Invention Grant
- Patent Title: Segment-wise prediction machine learning frameworks
-
Application No.: US17805340Application Date: 2022-06-03
-
Publication No.: US12160609B2Publication Date: 2024-12-03
- Inventor: Colum Foley , Paul Ferguson
- 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: H04N19/597
- IPC: H04N19/597 ; G06N20/00 ; H04N19/17 ; H04N19/503

Abstract:
Various embodiments of the present disclosure provide a segment-wise prediction machine learning framework. In one example, an embodiment provides for generating, using a segment-wise prediction machine learning framework, and based at least in part on a document segment for an input segment and a respective predictive code for the input segment, a segment-wise prediction score for the input segment. The segment-wise prediction machine learning framework may comprise a text embedding machine learning model and may be configured to generate a segment-wise prediction score for the input segment based at least in part on a document embedding for the input segment and a code embedding for the respective predictive code for the input segment. Additionally, the text embedding machine learning model may be trained as part of a code prediction machine learning model that is configured to generate, for a particular input document data object, a selected code subset.
Public/Granted literature
- US20230224493A1 SEGMENT-WISE PREDICTION MACHINE LEARNING FRAMEWORKS Public/Granted day:2023-07-13
Information query