Tools and techniques for extracting knowledge from unstructured data retrieved from personal data sources

• US 9,443,007 B2
• Filed: 11/02/2011
• Issued: 09/13/2016
• Est. Priority Date: 11/02/2011
• Status: Active Grant

• Current Assignee: Salesforce.com, Inc.
• Original Assignee: Salesforce.com, Inc.
• Inventors: Donneau-Golencer, Thierry, Singh, Rajan, Yarlagadda, Madhu, Hulen, Corey, Nitz, Kenneth C., Mark, William Scott
• Primary Examiner(s): CHEEMA, AZAM M
• Application Number:
  US13/287,983
• Publication Number:
  US 20130110842A1
• Time in Patent Office: 1,777 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/22 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/24522 Translation of natural language queries to structured queries
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/337 Profile generation, learning or modification

Abstract

A system may include multiple personal data sources and a machine-implemented data extractor and correlator configured to retrieve personal data from at least one of the personal data sources. The data extractor and correlator may extract information from unstructured data within the retrieved personal data and correlate the extracted information with previously stored structured data to generate additional structured data. The system may also include a storage device configured to store the previously stored structured data and the additional structured data. A natural language query module may be configured to receive a natural language query from a user and provide a response to the natural language query based at least in part on one or both of the previously stored structured data and the additional structured data.

Claims

1. A system, comprising:

a plurality of personal data sources;

a processor configured to operate;

a machine-implemented data extractor and correlator configured to retrieve personal data from at least one of the plurality of personal data sources, extract information from unstructured data within the retrieved personal data, and correlate the extracted information with previously stored structured data to generate additional structured data;

a user profile module configured to generate and update different user profiles associated with different user roles for a same user based on both the previously stored structured data and the additional structured data;

a natural language query module configured to receive a natural language query from the user and provide a response to the natural language query based at least in part on one or both of the previously stored structured data and the additional structured data;

a storage device configured to store the previously stored structured data and the additional structured data; and

a feedback module configured to interact with different user applications and direct the user profile module to update the different user profiles based on structured data and unstructured data from the different user applications.

2. The system of claim 1, wherein the plurality of personal data sources comprises at least two of a group consisting of:

an email message, a calendar item, a customer relationship management (CRM) application object, an address book entry, a tweet, and a blog entry.

3. The system of claim 1, wherein the data extractor and correlator is further configured to retrieve at least some of the personal data from the different user profiles.

4. The system of claim 1, wherein the data extractor and correlator comprises a semantic analysis module configured to determine semantic information based on the unstructured data, and wherein the extracted information comprises the semantic information.

5. The system of claim 4, wherein the data extractor and correlator is configured to correlate the extracted information with the previously stored structured data based at least in part on the semantic information.

6. The system of claim 1, wherein the data extractor and correlator comprises a semantic analysis module configured to determine semantic information based on public data retrieved from at least one public data source, and wherein the data extractor and correlator is further configured to correlate the semantic information with one or both of the previously stored structured data and the additional structured data to generate further structured data.

7. The system of claim 1, wherein the user profile module is further configured to generate a new user profile based at least in part on one or both of the previously stored structured data and the additional structured data.

8. The system of claim 1, wherein at least one of the user applications is configured to provide user interaction based at least in part on the user profiles.

9. The system of claim 1, wherein the feedback module is further configured to update the user profiles responsive to public data retrieved from at least one public data source.

10. The system of claim 1, further comprising a machine-implemented document harvester configured to retrieve a document from at least one of the plurality of personal data sources.

11. The system of claim 10, further comprising a machine-implemented document indexer configured to index a plurality of documents harvested by the document harvester.

12. The system of claim 1, wherein the machine-implemented data extractor and correlator is further configured to retrieve public data from at least one public data source, extract public information from unstructured data within the retrieved public data, and correlate the extracted public information with the previously stored structured data to generate further additional structured data.

13. The system of claim 1, wherein the data extractor and correlator is configured to extract information from the unstructured data by performing at least one of a group consisting of:

breaking at least one sentence into subject, verb, and object (SVO);

extracting phrases that link a subject to an object;

extracting at least one word in close proximity to an identified feature; and

extracting at least one word in close proximity to a known quality.

14. The system of claim 1, wherein the data extractor and correlator is configured to correlate the extracted information with the previously stored structured data by building at least one relationship between the extracted information and the previously stored structured data.

15. The system of claim 14, wherein the data extractor and correlator is configured to build the at least one relationship between the extracted information and the previously stored structured data by tagging a feature identified in the extracted information.

16. A machine-implemented method, comprising:

a processing device retrieving personal data from at least one of a plurality of personal data sources;

the processing device extracting unstructured data from the retrieved personal data;

the processing device correlating the extracted unstructured data with previously stored structured data to generate additional structured data and update different user profiles associated with different user roles for a same user with both the previously stored structured data and the additional structured data;

a storage device storing the previously stored structured data and the additional structured data;

the processing device receiving a natural language query from the user;

the processing device determining a response to the natural language query to be provided to the user, wherein the response is based at least in part on one or both of the previously stored structured data and the additional structured data; and

the processing device interacting with different user applications and updating the different user profiles based on structured data and unstructured data from the different user applications.

17. The machine-implemented method of claim 16, further comprising:

generating a new one of the user profiles based at least in part on one or both of the previously stored structured data and the additional structured data.

18. The machine-implemented method of claim 16, further comprising:

the processing device retrieving public data from at least one of a plurality of public data sources;

the processing device extracting public information from unstructured data within the retrieved public data; and

the processing device correlating the extracted public information with the previously stored structured data to generate further additional structured data.

19. The machine-implemented method of claim 18, further comprising:

updating a previously generated one of the user profiles based at least in part on the further additional structured data.