cisagov / pe-reports

Automated process to build and distribute Posture & Exposure Reports' bi-weekly to customers.
Creative Commons Zero v1.0 Universal
17 stars 6 forks source link

NER(Named Entity Recognition) stakeholder extraction #187

Open cduhn17 opened 2 years ago

cduhn17 commented 2 years ago

💡 Summary

Use NLP to extract executives from stakeholder web page

Motivation and context

The process of gathering executives for a stakeholder is time consuming and error prone and difficult to scale to maintain current executives for all stakeholders.

Implementation notes

This process would requires web scraping the about pages of the stakeholder website and NLP to extract the names of the executives.

Acceptance criteria

How do we know when this work is done?

cduhn17 commented 2 years ago

The NER has been implemented at the accessor in production at the flask UI.