Citation and policy based document classification

Patent metadata

Field	Value
Publication number	US-12456086-B2
Application number	US-202418584600-A
Country	US
Kind code	B2
Filing date	Feb 22, 2024
Priority date	Jun 11, 2020
Publication date	Oct 28, 2025
Grant date	Oct 28, 2025

Abstract

Disclosed herein are system, method, and computer program product embodiments for rapid identification and access to relevant regulatory documents. A data model relating regulatory mandates and requirements to citations appearing within an enforcement document is used to rapidly access specific citations within an enforcement document. In the case of image-based enforcement documents, the originality of these documents is preserved while allowing a user to see where the relevant citations appear in the document images. The relevant citations are further compared to business policies to identify potential impacts of regulatory mandates and requirements.

First claim

What is claimed is:

1. A method, comprising:
extracting, by at least one processor, a citation from a first enforcement document;
mapping, by the at least one processor, the extracted citation to a regulatory requirement of a mandate in accordance with a data model;
parsing, by the at least one processor, the extracted citation into first one or more sub-citations; and
classifying, by the at least one processor, the first enforcement document based on a level of matching between the first one or more sub-citations and second one or more sub-citations of a reference citation identified in a business policy document responsive to the regulatory requirement mapped to the extracted citation.

2. The method of claim 1 , further comprising:
identifying, by the at least one processor, a second enforcement document sharing one or more citations with the first enforcement document;
presenting, by the at least one processor, a link to the second enforcement document in a user interface.

3. The method of claim 1 , further comprising:
extracting, by the at least one processor, one or more fine amounts from the first enforcement document, wherein the one or more fine amounts correspond to the extracted citation;
removing, by the at least one processor, at least one duplicate fine amount from the one or more fine amounts to form a set of fine amounts; and
combining, by the at least one processor, the set of fine amounts into a total fine amount corresponding to the extracted citation.

4. The method of claim 3 , further comprising:
determining, by the at least one processor, a score describing an impact of the first enforcement document on a business based on one or more of the business policy document, the extracted citation, the classification of the first enforcement document, text in the first enforcement document relating to the extracted citation, or the total fine amount corresponding to the extracted citation; and
in response to the score being greater than a threshold, presenting, by the at least one processor, a summary of the impact of the first enforcement document on the business, wherein the summary comprises one or more of a link to the business policy document, the extracted citation, a link to a reference document described by the extracted citation, the classification of the first enforcement document, a link to the first enforcement document, or the score.

5. The method of claim 1 , wherein extracting the citation from the first enforcement document comprises:
comparing, by the at least one processor, a citation key to text in the first enforcement document, wherein the citation key comprises a first string of characters;
generating, by the at least one processor, a similarity score between the first string of characters and a second string of characters in the text from the first enforcement document, wherein the similarity score weights each character in the first string of characters based on its position in the citation key; and
extracting, by the at least one processor, the second string of characters from the first enforcement document when the similarity score is greater than a threshold.

6. The method of claim 5 , further comprising:
marking, by the at least one processor, the second sting of characters extracted from the first enforcement document as a false positive in response to determining that the second string of characters is not related to a regulatory action.

7. The method of claim 5 , further comprising:
marking, by the at least one processor, the second string of characters extracted from the first enforcement document as a citation extraction error in response to determining that the second string of characters differs from the first string of characters in the citation key by at least one character.

8. The method of claim 1 , wherein:
the first one or more sub-citations comprises a first root and a first sub-section;
the second one or more sub-citations comprises a second root and a second sub-section; and
classifying the first enforcement document based on the level of matching between the first one or more sub-citations and the second one or more sub-citations comprises:
in response to the first one or more sub-citations matching the second one or more sub-citations, classifying the first enforcement document as an exact match for the business policy document;
in response to the first root matching the second root and the first sub-section matching the second sub-section, classifying the first enforcement document as a sub-section match for the business policy document;
in response to the first root matching the second root and the first sub-section being different than the second sub-section, classifying the first enforcement document as a root match for the business policy document; and
in response to the first root being different than the second root, classifying the first enforcement document as a non-match for the business policy document.

9. A non-transitory computer-readable storage medium having instructions stored thereon that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
extracting a citation from a first enforcement document;
mapping the extracted citation to a regulatory requirement of a mandate in accordance with a data model;
parsing the extracted citation into first one or more sub-citations;
classifying the first enforcement document based on a level of matching between the first one or more sub-citations and second one or more sub-citations of a reference citation identified in a business policy document responsive to the regulatory requirement mapped to the extracted citation.

10. The non-transitory computer-readable storage medium of claim 9 , the operations further comprising:
identifying a second enforcement document sharing one or more citations with the first enforcement document;
presenting a link to the second enforcement document in a user interface.

11. The non-transitory computer-readable storage medium of claim 9 , the operations further comprising:
extracting one or more fine amounts from the first enforcement document, wherein the one or more fine amounts correspond to the extracted citation;
removing at least one duplicate fine amount from the one or more fine amounts to form a set of fine amounts; and
combining the set of fine amounts into a total fine amount corresponding to the extracted citation.

12. The non-transitory computer-readable storage medium of claim 11 , the operations further comprising:
determining a score describing an impact of the first enforcement document on a business based on one or more of the business policy document, the extracted citation, the classification of the first enforcement document, text in the first enforcement document relating to the extracted citation, or the total fine amount corresponding to the extracted citation; and
in response to the score being greater than a threshold, presenting a summary of the impact of the first enforcement document on the business, wherein the summary comprises one or more of a link to the business policy document, the extracted citation, a link to a reference document described by the extracted citation, the classification of the first enforcement document, a link to the first enforcement document, or the score.

13. The non-transitory computer-readable storage medium of claim 11 , wherein extracting the citation from the first enforcement document comprises:
comparing a citation key to text in the first enforcement document, wherein the citation key comprises a first string of characters;
generating a similarity s

Assignees

• Capital One Services Llc

Inventors

• Demchalk Chris
• Parker Ryan M
• Kumar Lokesh Vijay
• Fromknecht Brian

Classifications

• G06V30/418

  Document matching, e.g. of document images · CPC title

• G06V30/416

  Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors · CPC title

• G06F16/951

  Indexing; Web crawling techniques · CPC title

• G06F16/345

  Summarisation for human users · CPC title

• G06F40/30

  Semantic analysis · CPC title