From ICIHelp8.1
Revision as of 15:33, 26 August 2019 by IDT-5 (Talk | contribs)

Jump to: navigation, search

Obligation AI

The process of identifying Obligations in an existing Agreement manually is tedious, time consuming and error prone. Obligation Discovery automates this process by applying Natural Language Processing and Machine Learning to this problem. This enables discovery of Obligation from the Agreement without having to read the entire Agreement text by looking up similar Obligations from the Obligations library and automatically extracting key metadata from the discovered Obligations. This feature is available in ICM through a technical configuration.

To view the Obligations in an Agreement: 

1. Click the Obligation Discovery tab on the Agreement Details page. All the Obligations that AI has discovered from the Agreement document are highlighted.

Merge Obligation 1

2. The following actions can be taken on selected Obligation:

  • Click the Confirm to confirm the Obligation.
  • Click Review Later if you are unsure and want to review the Obligation later.
  • Click Metadata to view all the discovered metadata. The number (for example, 10.10) indicates the number of Attributes that are discovered such as Email, Numbers, Date and Time, and so on. 
  • Click Ignore to ignore the Obligation.
  • Click Parent Clause to see the parent Clause that the Obligation is linked to.

To configure Obligation Discovery:

1. Click the Create Agreement tile on the Agreement Management Index page.

2. Select the Category, Contract Type Name and Third Party Type of Paper.

Merge Obligation 2

3. Click Next. The Attributes page opens.

4. Select Discovery AI from the Clause Discovery Type drop-down.

5. Toggle the AI Obligation Discovery Enabled Attribute (Boolean type) to Yes.

Merge Obligation 3

6. Click Next.

Merge Obligation 4

7. Click Create and Publish. It may take some time to discover the Clauses, Obligations, etc.

Merge Obligation 5

8. Click the Clause Discovery tab on the Agreement Details page to see the number of Obligations that a Clause has which is indicated by the yellow icon next to the Clause. Click the icon to view the Obligation that is under the respective Clause.

Merge Obligation 6

9. Click the Obligation Discovery tab on the Agreement Details page. All the Obligations that AI has discovered from the Agreement document are highlighted. The Matched Library Obligations are visible on the right hand side. The top 5 matching options and the relevance are displayed.

Merge Obligation 7

10. Click Confirm to confirm the Obligation.

11. Click Finish to complete the discovery and continue with the workflow as expected. The Obligation Save Confirmation window opens.

12. Click Mark Confirmed, Mark Ignored orCancel as required.

Merge Obligation 8

13. Click Export Obligation Data to export the Obligation information to an Excel file.

Merge Obligation 9

 

Support for Template based discovered Obligations

With the 7.9 release, in addition to the ML based discovery obligations, support for Template based ones are also supported. The user can:

  • Choose the type of discovered obligations to be run for a contract i.e. from a ML based training model or from a predefined set of Templates.
  • Self-train/learn from the ML model internally based on the actions taken by the user on the discovered obligations and display a higher confidence the next time similar obligations are discovered.

To discover Obligations:

1. On the Create Agreement page, enter the Contract Type Name.

2. Select Third Party Type Of Paper.

3. Click Next.

4. On the Attributes page,enter the Attribute details and select ML based from the Obligation Discovery Type drop-down.

5. Click Next. The Obligation Discovery tab will be displayed on the Agreement Details page.

6. View the discovered obligations in the Discovered Obligations Mapped section.

7.Open the MS Excel sheet with the Obligation Template.

8. Select the Agreement on the Agreement Management page.

9. Click Confirm to confirm the discovered obligations or review them later.

 

 

 

Related Topics: AIML | Negotiate AI | Visualize AI