Collection and Storage of a Personalized, Searchable, Unstructured Corpora

• US 20160112391A1
• Filed: 05/25/2015
• Published: 04/21/2016
• Est. Priority Date: 10/18/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Jamrog, Daniel M., LaVoie, Jason D., Orrick, Nicholas W., Witherspoon, Kristin A.
• Granted Patent: US 9,524,320 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 16/337 Profile generation, learning or modification
• CPC Class Codes: G06F 16/338 Presentation of query results
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 21/31 User authentication
• CPC Class Codes: G06F 21/62 Protecting access to data via a platform, e.g. using keys or access control rules
• CPC Class Codes: G06F 21/6227 where protection concerns the structure of data, e.g. records, types, queries
• CPC Class Codes: H04L 63/08 for authentication of entities cryptographic mechanisms or cryptographic arrangements for entity authentication H04L9/32
• CPC Class Codes: H04L 63/10 for controlling access to devices or network resources

Abstract

An approach is provided for utilizing unstructured corpora in a Question and Answer (QA) system. A question is received at the QA system. A private corpora is generated with the private corpora being associated with the user. The private corpora is generated from private data stores associated with the user as well as private data stores associated with other users. Access to the other user'"'"'s private data sources is provided to the user by the other users. The system retrieves data responsive to the question from the private corpora. The responsive data is ranked based on its relevance to the question. Likely answers are identified based on the ranked responsive data and the likely answers are provided back to the user.

Claims

1. A method, in an information handling system comprising a processor and a memory, of utilizing unstructured corpora, the method comprising:

receiving, from a first user, a question at a question answering (QA) system;

generating a private corpora associated with the first user, wherein the private corpora is generated from a first set of one or more private data stores associated with a first user and a second set of one or more private data stores associated with a set of one or more second users, wherein access to the second set of private data stores is provided to the first user by the set of second users;

retrieving responsive data to the question from the private corpora, wherein the responsive data is ranked based on a relevance to the question;

identifying one or more likely answers based on the ranked responsive data; and

providing the one or more likely answers to the first user.

2. The method of claim 1 further comprising:

prior to receiving the question;

receiving a set of access credentials from the first user and the set of second users, wherein the access credentials are used to access the first and second sets of private stores; and

utilizing the set of access credentials to access the first and second sets of private data stores during the generation of the private corpora.

3. The method of claim 1 further comprising:

receiving one or more access restrictions from a selected one of the set of second users, wherein the access restrictions prevent the first user from accessing one or more types of data from the selected second user'"'"'s private data stores.

4. The method of claim 1 further comprising:

creating a security profile associated with a selected one of the second users, wherein the security profile restricts access by the first user to one or more types of data from the selected second user'"'"'s private data sources; and

inhibiting inclusion in the responsive data of the one or more types of data from the selected second user'"'"'s private data sources.

5. The method of claim 4 further comprising:

determining that the question is unanswerable due to the security profile restricting access to the type of data required by the question; and

informing the first user that the question is unanswerable due to the security profile.

6. The method of claim 1 wherein at least one of the first and second sets of private data stores is selected from the group consisting of a social media data store, a calendar data store, an email data store, and an instant message data store.

7. The method of claim 1 further comprising:

retrieving the responsive data to the question from the private corpora and a public corpora.