Section-linked document classifiers

Patent metadata

Field	Value
Publication number	US-11972195-B2
Application number	US-202217692846-A
Country	US
Kind code	B2
Filing date	Mar 11, 2022
Priority date	Jun 11, 2020
Publication date	Apr 30, 2024
Grant date	Apr 30, 2024

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.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
generating, by one or more computing devices, a modifiable version of an enforcement document obtained from document sources that include enforcement-related content, wherein the enforcement document is parsed to extract a corresponding enforcement action;
mapping, by the one or more computing devices, a citation within the modifiable version of the enforcement document to a requirement in accordance with a data model;
presenting, by the one or more computing devices, a list of requirements including the requirement, wherein the list of requirements is associated with a mandate through the data model;
linking, by the one or more computing devices, the enforcement document to the requirement presented in the list of requirements;
presenting, by the one or more computing devices, the enforcement document linked to the requirement in a viewer, responsive to selection of the requirement from the list of requirements; and
presenting, in the viewer, by the one or more computing devices, a portion of text within the enforcement document as relevant to the requirement, wherein the portion of text comprises a citation associated with the mandate or the requirement.

2. The computer-implemented method of claim 1 , wherein the enforcement document is received as an image-based document, the method further comprising:
performing, by the one or more computing devices, optical character recognition (OCR) on the image-based document to generate the modifiable version of the enforcement document as a text-based document from the image-based document;
receiving, by the one or more computing devices, the selection of the requirement from the list of requirements; and
presenting, by the one or more computing devices, the text-based document in the viewer to include at least the portion of text with the citation associated with the mandate or the requirement highlighted.

3. The computer-implemented method of claim 2 , further comprising:
presenting, by the one or more computing devices, a stream of the image-based document in the viewer by presenting a page of the image-based document corresponding to a page of the text-based document, wherein the image-based document and the text-based document are presented concurrently.

4. The computer-implemented method of claim 1 , further comprising:
generating, by the one or more computing devices, a summary of the enforcement document based on the modifiable version of the enforcement document.

5. The computer-implemented method of claim 4 , further comprising:
receiving, by the one or more computing devices, an additional document corresponding to the enforcement action;
mapping, by the one or more computing devices, the enforcement document and the additional document to the enforcement action in accordance with the data model; and
displaying, by the one or more computing devices, a summary page including the summary of the enforcement document and links to access the enforcement document and the additional document, wherein the links are determined via the data model based on the mapping of the enforcement document and the additional document to the enforcement action.

6. The computer-implemented method of claim 5 , wherein generating the modifiable version of the enforcement document corresponding to the enforcement action comprises:
connecting, by the one or more computing devices, to a repository of enforcement documents; and
scraping, by the one or more computing devices, the repository to obtain the enforcement document responsive to the addition of the additional document to the repository.

7. A system, comprising:
a memory configured to store operations; and
one or more processors configured to perform the operations, the operations comprising:
generating a modifiable version of an enforcement document obtained from document sources that include enforcement-related content, wherein the enforcement document is parsed to extract a corresponding enforcement action;
mapping a citation within the modifiable version of the enforcement document to a requirement in accordance with a data model;
presenting a list of requirements including the requirement, wherein the list of requirements is associated with a mandate through the data model;
linking the enforcement document to the requirement presented in the list of requirements;
presenting the enforcement document linked to the requirement in a viewer, responsive to selection of the requirement from the list of requirements; and
presenting, in the viewer, a portion of text within the enforcement document as relevant to the requirement, wherein the portion of text comprises a citation associated with the mandate or the requirement.

8. The system of claim 7 , wherein the enforcement document is obtained by identifying fields within a markup language document that contain relevant text.

9. The system of claim 7 , further comprising a pattern recognition component configured to identify regulatory citations in the enforcement document.

10. The system of claim 9 , wherein the pattern recognition component is further configured to identify other patterns in the enforcement document for association with a regulatory requirement.

11. The system of claim 7 , further comprising a phrase extraction component configured to perform phrase extraction of the enforcement document.

12. The system of claim 7 , further comprising a summarization component configured to generate a summary of the enforcement document.

13. The system of claim 7 , further comprising a document tagging component configured to classify the enforcement document according to the requirements and mandates associated with enforcement actions within the enforcement document.

14. The system of claim 7 , wherein the enforcement document is received as an image-based document, the operations further comprising:
performing optical character recognition (OCR) on the image-based document to generate the modifiable version of the enforcement document as a text-based document from the image-based document;
receiving the selection of the requirement from the list of requirements; and
presenting the text-based document in the viewer to include at least the portion of text with the citation associated with the mandate or the requirement highlighted.

15. The system of claim 14 , further comprising:
presenting a stream of the enforcement document in the viewer comprising presenting a page of the image-based document corresponding to a page of the text-based document, wherein the image-based document and the text-based document are presented concurrently.

16. The system of claim 7 , the operations further comprising:
receiving an additional enforcement document corresponding to the enforcement action;
mapping the enforcement document and the additional enforcement document to the enforcement action in accordance with the data model; and
displaying a summary page including a summary of the enforcement document and links to access the enforcement document and the additional enforcement document, wherein the links are determined via the data model based on the mapping of the enforcement document and the additional enforcement document to the enforcement action.

17. A computer readable storage device having instructions stored thereon, execution of which, by one or more processing devices, causes the one or more processing devices to perform operations comprising:
generating a modifiable version of an enforcement document obtained from document sources that incl

Assignees

• Capital One Services Llc

Inventors

• Kumar Lokesh Vijay
• Raju Poornima Bagare
• Parker Ryan M
• Fromknecht Brian
• Demchalk Chris

Classifications

• G06F40/106 Primary

  Display of layout of documents; Previewing · CPC title

• G06F3/0482

  Interaction with lists of selectable items, e.g. menus · CPC title

• G06F16/345

  Summarisation for human users · CPC title

• G06F16/94

  Hypermedia (Hyperlinking G06F40/134) · CPC title

• G06F16/9558

  Details of hyperlinks; Management of linked annotations · CPC title