This inventor holds 1 USPTO granted patent. Top assignee: Oracle International Corporation. Active years: 2026.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2026
Title: Filip Torjan: Inventor in Document Search and Machine Learning.
Introduction
Filip Torjan is an inventor based in Beroun, Czech Republic. His work includes a patented approach to finding similar documents across different document schemas.
Latest Patents
Torjan is associated with 1 patent, titled “Machine Learning for Similarity Scores Between Different Document Schemas.” The invention describes searching a document repository for documents similar to a source document. It can generate multiple queries based on the source document’s type and combine their results into a unified response. The system can also gather explicit and implicit user feedback about the relevance of search results, then use that feedback to adjust search parameters and improve later searches. In addition, a model may be trained to classify implicit feedback using explicit feedback from users.
Career Highlights
Torjan works at Oracle International Corporation. His patent reflects work at the intersection of machine learning, document search, and feedback-driven improvements to search performance.
Collaborations
Torjan’s listed coworker is Liviu-Sebastian Matei.
Conclusion
Filip Torjan’s patent focuses on using machine learning and user feedback to improve searches for similar documents across different schemas.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile