SYSTEM AND METHOD FOR SUPPORTING NATURAL LANGUAGE QUERIES AND REQUESTS AGAINST A USER'S PERSONAL DATA CLOUD

• US 20130185336A1
• Filed: 01/18/2012
• Published: 07/18/2013
• Est. Priority Date: 11/02/2011
• Status: Active Grant

• Current Assignee: SRI International, Inc.
• Original Assignee: SRI International, Inc.
• Inventors: Singh, Rajan, Donneau-Golencer, Thierry, Mark, William Scott, Hulen, Corey
• Granted Patent: US 9,471,666 B2
• Time in Patent Office: Days
• US Class Current: 707/794
• 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 16/3344 using natural language analysis
• 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 40/30 Semantic analysis

Abstract

A machine-implemented method for supporting a natural language user request against a user'"'"'s personal data cloud can include a machine receiving the natural language user request from the user, determining a semantic interpretation of the natural language user request, querying a semantically-indexed, integrated knowledge store based on the semantic interpretation, and responding to the natural language user request by displaying results of the querying, wherein the results correspond to an item within the user'"'"'s personal data cloud.

Claims

1. A machine-implemented method for supporting a natural language user request against a user'"'"'s personal data cloud, the method comprising:

a machine receiving the natural language user request from the user;

the machine determining a semantic interpretation of the natural language user request;

the machine querying a semantically-indexed, integrated knowledge store based at least in part on the semantic interpretation, said store storing information derived algorithmically from structured and unstructured personal textual data from a plurality of network sources in the user'"'"'s personal data cloud; and

the machine responding to the natural language user request by displaying one or more results of the querying, wherein the one or more results correspond to at least one item within the user'"'"'s personal data cloud.

2. The machine-implemented method of claim 1, further comprising:

extracting information from a plurality of heterogeneous network sources of data, the extracted information comprising the structured and unstructured personal textual data; and

constructing the semantically indexed, integrated knowledge store for storage and future retrieval of the extracted information;

3. The machine-implemented method of claim 2, wherein the personal textual data comprises user data from at least one of a group consisting of:

contacts, calendar events, email, personal notes, to-do lists, shared documents, music, photos, videos, personal financial data, and corporate data.

4. The machine-implemented method of claim 2, wherein the plurality of heterogeneous network sources of data comprise a plurality of network-based user accounts each associated with at least one of a group consisting of:

email, social networks, file sharing, calendar(s), media libraries, note-taking applications, enterprise software, CRM, customer support software, corporate wikis, project management software, source code development, and maintenance systems.

5. The machine-implemented method of claim 2, wherein said extracting comprises processing at least a portion of the unstructured data based on an analysis of at least a portion of the structured data.

6. The machine-implemented method of claim 2, wherein constructing the semantically-indexed, integrated knowledge store comprises an automated semantic analysis of the extracted information.

7. The machine-implemented method of claim 6, wherein the automated semantic analysis of the extracted information comprises one or both of automatic clustering and tagging operations.

8. The machine-implemented method of claim 1, wherein the natural language user request includes a natural language query, a natural language command, or both.

9. The machine-implemented method of claim 1, wherein the natural language request comprises one or more automatically suggested words.

10. The machine-implemented method of claim 1, further comprising receiving and responding to a non-natural language user request received from the user.

11. The machine-implemented method of claim 1, wherein determining the semantic interpretation comprises referencing a stored ontology that defines a semantic relationship among a set of personal data terminology.

12. The machine-implemented method of claim 11, further comprising refining the stored ontology over time based at least in part on machine learning.

13. The machine-implemented method of claim 11, further comprising refining the stored ontology over time based at least in part on interactive user feedback.

14. The machine-implemented method of claim 13, wherein the interactive user feedback comprises at least one from a group consisting of:

a star rating mechanism, a thumbs-up or thumbs-down mechanism, and a numbered scale mechanism.

15. The machine-implemented method of claim 1, wherein the determining further comprises soliciting one or more clarifying inputs from the user to disambiguate the natural language user request.

16. The machine-implemented method of claim 1, wherein the displaying comprises presenting to the user a ranked list of alternative potential responses to the natural language user request based on the one or more results of the querying.

17. The machine-implemented method of claim 16, further comprising refining the ranked list based on one or more additional user inputs solicited from the user.

18. The machine-implemented method of claim 1, wherein the responding comprises determining a ranked list of online documents containing a probable answer responsive to the natural language user request, and wherein the displaying comprises presenting to the user the ranked list.

19. The machine-implemented method of claim 1, wherein the responding comprises determining at least one probable answer responsive to the natural language user request, and wherein the displaying comprises presenting to the user the at least one probable answer.

20. The machine-implemented method of claim 1, wherein the responding comprises invoking one or more of a plurality of network services to perform a desired action responsive to the natural language user request.

21. The machine-implemented method of claim 20, wherein the plurality of network services comprises an alert creation mechanism configured to create an alert, and wherein the desired action comprises creation of the alert.

22. The machine-implemented method of claim 20, wherein the plurality of network services comprises a reminder creation mechanism configured to create a reminder, and wherein the desired action comprises creation of the reminder.

23. The machine-implemented method of claim 1, wherein the responding comprises integrating a plurality of the one or more results of the querying.

24. The machine-implemented method of claim 1, wherein the responding comprises integrating at least one of the one or more results of the querying with one or more additional results obtained by querying one or more network information sources that are external to the knowledge store.

25. The machine-implemented method of claim 24, wherein the one or more external network information sources comprise a geographic positioning system (GPS) source, and wherein the one or more additional results comprises a geographic location corresponding to at least one of the one or more results.

26. The machine-implemented method of claim 1, wherein the natural language user request is received by way of a voice command from the user.

27. The machine-implemented method of claim 1, further comprising presenting suggested actions to the user responsive to the user activating a help feature.

28. The machine-implemented method of claim 1, further comprising sorting the one or more results responsive to a command from the user.

29. The machine-implemented method of claim 1, further comprising filtering the one or more results responsive to a command from the user.

30. The machine-implemented method of claim 1, further comprising disambiguating the natural language user request.

31. The machine-implemented method of claim 30, wherein the disambiguating comprises presenting at least one element of the natural language user request in a manner distinct from the remainder of the natural language user request.

32. The machine-implemented method of claim 1, further comprising the user editing the natural language user request.

33. The machine-implemented method of claim 1, wherein at least one of the one or more results comprises a link to an external website.

34. The machine-implemented method of claim 1, further comprising the machine receiving a follow-up query from the user.

35. The machine-implemented method of claim 1, further comprising the machine calling a phone number responsive to the user selecting one of the one or more results.

36. The machine-implemented method of claim 1, wherein the one or more results comprises at least one image corresponding to at least one other user.

37. The machine-implemented method of claim 1, said store further storing information derived algorithmically from structured and/or unstructured data from at least one public network source.

38. The machine-implemented method of claim 37, wherein the one or more results correspond to at least one item within the at least one public network source.