Granted Patent B2

US 12,327,078 · App. 18/211,331 · Granted Jun 10, 2025

Inventors: Zachary A. Silverstein (Georgetown, TX); Jonathan D. Dunne (Dungarvan, IE); Norton Samuel Augustus Stanley (Bangalore, IN); Hemant Kumar Sivaswamy (Pune, IN)

Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION

G06F40/151G06F40/166G06F40/20

Abstract

Claims (44)

1. A computer-implemented method comprising:

detecting, using corpus linguistics, a signature discourse utterance of a user by analyzing a user's discourse history;

computing a term frequency of a collection of words used repeatedly by the user and distinct to the user;

sensing, using tone analysis and natural language process modeling, a tone of the collection of words distinct to the user in the signature discourse utterance;

deriving a signature discourse transformation (SDT) model from the signature discourse utterance, the collection of words used repeatedly by the user, and the tone; and

transforming, using the signature discourse transformation (SDT), an original writing by the user into an anonymized text.

2. The computer-implemented method of claim 1 , wherein the user's discourse history includes emails, reports, and chat history.

3. The computer-implemented method of claim 1 , wherein computing a term frequency includes analyzing a user's collocations and colligations.

4. The computer-implemented method of claim 1 , wherein the natural language process modeling includes word2vec modelling.

5. The computer-implemented method of claim 1 , further comprising mapping a cartesian value of the term frequency of a collection of words used repeatedly by the user and distinct to the user.

6. The computer-implemented method of claim 5 , wherein mapping a cartesian value of the word and the collection of words used repeatedly by the user and distinct to the user further comprises transforming the x, y coordinates and validating meaning and the tone of the user's signature utterance.

7. The computer-implemented method of claim 1 , wherein mapping a cartesian value comprises an affine transformation.

8. The computer-implemented method of claim 1 , wherein the anonymized text maintains an original meaning of the original writing of the user.

9. The computer-implemented method of claim 1 , further comprising determining a degree of transforming of an original discourse by the user into an anonymized text.

10. The computer-implemented method of claim 8 , further comprising adjusting the original writing to remove a linguistic monument from the writing.

11. A computer program product comprising one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable by a processor to cause the processor to perform operations comprising:

detecting, using corpus linguistics, a signature discourse utterance of a user by analyzing a user's discourse history;

computing a term frequency of a collection of words distinct to the user;

sensing, using Tone Analysis and natural language process modeling, a tone of the collection of words distinct to the user in the signature discourse utterance;

deriving a signature discourse transformation (SDT) model from the signature discourse utterance, the term frequency; the tone, and the collection of words; and

transforming, using the signature discourse transformation (SDT), an original writing by the user into an anonymized text.

12. The computer program product of claim 11 , wherein the stored program instructions are stored in a computer readable storage device in a data processing system, and wherein the stored program instructions are transferred over a network from a remote data processing system.

13. The computer program product of claim 11 , wherein the stored program instructions are stored in a computer readable storage device in a server data processing system, and wherein the stored program instructions are downloaded in response to a request over a network to a remote data processing system for use in a computer readable storage device associated with the remote data processing system, further comprising:

mapping a cartesian value of the word and the collection of words distinct to the user.

14. The computer program product of claim 11 , wherein the stored program instructions are stored in a computer readable storage device in a server data processing system, and wherein the stored program instructions are downloaded in response to a request over a network to a remote data processing system for use in a computer readable storage device associated with the remote data processing system, further comprising:

generalizing the SDT across a group of individuals; and

determining a degree of transforming an original writing by the user into an anonymized text based on the group of individuals.

15. The computer program product of claim 11 , wherein the stored program instructions are stored in a computer readable storage device in a server data processing system, and wherein the stored program instructions are downloaded in response to a request over a network to a remote data processing system for use in a computer readable storage device associated with the remote data processing system, further comprising:

determining a degree of transforming an original writing by the user into an anonymized text;

adjusting the original writing to remove a linguistic monument from the writing.

16. The computer program product of claim 11 , wherein the stored program instructions are stored in a computer readable storage device in a server data processing system, and wherein the stored program instructions are downloaded in response to a request over a network to a remote data processing system for use in a computer readable storage device associated with the remote data processing system, further comprising:

determining a degree of transforming an original writing by the user into an anonymized text.

17. The computer usable program product of claim 11 , wherein the computer usable code is stored in a computer readable storage device in a server data processing system, and wherein the computer usable code is downloaded over a network to a remote data processing system for use in a computer readable storage device associated with the remote data processing system.

18. A computer system comprising a processor and one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable by the processor to cause the processor to perform operations comprising:

detecting, using corpus linguistics, a signature discourse utterance of a user by analyzing the user's discourse history;

computing a term frequency of a collection of words distinct to the user;

sensing, using tone analysis and natural language process modeling, a tone of a collection of words distinct to the user in the signature discourse utterance;

mapping a cartesian value of the word and the collection of words distinct to the user;

deriving a signature discourse transformation (SDT) model from the signature discourse utterances, the term frequency; the tone, the collection of words, and the cartesian value; and

transforming, using the signature discourse transformation (SDT), an original writing by the user into an anonymized text.

19. The computer system of claim 18 , further comprising:

generalizing the SDT across a group of individuals and

determining a degree of transforming an original discourse by the user into an anonymized text based on the group of individuals.

20. The computer system of claim 18 , further comprising determining a degree of transforming an original writing by the user into an anonymized text.

Assignments (1)

Continuity (1)

References Cited (24)