QA Based on Context Aware, Real-Time Information from Mobile Devices

• US 20140365517A1
• Filed: 06/06/2013
• Published: 12/11/2014
• Est. Priority Date: 06/06/2013
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Calo, Seraphin Bernard, Freimuth, Douglas M., Ganti, Raghu Kiran, Fan, James J., Ye, Fan
• Granted Patent: US 10,380,105 B2
• Time in Patent Office: Days
• US Class Current: 707/760
• CPC Class Codes: G06F 16/243 Natural language query formulation

Abstract

A common infrastructure collects data from a plurality of mobile devices and traditional sensors at Internet scale to respond to natural language queries received at different applications. The infrastructure includes a semantic interpreter to translate the natural language query to a data request specification that is processed by the data collection system. The data collection system includes a phenomenon layer that expresses data and information needs in a declarative fashion and coordinates data collection and processing for queries. An edge layer manages devices, receives collection requirements from the backend layer, configures and instructs devices for data collection, and conducts aggregation and primitive processing of data. This layer contains network edge nodes, such as base stations in a cellular network. Each node manages a set of local data generating networked devices. The device agent data layer using common agents on the networked devices receives data collection instructions and performs data collection.

Claims

1. A method for question answering, the method comprising:

receiving a natural language query at an application running on a computing system;

translating the natural language query into a data request specification, the data request specification comprising an identification of types of data to be obtained that are responsive to the natural language query;

determining data collection requirements in a data capture system responsive to the data request specification, the data collection requirements comprising raw data and phenomena responsive to the data request specification, each phenomenon comprising an occurrence of a given event at a given physical location over a given time duration;

obtaining the raw data in real time using the data capture system;

generating the phenomena in the data collection requirements using the obtained raw data; and

communicating raw data and phenomena responsive to the data request specification and the natural language query to the application.

2. The method of claim 1, wherein:

the method further comprises identifying at an edge layer in the data capture system a set of common software agents within the data capture system capable of obtaining raw data sufficient to satisfy the data collection requirements, each common software agent running on one of a plurality of data generating networked devices; and

obtaining the raw data further comprises using the identified common software agents to obtain the raw data.

3. The method of claim 1, wherein:

receiving the natural language query further comprises receiving the natural language query from an entity;

the method further comprises obtaining profile information for the entity; and

translating the natural language query into a data request specification further comprising using the obtained profile information in identifying the types of data to be obtained that are responsive to the natural language query.

4. The method of claim 1, wherein translating the natural language query into a data request specification further comprises:

identifying a subject matter domain associated with the natural language query; and

using a corresponding subject matter domain template to create the data request specification, the corresponding subject matter domain template comprising;

a pre-define list of types of data relevant to the corresponding subject matter domain; and

a set of parameters for each type of data in the pre-defined list of types of data, the set of parameters comprising adjustable qualities and quantities for the types of data.

5. The method of claim 4, wherein:

translating the natural language query into a data request specification further comprises defining the set of parameters for each type of data by adjusting the qualities and quantities of each type of data; and

obtaining the raw data further comprises obtaining raw data responsive to the adjusted qualities and quantities of the types of data in the data request specification.

6. The method of claim 4, wherein:

translating the natural language query into a data request specification further comprises identifying data collection policies associated with the identified subject matter domain, each data collection policy comprising a pre-determined constraint on data collection; and

obtaining the raw data further comprises obtaining raw data responsive to the types of data in the data request specification in accordance with the identified data collection policies.

7. The method of claim 6, wherein the data collection policies comprise limitations on data generating networked devices that can be used to obtain the raw data, temporal limitations on data collection and spatial limitations on data collection.

8. The method of claim 1, wherein translating the natural language query into a data request specification further comprises:

identifying a subject matter domain associated with the natural language query; and

using a knowledge based expert system corresponding to the identified subject matter domain to create the data request specification.

9. The method of claim 1, wherein translating the natural language query into a data request specification further comprises:

identifying a concept in the natural language query, the concept comprising at least a portion of the natural language query;

building an ontology corresponding to the concept; and

using the ontology to describe the data request specification.

10. The method of claim 9, wherein the concept comprises a physical object or a physical phenomenon.

11. The method of claim 9, wherein using the ontology further comprises:

using the ontology to identify attributes of the concept; and

identifying the types of data available to obtain information about the identified attributes.

12. The method of claim 11, wherein obtaining the raw data further comprises:

identifying information about the identified attributes that has not been obtained; and

using the identified types of data to obtain the raw data corresponding to the identified information about the identified attributes that has not been obtained.

13. The method of claim 1, wherein:

the method further comprises processing the raw data into information comprising a higher semantic level; and

communicating raw data and phenomena further comprises communicating the processed raw data.

14. A computer-readable storage medium containing a computer-readable code that when read by a computer causes the computer to perform a method for question answering, the method comprising:

receiving a natural language query at an application running on a computing system;

translating the natural language query into a data request specification, the data request specification comprising an identification of types of data to be obtained that are responsive to the natural language query;

determining data collection requirements in a data capture system responsive to the data request specification, the data collection requirements comprising raw data and phenomena responsive to the data request specification, each phenomenon comprising an occurrence of a given event at a given physical location over a given time duration;

obtaining the raw data in real time using the data capture system;

generating the phenomena in the data collection requirements using the obtained raw data; and

communicating raw data and phenomena responsive to the data request specification and the natural language query to the application.

15. The computer readable medium of claim 14, wherein:

the method further comprises identifying at an edge layer in the data capture system a set of common software agents within the data capture system capable of obtaining raw data sufficient to satisfy the data collection requirements, each common software agent running on one of a plurality of data generating networked devices; and

obtaining the raw data further comprises using the identified common software agents to obtain the raw data.

16. The computer readable medium of claim 14, wherein translating the natural language query into a data request specification further comprises:

identifying a subject matter domain associated with the natural language query;

using a corresponding subject matter domain template to create the data request specification, the corresponding subject matter domain template comprising;

a pre-define list of types of data relevant to the corresponding subject matter domain; and

a set of parameters for each type of data in the pre-defined list of types of data, the set of parameters comprising adjustable qualities and quantities for the types of data;

defining the set of parameters for each type of data by adjusting the qualities and quantities of each type of data; and

obtaining the raw data further comprises obtaining raw data responsive to the adjusted qualities and quantities of the types of data in the data request specification.

17. The computer readable medium of claim 16, wherein:

translating the natural language query into a data request specification further comprises identifying data collection policies associated with the identified subject matter domain, the data collection policies comprising limitations on data generating networked devices that can be used to obtain the raw data, temporal limitations on data collection and spatial limitations on data collection; and

obtaining the raw data further comprises obtaining raw data responsive to the types of data in the data request specification in accordance with the identified data collection policies.

18. The computer readable medium of claim 14, wherein translating the natural language query into a data request specification further comprises:

identifying a concept in the natural language query, the concept comprising at least a portion of the natural language query;

building an ontology corresponding to the concept; and

using the ontology to describe the data request specification.

19. The computer readable medium of claim 18, wherein the concept comprises a physical object or a physical phenomenon.

20. The computer readable medium of claim 18, wherein:

using the ontology further comprises;

using the ontology to identify attributes of the concept; and

identifying the types of data available to obtain information about the identified attributes; and

obtaining the raw data further comprises;

identifying information about the identified attributes that has not been obtained; and

using the identified types of data to obtain the raw data corresponding to the identified information about the identified attributes that has not been obtained.

21-40. -40. (canceled)