# US 2019/0318028 A1 · Identifying functional zones within a geographic region

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

- Number: US 2019/0318028 A1
- Document ID: US20190318028A1
- Status: Published application
- Kind: A1
- Application number: 15/950,667
- Filed: 2018-04-11
- Published: 2019-10-17
- Earliest claimed: 2018-04-11
- Assignees: Nokia Technologies Oy
- Applicants: Nokia Technologies Oy
- Inventors: Jin Cao; Ran He; Yihao Zhang; Jingyuan Yang
- Web page: https://patentgrep.com/patent/US20190318028A1

## CPC

- G06F 16/2465: {Query processing support for facilitating data mining operations in structured databases}
- G06Q 10/00: Administration; Management
- G06F 16/248: Presentation of query results
- G06F 16/29: Geographical information databases
- G06N 20/00: Machine learning
- G06Q 10/08: Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A computer system may use machine learning to determine functional zones within a geographical region. The computer system may determine position data and functional data for locations within a geographical region. The computer system may use machine learning to determine functional zones with a two-stage clustering approach. During the first stage, the computer system may determine geoclusters by clustering locations based on the position data. During the second stage, the computer system may determine functional zones by clustering the geoclusters based on the functional data.

## Claims

### Claim 1

An apparatus comprising
at least one processor; and
at least one memory including computer program code;
the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus at least to perform:
identifying a geographic region;
determining, for each of multiple locations within the geographic region, position data;
determining geoclusters based on the position data, wherein each of the geoclusters includes a subset of the locations;
determining, for the locations, functional data;
determining, based on the functional data, feature vectors for each of the geoclusters;
determining functional zones within the geographical region by clustering, based on the feature vectors, the geoclusters; and
outputting the functional zones.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein the computer program code is configured to, with the at least one processor, cause the apparatus to perform the determining the geoclusters by clustering the locations based on density values computed for the locations.

### Claim 3 (depends on 1)

The apparatus of claim 1, wherein the computer program code is configured to, with the at least one processor, cause the apparatus to perform the determining the geoclusters by:
determining a corresponding set of nearest neighbors for each of the multiple locations, wherein, for each of the multiple locations, the corresponding set of nearest neighbors comprises a predetermined number of the other locations nearest to the location;
determining a similarity value for each pair of the locations, wherein, for each of the pairs, the similarity value indicates a commonality between the sets of nearest neighbors corresponding to the locations of the pair;
determining, for each of the pairs, whether the locations of the pair are similar by determining whether the similarity value for the pair satisfies a similarity threshold;
determining, for each location, a density value, wherein the density value indicates a number of the other locations determined to be similar to the location;
determining, for each of the locations, a classification based on the density value and the similarity value of the location; and
determining the geoclusters based on the classifications of the locations.

### Claim 4 (depends on 1)

The apparatus of claim 1, wherein the computer program code is configured to, with the at least one processor, cause the apparatus to obtain the position data and the functional data from separate sources.

### Claim 5 (depends on 1)

The apparatus of claim 1, wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus to perform:
classifying, based on the feature vectors of the geoclusters within each functional zone, the functional zones, wherein the classification of each functional zone indicates a type of activity associated with locations within the functional zone.

### Claim 6 (depends on 5)

The apparatus of claim 5, wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus to perform classifying the functional zones by averaging, for each functional zone, the feature vectors of the geoclusters that are within the functional zone.

### Claim 7 (depends on 5)

The apparatus of claim 5, wherein the functional data comprises data indicating, for each of at least a portion of the locations, one or more categories of human activity.

### Claim 8 (depends on 1)

The apparatus of claim 1, wherein the functional data comprises reviews associated with at least a portion of the locations, and wherein the at least one memory and the computer program code are configured to, with the at least one processor, cause the apparatus to perform the determining the feature vectors by:
determining, using a topic modeling algorithm, topics contained in the reviews;
determining, based on the topics, classifications for the at least a portion of the locations; and
determining the feature vectors for at least a portion of the geoclusters based on the classifications of the locations within the geocluster.

### Claim 9 (depends on 1)

The apparatus of claim 1, wherein the at least one memory and the computer program code are further configured to, with the at least one processor, cause the apparatus to perform:
normalizing the feature vectors after determining that one or more differences in magnitude between features of the feature vectors exceed a threshold.

### Claim 10

A method comprising:
identifying, by one or more computing devices, a geographic region;
determining, by the one or more computing devices and for each of multiple locations within the geographic region, position data;
determining, by the one or more computing devices, geoclusters based on the position data, wherein each of the geoclusters includes a subset of the locations;
determining, by the one or more computing devices and for the locations, functional data;
determining, by the one or more computing devices and based on the functional data, feature vectors for each of the geoclusters;
determining, by the one or more computing devices and based on the feature vectors, functional zones within the geographical region by clustering the geoclusters; and
outputting, by the one or more computing devices, the functional zones.

### Claim 11 (depends on 10)

The method of claim 10, wherein determining the geoclusters comprises clustering the locations based on density values computed for the locations.

### Claim 12 (depends on 10)

The method of claim 10, wherein the determining the geoclusters comprises:
determining a corresponding set of nearest neighbors for each of the multiple locations, wherein, for each of the multiple locations, the corresponding set of nearest neighbors comprises a predetermined number of the other locations nearest to the location;
determining a similarity value for each pair of the locations, wherein, for each of the pairs, the similarity value indicates a commonality between the sets of nearest neighbors corresponding to the locations of the pair;
determining, for each of the pairs, whether the locations of the pair are similar by determining whether the similarity value for the pair satisfies a similarity threshold;
determining, for each location, a density value, wherein the density value indicates a number of the other locations determined to be similar to the location;
determining, for each of the locations, a classification based on the density value and the similarity value of the location; and
determining the geoclusters based on the classifications of the locations.

### Claim 13 (depends on 10)

The method of claim 10, further comprising obtaining the position data and the functional data from separate sources.

### Claim 14 (depends on 10)

The method of claim 10, further comprising:
classifying, based on the feature vectors of the geoclusters within each functional zone, the functional zones, wherein the classification of each functional zone indicates a type of activity associated with locations within the functional zone.

### Claim 15 (depends on 14)

The method of claim 14, wherein classifying the functional zones comprises averaging, for each functional zone, the feature vectors of the geoclusters that are within the functional zone.

### Claim 16 (depends on 14)

The method of claim 14, wherein the functional data comprises data indicating, for each of at least a portion of the locations, one or more categories of human activity.

### Claim 17 (depends on 10)

The method of claim 10, wherein the functional data comprises reviews associated with at least a portion of the locations, and wherein determining the feature vectors comprises:
determining, using a topic modeling algorithm, topics contained in the reviews;
determining, based on the topics, classifications for the at least a portion of the locations; and
determining the feature vectors for at least a portion of the geoclusters based on the classifications of the locations within the geocluster.

### Claim 18 (depends on 10)

The method of claim 10, further comprising:
normalizing the feature vectors after determining that one or more differences in magnitude between features of the feature vectors exceed a threshold.

### Claim 19

A non-transitory computer-readable medium comprising program instructions for causing an apparatus to perform at least the following:
identifying a geographic region;
determining, for each of multiple locations within the geographic region, position data;
determining geoclusters based on the position data, wherein each of the geoclusters includes a subset of the locations;
determining, for the locations, functional data;
determining, based on the functional data, feature vectors for each of the geoclusters;
determining, based on the feature vectors, functional zones within the geographical region by clustering the geoclusters; and
outputting the functional zones.

### Claim 20 (depends on 19)

The computer-readable medium of claim 19, wherein the instructions, when executed, cause the apparatus to perform the determining the geoclusters by clustering the locations based on density values computed for the locations.
