NLU TRAINING WITH USER CORRECTIONS TO ENGINE ANNOTATIONS
First Claim
Patent Images
1. A method comprising:
- generating one or more medical billing codes for a free-form text documenting a clinical patient encounter and one or more links between each medical billing code and a corresponding portion of the free-form text by applying a natural language understanding engine implemented on a processor to the free-form text;
receiving, from one or more human users, one or more corrections to the one or more medical billing codes and/or the one or more links;
generating a finalized sequence of medical billing codes for the clinical patient encounter by applying the one or more corrections to the one or more medical billing codes and/or the one or more links; and
providing training data to the natural language understanding engine in the form of at least the free-form text, the one or more corrections, and the finalized sequence of medical billing codes.
3 Assignments
0 Petitions
Accused Products
Abstract
Techniques for training a natural language understanding (NLU) engine may include generating a first annotation of free-form text documenting a healthcare patient encounter and a link between the first annotation and a corresponding portion of the text, using the NLU engine. A second annotation of the text and a link between the second annotation and a corresponding portion of the text may be received from a human user. The first annotation and its corresponding link may be merged with the second annotation and its corresponding link. Training data may be provided to the engine in the form of the text and the merged annotations and links.
44 Citations
20 Claims
-
1. A method comprising:
-
generating one or more medical billing codes for a free-form text documenting a clinical patient encounter and one or more links between each medical billing code and a corresponding portion of the free-form text by applying a natural language understanding engine implemented on a processor to the free-form text; receiving, from one or more human users, one or more corrections to the one or more medical billing codes and/or the one or more links; generating a finalized sequence of medical billing codes for the clinical patient encounter by applying the one or more corrections to the one or more medical billing codes and/or the one or more links; and providing training data to the natural language understanding engine in the form of at least the free-form text, the one or more corrections, and the finalized sequence of medical billing codes. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A computer-readable storage medium having instructions that, when executed by a processor, cause performance of a method comprising:
-
generating one or more medical billing codes for a free-form text documenting a clinical patient encounter and one or more links between each medical billing code and a corresponding portion of the free-form text by applying a natural language understanding engine implemented on a processor to the free-form text; receiving, from one or more human users, one or more corrections to the one or more medical billing codes and/or the one or more links; generating a finalized sequence of medical billing codes for the clinical patient encounter by applying the one or more corrections to the one or more medical billing codes and/or the one or more links; and providing training data to the natural language understanding engine in the form of at least the free-form text, the one or more corrections, and the finalized sequence of medical billing codes. - View Dependent Claims (9, 10, 11, 12, 13, 14)
-
-
15. A system, comprising:
-
a processor; and a memory coupled to the processor and storing computer-readable instructions which, when executed by the processor, cause performance of a method comprising; generating one or more medical billing codes for a free-form text documenting a clinical patient encounter and one or more links between each medical billing code and a corresponding portion of the free-form text by applying a natural language understanding engine to the free-form text; receiving, from one or more human users, one or more corrections to the one or more medical billing codes and/or the one or more links; generating a finalized sequence of medical billing codes for the clinical patient encounter by applying the one or more corrections to the one or more medical billing codes and/or the one or more links; and providing training data to the natural language understanding engine in the form of at least the free-form text, the one or more corrections, and the finalized sequence of medical billing codes. - View Dependent Claims (16, 17, 18, 19, 20)
-
Specification