Challenges
- The client, an energy firm, wanted to be able search contracts, identify key words, and draw connections between documents.
- The system needed to collect document data.
- Key phrases and clauses needed to be extracted from the contract.
- The software had to be able to read and recognize ID documentation.
Xpertnest’s Solutions
- Xpertnest built a scraping tool to create a dataset from legal documents on the company website.
- Software cleaned the images and documents, and annotated them for Named Entity Recognition (NER).
- NER models were trained using annotated data and ID types for document organization.
Value Delivered
- Faster, more efficient document searching has generated significant savings in time and cost.
- Document digitalization allows multiple team members to work on the same document at same time.
- NER has reduced the risk of human errors.
- Easy document maintenance lowers the risk of file corruption.
