US 10,372,767 B2Granted

Sensor based context augmentation of search queries

AssigneeInternational Business Machines Corporation

InventorsJohn M. Cohn, Joseph N. Kozhaya, Veena S. Pureswaran

Life of this patent

Estimating the term…

Loading patent…

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.

Claims18

Dependent claims

A computer program product for sensor augmented searching, the computer program product comprising a non-transitory 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 search query concept expressed in the search query;
determine a response to the search query;
determine a confidence level corresponding to the response to the search query;
transmit the response to the search query to the query source when the confidence level is greater than a confidence threshold;
determine an information gain for a plurality of sensors with respect to the search query when the confidence level is not greater than the confidence threshold by evaluating a table of sensor data that equates query concepts to the information gain provided by each of the plurality of sensors for each respective query concept of the query concepts;
augment the search query with sensor data from a sensor from among the plurality of sensors to form an enhanced search query when the confidence level is not greater than the confidence threshold, the information gain of the sensor being greater than the information gain of a remainder of the plurality of sensors and exceeding an information gain threshold;
determine a response to the enhanced search query;
and
transmit the response to the enhanced search query to the query source when the confidence level is greater than the confidence threshold.

7 more elements

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 by evaluating a table of sensor data that equates search query contexts to the information gain provided by each of the one or more sensor classes for each respective search query context of the search query contexts;
identifying at least one sensor from among a group of sensors indicated by one of the one or more sensor classes, where the at least one sensor provides a greater information gain than sensors of at least some other sensors of the group of sensors and exceeds an information gain threshold;
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;
determining a response to the enhanced search query;
determining that the response to the enhanced search query has a confidence level not greater than a confidence level threshold;
reading second sensor data from at least a second sensor when the confidence level of the response to the enhanced search query is not greater than the confidence level threshold;
augmenting the enhanced search query with at least a portion of the second sensor data to form a second enhanced search query when the confidence level of the response to the enhanced search query is not greater than the confidence level threshold;
determining a response to the second enhanced search query;
determining that the response to the second enhanced search query has a confidence level greater than the confidence level threshold;
and
transmitting the response to the second enhanced search query to a user-equipment associated with a source of the search query such that the transmission of the response to the second enhanced 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.

11 more elements

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

receive a natural language 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;
augment the enhanced query with second sensor data to form a second enhanced query when the second confidence score does not exceed the threshold and the second sensor data is determined to provide an information gain over the first sensor data by evaluating a table of sensor data that equates the intent of the query and the concepts having the relationship to the intent to the information gain provided by each of a plurality of sensors including at least a second sensor that generates the second sensor data;
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.

7 more elements

Dependencies are inferred from the claim text.

Facts

Application: 15/243,721Filed 22 Aug 2016
Published: US 2018/0052925 A122 Feb 2018
Granted: 6 Aug 2019
Term ends: Not estimatedThe source records don’t support an estimate.

Classification5 codes

G06F 16/9537
Querying, e.g. by the use of web search engines: spatial or temporal dependent retrieval, e.g. spatiotemporal queries
G06F 16/24578
With adaptation to user needs: using ranking
G06F 16/3329
Query formulation: natural language query formulation
G06F 16/951
Retrieval from the web: indexing; Web crawling techniques

Family

US 2018/0052925 A1Pre-grant publication · published 22 Feb 2018
US 10,372,767 B2This patent

From the US filing history. Foreign family members aren’t listed.

Timeline

Citations

Open elsewhere

Building an agent or pulling many patents? Use the API or MCP server instead of scraping pages. Get an API key