# US 2017/0289764 A1 · Self-learning locator for mobile device

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2017/0289764 A1
- Document ID: US20170289764A1
- Status: Published application
- Kind: A1
- Application number: 15/087,161
- Filed: 2016-03-31
- Published: 2017-10-05
- Earliest claimed: 2016-03-31
- Assignees: Intel Corporation
- Applicants: Intel Corporation
- Inventors: Lei Yang; Jared B. Counts; Xue Yang; Shao-Wen Yang; Arvind Kumar
- Web page: https://patentgrep.com/patent/US20170289764A1

## CPC

- H04W 4/025: {using location based information parameters}
- H04W 4/023: {using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds}
- H04W 4/027: {using movement velocity, acceleration information}
- H04W 4/029: Location-based management or tracking services
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

A system for locating a mobile device includes an input that accesses a plurality of scans of wireless network access signaling, where the scans indicate received signal measurement results. A similarity measure module executes comparisons between the data of different scans in order to assess the similarity between those scans. The comparisons produce multi-dimensional comparison results. A dimension reduction module reduces dimensionality of the multi-dimensional comparison results to produce a dimension-reduced set of comparison results. A clustering module identifies groupings of similar scans based on the dimension-reduced set of comparison results.

## Claims

### Claim 1

A system for locating a mobile device, the system comprising a computing platform to implement:
an input module to access a plurality of scans of wireless network access signaling, the scans indicating received signal measurement results;
a similarity measure module to compute comparisons between the data of different scans in order to assess the similarity between those scans, wherein the comparisons produce multi-dimensional comparison results;
a dimension reduction module to map the multi-dimensional comparison results to a lower-dimensional space to reduce dimensionality while maintaining similarity properties of the multi-dimensional comparison results, the similarity properties including at least one of distances, variation, or structure, to thereby produce a dimension-reduced set of comparison results; and
a clustering module to identify groupings of similar scans based on the dimension-reduced set of comparison results.

### Claim 2 (depends on 1)

The system of claim 1, further comprising:
an input data filter module to test if a circumstance surrounding the scan renders the scan unsuitable for further processing as an indicator of location of the mobile device.

### Claim 3 (depends on 2)

The system of claim 2, wherein the circumstance that renders the scan unsuitable includes a motion indicator being indicative of motion of the mobile device.

### Claim 4 (depends on 2)

The system of claim 2, wherein the circumstance that renders the scan unsuitable includes a prior location classification of a prior scan having assessed similarity to the scan.

### Claim 5 (depends on 1)

The system of claim 1, further comprising:
a disjoint location detector module to recognize a circumstance where the mobile device is in an entirely different location.

### Claim 6 (depends on 1)

The system of claim 1, further comprising:
a data bucket module to apply a quantity threshold representing a target quantity of collected scans to be subject to clustering by the clustering module.

### Claim 7 (depends on 1)

The system of claim 1, further comprising:
a cluster merge module to apply an inter-cluster similarity measure and, in response to the inter-cluster similarity measure exceeding a threshold, to merge the clusters based on measured inter-cluster similarity.

### Claim 8 (depends on 1)

The system of claim 1, wherein the similarity measure module applies Euclidian distance assessments of pairs of scans.

### Claim 9 (depends on 1)

The system of claim 1, wherein the system is incorporated in the mobile device.

### Claim 10 (depends on 1)

The system of claim 1, further comprising:
a user annotation module to facilitate a user interface responsive to commands of a user to annotate the groupings of similar scans according to a physical location to be associated with each of the groupings.

### Claim 11

A machine-implemented method for locating a mobile device, the method comprising:
accessing a plurality of scans of wireless network access signaling, the scans indicating received signal measurement results;
computing comparisons between the data of different scans in order to assess similarity between those scans, wherein the comparisons produce multi-dimensional comparison results;
reducing dimensionality while maintaining similarity properties of the multi-dimensional comparison results, the similarity properties including at least one of distances, variation, or structure, including mapping the multi-dimensional comparison results to a lower-dimensional space, to produce a dimension-reduced set of comparison results; and
identifying groupings of similar scans based on the dimension-reduced set of comparison results.

### Claim 12 (depends on 11)

The method of claim 11, further comprising:
computationally testing whether a circumstance surrounding the scan renders the scan unsuitable for further processing as an indicator of location of the mobile device.

### Claim 13 (depends on 11)

The method of claim 11, further comprising:
applying a quantity threshold representing a target quantity of collected scans to be subject to clustering.

### Claim 14 (depends on 11)

The method of claim 11, further comprising:
applying an inter-cluster similarity measure and, in response to the inter-cluster similarity measure exceeding a threshold, merging the clusters based on measured inter-cluster similarity.

### Claim 15 (depends on 11)

The method of claim 11, wherein computing the comparisons between the data of different scans includes applying Euclidian distance assessments of pairs of scans.

### Claim 16 (depends on 11)

The method of claim 11, further comprising:
providing a user interface responsive to commands of a user to annotate the groupings of similar scans according to a physical location to be associated with each of the groupings.

### Claim 17

At least one non-transitory computer-readable medium containing instructions that, when executed on a computing platform, cause the computing platform to execute operations comprising:
accessing a plurality of scans of wireless network access signaling, the scans indicating received signal measurement results;
computing comparisons between the data of different scans in order to assess similarity between those scans, wherein the comparisons produce multi-dimensional comparison results;
reducing dimensionality while maintaining similarity properties of the multi-dimensional comparison results, the similarity properties including at least one of distances, variation, or structure, including mapping the multi-dimensional comparison results to a lower-dimensional space, to produce a dimension-reduced set of comparison results; and
identifying groupings of similar scans based on the dimension-reduced set of comparison results.

### Claim 18 (depends on 17)

The at least one computer-readable medium of claim 17, further comprising:
instructions for computationally testing whether a circumstance surrounding the scan renders the scan unsuitable for further processing as an indicator of location of the mobile device.

### Claim 19 (depends on 18)

The at least one computer-readable medium of claim 18, further comprising:
instructions for determining the scan to be unsuitable in response to a motion indicator being indicative of motion of the mobile device.

### Claim 20 (depends on 18)

The at least one computer-readable medium of claim 18, further comprising:
instructions for determining the scan to be unsuitable in response to a presence of a prior location classification of a prior scan having an assessed similarity to the scan.

### Claim 21 (depends on 17)

The at least one computer-readable medium of claim 17, further comprising:
instructions for detecting a circumstance where the mobile device is in an entirely different location.

### Claim 22 (depends on 17)

The at least one computer-readable medium of claim 17, further comprising:
instructions for applying a quantity threshold representing a target quantity of collected scans to be subject to clustering.

### Claim 23 (depends on 17)

The at least one computer-readable medium of claim 17, further comprising:
instructions for applying an inter-cluster similarity measure and, in response to the inter-cluster similarity measure exceeding a threshold, merging the clusters based on measured inter-cluster similarity.

### Claim 24 (depends on 17)

The at least one computer-readable medium of claim 17, wherein the instructions for computing the comparisons between the data of different scans include instructions for applying Euclidian distance assessments of pairs of scans.

### Claim 25 (depends on 17)

The at least one computer-readable medium of claim 17, further comprising:
instructions for providing a user interface responsive to commands of a user to annotate the groupings of similar scans according to a physical location to be associated with each of the groupings.
