# US 2025/0156446 A1 · Labeling assistance system, labeling assistance method, and labeling assistance program

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

- Number: US 2025/0156446 A1
- Document ID: US20250156446A1
- Status: Published application
- Kind: A1
- Application number: 18/836,438
- Filed: 2022-03-02
- Published: 2025-05-15
- Earliest claimed: 2022-03-02
- Assignees: NEC Corporation
- Applicants: NEC Corporation
- Inventors: Noritaka Yamashita; Takuroh Kashima; Norihito Oi; Asako Fujii
- Web page: https://patentgrep.com/patent/US20250156446A1

## CPC

- G06F 16/285: {Clustering or classification}
- G06F 16/75: Clustering; Classification
- G06F 16/906: Clustering; Classification
- G16Y 40/20: Analytics; Diagnosis
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G16Y: INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]

## Abstract

The classification means 191 generates a plurality of clusters by classifying data to be labeled through unsupervised learning. The search means 192 searches for common points of the data included in each generated cluster. The output means 193 outputs information on the searched common points for each cluster.

## Claims

### Claim 1

A labeling assistance system comprising:
a memory storing instructions; and
one or more processors configured to execute the instructions to:
generate a plurality of clusters by classifying data to be labeled through unsupervised learning;
search for common points of the data included in each generated cluster; and
output information on the searched common points for each cluster.

### Claim 2 (depends on 1)

The labeling assistance system according to claim 1, wherein the processor is configured to execute the instructions to:
extract features of each data included in the generated clusters; and
search for the common points of the features extracted for each data within the cluster.

### Claim 3 (depends on 1)

The labeling assistance system according to claim 1, wherein the processor is configured to execute the instructions to:
extract features based on sensor values included in the data to be labeled;
calculate contribution of the sensor values to the features; and
output the sensor value with the highest contribution as a common point.

### Claim 4 (depends on 3)

The labeling assistance system according to claim 3, wherein the processor is configured to execute the instructions to
display the contribution of each sensor within the cluster.

### Claim 5 (depends on 1)

The labeling assistance system according to claim 1, wherein the processor is configured to execute the instructions to
label and output information indicating the common point searched within each cluster for the data to be labeled.

### Claim 6 (depends on 1)

The labeling assistance system according to claim 1, wherein the processor is configured to execute the instructions to
output multiple common points searched within the cluster according to the degree of commonality.

### Claim 7 (depends on 6)

The labeling assistance system according to claim 6, wherein the processor is configured to execute the instructions to
output the common points with the highest degree of commonality as labeling candidates in a ranking format up to a predetermined rank.

### Claim 8

A labeling assistance method comprising:
generating a plurality of clusters by classifying data to be labeled through unsupervised learning, by a computer;
searching for common points of the data included in each generated cluster, by the computer; and
outputting information on the searched common points for each cluster, by the computer.

### Claim 9 (depends on 8)

The labeling assistance method according to claim 8, wherein
features of each data included in the generated clusters are extracted by the computer, and
the common points of the features extracted for each data within the cluster are searched by the computer.

### Claim 10

A non-transitory computer readable information recording medium storing a labeling assistance program, when executed by a processor, that performs a method for:
generating a plurality of clusters by classifying data to be labeled through unsupervised learning;
searching for common points of the data included in each generated cluster; and
outputting information on the searched common points for each cluster.

### Claim 11 (depends on 10)

The non-transitory computer readable information recording medium according to claim 10, the labeling assistance program further performs a method for:
extracting features of each data included in the generated clusters in the classification process; and
searching for common points of the features extracted for each data within the cluster in the search process.
