Method to allow for question and answer system to dynamically return different responses based on roles

• US 10,754,969 B2
• Filed: 09/22/2016
• Issued: 08/25/2020
• Est. Priority Date: 09/22/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Byron, Donna K., Feirouz, Elie, Jamrog, Daniel M., Witherspoon, Kristin A.
• Primary Examiner(s): Cribbs, Malcolm
• Assistant Examiner(s): Holmes, Angela R
• Application Number:
  US15/273,152
• Publication Number:
  US 20180083975A1
• Time in Patent Office: 1,433 Days
• Field of Search: 726 1
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 21/32 using biometric data, e.g. fingerprints, iris scans or voiceprints
• CPC Class Codes: G06F 21/6218 to a system of files or objects, e.g. local or distributed file system or database

Abstract

Embodiments are directed to a question and answer (QA) pipeline system that adjusts answers to input questions based on a user criteria, thus implementing a content-based determination of access permissions. The QA system allows for information to be retrieved based on permission granted to a user. Documents are ingested and assigned an access level based on a defined information access policy. The QA system is implemented with the defined information access policy, the ingested documents, and the inferred access levels. For the QA system implementation, a user enters a question; primary search and answer extraction stages are performed; candidate answer extraction is performed using only content the user is allowed to access; the candidate answers are scored, ranked, and merged; ranked answers based on user permissions are filtered; and answers are provided to the user.

Claims

1. A computer implemented method for implementing a content-based determination of access permissions by an information handling system capable of answering questions, the system comprising a processor and a memory comprising instructions executed by the processor, the method comprising:

receiving data indicative of an information access policy;

performing document ingestion and extracting a plurality of features from ingested documents;

performing access level classification of the ingested documents based on the information access policy and the plurality of features;

receiving a question from a user with data indicative of a user permission level;

performing search and answer extraction to retrieve primary search retrieved content;

implementing a document lifecycle process to update the access level classification of one or more of the ingested documents as the documents are modified;

performing candidate answer extraction using content the user is allowed to access based on the access level classification of the ingested documents and the user permission level; and

providing to the user a notification comprising the content the user is allowed to access.

2. The method of claim 1, further comprising:

utilizing all content or the content the user is allowed to access to score, rank, and merge candidate answers; and

filtering ranked answers based on the user permission level;

wherein the notification to the user further comprises the filtered, ranked answers.

3. The method of claim 1, wherein the access level classification of the ingested documents comprises one or more of manually tagged, extracted based on natural language processing (NLP) and deep analytic analysis, based on a rules-based policy, or based on a classification-based policy.

4. The method of claim 1, wherein data indicative of a responsibility role is associated with the user, and wherein the candidate answer extraction is further based on the responsibility role.

5. The method of claim 1, further comprising implementing a document lifecycle process to update the access level classification of one or more of the ingested documents.

6. The method of claim 1, wherein the notification to the user further comprises an indication of access levels of the content the user is allowed to access.

7. The method of claim 6, wherein the notification to the user further comprises one or more of an indication of areas where content is redacted and a portion of redacted content.

8. A computer program product for implementing a content-based determination of access permissions by an information handling system capable of answering questions, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:

receive data indicative of an information access policy;

perform document ingestion and extract a plurality of features from ingested documents;

perform access level classification of the ingested documents based on the information access policy and the plurality of features;

receive a question from a user with data indicative of a user permission level;

perform search and answer extraction to retrieve primary search retrieved content;

implement a document lifecycle process to update the access level classification of one or more of the ingested documents as the documents are modified;

perform candidate answer extraction using content the user is allowed to access based on the access level classification of the ingested documents and the user permission level; and

provide to the user a notification comprising the content the user is allowed to access.

9. The computer program product of claim 8, wherein the program instructions further cause the processor to:

utilize all content or the content the user is allowed to access to score, rank, and merge candidate answers; and

filter ranked answers based on the user permission level;

wherein the notification to the user further comprises the filtered, ranked answers.

10. The computer program product of claim 8, wherein the access level classification of the ingested documents comprises one or more of manually tagged, extracted based on natural language processing (NLP) and deep analytic analysis, based on a rules-based policy, or based on a classification-based policy.

11. The computer program product of claim 8, wherein data indicative of a responsibility role is associated with the user, and wherein the candidate answer extraction is further based on the responsibility role.

12. The computer program product of claim 8, wherein the program instructions further cause the processor to:

implement a document lifecycle process to update the access level classification of one or more of the ingested documents.

13. The computer program product of claim 8, wherein the notification to the user further comprises one or more of an indication of access levels of the content the user is allowed to access;

an indication of areas where content is redacted; and

a portion of redacted content.

14. A system for implementing a content-based determination of access permissions, the system comprising:

a memory comprising executable instructions; and

a processor configured to execute the executable instructions to;

receive data indicative of an information access policy;

perform document ingestion and extract a plurality of features from ingested documents;

performing access level classification of the ingested documents based on the information access policy and the plurality of features;

receive a question from a user with data indicative of a user permission level;

perform search and answer extraction to retrieve primary search retrieved content;

implementing a document lifecycle process to update the access level classification of one or more of the ingested documents as the documents are modified;

perform candidate answer extraction using content the user is allowed to access based on the access level classification of the ingested documents and the user permission level; and

provide to the user a notification comprising the content the user is allowed to access.

15. The system of claim 14, wherein the processor is further configured to:

utilize all content or the content the user is allowed to access to score, rank, and merge candidate answers; and

filter ranked answers based on the user permission level;

wherein the notification to the user further comprises the filtered, ranked answers.

16. The system of claim 14, wherein the access level classification of the ingested documents comprises one or more of manually tagged, extracted based on natural language processing (NLP) and deep analytic analysis, based on a rules-based policy, or based on a classification-based policy.

17. The system of claim 14, wherein data indicative of a responsibility role is associated with the user, and wherein the candidate answer extraction is further based on the responsibility role.

18. The system of claim 14, wherein the processor is further configured to:

implement a document lifecycle process to update the access level classification of one or more of the ingested documents.

19. The system of claim 14, wherein the notification to the user further comprises an indication of access levels of the content the user is allowed to access.

20. The system of claim 19, wherein the notification to the user further comprises one or more of an indication of areas where content is redacted and a portion of redacted content.