Space banner

 

This documentation supports the 19.08 version of Remedy IT Service Management Suite.

To view an earlier version, select the version from the Product version menu.

Generating training data for BMC Cognitive Helix Automation


Follow the procedures in this topic to generate training data by using a Data Qualifier or a CSV file.

Before you begin

To generate training data by using Data Qualifier as an input source

Perform the following steps to generate training data by using Data Qualifier:

  1. Navigate to Application Administration Console > Custom Configuration > Foundation > Advanced Options > Cognitive Service Configuration. On the Cognitive Data Setup form, select Cognitive Data Type.

    Cognitive Data TypeAction
    Categorization
    Select Company, Application, and Template. Click Add Selected Template. Select the training data record from the list of training data sets provided out-of-the-box. Click Generate Training Data.
    Application Template
    Select the training data record from the list of training data sets provided out-of-the-box.Ensure that TemplateGUID !=NULL is not removed from the Qualification field.

    Notes

    • By default the - Global - option is selected as Company. While training the data, the cognitive service considers the templates that are available under all the companies in their database.
    • While training the data, the cognitive service considers existing tickets data that have templates.
    • The cognitive service applies a template, only if you have permissions to access that template.
    • The option to delete trained data is disabled for the Application Template.
    • While creating a ticket if user selects the Reported Source as Email, the cognitive service automatically applies template to that ticket.
    • The training data set contains GUID that is unique for a Innovation Suite server or IBM Watson account. If this data set is used to train Application Templates on multiple ITSM stacks, the results of cognitive service are not predictable.
    Incident Knowledge SearchSelect Company, Application, and Template. Select Incident Management from the Application list.
    DWP CatalogThe Data Qualifier option is not available for generating training data of Digital Workplace Service Catalog links.
    Custom

    Select this option if you want recommendations for Risk Level in Change Management or Root Cause in Problem Management.

  2. Click View Details. The Training Details Form is displayed: 

  3. (For Custom data type only) Select Use OOTB to use OOTB training datasets for Risk Level or Root Cause recommendations. 
  4. Click Generate Training Data.
    The training data record is created. When you create a training data record by using an out-of-the-box template, the Qualification and Company Mapping fields are populated with the values used by the template. 

Cognitive Data Setup form

The following table describes some of the key fields on the Cognitive Data Setup form:

FieldDescription
Qualification

The cognitive service generates training data from the existing data according to the qualifications entered in this field.

For example, if the Qualification value is "Status" = "Closed", the service selects all the tickets that have the Status value as Closed to generate the training data.

Company Mapping

The value entered in this field maps the selected company with the company fields on the form.

For example, if you generate training data for Calbro Services and the Company Mapping field value is Location Company, the service selects the tickets that have the Location Company value as Calbro Services to generate training data.

Data set configuration table

This table displays the following information about the training data record created for your company.

  • Form Name – The form name from which the service pools the data.
  • Description – The template name that you selected from the Template drop-down menu.
  • Qualification – The qualifications that is configured for the training data.
  • Status – The status of the training data record. For information about the status values, see Monitoring status of training data.
  • Last Updated – The date and time when the data was last modified.


To generate training data by using a CSV file as an input source


Note

You can create a CSV file for training the cognitive service. For more details about the format of a CSV file, see Training data for BMC Helix Cognitive Automation.

  1. Navigate to Application Administration Console > Custom Configuration > Foundation > Advanced Options > Cognitive Service Configuration.
  2. On the Cognitive Data Setup form, select Cognitive Data Type
    • Categorization: Select this value to generate training data for auto-categorization.
    • Application Template: Select this value to generate training data for auto-applying templates to the tickets.
  3. Select Company.
  4. From the Application list, choose the application for which you want to generate training data; for example, Incident Management.
  5. (For Categorization only) From the Template  list: 
    • Click Add Selected Templates to add the selected template to the training data record.
    • Click Add All Templates to add all the templates to the training data record.
      A training record is created.
  6. Select the record from the table and click View Details.
  7. On the Training Details form, select Input Source as CSV File.
  8. Select the Locale value.
  9. In the Attach CSV table, click Attachment.
  10. Attach the CSV file and click Add.
  11. Click Save.

Training Details form

 

The following table describes the important fields on the Training Details form:

FieldDescription
DataSetTAGDisplays the DataSetTAG name defined for the training data which is a unique name for each dataset.
Status

Indicates the status of the training data. If you set the value of this field to Active, the training data is used to train the cognitive service. If you set the value of this field Inactive, the training data is not used to train the cognitive service.

Locale

Provides a locale when you generate the training data by using the CSV file input.

Note: The Locale field is enabled only when you select the Input Source value as CSV. It is mandatory to provide the Locale value.

Input Source

Indicates the CSV File value for training the data.

Input Fields

Indicates the field names from the drop-down menu to provide the list of Input Fields to be used to train the cognitive service.

For example, if you select Description from the drop-down menu for incident tickets, the information entered in this field on the incident ticket is used by the system for data training.

Training Output Fields

Indicates the field names to be used for training the cognitive service.

For example, when you select Categorization Tier 1Categorization Tier 2, and Categorization Tier 3, the information entered in the Input Fields is mapped with these fields.

Training data generation status

When you generate training data, the Data set configuration table displays the status of the training record. The status value helps you to understand the progress of your training data record.

The following table describes the status set by the system when the training data record is processed.

Training data status

StatusDescription
UNTRAINEDThis status is set by default when you create a training data record for your company by using the out-of-the-box templates provided by BMC.
QUEUEDThis status is set when request for generating this training data record is submitted.
PROCESSINGThis status is set after the training data is generated and being used to train the cognitive service.
COMPLETEDThis status is set when the system successfully trains the cognitive service by using the training data.
FAILED

This status is set when the system fails to train the cognitive service. An error message stating the reason for failure is displayed below the Data set configuration table.

Example of generating training data for a custom use case

This is an example of a use case where the cognitive service is customized to read the inbound email content of existing incidents. Depending on the training dataset, the cognitive service takes actions such as automatically resolving incidents or escalating incidents.

StepReference

Create input and output fields: Create two character type fields with names as COG_EMAIL_INPUT and COG_EMAIL_RESPONSE, and field size as 1024 on the HPD:Help Desk form. Provide the general public permissions to these fields.

Creating and managing fields
Set up the cognitive service in Remedy ITSMSetting up BMC Helix Cognitive Automation

Create a training dataset: Create a training dataset with the name as EMAIL_RESPONSE_ACTION.

File format to use CSV file as an input source

To generate training data by using a CSV file as an input source

Create a filter on HPD:WorkLog form

Creating filters

Create a filter for Set Fields action

To create a filter with input and output mappings

Create a filter for Service action

Service action

Create a filter for recording a response from the cognitive service

Set Fields action

Create a workflow for performing the actions recommended by the cognitive service

Defining workflow to automate processes

Reset the output field value to NULL

Set Fields action

To deactivate a previously trained dataset

In certain situations, if you don't want to use Cognitive Service to use a trained dataset, you can deactivate the option for that trained dataset to automatically categorize or automatically applying templates. For this, you must perform the following steps:

  1. Navigate to Application Administration Console > Custom Configuration > Foundation > Advanced Options > Cognitive Service Configuration.
  2. On the Cognitive Data Setup form, select Cognitive Data Type.
  3. Select the training data set that you want to deactivate.
  4. Change the Status to Inactive.

Additionally, if you want to delete the trained data for application templates, the option to delete the data set is disabled. To delete the trained data set, open the data set using Data Set ID on the form AR System Administration:Cognitive Service Training Data Set Pending.

Cognitive Service Training Data Set Pending form


Related topic

Troubleshooting BMC Helix Cognitive Automation


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

Comments