Using AI to transform high-volume, confidential, disparate data for the United States Patent Office
Tammy Bilitzky shares a case study that details lights-out automation and explains how DCL uses AI to transform massive volumes of confidential disparate data into searchable and structured information. Along the way, she outlines considerations for architecting a solution that processes a continuous flow of 5M+ pages of complex work units.
| Talk Title | Using AI to transform high-volume, confidential, disparate data for the United States Patent Office |
| Speakers | Tammy Bilitzky (DCL) |
| Conference | O’Reilly Artificial Intelligence Conference |
| Conf Tag | Put AI to Work |
| Location | New York, New York |
| Date | April 16-18, 2019 |
| URL | Talk Page |
| Slides | Talk Slides |
| Video | |
The United States Patent Office (USPTO) experiences a high-volume of patent applications that patent officers must process. Applications comprise a range of data elements, including free text, form fields, handwriting, images, image-based PDFs, and more. The data isn’t searchable or minable for the critical information that the USPTO required to effectively function. Join Tammy Bilitzky to learn how DCL implemented artificial intelligence to identify, classify, structure, and return large datasets back to the USPTO in a lights-out production process. Spoiler alert: The system continues to achieve a 99.6% accuracy rate with zero human intervention. Topics include:
