- From the IBM Cloud Dashboard, click the Watson service instance that you want to work with.
- To view the service credentials, click Service credentials in the left pane, and then click View credentials.
- Example of completed fields for connecting from App Connect using IAM authentication
When I create a new case in Salesforce, a message classified by Watson Natural Language Classifier is created in Slack
Learn how easy it is to create an event-driven flow in App Connect Designer to classify the text from a Salesforce case. Then, after the text has been classified, automatically create a message in Slack identifying the type of case that has been raised and the case number.