Systems and methods for censoring text inline

Patent metadata

Field	Value
Publication number	US-12379975-B2
Application number	US-202217836614-A
Country	US
Kind code	B2
Filing date	Jun 9, 2022
Priority date	Jul 6, 2018
Publication date	Aug 5, 2025
Grant date	Aug 5, 2025

Abstract

Systems and methods for censoring text-based data are provided. In some embodiments a censoring system may include at least one processor and at least one non-transitory memory storing application programming interface instructions. The censoring system may be configured to perform operations comprising storing a target pattern type and a computer-based model for identifying a target data pattern corresponding to a target pattern type within text based data. The censoring system may also be configured to receive text-based data by a server, and to retrieve the stored target pattern type to be censored in the text-based data. The censoring system may be configured to identify within the received text-based data, a target data pattern corresponding to the retrieved target pattern type. The censoring system may be configured to censor target characters within the identified target data pattern, and transmit the censored text-based data to a receiving party.

First claim

What is claimed is:

1. A system for censoring text-based data comprising:
at least one processor;
at least one non-transitory memory storing application programming interface instructions that, when executed by the at least one processor cause the system to perform operations comprising:
receiving text-based data;
retrieving a target pattern type based on at least one security characteristic associated with a receiving party for the text-based data, wherein the target pattern type indicates data that is to be censored for parties associated with the at least one security characteristic;
retrieving, from a database, a token corresponding to a target data pattern corresponding to the target pattern type;
retrieving, from the database and using the token, context-based alternative user information for the target data pattern based on the at least one security characteristic, the context-based alternative user information corresponding to lower sensitivity information than the target data pattern, and the context-based alternative user information having a level of sensitivity in accordance with the at least one security characteristic;
censoring the text-based data by replacing target characters of the target data pattern with the context-based alternative user information; and
transmitting the censored text-based data to the receiving party.

2. The system of claim 1 , wherein the censored text-based data further comprises an indication that the text-based data has been censored.

3. The system of claim 1 , wherein the operations further comprise determining if a network has been compromised and transmitting the censored text-based data to the receiving party based on a determination that the network has not been compromised.

4. The system of claim 1 , wherein the context-based alternative user information comprises non-descriptive text data.

5. The system of claim 1 , wherein the context-based alternative user information comprises synthetic characters.

6. The system of claim 1 , wherein the operations further comprise storing a computer-based model for identifying the target data pattern, identifying the target characters within the target data pattern, and censoring the target characters.

7. The system of claim 6 , wherein the operations further comprise combining a plurality of computer-based models, based on the at least one security characteristic, for identifying and censoring the text-based data.

8. The system of claim 1 wherein the context-based alternative user information corresponds to the target characters within the target data pattern and a permission level associated with the at least one security characteristic.

9. The system of claim 1 , wherein the operations further comprise analyzing a user profile of the receiving party to obtain the at least one security characteristic.

10. The system of claim 1 , wherein the operations further comprise: parsing the text-based data using a language parser; and labeling data objects of the text-based data with labels identifying parts of speech.

11. A method for censoring text-based data, the method comprising:
receiving text-based data;
retrieving a target pattern type based on at least one security characteristic associated with a receiving party for the text-based data;
accessing a token corresponding to a target data pattern corresponding to the target pattern type;
retrieving, using the token, context-based alternative user information for the target data pattern based on the at least one security characteristic, the context-based alternative user information corresponding to lower sensitivity information than the target data pattern, and the context-based alternative user information having a level of sensitivity in accordance with the at least one security characteristic;
censoring the text-based data by replacing target characters of the target data pattern with the context-based alternative user information; and
transmitting the censored text-based data to the receiving party.

12. The method of claim 11 , further comprising:
receiving a request, from a user, to reconstruct the censored text-based data, the request comprising authentication data of the user;
verifying a security characteristic of the authentication data;
substituting a portion of the censored text-based data with the received text-based data, based on a permission level of the user; and
transmitting the reconstructed text-based data to the user.

13. The method of claim 11 , wherein the at least one security characteristic is stored in a profile associated with the receiving party.

14. The method of claim 13 , wherein the profile comprises a list of target pattern types and associated permission levels.

15. The method of claim 11 , further comprising removing images or special characters from the text-based data.

16. The method of claim 11 , wherein the censored text-based data further comprises an indication that the text-based data has been censored.

17. The method of claim 11 , further comprising determining if a network has been compromised and transmitting the censored text-based data to the receiving party based on a determination that the network has not been compromised.

18. The method of claim 17 , wherein determining that the network has been compromised comprises analyzing a time to transmit data from a server system to a receiving system.

19. The method of claim 11 , wherein the context-based alternative user information comprises synthetic characters.

20. A system for censoring text-based data comprising:
at least one processor;
at least one non-transitory memory storing application programming interface instructions that, when executed by the at least one processor cause the system to perform operations comprising:
receiving text-based data;
retrieving respective target pattern types based on a first permission level and a second permission level associated with a receiving party for the text-based data, wherein the respective target pattern types indicate data that is to be censored for parties associated with the first permission level and the second permission level;
retrieving, from a database, respective tokens corresponding to respective target data patterns corresponding to the respective target pattern types;
retrieving, from the database and using the respective tokens, a first part of context-based alternative user information for a first of the respective target data patterns based on the first permission level and a second part of context-based alternative user information for a second of the respective target data patterns based on the second permission level;
censoring the text-based data by replacing target characters of the respective target data patterns with the first part and the second part; and
transmitting the censored text-based data to the receiving party.

Assignees

• Capital One Services Llc

Inventors

• Walters Austin
• Abdi Taghi Abad Fardin
• Pham Vincent
• Goodsitt Jeremy
• Truong Anh
• Watson Mark
• Farivar Reza
• Taylor Kenneth

Classifications

• G06T11/10

  Texturing; Colouring; Generation of textures or colours (retouching, inpainting or scratch removal G06T5/77) · CPC title

• G06N3/0455

  Auto-encoder networks; Encoder-decoder networks · CPC title

• G06N3/0985

  Hyperparameter optimisation; Meta-learning; Learning-to-learn · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/094

  Adversarial learning · CPC title