Process chart creation assistance device
The process chart creation support device automates the generation of process charts by extracting worker skeletal coordinates and calculating standard times, simplifying the creation process for supervisors.
Patent Information
- Application Number
- JP2023082302
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2023-05-18
- Publication Date
- 2024-11-28
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Creating a process chart that describes the standard time for each work process is complicated and requires manual observation and measurement by supervisors.
A process chart creation support device that uses an extraction unit to extract skeletal coordinates from worker videos, a machine-learned model to determine work steps, and a calculation unit to calculate standard times, supported by a creation unit to generate a process chart in a versatile data format.
Automates the creation of process charts, enabling supervisors to easily generate charts with standard, allowable, and fastest times for each step, reducing manual complexity.
Smart Images

Figure 2024165804000001_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to a process chart creation support device. [Background technology]
[0002] Workers in factories and the like perform their work according to a schedule that shows the work process in chronological order (see, for example, Patent Document 1). [Prior art documents] [Patent documents]
[0003] [Patent Document 1] JP 2022-175399 A Summary of the Invention [Problem to be solved by the invention]
[0004] The supervisor must manually create such a schedule, which is cumbersome. In particular, in order to create a schedule that indicates the standard time required to complete each work step, the supervisor must observe the workers and measure the standard time for each work step, which makes the creation of the schedule even more cumbersome.
[0005] The present invention has been made in consideration of the above-mentioned problems, and has an object to provide a process schedule creation support device that supports the creation of a process schedule. [Means for solving the problem]
[0006] The above objective can be achieved by a process schedule creation support device that includes an extraction unit that extracts skeletal coordinates of a worker from a video of the worker performing a plurality of work processes, a discrimination unit that discriminates each of the work processes performed by the worker using a machine-learned model that inputs the skeletal coordinates and outputs the work processes, a calculation unit that calculates the standard time required to complete each of the work processes, and a creation unit that creates a process schedule that lists the plurality of work processes in chronological order and the standard time for each of the work processes. Effect of the Invention
[0007] According to the present invention, it is possible to provide a process schedule creation support device that supports the creation of a process schedule. [Brief description of the drawings]
[0008] [Figure 1] FIG. 1 is a configuration diagram illustrating an example of a process chart creation support system. [Diagram 2] 11 is a flowchart illustrating a process schedule creation support control executed by a process schedule creation support server. [Diagram 3] FIG. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0009] (Example of the outline of the schedule creation support system) FIG. 1 is a schematic diagram of a schedule creation support system 9. As an example, the schedule creation support system 9 is installed in an assembly plant for automobiles or the like. The schedule creation support system 9 includes a schedule creation support server 1 and a camera device 2 that can communicate with each other via a LAN (Local Area Network) 90. The schedule creation support server 1 is an example of a schedule creation support device. The schedule creation support server 1 creates a schedule based on images of workers. The camera device 2 captures images of workers performing multiple work processes. The terminal 4 is held by a supervisor who supervises the workers.
[0010] The schedule creation support server 1 is an example of a computer, and includes a CPU (Central Processing Unit) 10, a ROM (Read Only Memory) 11, a RAM (Random Access Memory) 12, a HDD (Hard Disk Drive) 13, and a communication port 14. The CPU 10 is electrically connected to the ROM 11, the RAM 12, the HDD 13, and the communication port 14 via a bus 19 so as to enable input and output of signals to and from each other. The ROM 11 stores a program that drives the CPU 10. The RAM 12 functions as a working memory for the CPU 10. The communication port 14 is, for example, a wireless LAN (Local Area Network) card, and processes communication of the CPU 10 via a LAN 90.
[0011] When the CPU 10 reads the program from the ROM 11, it forms a device control unit 100, a creation unit 101, a calculation unit 102, a discrimination unit 103, and an extraction unit 104 as software functions. The HDD 13 stores skeleton data 130, part data 131, tool data 132, and process chart data 133. The device control unit 100 instructs the creation unit 101, the calculation unit 102, the discrimination unit 103, and the extraction unit 104 to operate in accordance with a sequence defined in the program. The device control unit 100, the creation unit 101, the calculation unit 102, the discrimination unit 103, and the extraction unit 104 are not limited to software, and may be realized by hardware such as an ASIC (Application Specified Integrated Circuit).
[0012] The extraction unit 104 extracts the skeletal coordinates of the worker, the parts used by the worker, and the tools used by the worker from the video captured by the camera device 2, for example, by image analysis using a general-purpose AI (Artificial Intelligence). The extraction unit 104 stores the time series of coordinates of multiple points of the worker's skeleton as skeleton data 130 in the HDD 13. The skeleton data 130 indicates the coordinates of the worker's nose, left shoulder, right shoulder, left elbow, right elbow, left hand, right hand, left hip, and right hip for each frame image number, for example. The coordinates are indicated by X coordinates and Y coordinates (x, y) when the horizontal and vertical directions of a rectangular frame of the image are defined as the X axis and the Y axis, respectively. Note that there is no limitation on the position of the origin. The extraction unit 104 also stores the names and product numbers of the parts used by the worker as part data 131 in the HDD 13. The extraction unit 104 stores the names of the tools used by the worker as tool data 132 in the HDD 13. The extraction unit 104 stores the tool name and the assembly torque in the HDD 13 as tool data 132 based on a table in which the tool name corresponds to the assembly torque required when assembling a part using the tool.
[0013] The discrimination unit 103 discriminates each work process performed by the worker based on the skeleton coordinates and the parts and tools used extracted by the extraction unit 104. The calculation unit 102 calculates the standard time, allowable time, and fastest time for each work process, which will be described in detail later. The creation unit 101 creates a process chart, which will be described in detail later, and stores the created process chart in the HDD 13 as process chart data 133.
[0014] (Schedule creation support control) 2 is a flow chart illustrating the process schedule creation support control executed by the process schedule creation support server 1. First, the extraction unit 104 receives video data from the camera device 2 via the communication port 14 (step S1). The extraction unit 104 receives the video data as a plurality of frame images. The video data is video data of a worker performing work over a plurality of cycles. Next, the extraction unit 104 extracts the skeleton coordinates of the worker, the parts used by the worker, and the tools used by the worker from each frame image (step S2). Next, the extraction unit 104 stores the extraction results as skeleton data 130, part data 131, and tool data 132 in the HDD 13 (step S3).
[0015] The discrimination unit 103 discriminates the work process performed by the worker using a discrimination model based on the skeleton data 130, the part data 131, and the tool data 132 (step S4). The discrimination model is a model that has been machine-learned through supervised learning. By inputting the skeleton coordinates, the parts used, and the tools used into the discrimination model, the discrimination model outputs the work process. The work process includes, for example, taking out parts, assembling parts, removing parts, moving, welding, painting, inspection, and transporting products. A neural network is used for the supervised learning. In this way, the discrimination unit 103 can accurately discriminate the work process performed by the worker by using a discrimination model that has been machine-learned through supervised learning.
[0016] The calculation unit 102 calculates the process time required to complete the work process over multiple cycles based on the work process determined by the discrimination unit 103 and the number of frame images in which the work process is being performed (step S5).
[0017] Next, the calculation unit 102 calculates the standard time, allowable time, and fastest time for each work process (step S6). The standard time is the standard time required to complete the work process. The standard time is calculated as the average time required to complete the work process. The allowable time is the time allowed for completing the work process. The allowable time is calculated by adding a predetermined time to the standard time. The time added to the standard time differs for each work process, but the longer the standard time, the longer the time added. The fastest time is the shortest time required to complete the work process.
[0018] Next, the creation unit 101 creates a process schedule that lists a plurality of work processes in chronological order and lists the standard time, allowable time, and fastest time for each work process (step S7). In detail, the creation unit 101 creates the process schedule in a versatile data format. Examples of the versatile data format include CSV (Comma-Separated Values) data, text data, and data formats for spreadsheet software such as Excel. Next, the creation unit 101 saves the created process schedule in the HDD 13 (step S8). FIG. 3 is an example diagram of a process schedule. The process schedule lists the names of parts and tools used in each work process. As described above, the process schedule creation support server 1 automatically creates a process schedule based on images of workers working.
[0019] For example, a supervisor can access the schedule creation support server 1 from a terminal 4 via the LAN 90 and check this schedule. If necessary, the supervisor can modify the schedule and save the final schedule as schedule data 133 in the HDD 13. In this way, the supervisor can easily create a schedule.
[0020] In the above embodiment, the creation of a schedule showing the allowable time and the fastest time has been described as an example, but the schedule is not limited to this and may show standard times. Also, images of parts and tools may be displayed on the schedule.
[0021] The above-described embodiment is a preferred example of the present invention, but the present invention is not limited to this embodiment and can be modified in various ways without departing from the scope of the present invention. [Explanation of symbols]
[0022] 1. Process schedule creation support server (process schedule creation support device) 2 Camera equipment 101 Creation Department 102 Calculation section 103 Discrimination part 104 Extraction part
Claims
[Claim 1] an extraction unit that extracts skeletal coordinates of a worker from a video of the worker performing a plurality of work processes; a discrimination unit that discriminates each of the work steps performed by the worker using a machine-learned model that inputs the skeleton coordinates and outputs the work steps; A calculation unit that calculates a standard time required to complete each of the work processes; a creation unit that creates a schedule in which the plurality of work processes are represented in chronological order and the standard time for each of the work processes is represented.
Citation Information
Patent Citations
Information processing device, information processing method, and program
JP2022175399A
Cited By
Information processing methods, information processing systems, and programs
JP2026142649A
