Communications Mining Series - Zero to Hero - Session 2

This session is focused on setting up Project, Train Model and Refine Model in Communication Mining platform. We will understand data ingestion, various phases of Model training and best practices.

• Administration

• Manage Sources and Dataset

• Taxonomy

• Model Training

• Refining Models and using Validation

• Best practices

• Q/A

1. UiPath
Southern California Chapter
Communications Mining Series –Session 2

2. 2
1.Introduction
2.UiPath SoCal Chapter
3.Communication Mining Administration
4.Manage Sources and Dataset
5.Taxonomy
6.Model Training
7.Refining Models & Using Validation
8.Best Practices
9.Live Demo
10.Q & A
Agenda

3. 3 3
About UiPath South California Chapter
We are an online and offline community where RPA developers,
professionals and enthusiasts:
-meet each other and share experiences in the RPA industry
-learn together about the challenges they encounter
-build projects and components together and expand upon
automation ideas

4. 4
UiPath
Community Marketing
Manager, Americas, UiPath
Diana Gray
Organizers/Team/Speakers
qBotica
Tech Lead
Devi Kandasamy

5. 5
Communications Mining - Overview

6. 6
Communications Mining - Phases

7. 7
❖Add Communications Mining as a Service
❖Create Project
❖Add User to Project
❖Update User Permissions
❖Remove user from project
❖Quotas
❖Deprecated Models
Communications Mining – Setup & Administration

8. 8
❖Create datasource
❖Upload CSV file into source
❖Using Exchange Integration
Communications Mining – Manage sources

9. 9
❖Headers on the first line delimited by commas or tabs
❖A minimum of three columns are required: the message text contents (the
message), a timestamp, and a unique ID that identifies the message
❖All text fields should be surrounded by double quotes
❖The file must be encoded as either UTF-8, UTF-16, or UTF-32
❖The file should be 64 MiB or less. Split larger file into multiple files
Timestamp format: If format is ambiguous for the order of days / months / years (e.g. 01/02/03 10:10),
suggest the correct interpretation: 2nd of January 2003 –None, 1st of February 2003 -Day first, 3rd of
February 2001 -Year first, 2nd of March 2001 -Day first + Year first
Recommended to supply timestamps in the RFC 3339 format if possible (e.g. 2020-01-31T12:34:56Z
for UTC or with a timezone: 2020-08-031T11:20:60-08:00)
Communications Mining – Upload CSV file

10. 10
❖Sign into Azure Cloud Portal
❖Register an application for Communication Mining and retrieve Application (client) IDand
aDirectory (tenant) ID
❖Create a Client Secret
❖Set API Permissions
❖Give access for service user to the shared mailboxes
❖Create Integration in the platform with Microsoft exchange and fill in the credential details
❖Add Mailboxes
Refer: Communications Mining - Exchange Integration with Azure (uipath.com)
Communications Mining – Exchange Integration with
Azure

11. 11
❖Create dataset
❖Importing Taxonomy
❖Update dataset
❖Delete Message
❖Delete dataset
Communications Mining – Manage Datasets

12. 12
Building your Taxonomy

13. 13
Example Taxonomy

14. 14
Entity Types: Pre-trained vs Trained from scratch

15. 15
Taxonomy – Best Practices

16. 16
Pruning & reorganizing a taxonomy

17. 17
Model Training & Validation

18. 18
Model Training & Validation
Performance Factors
❖All labels-the average performance of all labels in the taxonomy
❖Underperforming labels-the performance of the 10% of labels that
have the most significant performance issues or lowest overall health
❖Coverage-the proportion of messages that are predicted to have at
least one informative label
❖Balance-whether the reviewed data is an effective, balanced
representative of the whole dataset

19. 19
July 10, 2024 -Communications Mining Series - Zero to
Hero - Session 3
Upcoming Sessions

20. 20
Education
Learn RPA Skills
- Free Community Software
- Academy
- Certification
- Academic Alliance
Support
Solve problems
- Forum
- Documentation
- Community Blog
- Use Cases Repository
- Job Board
Network
Grow your career
- Meetups & DevCon
- Mentorship
- Hackathons
- MVP Program
- Automation Champions
An ecosystem enabling
developer success

21. 21
Vibrant ecosystem of more than1.5 million professionals and citizen developers learning, getting
support, and succeeding together in theirautomation careers.
•Start with the free Community Editionto get trained and certified
•Then upgrade to the Enterprise version of the product
A ca demy
Academy
•Get crowdsourced support and share product feedback on UiPath Forum
•Check the product documentation
•Join the Insider Preview for early testing
Forum
Community Events
•Access the latest articles and video tutorialcontent created by community members and
UiPath engineers in our Community Blog
•Contribute as an author.
UiPath Community MVPs
•Get recognized as a Most Valuable Professional (MVP), Automation Champion or one of
the Forum Leaders, based on the contribution to others’ growth
Join the UiPath Community
•Connectwith like-minded people and share best practices with theUiPath Community
•Solve challenges in engaginghackathon competitions
•Join meetups andconferences
Blog and Tutorials
A utoma tion Cloud
Automation Cloud
•Learn the skills of the future on UiPath Academyor through our Academic Alliance
•Earn globally recognized credentials withUiPath Certifications

22. Q & A