Systems and Methods for Room-Level Location Using WiFi
First Claim
1. A method of identifying a location of a mobile device in a building, performed at a server having one or more processors and memory, the method comprising:
- receiving base station signal strength measurements taken at a plurality of distinct points in the building, wherein the signals are received from a plurality of radio-transmitting base stations in the building, the building is partitioned into a plurality of regions, and at least one respective point of the distinct points is in each of the respective regions; and
training a respective region classifier for each respective region, wherein each region classifier is configured to compute a probability estimate that a test point is inside the respective region, the computation using inputs that are differences between signal strength measurements taken at the test point for signals received from the base stations.
2 Assignments
0 Petitions
Accused Products
Abstract
A method of identifying a location of a mobile device in a building includes identifying non-overlapping regions in a building. A server collects base station signal strength measurements at a plurality of distinct points in the building, with at least one point in each region. The server trains region classifiers for each region. Each region classifier is configured to compute a probability estimate that the test point is inside the region, using inputs that are signal strength differences. The server receives signal strength measurements from the base stations, taken by a mobile device at an unknown point. The server computes differences in signal strengths between pairs of base stations, and applies the region classifiers to the signal strength differences, thereby estimating the region where the mobile device is located. The server then transmits the estimated region to a user.
-
Citations
22 Claims
-
1. A method of identifying a location of a mobile device in a building, performed at a server having one or more processors and memory, the method comprising:
-
receiving base station signal strength measurements taken at a plurality of distinct points in the building, wherein the signals are received from a plurality of radio-transmitting base stations in the building, the building is partitioned into a plurality of regions, and at least one respective point of the distinct points is in each of the respective regions; and training a respective region classifier for each respective region, wherein each region classifier is configured to compute a probability estimate that a test point is inside the respective region, the computation using inputs that are differences between signal strength measurements taken at the test point for signals received from the base stations. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A system for determining a region in a building where a mobile device is located, comprising:
-
one or more processors; memory; and one or more programs stored in the memory, the one or more programs comprising instructions for; receiving base station signal strength measurements taken at a plurality of distinct points in the building, wherein the signals are received from a plurality of radio-transmitting base stations in the building, the building is partitioned into a plurality of regions, and at least one respective point of the distinct points is in each of the respective regions; and training a respective region classifier for each respective region, wherein each region classifier is configured to compute a probability estimate that a test point is inside the respective region, the computation using inputs that are differences between signal strength measurements taken at the test point for signals received from the base stations. - View Dependent Claims (9, 10, 11, 12, 13, 14)
-
-
15. A computer readable storage medium storing one or more programs configured for execution by a computer, the one or more programs comprising instructions for:
-
receiving base station signal strength measurements taken at a plurality of distinct points in a building, wherein the signals are received from a plurality of radio-transmitting base stations in the building, the building is partitioned into a plurality of regions, and at least one respective point of the distinct points is in each of the respective regions; and training a respective region classifier for each respective region, wherein each region classifier is configured to compute a probability estimate that the test point is inside the respective region, the computation using inputs that are differences between signal strength measurements taken at the test point for signals received from the base stations. - View Dependent Claims (16, 17, 18, 19, 20, 21)
-
-
22. A method of identifying a location of a mobile device in a building, performed at a server having one or more processors and memory, the method comprising:
-
receiving base station signal strength measurements taken at a plurality of distinct points in the building, wherein the signals are received from a plurality of radio-transmitting base stations in the building, the building is partitioned into a plurality of regions, and at least one respective point of the distinct points is in each of the respective regions; and building a respective known signal strength vector for each respective point comprising an ordered sequence of the base station identifiers, wherein the base station identifiers within each respective known signal strength vector are ordered by the signal strengths of the corresponding base stations as measured at the respective point; receiving signal strength measurements from at least a subset of the base stations, the measurements taken by a mobile device at an unknown point in the building; building a test signal strength vector comprising an ordered sequence of the base station identifiers, wherein the base station identifiers are ordered by the corresponding signal strengths; computing an edit distance between the test signal strength vector and at least a subset of the known signal strength vectors, wherein the edit distance between a pair of signal strength vectors comprises the minimum number of atomic operations required to transform one of the signal strength vectors in the pair into the other signal strength vector in the pair; selecting k known signal strength vectors whose corresponding edit distances from the test signal strength vector are the smallest of the computed edit distances, where k is a positive integer; determining a likely region where the mobile device is located based on the regions corresponding to the k known signal strength vectors; and transmitting that determination to a user seeking to identify the location of the mobile device.
-
Specification