US 2023/0145463 A1Published application

Natural language processing operations performed on multi-segment documents

AssigneeOptum Services (Ireland) Limited

InventorsMostafa Bayomi, Ahmed Selim, Kieran O'Donoghue, Michael Bridges, Gregory J. Boss

Life of this patent

Estimating the term…

Loading patent…

Abstract

Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing natural language processing (NLP) operations on multi-segment documents. For example, certain embodiments of the present invention utilize systems, methods, and computer program products that perform NLP operations on multi-segment documents by generating document segmentation machine learning models, using document segmentation machine learning models to determine document segments of input multi-segment documents, enabling adaptive multi-segment summarization of multi-segment documents, and enabling guided interaction with multi-segment documents.

Claims20

Dependent claims

A computer-implemented method comprising:

identifying, by one or more processors, a segment corpus for a segment type of a plurality of segment types of a multi-segment document, wherein:
(i) the plurality of segment types is defined by a segment schema, and
(ii) the segment corpus comprises a document segment of the multi-segment document that is associated with the segment type;
identifying, by the one or more processors, a summarization density hyper-parameter for the segment type, wherein the summarization density hyper-parameter identifies a percentage of the segment corpus to summarize;
generating, by the one or more processors and using a content unit significance prediction machine learning model, an adaptive segment summary for the segment type based at least in part on the segment corpus and the summarization density hyper-parameter;
generating, by the one or more processors, an adaptive multi-segment summary based at least in part on the adaptive segment summary;
and
initiating, by the one or more processors, the performance of one or more summarization-based actions based at least in part on the adaptive multi-segment summary.

5 more elements

An apparatus comprising one or more processors and at least one memory including program code, the at least one memory and the program code configured to, with the one or more processors, cause the apparatus to:

identify a segment corpus for a segment type of a plurality of segment types of a multi-segment document, wherein:
(i) the plurality of segment types are defined by a segment schema, and
(ii) the segment corpus comprises a document segment of the multi-segment document that is associated with the segment type;
identify a summarization density hyper-parameter for the segment type, wherein the summarization density hyper-parameter identifies a percentage of the segment corpus to summarize;
generate, using a content unit significance prediction machine learning model, an adaptive segment summary for the segment type based at least in part on the segment corpus and the summarization density hyper-parameter;
generate an adaptive multi-segment summary based at least in part on the adaptive segment summary;
and
initiate one or more summarization-based actions based at least in part on the adaptive multi-segment summary.

5 more elements

A computer program product comprising at least one non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions configured to:

identify a segment corpus for a segment type of a plurality of segment types of a multi-segment document, wherein:
(i) the plurality of segment types are defined by a segment schema, and
(ii) the segment corpus comprises a document segment of the multi-segment document that is associated with the segment type;
identify a summarization density hyper-parameter for the segment type, the summarization density hyper-parameter identifies a percentage of the segment corpus to summarize;
generate, using a content unit significance prediction machine learning model, an adaptive segment summary for the segment type based at least in part on the segment corpus and the summarization density hyper-parameter;
generate an adaptive multi-segment summary based at least in part on the adaptive segment summary;
and
initiate one or more summarization-based actions based at least in part on the adaptive multi-segment summary.

5 more elements

Dependencies are inferred from the claim text.