# US 2023/0068757 A1 · Work rate measurement device and work rate measurement method

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

- Number: US 2023/0068757 A1
- Document ID: US20230068757A1
- Status: Published application
- Kind: A1
- Application number: 17/796,335
- Filed: 2021-02-08
- Published: 2023-03-02
- Earliest claimed: 2020-02-18
- Assignees: NEC Platforms, Ltd.
- Applicants: NEC Platforms, Ltd.
- Inventors: Yutaka MATSUBAYASHI
- Web page: https://patentgrep.com/patent/US20230068757A1

## CPC

- G06Q 10/06398: {Performance of employee with respect to a job function}
- G06Q 50/04: Manufacturing
- G06Q 10/06: Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q 10/0639: Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06V 10/764: using classification, e.g. of video objects
- G06V 40/28: {Recognition of hand or arm movements, e.g. recognition of deaf sign language (static hand signs G06V40/113)}
- Y02P 90/30: Computing systems specially adapted for manufacturing
- 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
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- Y02P: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS

## Abstract

A work rate measurement device is used for measuring a work rate when manual work is performed within a prescribed work frame provided for each of a plurality of steps. The device captures an image within the work frame using cameras installed for the plurality of steps, causes machine learning to be performed on a hand of a worker held within the work frame based on the captured data, and generates a machine learning model for each of the cameras. The device analyzes whether or not a position of a hand of a worker is included within the work frame with respect to an image of actual work being performed using the generated machine learning model and saves, in chronological order, analysis data obtained by the analysis. The device determines a work rate within each work frame using the saved analysis data.

## Claims

### Claim 1

A work rate measurement device for measuring a work rate when manual work is performed within a prescribed work frame provided for each of a plurality of steps, the work rate measurement device comprising:
at least one memory configured to store instructions; and
at least one processor configured to execute the instructions to:
capture an image within the work frame using cameras installed for the plurality of steps, cause machine learning to be performed on a hand of a worker held within the work frame based on the captured data, and generate a machine learning model for each of the cameras;
analyze whether or not a position of a hand of a worker is included within the work frame with respect to an image of actual work being performed using the generated machine learning model and save, in chronological order, analysis data obtained by the analysis; and
determine a work rate within each work frame using the saved analysis data.

### Claim 2 (depends on 1)

The work rate measurement device according to claim 1, wherein the at least one processor is configured to execute the instructions to cause the machine learning to be performed based on a state change in which a hand of a worker in the work frame is made to move the hand to be at least one of palm upward, palm downward or rotated, or at least one background work environment among brightness, angle of view, type, brightness and glare in vicinity of the hand in the work frame.

### Claim 3 (depends on 1)

The work rate measurement device according to claim 1, wherein the at least one processor is configured to execute the instructions to set a plurality of work frames for an image capture area of one camera installed at a work area for a work step.

### Claim 4 (depends on 1)

The work rate measurement device according to claim 1, wherein the at least one processor is configured to execute the instructions to save in a server, as analysis data for each time, together with log data, a moving image representing a positional relationship between the work frame and a hand of a worker.

### Claim 5 (depends on 1)

The work rate measurement device according to claim 1, wherein the at least one processor is configured to execute the instructions to compute a work rate in the work frame based on ON and/or OFF data indicating whether or not a hand of a worker appears within the work frame.

### Claim 6 (depends on 1)

The work rate measurement device according to claim 1, wherein the at least one processor is configured to execute the instructions to display, in an hourly manner, a computed work rate in the work frame in graph form.

### Claim 7 (depends on 1)

The work rate measurement device according to claim 1, wherein the at least one processor is configured to execute the instructions to analyse a stay time of an object image other than the hand of the worker.

### Claim 8

A work rate measurement method for measuring a work rate when manual work is performed within a prescribed work frame provided for each of a plurality of steps, the work rate measurement method comprising:
capturing an image within the work frame using cameras installed for the plurality of steps, causing machine learning to be performed on a hand of a worker held within the work frame based on the captured data, and generating a machine learning model for each of the cameras;
analyzing whether or not a position of a hand of a worker is included within the work frame with respect to an image of actual work being performed using the generated machine learning model and saving, in chronological order, analysis data obtained by the analysis; and
determining a work rate within each work frame using the saved analysis data.
