US 11,900,289 B1
Structuring unstructured data via optical character recognition and analysis
Manoranjan Kumar, San Francisco, CA (US); Stacy R. Henryson, Clive, IA (US); Richard Penfil, II, San Francisco, CA (US); Nikhil Jog, San Francisco, CA (US); Bradley Miller, San Francisco, CA (US); and Matthew D. Wilson, San Francisco, CA (US)
Assigned to WELLS FARGO BANK, N.A., San Francisco, CA (US)
Filed by Wells Fargo Bank, N.A., San Francisco, CA (US)
Filed on Oct. 30, 2020, as Appl. No. 17/085,249.
Int. Cl. G06Q 10/06 (2023.01); G06Q 10/0631 (2023.01); G06F 16/93 (2019.01); G06F 16/25 (2019.01); G06V 30/41 (2022.01); G06V 30/19 (2022.01)
CPC G06Q 10/06315 (2013.01) [G06F 16/258 (2019.01); G06F 16/93 (2019.01); G06V 30/41 (2022.01); G06V 30/19 (2022.01)] 19 Claims
OG exemplary drawing
 
1. A method of analyzing unstructured data, the method comprising:
accessing, via a processor, from a document database, a plurality of electronic documents, each electronic document associated with a type of product;
generating, via the processor, a respective data instance for each of the plurality of electronic documents, the respective data instance comprising a plurality of data fields that are generated based on the type of product;
transforming, via the processor, data of the plurality of electronic documents into a plurality of values for each of the plurality of data fields, wherein transforming the data of the plurality of electronic documents comprises applying a respective character recognition algorithm to the plurality of electronic documents;
generating, via the processor, a confidence factor for each of the plurality of values, wherein the confidence factor for a respective value of the plurality of values is calculated based on a number of characters of a respective keyword in a respective electronic document associated with the respective value that match corresponding characters of an expected keyword;
storing, via the processor, the respective data instance for each of the plurality of electronic documents comprising the one or more values for each of the plurality of data fields within a second database in association with the confidence factor of each of the plurality of values;
presenting, via the processor, a first graphical user interface comprising (i) a first interactive element enabling selection of at least one category for a report, (ii) a second interactive element enabling selection of at least one summary variable for the report, and (iii) a third interactive element causing generation of the report; and
in response to an interaction with the third interactive element, generating, via the processor, a second graphical user interface comprising the report generated using at least two of the plurality of data instances of the plurality of electronic documents, the at least two data instances selected based on the at least one category selected via the first interactive element and the at least one summary variable selected via the second interactive element.