IP Library › Granted Patent US 12,373,479
Granted Patent B2
US 12,373,479 · App. 18/338,309 · Granted Jul 29, 2025

Systems and methods for document deviation detection

Inventors: Elizabeth Roman (Somerville, MA); Hella-Franziska Hoffmann (London, GB); Josh Lemaitre (Ipswich, MA); Nikolai Nefedov (Gattikon, CH); David Von Rickenbach (Baar, CH)
Assignee: Thomson Reuters Enterprise Centre GmbH
G06F16/367G06F16/334G06F16/93
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 12,373,479
App. No.
18/338,309
Granted
Jul 29, 2025
Kind
B2
Abstract

The present disclosure is directed towards systems and methods for detecting deviations from a standard document in a document being analyzed. The inventive systems and methods include performing a first level analysis to detect portions of a standard that are identical to, similar to, deleted from, and added to a document being evaluated. A second level analysis may be applied to those portions of the standard that are similar, but not identical to, portions of the document being evaluated to assist a user in identifying similarities and differences between the two portions of text.

Claims (20)

1. A system comprising memory and one or more processors communicatively coupled to the memory, the one or more processors configured to:

determine a deviation between a document and a standard document based on a long string matching analysis configured to obtain an identification of at least one of any identical groupings of text, any similar groupings of text, any groupings of text in the document that have been deleted from the standard document, and any groupings of text in the document that have been added to the standard document,

wherein the long string matching analysis is configured to iteratively increment a string of text from a text grouping from the standard document in a word by word manner within the text grouping such that each string of text within the text grouping is compared between the standard document and the document;

modify, based on the long string matching analysis, one or more visual characteristics of the document to generate a modified version of the document;

compare a deviation detected in the document from the standard document to an accepted deviation previously identified from the standard document in one or more previous documents; and

cause rendering of an interactive graphical interface element associated with the modified version of the document via a user interface of a user computing device, wherein the interactive graphical interface element is configured to (i) display visualization data associated with the modified version of the document, (ii) indicate whether a deviation detected in the document from the standard document has been previously accepted, and (iii) dynamically alter the visualization data based on user input received via the user interface.

2. The system of claim 1 , wherein the one or more processors are further configured to:

determine standard document based on the type of the first document.

3. The system of claim 1 , wherein the one or more processors are further configured to:

determine the deviation between the document and the standard document based on a deviation analysis with respect to any similar groupings of text that are identified to obtain similarity data indicating a degree to which the text grouping from the standard document is similar to a text grouping from the document.

4. The system of claim 3 , wherein the one or more processors are further configured to:

modify the one or more visual characteristics of the document based on the deviation analysis.

5. The system of claim 1 , wherein the one or more processors are further configured to:

perform a textual similarity mapping analysis that compares a number of shared tokens between the text grouping from the standard document and a text grouping from the document.

6. The system of claim 5 , wherein the one or more processors are further configured to:

modify the one or more visual characteristics of the document based on the textual similarity mapping analysis.

7. The system of claim 1 , wherein the one or more processors are further configured to:

perform a textual similarity mapping analysis that compares a number of unique tokens among the text grouping from the standard document and a text grouping from the document.

8. The system of claim 7 , wherein the one or more processors are further configured to:

modify the one or more visual characteristics of the document based on the textual similarity mapping analysis.

Assignments (8)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 28, 2025
From: HOFFMANN, HELLA-FRANZISKA
To: REUTERS LIMITED
Reel/Frame 070362/0228 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 28, 2025
From: LEMAITRE, JOSH
To: THOMSON REUTERS HOLDINGS INC.
Reel/Frame 070362/0492 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 28, 2025
From: NEFEDOV, NIKOLAI
To: THOMSON REUTERS GLOBAL RESOURCES UNLIMITED COMPANY
Reel/Frame 070362/0638 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 28, 2025
From: VON RICKENBACH, DAVID
To: THOMSON REUTERS GLOBAL RESOURCES UNLIMITED COMPANY
Reel/Frame 070362/0689 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 28, 2025
From: ROMAN, ELIZABETH
To: THOMSON REUTERS HOLDINGS INC.
Reel/Frame 070362/0856 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 28, 2025
From: REUTERS LIMITED
To: THOMSON REUTERS GLOBAL RESOURCES UNLIMITED COMPANY
Reel/Frame 070362/0859 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 28, 2025
From: THOMSON REUTERS HOLDINGS INC.
To: THOMSON REUTERS GLOBAL RESOURCES UNLIMITED COMPANY
Reel/Frame 070362/0970 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 28, 2025
From: THOMSON REUTERS GLOBAL RESOURCES UNLIMITED COMPANY
To: THOMSON REUTERS ENTERPRISE CENTRE GMBH
Reel/Frame 070363/0196 →
Continuity (3)
Continuation 16407385 · May 9, 2019
Provisional Application 62669021 · May 9, 2018
Related Publication 20230409623A1 · Dec 21, 2023
References Cited (16)
US 7519607B2 · Anderson · 2009 [cited by applicant]
US 20050010863A1 · Zernik · 2005 [cited by examiner]
US 20120179961A1 · Stollman · 2012 [cited by examiner]
US 20170039176A1 · Broderick · 2017 [cited by examiner]
1 [cited by applicant]
Crochemore et al., “ [cited by applicant]
Asad Sayeed et al: “Characteristics of document similarity measures for compliance analysis”, ACM 18th International Conference on Information and Knowledge Management, CIKM 2009; Nov. 2, 2009 to Nov. 6, 2009; Hong Kong… [cited by applicant]
Marco Lippi et al: “CLAUDETTE: An Automated Detector of Potentially Unfair Clauses in Online Terms of Service”, arxiv.org, Cornell University Library, 201 Olin Library Cornell University. [cited by applicant]
International Search Report and Written Opinion for Application No. PCT/IB2019/053830 dated Sep. 10, 2019. [cited by applicant]
1 [cited by applicant]
Examiner's Report for Canadian Application No. 3,098,644 dated Jan. 20, 2022 (4 pages). [cited by applicant]
Office Action for European Application No. 19732455.1 dated Mar. 15, 2022 (6 pages). [cited by applicant]
2 [cited by applicant]
Wikipedia, API [retrieved from Internet Jun. 28, 2022] https:/en.wikipedia.org/wiki/API (14 pages). [cited by applicant]
LibFLASM: a software library for fixed-length approximate string matching written by Lorraine A.K. Ayad (hereinafter Ayad), Bioinformatics (2016) 17:454 (Year: 2016). [cited by applicant]
Decision to Refuse a European Patent Application for EP Application No. 19732455.1 dated Sep. 19, 2023 (16 pages). [cited by applicant]