Create and train a solution definition for Vulnerability Response

Create and train a solution definition model for Vulnerability Response by using Predictive Intelligence. You can use this model to predict the assignment group for a vulnerable item (VI) or remediation task (RT) based on existing data.

始める前に

Role required: sn_vul.vulnerability_admin

手順

1. Navigate to All > Predictive Intelligence > Classification > Solution Definitions.
2. On the Classification Definitions form, click Vulnerable Item Assignment.
   This is the default solution definition.

   注:

   • The default Training Frequency is 30 days. This means that every 30 days, the model retrains automatically using the VI dataset that matches the configured filter condition.
   • Fields from the Vulnerable Item table can be used for training. The default solution definition trains on two VI fields: Vulnerability.Summary and Configuration item.Name. You can customize the fields used for training, depending on which fields you find helpful for predicting vulnerability ownership in your organization.
3. To create and train the classification solution, see Create and train a classification solution.
   注:

   You can also create and train a similarity or a clustering solution. For more information, see:

   • Create and train a similarity solution.
   • Create and train a clustering solution.
4. Click Update & Retrain.
   注:

   To configure advanced settings for ML solutions, see Configuring advanced settings for your ML solutions.