US State Supreme Court accelerates case document analytics and reporting with Intelligent Document Processing
State & Local GovernmentBusiness Impacts
500k+
Court documents processed across judgements, petitions and cover sheets
Reduced the turnaround time for searching case-related information from approximately 1 day to less than 2 minutes.
Saved over 45,000 hours of manual effort required to digitize and make case data searchable
Customer Key Facts
- Country : United States
- Industry : State & Local Government
Problem Context
The court needed to prepare a report for the state legislature before the end of the 2024 legislative session, based on specific data points from a large volume of court documents. Given the volume and report deadline, manual review was not an option. It sought a solution to automate the extraction of vital information from three types of documents: civil case cover sheets, petitions, and judgments for all tort suits filed in the district court. By utilizing an automated solution they aimed to mitigate human error associated with manual data entry and receive data for further analysis in a logical and searchable format.
Challenges
- Reviewing case files for specific data points from archives is a time consuming & tedious process
- Difficulty in analyzing case metrics across parishes or judgements
- Requirement for secure data transfer and integration with on-prem database servers
Technologies Used
Amazon SageMaker
Amazon Textract
Amazon Aurora
Amazon DynamoDB
AWS Lambda
Amazon S3
AWS Cloudfront (Caching)
Amazon Api Gateway
Amazon ECR
Solution
Quantiphi utilized QDox, its intelligent document processing solution powered by AWS, to digitize, classify, and extract key information from over 500,000 civil documents, including petitions, judgments, and cover sheets. Through a human-in-the-loop review process, Quantiphi ensured 100% extraction accuracy
Results
- Automated document classification for Cover Sheets, Petitions and Judgements
- Automated extraction of 8 essential data points from case files for courts, parishes, titles etc across printed as well as hand written texts
- Digitized over 500,000 court documents
