Edit

Run cognitive Business Process

Control Tower comes with two default use cases for Classification and Information Extraction tasks. These use cases can be used as examples for cognitive automation setup.

Below, you can find a step-by-step instruction on how to set up and run default use cases with automation.

The instruction can be used as an integration test for the cognitive automation setup check.

Check assets

Before creating automated Manual Tasks and Processes, you need to check that your Control Tower has all the Training Sets and Use Cases needed for Cognitive automation.

Training Sets

Go to the Main menu (left sidebar) > Campaigns > Automation Training Sets and check that Training Sets with the following names exist:

• classification_cognitive_automation_training_set_<wf_version>
• ie_cognitive_automation_training_set_<wf_version>

Data Stores

Go to the Main menu (left sidebar) > Campaigns > Data Stores.

Download the following Data Stores as CSV files:

• classification_cognitive_automation_input_data_<wf_version>
• ie_cognitive_automation_input_data_<wf_version>

These CSV files are used as input data for Manual Task and Cognitive BP.

Use Cases

Go to the Main menu (left sidebar) > Configuration > Use Cases.

On the Business Process tab, check that the following Use Case is present: Cognitive Automation Business Process <wf_version>

On the Manual tab, check that the following Use Cases are present:

• IE Cognitive Automation Task <wf_version>
• Classification Cognitive Automation Task <wf_version>

Hypermodels on S3

Open the S3 (cloud or on-premise) > the vds-models bucket.

Check that the following folders contain hypermodels with appropriate version (subfolders):

• presentation-company-classification-model
• presentation-information-extraction

Test cognitive automation

If all assets are available, you are ready to create a Manual Task, start model training, and extraction.

The guide shows the Classification use case example, but you can also use the Information Extraction (IE) example – just select appropriate Use Case, Hypermodel, and Training Set.

Create Manual Task

1. Go to Manual Tasks > Create Manual Task.

2. Select Cognitive Automation Use Cases > Classification Cognitive Automation Task <wf_version>.

   

3. Click Select this Use Case.

4. On the Data tab, click Upload Data, and select a CSV file downloaded from the classification_cognitive_automation_input_data_<wf_version> Data Store.

   

5. On the Run tab, click Advanced Options > the Automation tab:

   

   1. Select an ML Model: Presentation Company Classification
   2. Select a BP Use Case: Cognitive Automation Business Process <wf_version>
   3. Select a Training Set: classification_cognitive_automation_training_set_<wf_version>

   The resulting page looks like this one:

   

   4. Reset the Training Set by clicking the arrow icon and Reset Data Status.

   

   Confirm by clicking Reset.

   

   5. Click OK and save the Task.

Start Training Process

Now, you are ready to start the Training process:

1. On the Run tab, click Run This Task.

2. In the Actions dropdown, click Stop.

3. In the Actions dropdown, click Evaluate Automation > Continue.

4. Go to List of BPs, select the Automation Training filter and check that Automation BP was created and training was started.

   

5. The training BP should have records that passed the Training branch.

   

6. (Optional) Check Mesos for message_** jobs present for the vds user.

7. Go to View All Manual Tasks:

   1. Your Task should have the AUTOMATION EVALUATION label.

   

   2. Wait until the training is finished (~10 minutes for classification). Your task should have the AUTOMATION AVAILABLE label.

   

Set up Automation Chart

1. Click the AUTOMATION AVAILABLE label. You are redirected to the Automation tab.

   

2. Set the Accuracy Threshold.

3. Click the Apply Recommendation button. You are redirected to the Cognitive Business Process creation wizard.

Run Cognitive Business Process

1. Upload the same input data CSV downloaded from the classification_cognitive_automation_input_data_<wf_version> Data Store. You can also use the CSV file downloaded from the classification_cognitive_automation_training_set_<wf_version> Training Set, but this requires more time for extraction.

2. Run the Cognitive Automation BP.

3. Check the BP Results. Record(s) should pass the Extract step.

   1. BP Design tab:

   

   2. Results > Data: