Invention Grant
- Patent Title: Predictive data analysis techniques using bidirectional encodings of structured data fields
-
Application No.: US16915135Application Date: 2020-06-29
-
Publication No.: US12131229B2Publication Date: 2024-10-29
- Inventor: Louise O'Connor , Giorgio Mondauto , David Walsh , Rachel Costello , Darragh Hanley
- Applicant: Optum Services (Ireland) Limited
- Applicant Address: IE Dublin
- Assignee: Optum Services (Ireland) Limited
- Current Assignee: Optum Services (Ireland) Limited
- Current Assignee Address: IE Dublin
- Agency: Alston & Bird LLP
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06N20/00 ; G06N5/045

Abstract:
There is a need for more effective and efficient predictive data analysis based at least in part on structured data. This need can be addressed by, for example, solutions for performing predictive data analysis using bidirectional encoder deep learning models that are configured to process structured data attributes. In one example, a method includes identifying a group of training structured data fields; generating a group of per-field tokenized values for each training structured data field; generating a bidirectional encoder deep learning model based at least in part on each group of per-field tokenized values for a training structured data field; and performing one or more prediction-based actions based at least in part on the trained bidirectional encoder deep learning model.
Public/Granted literature
- US20210406739A1 PREDICTIVE DATA ANALYSIS TECHNIQUES USING BIDIRECTIONAL ENCODINGS OF STRUCTURED DATA FIELDS Public/Granted day:2021-12-30
Information query