Data analysis

Task Mining is integrated with AI Center to run the machine learning model and analyze the dataset.

For a Data Analysis, the datasets you upload should contain at least 10,000 actions, but we recommend 50K actions as a good baseline. The model can support up to 200K actions collected in a given project. As a quick way of estimating, an active user typically provides 200-1K actions per hour, depending on the scenario they are recording.

To run the analysis, follow the below steps. Knowledge of data science techniques is NOT required as the model takes care of this for you.

1. Log in with your Cloud account and access the AI Center service.
   
   

   

   
   
2. Click the project where the dataset was uploaded.
   Warning: Please be careful when deleting a dataset, the data won't be recovered after deletion.

   
   

   

   
   
3. Click ML Packages > Out of the box Packages.
   
   

   

   
   
4. Select the UiPath Task Mining package.
   
   

   

   
   
5. Select TMAnalyzerModel and click Submit.
   Note: Please always select the latest version of the model packages.

   
   

   

   
   
6. Name the package, choose the most recent package version, and click Submit to create a machine-learning deployment package.
   
   

   

   
   
7. Access Pipelines and click Create new to create a new pipeline that runs the Task Mining model.
   
   

   

   
   
8. Select Evaluation Run for the Pipeline type. Select the package you created in step 6, its minimum and maximum versions.
   
   

   

   
   
9. Select the dataset to execute analysis on.
   Note: Make sure you select the entire dataset. Selecting user folders in the dataset would cause analysis to fail.

   
   

   

   
   
10. Make sure 'Run Now' is selected and click 'Create' to run the pipeline.
    Warning: Please do not enable GPU run as this will cause an error.
11. A Task Mining pipeline is deployed and starts running the analysis. Execution time will depend on the dataset size.
12. When the model run is complete a notification email is sent. The analysis results are uploaded automatically to the Task Mining project.