Configure Task Intelligence for Customer Service

  • Release version: Xanadu
  • Updated August 1, 2024
  • 2 minutes to read
    • Summarize
    Summarized using AI
    This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete.

    Summary of Configure Task Intelligence for Customer Service

    Task Intelligence for Customer Service is an application designed to enhance customer service processes by leveraging AI-driven features such as record categorization, language detection, sentiment analysis, and document intelligence. ServiceNow customers with admin roles can install and configure these features to improve case handling and data extraction.

    Show full answer Show less

    Key Features

    • Record Categorization: Enables creation and training of models to predict field values for cases and interactions by activating necessary plugins and importing training data.
    • Sentiment Analysis: Allows prediction of case sentiment by enabling specific plugins, activating the sentiment analysis property, assigning roles, and training sentiment models.
    • Language Detection: Detects the language used in customer service cases by activating required plugins and the ServiceNow translator, followed by setting up detection models.
    • Document Intelligence for Customer Service: Facilitates extraction of relevant data from emails and case attachments via configurable use cases.

    Model Setup and Deployment

    After feature configuration, the Task Intelligence Admin Console provides a centralized interface to:

    • Create and train models for record field prediction, sentiment analysis, and language detection.
    • Edit, test, and redeploy pre-trained and custom models, including similar case prediction models.
    • Develop and manage Document Intelligence use cases for data extraction from documents.
    • Export models to other ServiceNow instances for reuse.
    • Create custom similar case models by training on field similarities across different tables to enhance case similarity predictions.

    Practical Benefits

    By configuring Task Intelligence for Customer Service, organizations can automate and improve case classification, understand customer sentiment, handle multilingual cases efficiently, and extract structured data from unstructured documents. This leads to more accurate case management, faster resolution times, and enhanced customer satisfaction.

    Install the Task Intelligence for Customer Service application and configure the different features: record categorization, language detection, Sentiment Analysis, and Document Intelligence for Customer Service.

    Install and configure Task Intelligence features

    Complete the following tasks to install Task Intelligence for Customer Service and configure the features.
    Table 1. Task Intelligence feature configuration
    Task Description
    Install the Task Intelligence for Customer Service application You can install the Task Intelligence for Customer Service application (com.snc.csm_ml_task) if you have the admin role.
    Configure record categorization Activate the required plugins and import training data. Then you can create and train a model to predict field values.
    Configure Sentiment Analysis Activate the required plugins, enable the sentiment analysis property, and assign roles. Then you can train a model to predict case sentiment.
    Configure language detection Activate the required plugins and the ServiceNow translator to use the language detection feature. Then you can set up a model to detect the case language.
    Configure Document Intelligence for Customer Service Enable Document Intelligence for Customer Service and create use cases to extract data.

    Set up and deploy Task Intelligence models

    Once you have completed the configuration tasks, you can use the Task Intelligence Admin Console to set up and deploy models for record categorization, sentiment analysis, and language detection. You can also use the Task Intelligence Admin Console to access the Document Intelligence Admin interface, which you can use to create document processing use cases.
    Table 2. Model deployment in Task intelligence
    Task Description
    Create a model to predict record fields Create and train a model to predict fields for cases and interactions.
    Create a model to predict case sentiment Edit and test the pre-trained sentiment model to predict sentiment for customer service cases.
    Create a model to detect case language Edit and test the pre-trained model to detect the language used to create customer service cases.
    Create a Document Intelligence use case Create a use case to identify the information to extract from email and case attachments.
    Create a model to predict similar cases Test and edit the pre-trained similar cases model for predicting similarity in customer service cases and create a new model for custom cases.
    Edit a model Edit the case models that have already been trained and deployed. Change the model configurations, view the updated training results, and redeploy the model.
    Export a model Export a Task Intelligence model to another instance.
    Create a custom similar case model

    Set up a training model to help it recognize similarities between two types of tables by comparing their fields.

    The model looks at the prediction fields of a prediction table and the training fields of a training table. It uses the similarities in these fields to predict similar records.