US 12,327,424 B2
Systems and methods for intelligent zonal recognition and automated context mapping
Satish Chandra Paled, Hyderabad (IN); Darshil Ajay Parekh, Hyderabad (IN); Shabhari Nath Gampa, Hyderabad (IN); and Sai Krishna Bhargav Veldi, Khammam District (IN)
Assigned to OPEN TEXT HOLDINGS, INC., Menlo Park, CA (US)
Filed by OPEN TEXT HOLDINGS, INC., San Mateo, CA (US)
Filed on Apr. 8, 2022, as Appl. No. 17/716,152.
Claims priority of provisional application 63/313,776, filed on Feb. 25, 2022.
Prior Publication US 2023/0274569 A1, Aug. 31, 2023
Int. Cl. G06V 30/414 (2022.01); G06V 30/412 (2022.01); G06V 30/418 (2022.01)
CPC G06V 30/414 (2022.01) [G06V 30/412 (2022.01); G06V 30/418 (2022.01)] 21 Claims
OG exemplary drawing
 
1. A system for mapping zones in documents with a context, comprising:
a processor;
a non-transitory computer-readable medium comprising instructions for:
receiving a plurality of documents;
identifying key zones in the plurality of documents, the key zones representative of common keys in the plurality of documents, wherein identifying the key zones comprises:
generating a difference image for a pair of example documents of the plurality of documents based on denoised images for the example documents:
consolidating difference images for a plurality of pairs of the example documents;
removing the differences of the consolidated difference image from a denoised threshold image of one of the example documents;
associating key zones and value zones based on their relative positions within the denoised threshold image of the one of the example documents;
identifying values for each common key in each of the plurality of documents based on the associated key zone;
mapping the values for each identified value of each common key to a set of context fields.