公开(公告)号：US12217013B2

公开(公告)日：2025-02-04

申请号：US17937616

申请日：2022-10-03

Applicant: UnitedHealth Group Incorporated

Inventor： Rajesh Sabapathy ,  Chirag Mittal ,  Gourav Awasthi ,  Aditya Teja Josyula

IPC: G06F40/56 ,  G06F40/247 ,  G06F40/30 ,  G06F40/35 ,  G06N5/022

Abstract: There is a need for more effective and efficient predictive natural language summarization. This need is addressed by applying hybrid extractive and abstractive summarization techniques in a unique processing pipeline to generate a cohesive and comprehensive summary of a multi-party interaction. A method for generating the summary of a multi-party interaction includes receiving a multi-party interaction transcript data object comprising a plurality of interaction utterances from at least two participants; using an extractive summarization model to identify a key sentence of the multi-party interaction transcript data object; identifying an interaction utterance from the multi-party interaction transcript data object that corresponds to the key sentence; generating a contextual summary for the multi-party interaction transcript data object based at least in part on the interaction utterance; and generating a reported contextual summary for the multi-party interaction transcript data object based at least in part on the contextual summary.

公开(公告)号：US20230385557A1

公开(公告)日：2023-11-30

申请号：US17938089

申请日：2022-10-05

Applicant: UnitedHealth Group Incorporated

Inventor： Rajesh Sabapathy ,  Chirag Mittal ,  Gourav Awasthi ,  Aditya Teja Josyula ,  Ankur Gulati ,  Lubna Khan ,  Tarun Bansal

IPC: G06F40/40 ,  G06F40/186 ,  G06F16/34

CPC classification number: G06F40/40 ,  G06F40/186 ,  G06F16/345

Abstract: As described herein, various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for performing natural language processing operations for generating guided summaries using summarization templates that are mapped to hybrid classes of a hybrid classification space for a hybrid classification machine learning model. In some embodiments, by using summarization templates, a proposed summarization framework is able to vastly reduce the computational complexity of performing summarization on an input document data object, such as an input multi-party communication transcript data object, by defining the set of dynamic data fields that apply to the input document data object based at least in part on an assigned class/category of the input document data object.