This documentation supports the 21.05 version of BMC Helix ITSM. To view an earlier version, select the version from the Product version menu.

Training data for BMC Helix Cognitive Automation

As a system administrator, you can train the cognitive service for the following purposes:

  • Enabling the Service Desk Agents to automatically categorize tickets:
    • While creating incidents, work orders, or change requests in BMC Helix ITSM
    • While creating tickets in BMC Helix ITSM
    • While creating tickets by using Smart Recorder
  • Enabling options for responding to an email from the business user by:
    • Replying with the BMC Digital Workplace (DWP) service catalog to create a service request
    • Replying with the knowledge articles to use as a Self Service option
    • Applying a ticket template to an incident created by using emails
  • Enabling options to receive recommendations for Root Cause in Problem Managementand Risk Level in Change Management



Options for generating training data

You can use the Data Qualifier or CSV file as an input source to train the cognitive service.

By using the Data Qualifier input source, the training dataset is generated from the existing data in your system and by applying the qualifications that you provide to the system. In this type of input source, a CSV file is generated by the system.

By using the CSV file input source, you need to provide a CSV file to train the cognitive service. The CSV file must contain two columns. In this type of input source, a CSV file is created manually.


Training data guidelines

Understand the following guidelines before generating a training dataset record.

Maximum number of training dataset records

  • You can generate a maximum of 20 training dataset records at a given time.
  • An error message is displayed if this limit is exceeded. If you get an error message, you must delete an existing dataset record and then create a new record.

Data Qualifier training data

  • Data Qualifier is the default training dataset input source.
  • Generate the training dataset by using Data Qualifier if your system has tickets that match the qualification used in the out-of-the-box templates, and if your system has a sizeable number of tickets with all possible categorizations.
  • If the number of records in the training dataset exceeds 15000, the system selects the most recently modified 15000 records.

CSV file training data

  • Use the CSV file to generate dataset if you have your own set of descriptions and matching categorizations or ticket templates.
  • When you provide the CSV file as a training dataset source, make sure that it contains at least 5 records.
  • If your CSV file contains more than 15000 records, only the first 15000 records are used by the system to train the cognitive service.
  • If the description in the input column of the CSV file contains more than 1024 characters, only the first 1024 characters are used by the system to train the cognitive service.

Incremental training

  • The cognitive service is not trained incrementally. To train the cognitive service with new tickets entered in the system, you must generate a new training dataset for the same record again.


Templates to use the Data Qualifier as an input source

We provide out-of-the-box training dataset templates for each application. The templates have default qualifications based on which the system generates training datasets in the CSV format. For more information about generating training datasets by using Data Qualifier, see To generate training data by using Data Qualifier

Important

For training data, you must use the out-of-the-box templates without customizing them. If you try to customize the templates, the automatic categorization in BMC Helix ITSM fails.

The following table lists the out-of-the-box training dataset templates provided by BMC for each application.

ApplicationTraining dataset templates
for Categorizationfor ticket templatesfor knowledge articles

for BMC Digital Workplace service catalog

for Custom options

Change Management

  • Change Ops Categorization Training Data
  • Change Product Categorization Training Data
Change Template Training DataNot availableNot availableChange Risk Level

Incident Management

  • Incident Ops Categorization Training Data
  • Incident Product Categorization Training Data
  • Incident Resolution Categorization Training Data
  • Incident Resolution Product Categorization Training Data
Incident Template Training DataIncident Knowledge Articles Training DataIncident-DWP Catalog Training DataNot available

Knowledge Management

  • Knowledge Ops Categorization Training Data
  • Knowledge Product Categorization Training Data
  • Knowledge Resolution Categorization Training Data
  • Knowledge Resolution Product Categorization Training Data
Not availableNot availableNot availableNot available

Problem Management

  • Problem Known Error Ops Categorization Training Data
  • Problem Known Error Product Categorization Training Data
  • Problem Ops Categorization Training Data
  • Problem Product Categorization Training Data
Not availableNot availableNot availableProblem Root Cause

Release Management

  • Release Ops Categorization Training Data
  • Release Product Categorization Training Data
Not availableNot availableNot availableNot available

Service Request Management

  • Work Order Ops Categorization Training Data
  • Work Order Product Categorization Training Data

Work Order Template Training Data

Not availableNot availableNot available

Task Management

  • Task Ops Categorization Training Data
  • Task Product Categorization Training Data
Not availableNot availableNot availableNot available


File format to use CSV file as an input source

In this input source, you need to provide a CSV file to train the cognitive service. You can create a CSV file from the historical data that is available in your system. The CSV file must contain two columns. The records in the CSV file are used as is to train the cognitive service. You must make sure that the description text and the matching categories exist in the system. Make sure that the CSV file does not contain any header row. For more information about generating the training data set by using the CSV file, see To generate training data by using CSV file.

The following table explains the format of a CSV file:

ProcessFirst column in CSV fileSecond column in CSV fileSample CSV file
For automatic categorization of ticketsDescription or keywords or phrasesThe categories that match each description

For automatically applying ticket templates to the tickets that are created by using emails sent by usersDescription or keywords or phrasesThe GUID of templates that match each description

For responding to user emails with the BMC Digital Workplace service catalog

Summary from user emails

Links to the relevant BMC Digital Workplace service catalog

For responding to user emails with knowledge articlesSummary and email content from user emailsLinks to the relevant knowledge articles

For taking customized actions depending upon user emails.Summary and email content from user emails
Custom actions, events, or any keywords that should be customized for taking relevant actions in the system


Was this page helpful? Yes No Submitting... Thank you

Comments