Removal of personality signatures

Patent metadata

Field	Value
Publication number	US-11551006-B2
Application number	US-201916564013-A
Country	US
Kind code	B2
Filing date	Sep 9, 2019
Priority date	Sep 9, 2019
Publication date	Jan 10, 2023
Grant date	Jan 10, 2023

Abstract

Embodiments relate to an intelligent computer platform to selectively amend one or more document elements. A first document is subjected to natural language processing (NLP) and two or more document characteristics are subjected to an assessment to produce a characteristic value. The document characteristics and corresponding characteristic values are analyzed to produce a characteristic profile for each identified document characteristic. Upon receipt of a new document, document characteristic data and corresponding characteristic value(s) are identified. The corresponding characteristic value(s) of the new document is applied against the produced characteristic profile. New document characteristic data is selectively amended responsive to the comparison, and a new document version is created from the selective amendment.

First claim

What is claimed is:

1. A computer system comprising:
a processing unit operatively coupled to memory; and
an artificial intelligence (AI) platform in communication with the processing unit, the AI platform including one or more tools to identify and amend one or more document characteristic values, including:
a natural language (NL) manager configured to subject a document set comprising two or more documents authored by a common author to natural language processing (NLP), including identify two or more document characteristics within the two or more documents of the document set, and subject the identified two or more document characteristics to an assessment, the assessment to produce a corresponding characteristic value for each of the identified two or more document characteristics in each of the two or more documents authored by the common author;

a profile manager, operatively coupled to the NL manager, the profile manager configured to statistically analyze the identified two or more document characteristics and the corresponding characteristic values across the two or more documents authored by the common author, the statistical analysis to produce a characteristic profile for each identified document characteristic;
a document manager, operatively coupled to the profile manager, the document manager configured to detect receipt of a new document authored by the common author, and statistically analyze the new document with respect to the identified two or more document characteristics, including identify document characteristic data and a corresponding characteristic value;
a director, operatively coupled to the document manager, the director configured to:
selectively identify an intersection or a non-intersection of one or more vector component values of the new document and one or more vector scores from the document set;

responsive to the intersection, selectively amend one or more tokens of text of the new document to change the characteristic value of the new document to fall outside of the characteristic profile; and
create a new document version from the selective amendment.

2. The computer system of claim 1 , wherein the selective amendment of one or more tokens of text of the new document to change the characteristic value comprises the director configured to modify the one or more tokens, the modification comprising replacement of the one or more tokens with one or more new tokens.

3. The computer system of claim 2 , wherein the profile manager is further configured to subject the new document version to a characteristic assessment, including produce a new characteristic value for each modified token.

4. The computer system of claim 3 , wherein the document manager is further configured to accept the new document amendment responsive to identification of divergence of the new document characteristic assessment from the characteristic values across the two or more documents authored by the common author.

5. The computer system of claim 1 , wherein the director configured to selectively amend tokens of text of the new document provides authorship anonymity with respect to the new document version.

6. The computer system of claim 1 , wherein the characteristic value for each document characteristic in each of the documents is a composite value.

7. The computer system of claim 1 , wherein the director is further configured to, responsive to the non-intersection, not selectively amend the new document.

8. A computer program product to identify and amend one or more document characteristic values, the computer program product comprising:
a computer readable storage medium having program code embodied therewith, the program code executable by a processor to:
subject a document set comprising two or more documents authored by a common author to natural language processing (NLP), including identify two or more document characteristics within the two or more documents of the document set, and subject the identified two or more document characteristics to an assessment, the assessment producing a corresponding characteristic value for each of the identified two or more document characteristics in each of the two or more documents authored by the common author;
statistically analyze the identified two or more document characteristics and the corresponding characteristic values across the two or more documents authored by the common author, the statistical analysis producing a characteristic profile for each identified document characteristic;
responsive to receiving a new document authored by the common author, statistically analyze the new document with respect to the identified two or more document characteristics, including identify document characteristic data and a corresponding characteristic value;
selectively identify an intersection or a non-intersection of one or more vector component values of the new document and one or more vector scores from the document set;
responsive to the intersection, selectively amend one or more tokens of text of the new document to change the characteristic value of the new document to fall outside of the characteristic profile; and
create a new document version from the selective amendment.

9. The computer program product of claim 8 , wherein the selective amendment of one or more tokens of text of the new document to change the characteristic value comprises program code executable by the processor to modify the one or more tokens, the modification comprising replacement of the one or more tokens with one or more new tokens.

10. The computer program product of claim 9 , further comprising program code executable by the processor to subject the new document version to a characteristic assessment, including produce a new characteristic value for each modified token.

11. The computer program product of claim 10 , further comprising program code executable by the processor to accept the new document amendments responsive to identifying divergence of the new document characteristic assessment from the characteristic value of the document set.

12. The computer program product of claim 8 , wherein the characteristic value for each document characteristic in each of the documents is a composite value.

13. The computer program product of claim 8 , further comprising program code executable by the processor to, responsive to the non-intersection, not selectively amend the new document.

14. A method comprising:
using a computer processor to support an artificial intelligence (AI) platform to identify and amend one or more tokens, including:
subjecting a document set comprising two or more documents authored by a common author to natural language processing (NLP), including identifying two or more document characteristics within the two or more documents of the document set, and subjecting the identified two or more document characteristics to an assessment, the assessment producing a corresponding characteristic value for each of the identified two or more document characteristics in each of the two or more documents authored by the common author;
statistically analyzing the identified two or more document characteristics and the corresponding characteristic values across the two or more documents authored by the common author, the statistical analysis producing a characteristic profile for each identified document characteristic;
responsive to receiving a new document authored by the common author, statistically analyzing the new document with respect to the identified two or more document characteristics, including identifying document characteristic data and a corresponding characte

Assignees

• IBM

Inventors

• Beller Charles E
• Ackermann Christopher F
• Summers Kristen Maria
• Mcquenney David
• High Rob

Classifications

• G06F40/30 Primary

  Semantic analysis · CPC title

• G06F40/284

  Lexical analysis, e.g. tokenisation or collocates · CPC title

• G06F21/6254 Primary

  by anonymising data, e.g. decorrelating personal data from the owner's identification · CPC title

• G06N5/041

  Abduction · CPC title

• G06N20/00

  Machine learning · CPC title