Venue identification using sensor fingerprints
When a mobile device is known to be at a venue, readings from one or more sensors of the device are used to generate a sensor fingerprint of the venue and/or a venue category corresponding to the venue. The sensor fingerprint indicates typical sensor readings for the one or more physical sensors for devices that are located at the venue and/or venues of the same category. Sensor fingerprints can also be generated for other circumstances associated with the mobile device, such as the activity being undertaken by the corresponding user and a type of event currently occurring at the venue. Fingerprints can also be generated for combinations of circumstances, such as a particular activity at a certain category of venue. When location data cannot distinguish at which venue a mobile device is located, sensor fingerprints are compared to sensor readings received from the device to resolve this ambiguity.
1. A method for determining a venue of a mobile device, the method comprising:
receiving location data describing a geographical location of a mobile device, a sensor reading collected by a physical sensor of the mobile device, the sensor reading quantifying a physical property of an environment around the mobile device, and a collection time at which the sensor reading was collected by the physical sensor;
identifying candidate venues based on the location data, the candidate venues located within a threshold distance of the geographical location;
retrieving, from a fingerprint database, sensor fingerprints corresponding to the candidate venues, a sensor fingerprint comprising typical sensor readings from the physical sensor at a corresponding candidate venue, the sensor fingerprints including a time-specific sensor fingerprint comprising typical sensor readings from the physical sensor at the corresponding candidate venue during a recurring time period that includes the collection time; and
determining a venue of the mobile device by comparing the sensor reading to the typical sensor readings of the retrieved sensor fingerprints.
2. The method of claim 1 , wherein determining the venue of the mobile device comprises:
determining scores indicating degrees to which the sensor reading matches the typical sensor readings of the sensor fingerprints;
selecting a sensor fingerprint from the retrieved sensor fingerprints based on the determined scores; and
determining the venue of the mobile device from a candidate venue corresponding to the selected sensor fingerprint.
3. The method of claim 1 , wherein determining the venue of the mobile device comprises:
determining whether the sensor reading is within a threshold tolerance from a typical sensor reading of a candidate sensor fingerprint of the retrieved sensor fingerprints; and
responsive to determining that the sensor reading is within the threshold tolerance from the typical sensor reading, determining the venue of the mobile device from a candidate venue corresponding to the candidate fingerprint.
4. The method of claim 3 , wherein determining whether the sensor reading is within the threshold tolerance from the typical sensor reading comprises:
obtaining, from the candidate sensor fingerprint, a measure of sensor reading variability specific to a sensor reading type of the sensor reading; and
determining whether the sensor reading is within the measure of sensor reading variability from the typical sensor reading.
5. The method of claim 1 , wherein retrieving sensor fingerprints comprises:
for a candidate venue of the candidate venues, determining that the fingerprint database lacks a venue fingerprint comprising typical sensor readings for the physical sensor at the candidate venue;
identifying a venue category of the candidate venue; and
retrieving a venue category fingerprint generated by aggregating sensor readings collected at venues other than the candidate venue in the venue category.
6. The method of claim 1 , wherein retrieving sensor fingerprints comprises:
for a candidate venue of the candidate venues, determining that the fingerprint database comprises a venue fingerprint generated from fewer than a threshold number of typical sensor readings;
identifying a venue category of the candidate venue;
retrieving a venue category fingerprint generated by aggregating sensor readings collected at venues in the venue category including at least one venue other than the candidate venue; and
generating a hybrid fingerprint comprising typical sensor readings determined from a weighted average of sensor readings collected at the candidate venue and typical sensor readings indicated by the venue category fingerprint.
7. The method of claim 1 , wherein retrieving sensor fingerprints comprises:
obtaining a device type of the mobile device; and
retrieving a device-specific sensor fingerprint generated from sensor readings taken at one of the candidate venues by mobile devices of the obtained device type.
8. The method of claim 1 , wherein the physical sensor is selected from a group consisting of: a camera, a microphone, an accelerometer, a thermometer, and a barometer.
9. A system for determining a venue of a mobile device, the system comprising:
a processor;
a non-transitory, computer-readable medium comprising instructions executable by the processor, the instructions comprising instructions for:
receiving location data describing a geographical location of a mobile device, a sensor reading collected by a physical sensor of the mobile device, the sensor reading quantifying a physical property of an environment around the mobile device, and a collection time at which the sensor reading was collected by the physical sensor;
identifying candidate venues based on the location data, the candidate venues located within a threshold distance of the geographical location;
retrieving, from a fingerprint database, sensor fingerprints corresponding to the candidate venues, a sensor fingerprint comprising typical sensor readings from the physical sensor at a corresponding candidate venue, the sensor fingerprints including a time-specific sensor fingerprint comprising typical sensor readings from the physical sensor at the corresponding candidate venue during a recurring time period that includes the collection time; and
determining a venue of the mobile device by comparing the sensor reading to the typical sensor readings of the retrieved sensor fingerprints.
10. The system of claim 9 , wherein determining the venue of the mobile device comprises:
determining scores indicating degrees to which the sensor reading matches the typical sensor readings of the sensor fingerprints;
selecting a sensor fingerprint from the retrieved sensor fingerprints based on the determined scores; and
determining the venue of the mobile device from a candidate venue corresponding to the selected sensor fingerprint.
11. The system of claim 9 , wherein determining the venue of the mobile device comprises:
determining whether the sensor reading is within a threshold tolerance from a typical sensor reading of a candidate sensor fingerprint of the retrieved sensor fingerprints; and
responsive to determining that the sensor reading is within the threshold tolerance from the typical sensor reading, determining the venue of the mobile device from a candidate venue corresponding to the candidate fingerprint.
12. The system of claim 11 , wherein determining whether the sensor reading is within the threshold tolerance from the typical sensor reading comprises:
obtaining, from the candidate sensor fingerprint, a measure of sensor reading variability specific to a sensor reading type of the sensor reading; and
determining whether the sensor reading is within the measure of sensor reading variability from the typical sensor reading.
13. The system of claim 9 , wherein retrieving sensor fingerprints comprises:
for a candidate venue of the candidate venues, determining that the fingerprint database lacks a venue fingerprint comprising typical sensor readings for the physical sensor at the candidate venue;
identifying a venue category of the candidate venue; and
retrieving a venue category fingerprint generated by aggregating sensor readings collected at venues other than the candidate venue in the venue category.
14. The system of claim 9 , wherein retrieving sensor fingerprints comprises:
for a candidate venue of the candidate venues, determining that the fingerprint database comprises a venue fingerprint generated from fewer than a threshold number of typical sensor readings;
identifying a venue category of the candidate venue;
retrieving a venue category fingerprint generated by aggregating sensor readings collected at venues in the venue category including at least one venue other than the candidate venue; and
generating a hybrid fingerprint comprising typical sensor readings determined from a weighted average of sensor readings collected at the candidate venue and typical sensor readings indicated by the venue category fingerprint.
15. The system of claim 9 , wherein retrieving sensor fingerprints comprises:
obtaining a device type of the mobile device; and
retrieving a device-specific sensor fingerprint generated from sensor readings taken at one of the candidate venues by mobile devices of the obtained device type.
16. The system of claim 9 , wherein the physical sensor is selected from a group consisting of: a camera, a microphone, an accelerometer, a thermometer, and a barometer.
17. A non-transitory, computer-readable medium comprising instructions executable by a processor, the instructions comprising instructions for:
receiving location data describing a geographical location of a mobile device, a sensor reading collected by a physical sensor of the mobile device, the sensor reading quantifying a physical property of an environment around the mobile device, and a collection time at which the sensor reading was collected by the physical sensor;
identifying candidate venues based on the location data, the candidate venues located within a threshold distance of the geographical location;
retrieving, from a fingerprint database, sensor fingerprints corresponding to the candidate venues, a sensor fingerprint comprising typical sensor readings from the physical sensor at a corresponding candidate venue, the sensor fingerprints including a time-specific sensor fingerprint comprising typical sensor readings from the physical sensor at the corresponding candidate venue during a recurring time period that includes the collection time; and
determining a venue of the mobile device by comparing the sensor reading to the typical sensor readings of the retrieved sensor fingerprints.
18. The computer-readable medium of claim 17 , wherein the physical sensor is selected from a group consisting of: a camera, a microphone, an accelerometer, a thermometer, and a barometer.