California Department of Justice Office of Attorney General represents the People of State of California. AG office deals with civil and criminal matters before courts of California and the United States.
SoftSol undertook work of document processing and redacting about 3 million documents in six weeks. There were about 60 different codes to retrieve and purge that were all based on a specified date range. The documents in question were generated by hundreds of law enforcement agencies over a period of several decades. Given the non-standardized nature of these documents, locations of offense codes varied significantly. This made it difficult to use any commercially available OCR-based software engines to automatically retrieve this information. To retrieve the specified codes, SoftSol built a custom information retrieval engine that could extract the metadata for the specified codes regardless of its location on document with 95% accuracy.
SOFTSOL Information retrieval and Metadata extraction for US California’s Department of Justice Case Study