How to make Predictive Intelligence models work in Incident form?

SNDP
Tera Contributor

I have trained the models, and while testing the solutions it predicts successfully for the assignment group/business service/Service Offering, but how do I make it work with the incident form because even after saving the incident the PI doesn't predict anything.  

Thank you in advance

1 ACCEPTED SOLUTION

Brian Bakker
ServiceNow Employee
ServiceNow Employee

Hello @SNDP 

 

To trigger predictions on the incident form can be done several ways. Out-of-box, we provide a BEFORE INSERT business rule "Default Task Based Prediction" on table [task] as a template. If the Classification solution has the Input table [incident], then you should create a new BEFORE INSERT BR on table [incident] using Machine Learning APIs to trigger a prediction. You also need duplicate the Business Rule "Update Prediction Results" and ensure it is created on the same table, as the Classification Solution Input table. This is to ensure predictions are updated in [ml_predictor_results] table with Final Values, once the source record where the prediction was made is made inactive.

 

If you want to avoid scripting a BR, you can also use Machine Learning solutions for Flow Designer, and use a workflow to trigger the prediction on your Classification solution that does not require any scripting.

 

I hope this helps.

 

Regards,

Brian

View solution in original post

8 REPLIES 8

Brian Bakker
ServiceNow Employee
ServiceNow Employee

Hello @SNDP 

 

To trigger predictions on the incident form can be done several ways. Out-of-box, we provide a BEFORE INSERT business rule "Default Task Based Prediction" on table [task] as a template. If the Classification solution has the Input table [incident], then you should create a new BEFORE INSERT BR on table [incident] using Machine Learning APIs to trigger a prediction. You also need duplicate the Business Rule "Update Prediction Results" and ensure it is created on the same table, as the Classification Solution Input table. This is to ensure predictions are updated in [ml_predictor_results] table with Final Values, once the source record where the prediction was made is made inactive.

 

If you want to avoid scripting a BR, you can also use Machine Learning solutions for Flow Designer, and use a workflow to trigger the prediction on your Classification solution that does not require any scripting.

 

I hope this helps.

 

Regards,

Brian

Thank you @Brian Bakker now the predictions are getting updated in the incident form.

The predictions are updated after the incident form is saved, Is it possible to trigger the prediction in the form as soon as I enter the description of the incident or it will only update once I save it.

Brian Bakker
ServiceNow Employee
ServiceNow Employee

@SNDP 

 

You can also trigger predictions in a form using Client Script/Script Include instead of using a BEFORE INSERT BR. Please review the following Community article -

 

In Predictive Intelligence how to get predicted data in Portal/Client side

 

Regards,
Brian

RVM
Tera Contributor

Hi @SNDP  @Brian Bakker 
is it possible to trigger the prediction in the predictor result table without even saving the record?