# US 2023/0274568 A1 · Systems and methods for intelligent zonal recognition and automated context mapping

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0274568 A1
- Document ID: US20230274568A1
- Status: Published application
- Kind: A1
- Application number: 17/716,148
- Filed: 2022-04-08
- Published: 2023-08-31
- Earliest claimed: 2022-02-25
- Assignees: Open Text Holdings, Inc.
- Applicants: Open Text Holdings, Inc.
- Inventors: Satish Chandra Paled; Darshil Ajay Parekh; Shabhari Nath Gampa; Sai Krishna Bhargav Veldi
- Web page: https://patentgrep.com/patent/US20230274568A1

## CPC

- G06V 30/414: Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
- G06V 30/10: Character recognition
- G06V 30/412: Layout analysis of documents structured with printed lines or input boxes, e.g. business forms or tables
- G06V 30/413: Classification of content, e.g. text, photographs or tables
- G06V 30/418: Document matching, e.g. of document images
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Embodiments of document processing systems and methods for intelligent zonal recognition and context mapping are disclosed. These document processing systems and methods may utilize image processing and heuristic techniques to determine key zones from a minimal set of example documents of a document type and map those key zones to a context definition.

## Claims

### Claim 1

A system, comprising:
a processor;
a non-transitory computer-readable medium comprising instructions for:
receiving a set of example documents of a document type, wherein each of the example documents is an image;
receiving a context definition comprising a set of field definitions, each field definition associated with a label;
determining a set of key zones and associated zonal coordinates for the document type based on the set of example documents by processing the images of the set of example documents to extract the set of key zones;
extracting the key associated with each key zone from a first document of the example document based on the zonal coordinates associated with the determined key zones; and
mapping each of the set of key zones to a corresponding field definition of the context definition based on a comparison of the keys of each key zone and the labels of each of the set of field definitions.

### Claim 2 (depends on 1)

The system of claim 1, wherein the set of key zones are determined by processing the images of the example set of documents to extract a set of values zones associated with the set of example documents, and processing the images of the set of example documents based on the extracted set of value zones to determine the set of key zones.

### Claim 3 (depends on 2)

The system of claim 2, wherein the processing of the images of the set of example documents comprises:
determining an aggregate difference image from the images of the set of example documents, and
extracting the set of values zones from the aggregated difference image.

### Claim 4 (depends on 3)

The system of claim 3, wherein the aggregated difference image is determined by:
determining a pairwise difference image for each pair of images of the set of example documents; and
aggregating the pairwise difference images to form the aggregate difference image.

### Claim 5 (depends on 4)

The system of claim 4, wherein dilation is performed on the aggregated difference image before the set of value zones are extracted.

### Claim 6 (depends on 3)

The system of claim 3, wherein the set of values zones are determined by subtracting the aggregate difference image from a first image for a first example document of the set of example documents.

### Claim 7 (depends on 1)

The system of claim 1, wherein the comparison of the keys of each key zone and the labels of each of the set of field definitions is based on an editing distance between the keys and the labels of the set of field definitions.

### Claim 8

A method, comprising:
receiving a set of example documents of a document type, wherein each of the example documents is an image;
receiving a context definition comprising a set of field definitions, each field definition associated with a label;
determining a set of key zones and associated zonal coordinates for the document type based on the set of example documents by processing the images of the set of example documents to extract the set of key zones;
extracting the key associated with each key zone from a first document of the example document based on the zonal coordinates associated with the determined key zones; and
mapping each of the set of key zones to a corresponding field definition of the context definition based on a comparison of the keys of each key zone and the labels of each of the set of field definitions.

### Claim 9 (depends on 8)

The method of claim 8, wherein the set of key zones are determined by processing the images of the example set of documents to extract a set of values zones associated with the set of example documents, and processing the images of the set of example documents based on the extracted set of value zones to determine the set of key zones.

### Claim 10 (depends on 9)

The method of claim 9, wherein the processing of the images of the set of example documents comprises:
determining an aggregate difference image from the images of the set of example documents, and
extracting the set of values zones from the aggregated difference image.

### Claim 11 (depends on 10)

The method of claim 10, wherein the aggregated difference image is determined by:
determining a pairwise difference image for each pair of images of the set of example documents; and
aggregating the pairwise difference images to form the aggregate difference image.

### Claim 12 (depends on 11)

The method of claim 11, wherein dilation is performed on the aggregated difference image before the set of value zones are extracted.

### Claim 13 (depends on 10)

The method of claim 10, wherein the set of values zones are determined by subtracting the aggregate difference image from a first image for a first example document of the set of example documents.

### Claim 14 (depends on 8)

The method of claim 8, wherein the comparison of the keys of each key zone and the labels of each of the set of field definitions is based on an editing distance between the keys and the labels of the set of field definitions.

### Claim 15

A non-transitory computer readable medium, comprising instructions for:
receiving a set of example documents of a document type, wherein each of the example documents is an image;
receiving a context definition comprising a set of field definitions, each field definition associated with a label;
determining a set of key zones and associated zonal coordinates for the document type based on the set of example documents by processing the images of the set of example documents to extract the set of key zones;
extracting the key associated with each key zone from a first document of the example document based on the zonal coordinates associated with the determined key zones; and
mapping each of the set of key zones to a corresponding field definition of the context definition based on a comparison of the keys of each key zone and the labels of each of the set of field definitions.

### Claim 16 (depends on 8)

The non-transitory computer readable medium of claim 8, wherein the set of key zones are determined by processing the images of the example set of documents to extract a set of values zones associated with the set of example documents, and processing the images of the set of example documents based on the extracted set of value zones to determine the set of key zones.

### Claim 17 (depends on 16)

The non-transitory computer readable medium of claim 16, wherein the processing of the images of the set of example documents comprises:
determining an aggregate difference image from the images of the set of example documents, and
extracting the set of values zones from the aggregated difference image.

### Claim 18 (depends on 17)

The non-transitory computer readable medium of claim 17, wherein the aggregated difference image is determined by:
determining a pairwise difference image for each pair of images of the set of example documents; and
aggregating the pairwise difference images to form the aggregate difference image.

### Claim 19 (depends on 18)

The non-transitory computer readable medium of claim 18, wherein dilation is performed on the aggregated difference image before the set of value zones are extracted.

### Claim 20 (depends on 17)

The non-transitory computer readable medium of claim 17, wherein the set of values zones are determined by subtracting the aggregate difference image from a first image for a first example document of the set of example documents.

### Claim 21 (depends on 15)

The non-transitory computer readable medium of claim 15, wherein the comparison of the keys of each key zone and the labels of each of the set of field definitions is based on an editing distance between the keys and the labels of the set of field definitions.
