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 Agent to auto categorize tickets:
- While creating incidents, work order, or change requests in BMC Helix ITSM
- While creating tickets in the Smart IT Console
- 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) Catalog link to create service request
- Replying with the knowledge articles to use as a Self Service option
- Applying a ticket template to the incident created by using emails

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

Using the Data Qualifier input source, the training dataset is generated from the existing data in your system and by applying the qualifications you provide to the system.

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.

Training data guidelines

Understand the following guidelines before generating a training dataset record.

Maximum number of training data 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. You must delete an existing dataset record and then create a new record.

Data Qualifier training data

Data Qualifier is the default training input source.
Generate training data by using the Data Qualifier if your system has tickets that match the qualification which is 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 data 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, ensure 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 new training dataset for the same record again.

Templates for Data Qualifier training

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

Warning

For training data, you must use the out-of-the-box templates without customizing them. If you try to customize the templates, the auto-categorization in Remedy with Smart IT fails.

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

Application	Training data template for Categorization	Training data template for ticket templates	Training data template for knowledge articles	Training data template for BMC Digital Workplace Catalog
Change Management	Change Ops Categorization Training Data Change Product Categorization Training Data	Change Template Training Data	Not available	Not available
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 Data	Incident Knowledge Articles Training Data	Incident-DWP Catalog Training Data
Knowledge Management	Knowledge Ops Categorization Training Data Knowledge Product Categorization Training Data Knowledge Resolution Categorization Training Data Knowledge Resolution Product Categorization Training Data	Not available	Not available	Not 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 available	Not available	Not available
Release Management	Release Ops Categorization Training Data Release Product Categorization Training Data	Not available	Not available	Not available
Service Request Management	Work Order Ops Categorization Training Data Work Order Product Categorization Training Data	Work Order Template Training Data	Not available	Not available
Task Management System	Task Ops Categorization Training Data Task Product Categorization Training Data	Not available	Not available	Not available

CSV file format for training data

In this data type, 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 ensure that the description text and the matching categories exist in the system. Ensure that the CSV file does not contain any header row. For more information about generating 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:

Process	First column in CSV file	Second column in CSV file
For auto-categorization of tickets	Description or keywords or phrases	The categories that match each description
For auto-applying ticket template to the tickets that are created using emails sent by users	Description or keywords or phrases	The instance ID of templates that match each description Note: the field name for template instance ID might be varies in different applications.
For responding to users' emails with BMC Digital Workplace service catalog	Summary from users' emails	Links to the relevant BMC Digital Workplace service catalog
For responding to users' emails with Remedy Knowledge Articles	Summary and email content from users' emails	Links to the relevant Remedy Knowledge Articles

Training data for BMC Helix Cognitive Automation

Training data guidelines

Templates for Data Qualifier training

CSV file format for training data

Related topics

Comments