US 11,775,866 B2
Automated document filing and processing methods and systems
Gordon Scott Paterson, Toronto (CA); Michael Bradley, Toronto (CA); Brad Rosenberg, Toronto (CA); and Ka Fu Ko, Mississauga (CA)
Assigned to Future Vault Inc., Toronto (CA)
Filed by FutureVault Inc., Toronto (CA)
Filed on Dec. 1, 2020, as Appl. No. 17/108,377.
Application 17/108,377 is a continuation of application No. 15/693,584, filed on Sep. 1, 2017, granted, now 10,884,979.
Claims priority of provisional application 62/383,284, filed on Sep. 2, 2016.
Prior Publication US 2021/0149839 A1, May 20, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/13 (2019.01); G06N 20/00 (2019.01); G06F 16/185 (2019.01); G06F 16/31 (2019.01); G06F 16/93 (2019.01); G06F 40/14 (2020.01); G06F 40/114 (2020.01); G06F 40/137 (2020.01); G06F 40/205 (2020.01)
CPC G06N 20/00 (2019.01) [G06F 16/13 (2019.01); G06F 16/185 (2019.01); G06F 16/313 (2019.01); G06F 16/93 (2019.01); G06F 40/114 (2020.01); G06F 40/137 (2020.01); G06F 40/14 (2020.01); G06F 40/205 (2020.01)] 18 Claims
OG exemplary drawing
 
1. A system for automatic ingestion and filing of documents, the system comprising:
a database, the database having a plurality of folder levels within a hierarchy and a plurality of file locations of previously stored documents, wherein each file location of the plurality of file locations is associated with any one of the plurality of folder levels; and
a processor configured to:
store a plurality of stored keywords based on the previously stored documents, wherein each of the plurality of stored keywords is associated with at least one of the plurality of file locations, wherein a selected keyword in the plurality of stored keywords is associated with at least two of the plurality of file locations, wherein a first location of the at least two of the plurality of file locations has a first location-specific weighting indicating a relevance of the first location to the selected keyword, and wherein a second location of the at least two of the plurality of file locations has a second location-specific weighting indicating a relevance of the second location to the selected keyword;
receive a document containing one or more document keywords;
compare the one or more document keywords to the plurality of stored keywords;
based on the comparing, generate a ranked plurality of suggested file locations for the document, wherein the generating the ranked plurality comprises, for each element of the one or more document keywords:
generating a respective keyword score for the element, wherein the respective keyword score is based on a similarity measure between any selected one of the plurality of stored keywords and the element;
adding the at least one file location associated with the selected one to the ranked plurality in association with the element; and
ranking the at least one file location associated with the element in the ranked plurality according to the respective keyword score of the element and, when the selected one is the selected keyword, modifying the ranking of the first location based on the first location-specific weighting, and modifying the ranking of the second location based on the second location-specific weighting.