Predictive Intelligence for Incident Management

  • Release version: Washingtondc
  • Updated February 7, 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 Predictive Intelligence for Incident Management

    Predictive Intelligence for Incident Management utilizes your instance records to enhance incident handling through predictive solutions. It offers predefined templates that allow for customization, enabling better management of incidents based on historical data.

    Show full answer Show less

    Key Features

    • Solution Definitions: These templates include various classification and similarity predictions, such as:
      • Incident Assignment Classification: Predicts the Assignment group.
      • Incident Categorization Classification: Predicts the Category field.
      • Incident Service Classification: Predicts the Service field.
      • Major Incident Detection: Recommends similar major incidents.
      • Similar Incidents Recommendations: Links to both active and closed incidents for improved investigation.
    • Required Plugins: Essential plugins must be active for functionality, including com.glide.platformml and com.snc.incident.mlsolution.
    • Business Rules: Custom business rules can be created for Incident Assignment and Categorization to enhance prediction and reporting.

    Key Outcomes

    By implementing these predictive solutions, customers can expect improved incident resolution efficiency, reduced time for categorization and assignment, and enhanced overall service management capabilities. Regular maintenance of prediction accuracy through retraining and testing is necessary to adapt to changing business conditions.

    Use your instance records to build specific solutions for Incident Management.

    Solution definitions

    These solution definitions are available as templates on instances where both Predictive Intelligence and Incident Management are active. Create your own solution definition records to customize the behavior.

    Table 1. Solution Definitions for Incident Management
    Solution Definition Solution Type Description
    Incident Assignment Classification Predicts the Assignment group field from the Short description.
    Incident Categorization Classification Predicts the Category field from the Short description.
    Incident Service Classification Predicts the Service field from the Short description.
    Incident Configuration Item Classification Predicts the Configuration item field from the Short description.
    Major Incident Detection Similarity

    Recommends similar active major incidents which the current incident can be linked to.

    Recommends similar incidents to propose a major incident.

    Similar Incidents (Major Incident Workbench) Similarity Recommends similar incidents that are not linked as child incidents to a major incident.
    Similar Incidents Similarity Recommends similar incidents based on the Short description and Description fields, to help with incident investigation and resolution processes.
    Similar Open Incidents Similarity Recommends similar open incidents based on the Short description and Description fields, that the current incident can be linked to.
    Similar Closed Incidents Similarity Recommends similar closed incidents based on the Short description and Description fields, to help with incident investigation and resolution processes.
    Similar Resolved Incidents Similarity Recommends similar resolved incidents to help with incident investigation and resolution processes.
    Solution definitions and the required plugins are as follows:
    Table 2. Solution definitions and plugins
    Solution definition Plugins
    • Incident Assignment
    • Incident Categorization
    • Incident Service
    • Incident Configuration Item
    The plugins com.glide.platform_ml and com.snc.incident.ml_solution must be active.
    Similar Incidents (MIM) The plugins com.glide.platform_ml and com.snc.incident.mim.ml_solution must be active.
    Major Incident Recommendation The plugins com.snc.contextual_search_ml and com.snc.incident.mim.ml_solution must be active.
    • Similar Open Incidents
    • Similar Resolved Incidents
    • Similar Incidents
    • Similar Knowledge Articles
    The plugins com.snc.contextual_search_ml and com.snc.incident.mim.ml_solution must be active.

    For more information on classification and similarity solution, refer to Create solution definition and Create similarity solution.

    Business rule for classification solutions

    This business rule applies only to the Incident Assignment and Incident Categorization solution definitions and is available only on instances where both Predictive Intelligence and Incident Management are active. Create your own business rules on the Incident table to customize prediction and reporting behaviors.

    Table 3. Business rule for Incident Management
    Business rule Table Description
    Update Prediction Results Incident Updates the solution precision and coverage statistics. Runs when an incident record is closed.

    For more flexibility with classification solutions, consider using ITSM Predictive Intelligence Workbench.

    Upgrade Information

    If your instance is running on the Kingston release and you are upgrading to the Washington DC release:
    • In a global domain environment, use the new solutionNames array variable which requires that you explicitly provide the solutions that are called by the business rule.
    • In a domain-separated environment, such as an MSP environment, refer to the commented code in the business rule template for easy customization.
    • The business rule template now calls the applyPredictionForSolution() method to predict regardless of any changes to the default value.

    Maintaining prediction accuracy

    You can manage prediction drift by retraining, modifying, or creating new solutions to reflect changes in your business conditions. Test and modify your business rule over time to ensure it works as desired across multiple consumption points and user Personas.