IP Library › Granted Patent US 12,254,280

Granted Patent B2

US 12,254,280 · App. 18/378,948 · Granted Mar 18, 2025

Document classification

Inventors: Eric Jon Bersagel (Fort Collins, CO); Sibi Mollykutty Luke (Kerala, IN); Alex Kallolickal Joseph (Tiruvallur, IN)

Assignee: GLOBAL HEALTHCARE EXCHANGE, LLC

G06F40/40

View Patent ↗

Loading inventors, assignments & file history…

Monitor This Case

Get email alerts when status or documents change.

Order Certified Copies

Most orders are placed with the USPTO same day — all within 24 business hours.

Order via The Patent Place →

Pre-filled with this patent's details

Quick Facts

Patent No.: US 12,254,280
App. No.: 18/378,948
Granted: Mar 18, 2025
Kind: B2

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

The system provides the ability to understand the contextual values of an image-based document, regardless of the sender format. The system may analyze the contextual values associated with the different formats and classify the documents based on the contextual values and a business process. The system may provide filters that may be defined by the business process. The system may be adapted for different business process types, input formats and languages. The system may filter out documents that are not intended for a particular business process. The system may also create and send exemption reports about the rejected documents.

Claims (83)

1. A method comprising:

detecting, by one or more processors, one or more languages from different countries in a document;

assigning, by the one or more processors, a weight to the one or more languages from different countries;

determining, by the one or more processors, document content concepts in the document from a bag of words associated with the document, wherein the document content concepts include an attribute of a type of document;

determining, by the one or more processors, that synonyms are associated with the document content concepts, wherein the synonyms include at least one of a wording variation, abbreviation or acronym of the document content concepts that is used to link the synonyms to the document content concepts;

linking, by the one or more processors, the synonyms to the document content concepts;

assigning, by the one or more processors, a weight to each of the document content concepts, wherein the document content concepts include the synonyms to the respective document content concepts;

scoring, by the one or more processors, the document with a classification score based on the weight of each of the document content concepts and the weights of the one or more languages from different countries in the document;

determining, by the one or more processors, that the classification score meets a threshold;

determining, by the one or more processors, a pattern in the document;

determining, by the one or more processors, an object within the pattern in the document;

creating, by the one or more processors, a region around the object using x-y coordinates;

searching, by the one or more processors, in the region for data relevant to the object;

determining, by the processor, that the document lacks personal health information;

determining, by the processor, that the document lacks personal credit information;

determining, by the one or more processors, that one or more rejected keywords are not in the bag of words;

avoiding, by the one or more processors, portions of the document based on an opt-out request;

classifying, by the one or more processors, the document based on the classification score; and

assigning, by the one or more processors, and based on the classifying, the document to at least one of a release report in response to the document being a valid document or an exemption report in response to the document being a rejected document.

2. The method of claim 1 , further comprising at least one of:

receiving, by a processor, the document;

validating, by the processor, at least one of a sender or a receiver of the document;

determining, by the processor, that a number of pages in the document is less than a threshold number of pages;

conducting, by the processor, optical character recognition (OCR) of the document;

storing, by the one or more processors, the bag of words associated with the document, based on the OCR of the document; or

determining, by the processor, that the document exceeds an image clarity threshold.

3. The method of claim 1 , wherein the assigning the weight includes combining the synonyms of each document content concept into the document content concept, then assigning the weight to the document content concept.

4. The method of claim 1 , wherein the document content concept includes at least one of a purchase order, order date, delivery date, address, bill to, ship to, buyer, account number, purchase order table, tax information, terms, total, currency or order confirmation.

5. The method of claim 1 , wherein the supplier provides the rejected keywords.

6. The method of claim 1 , further comprising sending, by the one or more processors, a data packet with data about contents of the document to at least one of a procurement system to initiate a procurement process or an accounts receivable system to initiate an accounts receivable process.

7. The method of claim 1 , further comprising conducting, by the one or more processors, analytics about one or more of the determining steps.

8. The method of claim 1 , further comprising determining, by the one or more processors, that the document includes a pre-determined format.

9. The method of claim 1 , wherein the opt-out request includes avoiding at least one of a terms and conditions (T&C) block of text in the document or avoiding a phrase in the document.

10. The method of claim 1 , wherein the receiving the document further comprises using a listener to monitor for at least one of email, facsimile or web form.

11. The method of claim 1 , further comprising converting, by the one or more processors, the document into a PDF format.

12. The method of claim 1 , further comprising detecting, by the one or more processors, one or more tables in the document, wherein the classifying of the document is further based on the document containing the one or more tables.

13. The method of claim 1 , further comprising determining, by the one or more processors, a country of origin of the document.

14. The method of claim 1 , further comprising determining, by the one or more processors, a country of origin of the document based on at least one of a fax number or email address associated with the document.

15. The method of claim 13 , further comprising implementing, by the one or more processors, at least one of a European process or a United States process, based on the country of origin.

16. The method of claim 1 , further comprising reviewing, by the one or more processors, regions of the document with patterns of data related to at least one of the personal health information or the personal credit information for the determining that the document lacks at least one of the personal health information or the personal credit information.

17. The method of claim 1 , wherein the rejected keywords include global keywords that are common to a plurality of buyers.

18. The method of claim 1 , further comprising performing, by the one or more processors, a different process on the document based on the one or more rejected keywords.

19. An article of manufacture including one or more non-transitory, tangible computer readable storage mediums having instructions stored thereon that, in response to execution by one or more processors, cause the one or more processors to perform operations comprising:

detecting, by the one or more processors, one or more languages from different countries in a document;