Generating training data for BMC Cognitive Helix Automation
As an administrator, you can generate training data by using a Data Qualifier or a CSV file.
Before you begin
- Make sure that you have the Cognitive Service Config permission. For information about this permission, see BMC Cognitive Service Management permission.
- Make sure that you understand the types of training data and the guidelines to follow while generating the data. For more information, see Training data for BMC Helix Cognitive Automation.
To generate training data by using Data Qualifier as an input source
Navigate to Application Administration Console > Custom Configuration > Foundation > Advanced Options > Cognitive Service Configuration.
On the Cognitive Data Setup form, select the required Cognitive Data Type, and perform the steps indicated in the following table:
Cognitive Data Type Action 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. Make sure that
TemplateGUID !=NULL
is not removed from the Qualification field.- 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 ticket 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 a user selects the Reported Source as Email, the cognitive service automatically applies a template to that ticket.
- The training data set contains GUID that is unique for a BMC Helix Innovation Studio 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 Search - Select Company, Application, and Template.
- Select Incident Management from the Application list.
DWP Catalog The 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 Root Cause in Problem Management or Risk Level in Change Management. You can also use this option for custom use cases.
Fields Description
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 qualification that is configured for the training data.
- Status—The status of the training data record.
- Last Updated—The date and time when the data was last modified.
Click View Details.
- (For Custom data type only) On the Training Details form, select Use OOTB to use OOTB training datasets for Risk Level or Root Cause recommendations.
- 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 that are used by the template.
To generate training data by using a CSV file as an input source
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.
- Navigate to Application Administration Console > Custom Configuration > Foundation > Advanced Options > Cognitive Service Configuration.
- 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.
- Select Company.
- From the Application list, select the application for which you want to generate training data; for example, Incident Management.
- (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.
- Click Add Selected Templates to add the selected template to the training data record.
- Select the record from the table and click View Details.
On the Training Details form, select Input Source as CSV File.
Field Description DataSetTAG Displays 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 to 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.
Important: 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 list to provide the Input Fields to be used to train the cognitive service.
For example, if you select Description from the list 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 1, Categorization Tier 2, and Categorization Tier 3, the information entered in the Input Fields is mapped with these fields.
- Select the Locale value.
- In the Attach CSV table, click Attachment.
- Attach the CSV file and click Add.
- Click Save.
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.
Status | Description |
---|---|
UNTRAINED | This 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. |
QUEUED | This status is set when a request for generating this training data record is submitted. |
PROCESSING | This status is set after the training data is generated and is being used to train the cognitive service. |
COMPLETED | This 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 table. |
Example of generating training data for a custom use case
In this use case, the cognitive service is customized to read the inbound email content of existing incidents. Depending on the training data set, the cognitive service takes actions such as automatically resolving incidents or escalating incidents.
Task | Reference |
---|---|
Create input and output fields
| |
Set up the cognitive service in BMC Helix ITSM. | Setting up BMC Helix Cognitive Automation |
Create a training dataset Create a training dataset with the name as EMAIL_RESPONSE_ACTION. | To generate training data by using a CSV file as an input source |
Create a filter on the HPD:WorkLog form. | |
Create a filter for the Set Fields action. | To create a filter with input and output mappings |
Create a filter for the Service action. | |
Create a filter for recording a response from the cognitive service. | |
Create a workflow for performing the actions recommended by the cognitive service. | |
Reset the output field value to NULL. |
To deactivate a previously trained dataset
In certain situations, if you do not want to use Cognitive Service as a trained dataset, you can deactivate the option for that trained dataset to automatically categorize or automatically apply templates. For this, you must perform the following steps:
- Navigate to Application Administration Console > Custom Configuration > Foundation > Advanced Options > Cognitive Service Configuration.
- On the Cognitive Data Setup form, select Cognitive Data Type.
- Select the training data set that you want to deactivate.
- Change the Status to Inactive.
Comments
Log in or register to comment.