Predictive search with context filtering

Abstract

A method may include a processing system detecting a biometric condition of a user exceeding a threshold, determining a triggering object associated with the biometric condition, where the triggering object is captured via a camera, and applying the triggering object and at least one personal parameter to a plurality of context filters. The plurality of context filters may provide a relevance topic based upon the triggering object and the at least one personal parameter. The processing system may further generate a plurality of search terms based upon the relevance topics that are determined from the plurality of context filters and present the plurality of search terms via a user interface.

What is claimed is: 
     
         1 . A device comprising:
 a processing system including at least one processor; and   a computer-readable medium storing instructions which, when executed by the processing system, cause the processing system to perform operations, the operations comprising:
 detecting a biometric condition of a user exceeding a threshold; 
 determining a triggering object associated with the biometric condition, wherein the triggering object is captured via a haptic sensor; 
 applying the triggering object and at least one personal parameter to a plurality of context filters, wherein each of the plurality of context filters provides a relevance topic based upon the triggering object and the at least one personal parameter; 
 generating a plurality of search terms based upon the relevance topics that are determined from the plurality of context filters; and 
 presenting the plurality of search terms via a user interface. 
   
     
     
         2 . The device of  claim 1 , wherein the operations further comprise:
 receiving a selection of one of the plurality of search terms;   applying the one of the plurality of search terms that is selected to a search engine; and   presenting results from the search engine in response to the one of the plurality of search terms via the user interface.   
     
     
         3 . The device of  claim 2 , wherein the operations further comprise:
 retraining at least one of the plurality of context filters based upon the selection.   
     
     
         4 . The device of  claim 1 , wherein the operations further comprise:
 detecting a confirmatory condition relating to the triggering object, wherein the applying is performed in response to the detecting of the confirmatory condition.   
     
     
         5 . The device of  claim 4 , wherein the confirmatory condition comprises at least one of:
 a verbal reference to the triggering object;   a text reference to the triggering object;   a gesture; or   a maintenance of the triggering object within a field of view.   
     
     
         6 . The device of  claim 1 , wherein the biometric condition of the user comprises at least one of:
 a heart rate;   a blood pressure;   a breathing rate;   a blood oxygen concentration;   a facial expression;   a pupil dilation;   a voice pitch;   a voice tone;   an activity level;   a skin conductance;   a body temperature;   an electrocardiogram pattern;   an electroencephalography scan pattern; or   a diffuse optical tomography scan pattern.   
     
     
         7 . The device of  claim 1 , wherein the biometric condition of the user is determined via at least one of:
 a heart rate monitor;   a blood pressure monitor;   an electrocardiogram device;   a microphone;   a camera;   a galvanic skin response device;   an electroencephalography device;   an event-related potential measurement device; or   a diffuse optical tomography scanning device.   
     
     
         8 . The device of  claim 1 , wherein the at least one personal parameter comprises at least one of:
 calendar information;   location information;   a communication history;   a search history;   a television viewing history;   credit card transaction information;   user preference information; or   auditory information from a vicinity of the user.   
     
     
         9 . The device of  claim 1 , wherein the determining the triggering object comprises:
 applying a tactile salience model to a tactile sensation captured via the haptic sensor.   
     
     
         10 . The device of  claim 9 , wherein the operations further comprise:
 retraining the tactile salience model based upon a user action pertaining to the plurality of search terms.   
     
     
         11 . The device of  claim 1 , wherein the plurality of context filters comprises machine learning models to determine the relevance topics based upon the triggering object and the at least one personal parameter. 
     
     
         12 . The device of  claim 11 , wherein the machine learning models are trained with training data associated with at least one of:
 the user; or   a plurality of other users.   
     
     
         13 . The device of  claim 11 , wherein each of the machine learning models is specific to a different theme of a plurality of themes. 
     
     
         14 . The device of  claim 13 , wherein the plurality of themes includes:
 a family theme;   a work theme;   a sports theme;   a relationship theme;   a food theme;   a shopping theme; or   an entertainment theme.   
     
     
         15 . The device of  claim 1 , wherein a subset of the plurality of context filters is configured to be a limited set of context filters, wherein the operations further comprise:
 selecting the limited set of context filters to be active context filters.   
     
     
         16 . The device of  claim 15 , wherein the limited set of context filters is selected to be the active context filters based upon at least one of:
 a selection by the user;   a time; or   a location.   
     
     
         17 . The device of  claim 1 , wherein the generating the plurality of search terms comprises, for each relevance topic, selecting auto-complete or auto-suggest terms associated with the relevance topic and the triggering object from a database. 
     
     
         18 . The device of  claim 1 , wherein the haptic sensor is integrated with a wearable device, wherein the plurality of search terms is presented via the user interface comprising a display of the wearable device. 
     
     
         19 . A non-transitory computer-readable medium storing instructions which, when executed by a processing system comprising at least one processor, cause the processing system to perform operations, the operations comprising:
 detecting a biometric condition of a user exceeding a threshold;   determining a triggering object associated with the biometric condition, wherein the triggering object is captured via a haptic sensor;   applying the triggering object and at least one personal parameter to a plurality of context filters, wherein each of the plurality of context filters provides a relevance topic based upon the triggering object and the at least one personal parameter;   generating a plurality of search terms based upon the relevance topics that are determined from the plurality of context filters; and   presenting the plurality of search terms via a user interface.   
     
     
         20 . A method comprising:
 detecting, by a processing system including at least one processor, a biometric condition of a user exceeding a threshold;   determining, by the processing system, a triggering object associated with the biometric condition, wherein the triggering object is captured via a haptic sensor;   applying, by the processing system, the triggering object and at least one personal parameter to a plurality of context filters, wherein each of the plurality of context filters provides a relevance topic based upon the triggering object and the at least one personal parameter;   generating, by the processing system, a plurality of search terms based upon the relevance topics that are determined from the plurality of context filters; and   presenting, by the processing system, the plurality of search terms via a user interface.