Smoothed activity signals for suggestion ranking

• US 9,532,176 B1
• Filed: 11/26/2013
• Issued: 12/27/2016
• Est. Priority Date: 11/26/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Gordon, David R., Kosakai, Takahiro, Sawa, Yuta
• Primary Examiner(s): Khan, Suhail
• Application Number:
  US14/090,500
• Time in Patent Office: 1,127 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/90324 using system suggestions
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
• CPC Class Codes: G06Q 30/0259 based on store location
• CPC Class Codes: H04W 4/021 Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
• CPC Class Codes: H04W 4/024 Guidance services
• CPC Class Codes: H04W 4/025 using location based information parameters
• CPC Class Codes: H04W 4/029 Location-based management or tracking services
• CPC Class Codes: H04W 4/42 for mass transport vehicles, e.g. buses, trains or aircraft

Abstract

Relevant geospatial data is provided to a portable device. In particular, several activity detection results collected over a period of time, spanning several time intervals, are received, where each activity detection result provides an estimate of the portable device activity, and where the activity detection results indicate at least two different activities. A single predominant activity of the portable device is determined using the activity detection results. Based on the predominant activity, geospatial data is selected and then provided to the portable device.

Claims

1. A method for providing relevant geospatial data to a portable device, the method comprising:

receiving, by one or more processors, a plurality of activity detection results collected over a period of time, wherein the period of time spans a plurality of intervals, wherein each of the activity detection results provides an estimate of a mode of transport of the portable device during a respective one of the plurality of intervals, and wherein at least two of the plurality of activity detection results indicate different modes of transport;

determining, by the one or more processors, a single predominant mode of transport of the portable device during the period of time, using the plurality of activity detection results, including;

for each mode of transport, determining a number of activity detection results within the period of time that correspond to the mode of transport and assigning a respective weight to each of the activity detection results based on the corresponding mode of transport; and

determining the single predominant mode of transport according to the number of activity detection results and the weights assigned to the activity detection results for each mode of transport;

causing, by the one or more processors, geospatial data to be selected based on the predominant mode of transport of the portable device, the geospatial data including points of interest (POIs) selected based on accessibility to the POIs based on the predominant mode of transport, wherein a first set of POIs are selected when the predominant mode of transport is a first predominant mode of transport and a second set of POIs are selected when the predominant mode of transport is a second predominant mode of transport which is different from the first predominant mode of transport; and

causing, by the one or more processors, search suggestions including the geospatial data to be provided to the portable device.

2. The method of claim 1, wherein each of the plurality of activity detection results indicates a mode of transport selected from a set including (i) driving, (ii) riding in a public transit vehicle, (iii) bicycling, (iv) walking, and (v) being substantially stationary.

3. The method of claim 1, wherein assigning a respective weight to each of the activity detection results based on the corresponding mode of transport includes applying, by the one or more processors, a thresholding function to eliminate outliers in the plurality of activity detection results.

4. The method of claim 1, wherein the plurality of activity detection results are received from the portable device, the method further comprising:

receiving, by the one or more processors, respective weights assigned to the plurality of activity detection results by the portable device in view of levels of confidence associated with the plurality of activity detection results.

5. The method of claim 1, wherein determining the single predominant mode of transport using the plurality of activity detection results includes:

determining, by the one or more processors, aggregate scores for each mode of transport indicated by the plurality of activity detection results to generate a plurality of candidate modes of transport,

selecting as the predominant mode of transport, from among the plurality of candidate modes of transport, a mode of transport with an aggregate score that exceeds aggregates scores of the rest of the plurality of candidate modes of transport by a confidence threshold value.

6. The method of claim 1, wherein the period of time is between one and ten minutes long.

7. The method of claim 6, wherein each of the plurality of intervals is between one and 20 seconds long.

8. The method of claim 1, further comprising:

receiving, by the one or more processors, a geospatial query submitted via a user interface of portable device;

wherein causing the geospatial data to be selected includes;

obtaining candidate geospatial data responsive to the geospatial query, and

selecting a subset of the candidate geospatial data that corresponds to the single predominant mode of transport, as the geospatial data.

9. The method of claim of claim 1, wherein the plurality of activity detection results are generated at the portable device, and wherein determining the single predominant mode of transport of the portable device during the period of time is implemented in a network server coupled to the portable device via a communication network.

10. A computing device comprising:

a communication interface;

one or more processors coupled to the communication interface;

a non-transitory computer-readable memory coupled to the one or more processors and storing thereon instructions that, when executed by the one or more processors, cause the computing device to;

receive, via the communication interface from a portable device, a plurality of activity detection results collected over a period of time, wherein the period of time spans a plurality of intervals, wherein each of the activity detection results provides an estimate of a mode of transport of the portable device during a respective one of the plurality of intervals, and wherein at least two of the plurality of activity detection results indicate different modes of transport;

determine a single predominant mode of transport of the portable device during the period of time, using the plurality of activity detection results, including;

for each mode of transport, determine a number of activity detection results within the period of time that correspond to the mode of transport and assign a respective weight to each of the activity detection results based on the corresponding mode of transport; and

determine the single predominant mode of transport according to the number of activity detection results and the weights assigned to the activity detection results for each mode of transport;

cause geospatial data to be selected based on the predominant mode of transport of the portable device, the geospatial data including points of interest (POIs) selected based on accessibility to the POIs based on the predominant mode of transport, wherein a first set of POIs are selected when the predominant mode of transport is a first predominant mode of transport and a second set of POIs are selected when the predominant mode of transport is a second predominant mode of transport which is different from the first predominant mode of transport; and

cause search suggestions including the geospatial data to be provided to the portable device.

11. The computing device of claim 10, wherein each of the plurality of activity detection results indicates a mode of transport selected from a set including (i) driving, (ii) riding in a public transit vehicle, (iii) bicycling, (iv) walking, and (v) being substantially stationary.

12. The computing device of claim 10, wherein to assign a respective weight to each of the activity detection results based on the corresponding mode of transport includes applying a thresholding function to eliminate outliers in the plurality of activity detection results.

13. The computing device of claim 10, wherein the instructions further cause the system to:

receive, via the communication network, respective weights assigned to the plurality of activity detection results by the portable device in view of levels of confidence associated with the plurality of activity detection results.

14. The computing device of claim 10, wherein to determine the single predominant mode of transport using the plurality of activity detection results, the instructions cause the system to:

determine aggregate scores for each mode of transport indicated by the plurality of activity detection results to generate a plurality of candidate modes of transport,

select as the predominant mode of transport, from among the plurality of candidate modes of transport, a mode of transport with an aggregate score that exceeds aggregates scores of the rest of the plurality of candidate modes of transport by a confidence threshold value.

15. A non-transitory computer-readable medium storing instructions for providing relevant geospatial data to a portable device, when executed by one or more processors in a computing device, cause the one or more processors to:

receive, via a communication interface from a portable device, a plurality of activity detection results collected over a period of time, wherein the period of time spans a plurality of intervals, wherein each of the activity detection results provides an estimate of a mode of transport of the portable device during a respective one of the plurality of intervals, and wherein at least two of the plurality of activity detection results indicate different modes of transport;

determine a single predominant mode of transport of the portable device during the period of time, using the plurality of activity detection results, including;

for each mode of transport, determine a number of activity detection results within the period of time that correspond to the mode of transport and assign a respective weight to each of the activity detection results based on the corresponding mode of transport; and

determine the single predominant mode of transport according to the number of activity detection results and the weights assigned to the activity detection results for each mode of transport;

cause geospatial data to be selected based on the predominant mode of transport of the portable device, the geospatial data including points of interest (POIs) selected based on accessibility to the POIs based on the predominant mode of transport, wherein a first set of POIs are selected when the predominant mode of transport is a first predominant mode of transport and a second set of POIs are selected when the predominant mode of transport is a second predominant mode of transport which is different from the first predominant mode of transport; and

cause the geospatial data to be provided to the portable device.

16. The computer-readable medium of claim 15, wherein each of the plurality of activity detection results indicates a mode of transport selected from a set including (i) driving, (ii) riding in a public transit vehicle, (iii) bicycling, (iv) walking, and (v) being substantially stationary.

17. The computer-readable medium of claim 15, wherein to assign a respective weight to each of the activity detection results based on the corresponding mode of transport includes applying a thresholding function to eliminate outliers in the plurality of activity detection results.