Context aware map application

• US 10,274,336 B2
• Filed: 09/26/2012
• Issued: 04/30/2019
• Est. Priority Date: 06/06/2012
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Piemonte, Patrick, Tu, Xiaoyuan, Moore, Christopher, Chen, Billy P., Blumenberg, Christopher, Pylappan, Seejo
• Primary Examiner(s): Bhat, Aditya S
• Application Number:
  US13/627,871
• Publication Number:
  US 20130332113A1
• Time in Patent Office: 2,407 Days
• Field of Search: 702189
• CPC Class Codes: G01C 21/367 Details, e.g. road map scale, orientation, zooming, illumination, level of detail, scrolling of road map or positioning of current position marker
• CPC Class Codes: G01S 19/14 specially adapted for specific applications
• CPC Class Codes: G01S 19/39 the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
• CPC Class Codes: G06F 11/3058 Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations thermal management in cooling arrangements of a computing system G06F1/206
• CPC Class Codes: G06F 11/3093 Configuration details thereof, e.g. installation, enabling, spatial arrangement of the probes
• CPC Class Codes: H04M 1/72454 according to context-related or environment-related conditions
• CPC Class Codes: H04M 1/72457 according to geographic location
• CPC Class Codes: H04M 2250/10 including a GPS signal receiver
• CPC Class Codes: H04M 2250/12 including a sensor for measuring a physical value, e.g. temperature or motion telephones including GPS signal receivers H04M2250/10

Abstract

The embodiments described relate to techniques and systems for utilizing a portable electronic device to monitor, process, present and manage data captured by a series of sensors and location awareness technologies to provide a context aware map and navigation application. The context aware map application offers a user interface including visual and audio input and output, and provides several map modes that can change based upon context determined by data captured by a series of sensors and location awareness technologies.

Claims

1. A method comprising:

detecting ambient activity from one or more outputs from a set of sensors on an electronic device;

filtering the ambient activity using a statistical model via a set of ambient activity profiles created from sample sensor data, the set of ambient activity profiles including at least a first activity profile and a second activity profile;

determining a change in ambient activity from the first activity profile to the second activity profile based on the filtering;

changing a mode of a mapping application executing on the electronic device in response to determining the change in ambient activity from the first activity profile to the second activity profile, wherein changing the mode of the mapping application includes transitioning a user interface (UI) of the mapping application operating in a first map mode associated with the first activity profile to operating in a second map mode associated with the second activity profile; and

switching from rendering map data for the mapping application according to the UI operating in the first map mode to rendering map data for the mapping application according to the UI operating in the second map mode.

2. The method as in claim 1, the statistical model is a Bayesian statistical model and the ambient activity includes output from multiple sensors selected from a set of sensors comprising a Global Positioning System (GPS) receiver, a proximity sensor, an ambient light sensor, an accelerometer, a touch input panel, an orientation sensor, or an electronic compass.

3. The method as in claim 1, wherein ambient activity profiles are created from sample sensor data during a training phase via linear discriminant analysis and wherein creating the ambient activity profiles comprises:

receiving ambient activity data from the set of sensors on the electronic device;

generating a data profile corresponding to received ambient activity data using linear discriminant analysis;

comparing the data profile with recognized ambient activity using a Bayesian classifier;

normalizing sensor output across device classes via the linear discriminant analysis and Bayesian classifier; and

adding received ambient activity to a set of recognized ambient activity profiles.

4. The method as in claim 1, wherein changing the mode of a mapping application executing on the electronic device additionally comprises:

storing sensor data while in the first map mode of the mapping application;

receiving a mode switch trigger based on the change in ambient activity;

changing the mode of the mapping application to a second mode;

receiving activity data from the set of sensors in accordance with a current activity session;

retrieving at least a portion of the sensor data stored while in the first map mode of the mapping application; and

processing the stored sensor data for the second mode of the mapping application.

5. The method as in claim 4, wherein the mapping application has map modes comprising a walking mode, a running or a driving mode.

6. The method as in claim 5, further comprising a mass transit mode or a cycling mode.

7. The method as in claim 5 or 6, wherein each mode has alternate mode variants comprising a day mode variant, and a night mode variant.

8. The method as in claim 7, wherein each alternate mode variant is determined by parameters comprising light level, current time, geographic location, and map data.

9. A machine implemented method at an electronic device, the method comprising:

receiving ambient activity data from one or more outputs from a set of sensors on the electronic device;

generating a data profile corresponding to received ambient activity data using linear discriminant analysis; and

comparing the data profile with recognized ambient activity using a Bayesian classifier;

normalizing sensor output across device classes via the linear discriminant analysis and Bayesian classifier;

adding received ambient activity data to a set of recognized ambient activity profiles including at least a first activity profile and a second activity profile;

determining if the received ambient activity data indicates a change from the first activity profile to the second activity profile;

changing a mode of a mapping application executing on the electronic device in response to determining the change from the first activity profile to the second activity profile, wherein changing the mode of the mapping application includes transitioning a user interface (UI) operating of the mapping application operating in a first mode associated with the first activity profile to operating in a second mode associated with the second activity profile; and

switching from rendering map data for the mapping application according to the UI operating in the first mode to rendering map data for the mapping application according to the UI operating in the second mode.

10. The machine implemented method as in claim 9, wherein the data profile for the received ambient activity data matches a data profile in a set of recognized ambient activity profiles including the first activity profile and second activity profile.

11. The machine implemented method as in claim 10, wherein the data profile for the received ambient activity data is added to the set of recognized ambient activity profiles.

12. A non-transitory machine-readable storage medium having instructions stored therein, which when executed by a machine cause the machine to perform operations, the operations comprising:

detecting ambient activity from one or more outputs from a set of sensors on an electronic device;

filtering the ambient activity using a statistical model via a set of ambient activity profiles created from sample sensor data, the set of ambient activity profiles including at least a first activity profile and a second activity profile;

determining a change in ambient activity from the first activity profile to the second activity profile based on the filtering;

changing a mode of a mapping application executing on the electronic device in response to determining the change in ambient activity from the first activity profile to the second activity profile,

wherein changing the mode of the mapping application includes transitioning the mapping application from operating with a first user interface (UI) template associated with the first activity profile to operating with a second UI template associated with the second activity profile; and

switching from rendering map data via the mapping application according to the first UI template to rendering map data via the mapping application according to the second UI template in response to changing the mode of the mapping application.

13. The machine-readable storage medium of claim 12, wherein the statistical model is a Bayesian statistical model and the ambient activity includes output from multiple sensors selected from a set of sensors comprising a Global Positioning System (GPS) receiver, a proximity sensor, an ambient light sensor, an accelerometer, a touch input panel, an orientation sensor, or an electronic compass.

14. The machine-readable storage medium of claim 13, wherein the Bayesian statistical model filters detected ambient activity using ambient activity profiles created from sample sensor data during a training phase via linear discriminant analysis and wherein creating the ambient activity profiles comprises:

receiving ambient activity data from the set of sensors on the electronic device;

generating a data profile corresponding to received ambient activity data using linear discriminant analysis;

comparing the data profile with recognized ambient activity using a Bayesian classifier;

normalizing sensor output across device classes via the linear discriminant analysis and Bayesian classifier; and

adding received ambient activity to a set of recognized ambient activity profiles including the first activity profile and second activity profile.

15. The machine-readable storage medium of claim 12, wherein launching or changing a mode of a mapping application executing on the electronic device comprises:

storing sensor data while in a first mode of the mapping application;

receiving a mode switch trigger based on the change in ambient activity;

changing the mode of the mapping application to a second mode;

receiving activity data from the set of sensors in accordance with a current activity session;

retrieving at least a portion of the sensor data stored while in the first mode of the mapping application; and

processing the stored sensor data for the second mode of the mapping application.

16. The machine-readable storage medium of claim 15, wherein the mapping application has map modes comprising a walking mode, a running mode or a driving mode, each mode with an alternate variant comprising at least a day mode and a night mode.

17. The machine-readable storage medium of claim 16, further comprising a mass transit mode or a cycling mode.

18. The machine-readable storage medium of claim 17, wherein the alternate mode variant of each mode is determined by parameters comprising light level, current time, geographic location, and map data.

19. An electronic device comprising:

one or more sensors, to sense ambient activity for the electronic device;

a data storage device, to store sensor data received from the one or more sensors; and

processing logic to execute a context aware map application, the context aware map application to cause the processing logic to;

detect ambient activity via sensor data from the one or more sensors while in a first map mode;

filter the sensor data using a statistical classifier to determine an activity profile associated with the ambient activity;

store sensor data associated with the ambient activity including a first activity profile and a second activity profile;

receive a trigger indicating a mode change for the context aware map application from a first map mode associated with the first activity profile to a second map mode associated with the second activity profile;

transition a user interface (UI) of the context aware map application from the first map mode to the second map mode in response to the ambient activity changing from the first activity profile to the second activity profile;

receive activity data from the one or more sensors in accordance with an activity session associated with the second map mode;

retrieve at least a portion of the stored sensor data;

process the stored sensor data for the second map mode of the context aware mapping application; and

switch from render map data for the context aware mapping application according to the first map mode to render map data for the mapping application according to the UI operating in the second map mode.

20. The electronic device as in claim 19, wherein the statistical classifier is a Bayesian statistical classifier.

21. The electronic device as in claim 19, wherein the first or second map mode is a walking mode, a running mode, or a driving mode.

22. The electronic device as in claim 19, wherein the first or second map mode is a mass transit mode or a cycling mode.

23. The electronic device as in claim 19, wherein each mode has alternate variants comprising a day mode variant, and a night mode variant and one or more of the alternate variants for the mode is determined by parameters comprising light level, current time, geographic location, and map data.

24. The electronic device as in claim 19, wherein the processing logic, in response to the trigger indicating the mode change for the context aware map application, is further to:

recognize sensor data characteristics associated with an activity; and

retrieve a template associated with the activity, the template to change a manner in which map data is displayed via the context aware map application.

25. The electronic device as in claim 24, the processing logic additionally configured to learn additional activity profiles associated with the ambient activity, wherein to learn the additional activity profiles, the processing logic is further to:

analyze and filter data to generate a data profile;

tag the data profile as a recognized data profile;

associate the recognized data profile with a map template;

update a recognized data profile database to include the recognized data profile and a link to the map template.

26. A non-transitory machine-readable storage medium having instructions stored therein, which when executed by a machine cause the machine to perform operations, the operations comprising:

detecting ambient activity from output of multiple sensors in a set of sensors on an electronic device;

filtering the ambient activity using a statistical model via a set of ambient activity profiles created from sample sensor data, the set of ambient activity profiles including at least a first activity profile and a second activity profile;

determining a change in ambient activity from the first activity profile to the second activity profile based on the filtering; and

changing a mode of a mapping application executing on the electronic device in response to determining the change in ambient activity from the first activity profile to the second activity profile, wherein changing the mode of the mapping application includes transitioning the mapping application from operating with a first user interface (UI) template associated with the first activity profile to operating with a second UI template associated with the second activity profile; and

switching from rendering map data via the mapping application according to the first UI template to rendering map data via the mapping application according to the second UI template after changing the mode of the mapping application.

27. The non-transitory machine-readable storage medium as in claim 26, wherein the statistical model is a Bayesian statistical model and the multiple sensors in the set of sensors include at least a Global Positioning System (GPS) receiver, an ambient light sensor and an accelerometer.