US 11,989,500 B2
Framework agnostic summarization of multi-channel communication
Zhewen Fan, San Diego, CA (US); Farzaneh Khoshnevisan, San Diego, CA (US); Byungkyu Kang, San Diego, CA (US); Yingxin Wang, Newark, CA (US); and Sonia Sharma, Fremont, CA (US)
Assigned to Intuit Inc., Mountain View, CA (US)
Filed by INTUIT INC., Mountain View, CA (US)
Filed on Aug. 22, 2023, as Appl. No. 18/453,772.
Application 18/453,772 is a continuation of application No. 17/937,086, filed on Sep. 30, 2022, granted, now 11,783,112.
Prior Publication US 2024/0111941 A1, Apr. 4, 2024
Int. Cl. G06F 40/106 (2020.01); G06F 16/34 (2019.01); G06F 40/205 (2020.01)
CPC G06F 40/106 (2020.01) [G06F 16/345 (2019.01); G06F 40/205 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A method for improved automated parsing and display of electronic documents, comprising:
determining, for a first electronic document, based on a type of the first electronic document, to use a rules-based model and not a machine learning model for formatting the first electronic document, wherein:
the rules-based model comprises one or more rules related to one or more keywords in the first electronic document, and
the machine learning model is configured to analyze vectors representing text in a document and respective vectors representing keywords associated with topics;
identifying a set of topics in the first electronic document using the rules-based model;
determining, for a second electronic document, based on a respective type of the second electronic document, to use a technique involving the machine learning model for formatting the second electronic document;
providing one or more inputs to the machine learning model based on the second electronic document;
receiving, from the machine learning model in response to the one or more inputs, one or more outputs related to formatting the second electronic document for display;
generating a formatted version of the first electronic document based on the set of topics;
generating a formatted version of the second electronic document based on the one or more outputs; and
displaying the formatted version of the first electronic document and the formatted version of second electronic document via a user interface.