SENSOR BASED CONTEXT AUGMENTATION OF SEARCH QUERIES

• US 20180052925A1
• Filed: 08/22/2016
• Published: 02/22/2018
• Est. Priority Date: 08/22/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Cohn, John M., Kozhaya, Joseph N., Pureswaran, Veena S.
• Granted Patent: US 10,372,767 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques

Abstract

A computing device and method is usable to augment search queries with data obtained from sensors. The computing device comprises a processor configured to receive, from a query source, a search query comprising a query concept. The processor is further configured to determine a context of the query concept expressed in the query. The processor is further configured to determine a response to the query. The processor is further configured to validate the context of the query using at least one sensor. The processor is further configured to transmit the response to the query to the query source.

Claims

1. A computer program product for sensor augmented searching, 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, from a query source, a search query comprising a query concept;

determine a context of the query concept expressed in the query;

determine a response to the query;

validate the context of the query using at least one sensor; and

transmit the response to the query to the query source.

2. The computer program product of claim 1, wherein the search query is a natural language search query.

3. The computer program product of claim 2, wherein the at least one sensor is an Internet of things sensor configured to allow use to enhance search queries.

4. The computer program product of claim 1, wherein validating the context of the query using at least one sensor comprises:

determining a confidence level corresponding to the response to the query;

determining whether sensor data from the at least one sensor increases the confidence level; and

determining that the sensor data from the at least one sensor validates the context of the query when the sensor data from the at least one sensor does not change the confidence level.

5. The computer program product of claim 4, wherein validating the context of the query using the at least one sensor further comprises:

determining that the sensor data from the at least one sensor does not validate the context of the query when the sensor data from the at least one sensor increases the confidence level; and

determining that the sensor data from the at least one sensor does not validate the context of the query when the sensor data from the at least one sensor decreases the confidence level.

6. The computer program product of claim 1, wherein the at least one sensor is a member of a sensor class that comprises a plurality of related sensors.

7. The computer program product of claim 1, wherein the computer program product is provided in a cloud environment as software as a service to a user who generates the search query.

8. A computer-implemented method, comprising:

receiving a search query;

determining a context of the search query;

determining one or more sensor classes that effect an information gain by providing additional context to the search query;

determining a response to the search query based on the additional context; and

transmitting the response to the search query to a user-equipment associated with a source of the search query such that the transmission of the response to the search query enables the user-equipment associated with the source of the search query to present the response to the search query via one or more interfaces.

9. The computer-implemented method of claim 8, wherein the information gain is determined at least partially based on a table of sensor data.

10. The computer-implemented method of claim 9, wherein the table of sensor data indicates a relevance of one or more sensors belonging to the one or more sensor classes to the context of the search query.

11. The computer-implemented method of claim 8, wherein the computer-implemented method is implemented in a cloud environment as an on-demand service.

12. The computer-implemented method of claim 8, wherein each of the one or more sensor classes comprises one or more sensors having a relationship to each of the other one or more sensors within a same sensor class.

13. The computer-implemented method of claim 8, further comprising:

identifying at least one sensor from among a group of sensors indicated by the sensor class that effect the information gain by providing the additional context to the search query;

reading sensor data from the at least one sensor;

augmenting the search query with at least a portion of the sensor data to form an enhanced search query having the additional context;

determining a response to the enhanced search query based on the additional context; and

transmitting the response to the enhanced search query to the user-equipment associated with the source of the search query such that the transmission of the response to the search query enables the user-equipment associated with the source of the search query to present the response to the enhanced search query via the one or more interfaces.

14. The computer-implemented method of claim 8, further comprising validating the context of the search query according to at least one sensor of the one or more sensor classes.

15. A system capable of learning, comprising a processor configured to:

receive a natural language search query from a query source;

determine an intent of the query and concepts having a relationship to the intent;

determine a response to the query based on the intent of the query and the concepts having the relationship to the intent, the response having a first associated confidence score;

transmit the response to the query source when the first confidence score exceeds a threshold;

augment the query with first sensor data to form an enhanced query when the first confidence score does not exceed the threshold;

determine a response to the enhanced query, the response having a second associated confidence score; and

transmit the response to the enhanced query to the query source when the second confidence score exceeds the threshold.

16. The system of claim 15, wherein the processor is further configured to retrieve the first sensor data from at least one sensor when the at least one sensor is included in a class of sensors that provides an information gain to the query.

17. The system of claim 16, wherein the at least one sensor is selected at least partially according to a table of sensors associated with a predicted information gain for at least one of the intent of the query or the concepts having the relationship to the query.

18. The system of claim 17, wherein the table is formed according to training data that indicates an effect of data from a given sensor on a confidence score of a search query.

19. The system of claim 15, wherein when the second confidence score does not exceed the threshold, the processor is further configured to:

augment the enhanced query with second sensor data to form a second enhanced query when the second confidence score does not exceed the threshold;

determine a response to the second enhanced query, the response having a third associated confidence score; and

transmit the response to the second enhanced query to the query source when the third confidence score exceeds the threshold.

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

determine a query context corresponding to the intent of the query and the concepts having the relationship to the intent; and

determine at least one sensor class comprising at least one sensor that validates the determined query context according to at least one sensor data of the at least one sensor.