Travel and activity capturing

Abstract

A mobile device includes a positioning module sampling at least a position of the mobile device at a sampling rate when active and a processor capable of determining whether a mobile device is travelling or dwelling based on at least the sampled position of the mobile device. The processor further identifies a travel mode for a trip segment for the mobile device based on at least the sampled position of the mobile device when the mobile device is travelling and identifies an activity when then the mobile device is dwelling.

1 . A mobile device comprising:
 a positioning module sampling at least a position of the mobile device at a sampling rate when active and providing values comprising at least the position of the mobile device;   a processor generating features from the provided values, applying the features to a model to determine a travel mode for each of a collection of respective time points, and smoothing the travel modes for the collection of respective time points to identify a travel mode for a trip segment for the mobile device.   
     
     
         2 . The mobile device of  claim 1  wherein generating the features comprises receiving a set of positions of the mobile device and removing positions from the set of positions based on at least one of an accuracy measure associated with the position, a speed of the mobile device associated with the position and an acceleration of the mobile device associated with the position and using the remaining positions in the set of positions to generate the features. 
     
     
         3 - 6 . (canceled) 
     
     
         7 . The mobile device of  claim 1  further comprises receiving indications from a user of the correctness of travel modes identified by the model and revising the model based on the indications. 
     
     
         8 . The mobile device of  claim 1  wherein in response to the travel mode, the processor alters the sampling rate of the positioning module. 
     
     
         9 . The mobile device of  claim 1  wherein the processor is further capable of determining that the mobile device is travelling along a known route and in response, the processor reducing the sampling rate of the positioning module. 
     
     
         10 . The mobile device of  claim 1  wherein the processor is further capable of determining that the mobile device has stopped travelling and has begun a dwelling episode and in response, the processor setting the positioning module to inactive so that it does not sample the position of the mobile device. 
     
     
         11 . The mobile device of  claim 10  wherein the processor is further capable of identifying an activity for the dwelling episode. 
     
     
         12 . The mobile device of  claim 11  wherein the processor identifies an activity for the dwelling episode by examining past activities near a location for the dwelling episode. 
     
     
         13 . The mobile device of  claim 11  wherein the processor identifies an activity for a dwelling episode by identifying labels assigned to locations near a location for the dwelling episode and using the labels to identify a most likely activity. 
     
     
         14 . The mobile device of  claim 1  wherein the mobile device further comprises a display and wherein the processor is capable of displaying the travel mode identified for the segment on a user interface on the display. 
     
     
         15 . The mobile device of  claim 14  wherein the processor is further capable of displaying a split user interface that allows a user to divide the trip segment into smaller actions and to assign at least one of a travel mode and an activity to each smaller action. 
     
     
         16 . A memory having computer-executable instructions stored thereon, the computer-executable instructions causing a processor to execute steps comprising:
 collecting information comprising at least one of position information, speed information and acceleration information from a positioning module in a mobile device containing the processor;   using the collected information to determine at least a travel mode for the mobile device;   comparing the travel mode to a travel mode of at least one previous trip to identify a matching previous trip; and   reducing a sampling rate of the positioning module based on identifying the matching previous trip.   
     
     
         17 . The memory of  claim 16  wherein the processor executes additional steps comprising:
 before collecting the information, using an accelerometer to determine that a dwelling episode has ended and in response activating the positioning module. 
 
     
     
         18 . The memory of  claim 17  wherein the processor executes additional steps comprising:
 using past activities of a user of the mobile device to identify an activity to assign to the dwelling episode. 
 
     
     
         19 . The memory of  claim 17  wherein the processor executes additional steps comprising:
 using past activities of other users of other mobile devices to identify an activity to assign to the dwelling episode. 
 
     
     
         20 . (canceled) 
     
     
         21 . The memory of  claim 17  wherein the processor executes additional steps comprising:
 determining an activity for the dwelling episode; 
 generating a user interface for a display on the mobile device to show the determined activity; and 
 receiving input from the user that either indicates that the user has confirmed the activity or that the user has selected a different activity for the dwelling episode. 
 
     
     
         22 . The memory of  claim 16  wherein the processor executes additional steps comprising:
 generating a user interface for a display on the mobile device to show a determined travel mode for a trip segment; 
 receiving a selection of a control; and 
 in response to selection of the control displaying a user interface that allows the user to split the trip segment into two actions. 
 
     
     
         23 . A method on a mobile device, the method comprising:
 identifying a dwelling episode during which the mobile device is not considered to be traveling;   determining a location for the dwelling episode;   determining whether the user of the mobile device performed any activities in the past within a set distance of the location of the dwelling episode;   when the user of the mobile device performed at least one activity in the past within the set distance of the location of the dwelling episode, classifying the dwelling episode as an activity type based on the at least one activity performed by the user in the past instead of using a more processor-intensive technique to classify the dwelling episode as an activity type.   
     
     
         24 . The method of  claim 23  wherein when the user of the mobile device did not perform at least one activity in the past within the set distance of the location of the dwelling episode, retrieving activities performed by other users of other mobile devices from a server and using the activities performed by other users to classify the dwelling episode as an activity type. 
     
     
         25 . (canceled) 
     
     
         26 . The method of  claim 23  further comprising:
 while the user is traveling from the location of the dwelling episode, presenting a user interface to the user to show the activity type that the dwelling episode was classified under and allowing the user to change the activity type. 
 
     
     
         27 . A method of improving a computing system used to classify actions into travel modes and activity types, the method comprising:
 classifying an action as one of an activity type and a travel mode;   displaying controls to allow a user to divide the action into two temporally shorter actions such that the controls allow the user to classify each of the shorter actions into one of an activity type and a travel mode;   receiving selections of the controls indicating how the user has classified the shorter actions;   based on how the user has classified the shorter actions, enhancing at least one method used by the computing system to classify actions into travel modes and activity types.   
     
     
         28 . The method of  claim 27  wherein displaying controls comprises displaying controls for each shorter action to allow the user to toggle between defining the shorter action as an activity or as a trip. 
     
     
         29 . The method of  claim 27  wherein displaying controls comprises displaying a time control that allows the user to change a time boundary between the shorter actions. 
     
     
         30 . The method of  claim 27  wherein enhancing at least one method used by the computing system to classify actions into travel modes and activity types comprises storing an activity type that a user classified a shorter action under so that the at least one method can use the stored activity type to determine an activity type for a future dwelling episode. 
     
     
         31 . The method of  claim 27  wherein enhancing at least one method used by the computing system to classify actions into travel modes and activity types comprises retraining at least one model based on how the user classified the shorter actions. 
     
     
         32 . The method of  claim 27  further comprising merging at least one of the shorter actions with another action that has the same classification to form a single action.