# US 2024/0203043 A1 · Generative content system that supports location-based services and methods therefor

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

- Number: US 2024/0203043 A1
- Document ID: US20240203043A1
- Status: Published application
- Kind: A1
- Application number: 18/594,609
- Filed: 2024-03-04
- Published: 2024-06-20
- Earliest claimed: 2017-06-05
- Assignees: Umajin Inc.
- Applicants: Umajin Inc.
- Inventors: David Brebner
- Web page: https://patentgrep.com/patent/US20240203043A1

## CPC

- G01S 5/02522: {The radio-map containing measured values of non-radio values}
- G06T 15/205: {Image-based rendering}
- G01S 5/02521: {using a radio-map}
- G01S 5/0278: {involving statistical or probabilistic considerations (G01S5/0252, G01S5/0294 take precedence)}
- G06N 20/00: Machine learning
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06T 15/80: Shading
- H04B 17/318: Received signal strength
- H04W 4/021: Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
- H04W 4/029: Location-based management or tracking services
- H04W 4/33: for indoor environments, e.g. buildings
- G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04B: TRANSMISSION
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

A generative content system is disclosed. According to implementations, the generative content system generates literal representations of an environment based on data collected from a plurality of data sources that are selected in correspondence of the environment. In embodiments, the literal representations are used to generate a 3D rendering of the environment. In some embodiments, the generative content is used to support a location-based service system that locates devices based on a literal representation of an area as represented by the signal strengths observed throughout the area.

## Claims

### Claim 1

A method comprising:
receiving, by a processing system, a plurality of samples corresponding to an area to be sampled, wherein the plurality of samples are received from a plurality of different devices, wherein each sample is received from a respective device of the plurality of different devices and indicates a location at which the sample was taken, one or more network identifiers of respective network detected by the respective device, and, for each network identifier, a signal strength of a signal received from the respective network as measured by the device at the location;
generating, by the processing system, a plurality of sample nodes based on the plurality of samples, wherein each sample node corresponds to a respective sample from the plurality of samples and indicates the location at which the sample was taken, the one or more network identifiers detected at the location when the sample was taken, and the one or more signal strengths at the location;
generating, by the processing system, a graph based on the plurality of sample nodes, wherein the graph connects the sample nodes to point of interest nodes, wherein each point of interest node corresponds to a point of interest within the area;
generating, by the processing system, a simulated sample node based on an analysis of the graph, wherein the synthesized sample node indicates simulated sample data generated in response to identifying a missing signal strength or an outlier signal strength corresponding to a particular point of interest;
updating, by the processing system, the graph with the simulated sample node;
generating, by the processing system, a training data set based on the updated graph, wherein the training data set includes the simulated sample data;
training, by the processing system, a machine-learned classification model based on the training data, wherein the machine-learned classification model is configured to receive signal profiles indicating detected network identifiers and measured signal strengths corresponding to the detected network identifiers and to output one or more candidate locations within the area and, for each candidate location, a confidence score corresponding to the candidate location, wherein each candidate location corresponds to a different point of interest within the area; and
storing, by the processing system, the machine-learned model in a datastore, the machine-learned classification model being used in location-based services corresponding to the area.

### Claim 2 (depends on 1)

The method of claim 1, wherein the area is a building and the points of interest are rooms within the building.

### Claim 3 (depends on 1)

The method of claim 1, wherein each sample further indicates global positioning system satellite signals that were detected.

### Claim 4 (depends on 1)

The method of claim 1, wherein the network identifiers indicate one or more of detected WIFI networks, detected cellular networks, and detected Bluetooth networks.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
receiving a signal profile from a client device, wherein the signal profile indicates a list of detected network identifiers, and, for each detected network identifiers, a detected signal strength corresponding to the detected network identifiers;
determining a location estimate of the client device based on the signal profile and the machine-learned classification model.

### Claim 6 (depends on 5)

The method of claim 5, wherein determining the location estimate includes:
inputting the list of detected network identifiers and the detected signal strengths into the machine-learned classification model;
receiving a set of candidate locations and, for each candidate location, a respective confidence scores from the machine-learned classification model; and
determining the location estimate based on the set of candidate locations and the respective confidence scores.

### Claim 7 (depends on 6)

The method of claim 6, wherein determining the location estimate based on the set of candidate locations includes:
identifying one or more candidate locations having a respective confidence score that exceeds a threshold;
in response to determining that only one candidate location has a respective confidence score that exceeds the threshold, setting the location estimate based on the only one candidate location;
in response to determining that none of the candidate locations have a respective confidence score that exceeds the threshold or more than one candidate location have respective confidence scores that exceed the threshold:
generating a simulated data point based on the signal profile, the simulated data point indicating a simulated signal strength corresponding to a known network;
inputting the list of detected network identifiers, the detected signal strengths, the network identifier of the known network, and the simulated signal strength into the machine-learned classification model; and
determining the estimated location based on the output of the machine-learned classification model.

### Claim 8 (depends on 5)

The method of claim 5, wherein the machine-learned classification model is partitioned into a plurality of partitions, each partition corresponding to a different segment of the area.

### Claim 9 (depends on 8)

The method of claim 8, wherein determining the location estimate includes:
clustering the signal profile with the training data to obtain a plurality of clusters, each cluster corresponding to a respective segment of the area, wherein the signal profile is clustered into one of the clusters;
selecting a selected partition from the plurality of partitions based on the cluster of the signal profile; and
determining the location estimate based on the selected partition of the machine-learned classification model.

### Claim 10 (depends on 1)

The method of claim 1, wherein each sample indicates a device type of a device that transmitted the sample.

### Claim 11

A generative content system that performs location-based services, the generative content system comprising:
one or more processing devices;
memory that stores a plurality of computer-executable instructions that, when executed by the one or more processing devices, cause the one or more processing devices to:
receive a plurality of samples corresponding to an area to be sampled, wherein the plurality of samples are received from a plurality of different devices, wherein each sample is received from a respective device of the plurality of different devices and indicates a location at which the sample was taken, one or more network identifiers of respective network detected by the respective device, and, for each network identifier, a signal strength of a signal received from the respective network as measured by the device at the location;
generate a plurality of sample nodes based on the plurality of samples, wherein each sample node corresponds to a respective sample from the plurality of samples and indicates the location at which the sample was taken, the one or more network identifiers detected at the location when the sample was taken, and the one or more signal strengths at the location;
generate a graph based on the plurality of sample nodes, wherein the graph connects the sample nodes to point of interest nodes, wherein each point of interest node corresponds to a point of interest within the area;
generate a simulated sample node based on an analysis of the graph, wherein the synthesized sample node indicates simulated sample data generated in response to identifying a missing signal strength or an outlier signal strength corresponding to a particular point of interest;
update the graph with the simulated sample node;
generate a training data set based on the updated graph, wherein the training data set includes the simulated sample data;
train a machine-learned classification model based on the training data, wherein the machine-learned classification model is configured to receive signal profiles indicating detected network identifiers and measured signal strengths corresponding to the detected network identifiers and to output one or more candidate locations within the area and, for each candidate location, a confidence score corresponding to the candidate location, wherein each candidate location corresponds to a different point of interest within the area; and
store the machine-learned model in a datastore, the machine-learned classification model being used in location-based services corresponding to the area.

### Claim 12 (depends on 11)

The generative content system of claim 11, wherein the area is a building and the points of interest are rooms within the building.

### Claim 13 (depends on 11)

The generative content system of claim 11, wherein each sample further indicates global positioning system satellite signals that were detected.

### Claim 14 (depends on 11)

The generative content system of claim 11, wherein the network identifiers indicate one or more of detected WIFI networks, detected cellular networks, and detected Bluetooth networks.

### Claim 15 (depends on 11)

The generative content system of claim 11, further comprising:
receiving a signal profile from a client device, wherein the signal profile indicates a list of detected network identifiers, and, for each detected network identifiers, a detected signal strength corresponding to the detected network identifiers;
determining a location estimate of the client device based on the signal profile and the machine-learned classification model.

### Claim 16 (depends on 15)

The generative content system of claim 15, wherein determining the location estimate includes:
inputting the list of detected network identifiers and the detected signal strengths into the machine-learned classification model;
receiving a set of candidate locations and, for each candidate location, a respective confidence scores from the machine-learned classification model; and
determining the location estimate based on the set of candidate locations and the respective confidence scores.

### Claim 17 (depends on 16)

The generative content system of claim 16, wherein determining the location estimate based on the set of candidate locations includes:
identifying one or more candidate locations having a respective confidence score that exceeds a threshold;
in response to determining that only one candidate location has a respective confidence score that exceeds the threshold, setting the location estimate based on the only one candidate location;
in response to determining that none of the candidate locations have a respective confidence score that exceeds the threshold or more than one candidate location have respective confidence scores that exceed the threshold:
generating a simulated data point based on the signal profile, the simulated data point indicating a simulated signal strength corresponding to a known network;
inputting the list of detected network identifiers, the detected signal strengths, the network identifier of the known network, and the simulated signal strength into the machine-learned classification model; and
determining the estimated location based on the output of the machine-learned classification model.

### Claim 18 (depends on 15)

The generative content system of claim 15, wherein the machine-learned classification model is partitioned into a plurality of partitions, each partition corresponding to a different segment of the area.

### Claim 19 (depends on 18)

The generative content system of claim 18, wherein determining the location estimate includes:
clustering the signal profile with the training data to obtain a plurality of clusters, each cluster corresponding to a respective segment of the area, wherein the signal profile is clustered into one of the clusters;
selecting a selected partition from the plurality of partitions based on the cluster of the signal profile; and
determining the location estimate based on the selected partition of the machine-learned classification model.

### Claim 20 (depends on 11)

The generative content system of claim 11, wherein each sample indicates a device type of a device that transmitted the sample.
