Dynamic analysis system and dynamic analysis method

Abstract

A movement analysis system and a movement analysis method are provided that can grasp in detail how a worker moves and what work he or she has performed. [Solution] The movement analysis system 200 has a position information acquisition unit 30 that acquires position information of a worker via wireless communication, an image information acquisition unit 20 that acquires image information within a work area as a video, and an analysis unit 10 that analyzes the worker's movements and the work content of the worker based on the position information of the worker acquired by the position information acquisition unit 30 and the image information acquired by the image information acquisition unit 20. The analysis unit 10 analyzes the position information acquired by the position information acquisition unit 30 to grasp the worker's work flow line over time, analyzes the video acquired by the image information acquisition unit 20 to grasp the worker's position, posture, and work status, and determines the work content of the worker from the work flow line, the worker's position and posture extracted from the video, and the worker's work status, and classifies the work content.

Description

[Technical Field]

[0001] The present invention relates to a system and method for analyzing the behavior of workers in a work area at a production site such as a factory. [Background technology]

[0002] For example, in a factory, which is a production site, there is a work area where multiple workers work. To improve the productivity of workers in such a work area, techniques for analyzing the movements of workers have been proposed. For example, Patent Document 1 proposes a technique for improving productivity by recording work flow lines using a transmitter installed in the target area and a receiver worn by the user. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6469285 Summary of the Invention [Problem to be solved by the invention]

[0004] However, although the technology of Patent Document 1 can grasp the movements of each worker, it cannot fully grasp what work each worker has performed, and there is a limit to the productivity improvement effect.

[0005] Therefore, an object of the present invention is to provide a movement analysis system and a movement analysis method that can grasp in detail how a worker moved and what work he or she performed. [Means for solving the problem]

[0006] The present invention provides the following means (1) to (11).

[0007] (1) A movement analysis system that analyzes the movement of workers working in a work area at a production site, a location information acquisition unit that acquires location information of the worker via wireless communication; an image information acquisition unit that acquires image information within the work area as a video; an analysis unit that analyzes the movement of the worker and the work content of the worker based on the position information of the worker acquired by the position information acquisition unit and the image information acquired by the image information acquisition unit; and The analysis unit analyzes the position information of the worker acquired by the position information acquisition unit to grasp the work flow of the worker over time, analyzes the image information acquired by the image information acquisition unit to extract the position of the worker and grasp the worker's posture and work status, and determines the work content of the worker from the work flow, the position and posture of the worker extracted from the image information, and the worker's work status, and classifies the work content.

[0008] (2) The dynamic analysis system according to (1), wherein the image information acquisition unit has a plurality of cameras that acquire images within the work area as video.

[0009] (3) The dynamic analysis system described in (1) is characterized in that the location information acquisition unit has a transmitter attached to the worker and a receiving unit having a fixedly installed receiver.

[0010] (4) The dynamic analysis system according to (3), wherein the transmitter is a beacon and the receiver is a locator.

[0011] (5) The analysis unit a position information analysis unit that analyzes the position information of the worker acquired by the position information acquisition unit and grasps the work flow line of the worker over time; an image information analysis unit that analyzes the video acquired by the image information acquisition unit, extracts the position of the worker, and grasps the working state of the worker; a work content determination unit that determines the work content of the worker and classifies the work content based on the position and posture of the worker obtained by the position information analysis unit and the image information analysis unit, and the work state of the worker; an output information creation unit that creates output information including the work flow line trajectory of the worker and the movement distance of the worker grasped by the position information analysis unit, and the work classification obtained by the work content determination unit; and The dynamic analysis system according to any one of (1) to (4), comprising:

[0012] (6) The dynamic analysis system described in (5) is characterized in that the analysis unit further has a linking unit that links the worker's position information obtained by the position information analysis unit with the worker's position extracted from the video by the image information analysis unit.

[0013] (7) The dynamic analysis system described in (5) is characterized in that the work content determination unit uses AI to machine-learn the image information.

[0014] (8) A movement analysis method for analyzing the movement of a worker working in a work area at a production site, comprising: a step in which a location information acquisition unit acquires location information of the worker by wireless communication; an image information acquisition unit acquiring image information within the work area as a video; an analysis unit analyzing the movement of the worker and the work content of the worker based on the position information and the image information of the worker, The analyzing step includes analyzing the position information of the worker acquired by the position information acquisition unit to grasp the work flow of the worker over time, analyzing the image information acquired by the image information acquisition unit to extract the position of the worker and grasp the posture and work status of the worker, and determining the work content of the worker from the work flow, the position and posture of the worker extracted from the image information, and the work status of the worker, and classifying the work content.

[0015] (9) The analyzing step analyzing the location information; analyzing the image information; determining the work content of the worker based on the analysis result of the position information and the analysis result of the image information, and classifying the work content; creating output information including the work flow path trajectory of the worker and the movement distance of the worker ascertained by analyzing the position information, and a classification of the work content; The kinetic analysis method according to (8), characterized by comprising:

[0016] (10) The dynamic analysis method according to (9), further comprising a step of linking the position information of the worker with the position of the worker extracted from the video.

[0017] (11) The dynamic analysis method described in (9), characterized in that the process of determining the work content of the worker and classifying the work content is performed by machine learning the image information using AI. [Effects of the Invention]

[0018] According to the present invention, the movements of workers are grasped based on the position information and image information of the workers, and the work performed by the workers is determined and automatically classified, so that it is possible to analyze in detail how each worker moved and what work was performed and at what rate. As a result, each worker can grasp their own movements and work status in detail, resulting in a significant improvement in productivity. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a plan view showing an example of a work area to which a dynamic analysis system according to an embodiment of the present invention is applied. [Figure 2] 1 is a block diagram showing a dynamic analysis system according to an embodiment of the present invention. [Figure 3]FIG. 2 is a functional block diagram of an analysis unit in the dynamic analysis system according to one embodiment of the present invention. [Figure 4] 1 is a flowchart showing an example of a dynamic analysis method in a dynamic analysis system according to an embodiment of the present invention. [Figure 5] FIG. 10 is a diagram showing an example of the flow line of each worker as output information. [Figure 6] FIG. 10 is a diagram illustrating an example of the travel distance of each worker as output information. [Figure 7] FIG. 10 is a diagram illustrating an example of a task classification result of a worker as output information. DETAILED DESCRIPTION OF THE INVENTION

[0020] Hereinafter, an embodiment of the present invention will be described with reference to the accompanying drawings. FIG. 1 is a plan view showing an example of a work area to which a dynamic analysis system according to an embodiment of the present invention is applied, and FIG. 2 is a block diagram showing the dynamic analysis system according to an embodiment of the present invention.

[0021] In Figure 1, a building for a foundry and molding factory is shown as the work area 100. The work area 100 has a long, narrow rectangular shape. Although not shown, the foundry and molding factory also has another work area, a main building that is slightly larger than the building and is located adjacent to the building.

[0022] In a work area 100 serving as a building for a casting and molding factory, there are provided a plurality of work areas, for example, a core molding area 101 where cores are molded, and two molding areas 102A and 102B where molds are manufactured.

[0023] Additionally, multiple cameras 21 that constitute part of the image information acquisition unit, which is a component of the dynamic analysis system, are provided around the work area 100. The multiple cameras 21 are used to capture images of the work state within the work area 100, and are arranged so that their respective capture areas partially overlap, capturing images of the entire work area 100 as a whole. In the example of Figure 1, 14 cameras 21 are arranged, but the number can be any number as long as they can capture images of the entire work area.

[0024] Multiple workers are working within the work area 100. The number of workers can be any number, but FIG. 1 shows seven workers, workers A to G, working. Each worker wears a transmitter 31 on their helmet, which constitutes part of the position information acquisition unit, a component of the dynamic analysis system, and moves around within the work area 100 to perform the specified tasks.

[0025] In the main building, which is another work area, there are multiple work areas such as a casting bit and a molding area, and multiple cameras are installed around them.Similarly, multiple workers move around inside the main building while wearing transmitters 31 and perform their designated tasks.

[0026] The movement analysis system 200 analyzes the movement of a worker working in the work area 100, and includes an analysis unit 10, an image information acquisition unit 20, and a position information acquisition unit 30.

[0027] The analysis unit 10 analyzes the movements of the workers and the work content of the workers based on the position information of the multiple workers acquired by the position information acquisition unit 30 and the image information acquired by the image information acquisition unit 20. Details of the analysis unit 10 will be described later.

[0028] The image information acquisition unit 20 acquires image information of the work area 100 where the worker is working as a video. The image information acquisition unit 20 has, for example, the above-mentioned multiple cameras 21 and a recorder 22 that stores the videos taken by the multiple cameras and processes the images as necessary. The image information acquisition unit 20 sends the acquired image information to the analysis unit 10.

[0029] The location information acquisition unit 30 acquires location information of each worker in the work area 100 via wireless communication. The location information acquisition unit 30 includes, for example, the above-mentioned transmitters 31 attached to the helmets of multiple workers and a receiving unit 32 including multiple fixedly installed receivers. The location information acquisition unit 30 sends the acquired location information to the analysis unit 10. For example, a beacon can be used as the transmitter 31, and a locator can be used as the receiver. Multiple locators can be placed around the work area 100. The beacon outputs a beacon signal conforming to the Bluetooth (registered trademark) Low Energy (BLE) standard at regular intervals, and wirelessly communicates with the locator, which is a receiver. Note that the receiver may be attached to each worker, and the transmitter may be fixedly installed. Alternatively, communication between the transmitter and receiver may be performed via other wireless communication technologies, such as Wi-Fi (registered trademark) or Zigbee (registered trademark).

[0030] Next, the analysis unit 10 will be described in detail. The analysis unit 10 has a CPU, RAM, a storage unit, an input unit, a display unit, and an output unit. The storage unit is composed of, for example, a flash memory or a hard disk, and stores programs necessary for control. The RAM temporarily stores programs. The CPU uses the RAM as a working area to execute the programs stored in the storage unit.

[0031] 3 is a functional block diagram of the analysis unit 10. As shown in FIG. 3, the analysis unit 10 includes a position information analysis unit 11, an image information analysis unit 12, a linking unit 13, a work content determination unit 14, and an output information creation unit 15.

[0032] The position information analysis unit 11 analyzes the position information of each worker acquired by the position information acquisition unit 30, and grasps the work flow line of each worker over time.

[0033] The image information analysis unit 12 analyzes the video acquired by the image information acquisition unit 20, extracts the position of each worker, and grasps the working state of each worker.

[0034] The linking unit 13 links the position information of each worker obtained by the position information analysis unit 11 with the position of each worker extracted from the video by the image information analysis unit 12.

[0035] The work content determination unit 14 determines the general process from the installation positions of each camera, and determines the work content of the worker from the position and posture of the worker and the worker's work status obtained by the position information analysis unit 11 and the image information analysis unit 12, and classifies the work content. For example, the work content determination unit 14 determines the worker's behavior (whether or not the worker is working directly, etc.) from the positional relationship between the worker's posture and a work item such as a metal frame, determines the work content, and classifies the determined work content. Then, by classifying the work content, it is possible to determine the proportion of each work performed. The work content determination unit 14 may perform machine learning on the image information using AI. AI machine learning can be performed by processing the image information into point data required for AI learning and training this point data using an AI with a specific model. By repeating AI machine learning on a large amount of image information in this way, it is possible to determine the work content and classify the work content with high accuracy.

[0036] The output information creation unit 15 creates output information including the work flow line trajectory of each worker and the movement distance of each worker grasped by the position information analysis unit 11, and the work classification based on the determination result of the work content determination unit 14. The output information created by the output information creation unit 15 is displayed on the display unit and output from the output unit.

[0037] Next, an example of a dynamic analysis method in the dynamic analysis system 200 configured as above will be described. Fig. 4 is a flowchart showing an example of a dynamic analysis method in the dynamic analysis system according to one embodiment of the present invention. First, the position information acquisition unit 30 acquires position information of the worker (step ST1), and the image information acquisition unit 20 acquires image information within the work area 100 (step ST2).

[0038] Next, the acquired position information is analyzed (step ST3), and the acquired image information is analyzed (step ST4). The analysis of the position information is performed by inputting the acquired position information to the analysis unit 10 and analyzing it in the position information analysis unit 11. The analysis of the image information is performed by inputting the acquired image information to the analysis unit 10 and analyzing it in the image information analysis unit 12.

[0039] Next, the work content of each worker is determined and classified based on the results of the analysis of the position information and the image information (step ST5). The determination and classification of the work content of each worker at this time is performed based on the rough process being grasped from the installation positions of each camera, as well as the position and posture of the worker and the working status of the worker obtained by the position information analysis unit 11 and the image information analysis unit 12. At this time, it is preferable that the position information of each worker obtained by the position information analysis unit 11 and the position of each worker extracted from the video by the image information analysis unit 12 are linked by the linking unit 13.

[0040] In addition, step ST3 of analyzing the position information, step ST4 of analyzing the acquired image information, and step ST5 of determining and classifying the work content of each worker constitute a process of analyzing the movements and work content of each worker.

[0041] Next, output information is created that includes the work flow path trajectory and movement distance of each worker based on the position information of each worker, and the work classification based on the determination result of the work content (step ST6).

[0042] FIG. 5 is a diagram showing an example of the work flow line trajectory of a worker. FIG. 5 shows an example of the work flow line trajectory of worker E and worker A in FIG. 1 within the work area. FIG. 6 is a diagram showing an example of the travel distance of each worker. FIG. 6 shows an example of the travel distance of workers A to G in FIG. 1. As shown in FIGS. 5 and 6, by analyzing the position information, it is possible to understand the movement and travel distance of each worker within the work area 100.

[0043] Figure 7 shows an example of the results of worker task classification. Figure 7 shows an example of the work content determined and classified when the work area is the shed of a casting and molding factory, where a indicates "core setting," b indicates "mold coating," c indicates "crane work," d indicates "mold finishing," e indicates "casting setup," f indicates "cleaning," g indicates "setup," and h indicates "non-work." In this way, it is possible to understand what type of work a worker performed and to what extent.

[0044] According to this embodiment, the movements of the workers are grasped based on the position information of the workers acquired by the position information acquisition unit 30 and the image information acquired by the image information acquisition unit 20, and the work performed by the workers is determined and automatically classified, thereby enabling a detailed analysis of how each worker moved and what work they performed and at what rate. As a result, each worker can easily understand areas for improvement in their own movements and work status based on the analysis results, and can easily derive countermeasures, resulting in a high productivity improvement effect.

[0045] Although the embodiments of the present invention have been described above, these are merely examples and should not be considered limiting. The above embodiments may be omitted, substituted, or modified in various ways without departing from the spirit of the present invention.

[0046] For example, in the above embodiment, a casting and molding factory is used as an example of the work area, but the present invention is not limited to this and can be applied to any work area where workers move around and perform their work. [Explanation of symbols]

[0047] 10;Analysis Department 11;Location information analysis department 12. Image information analysis section 13; Binding section 14;Work content judgment department 15: Output information creation section 20: Image information acquisition unit 21;Camera 22; Recorder 30; Location information acquisition unit 31: Transmitter 32; Receiver 100;Work area A~G: Workers

Claims

1. A movement analysis system that analyzes the movement of workers working in a work area at a production site, a location information acquisition unit that acquires location information of the worker via wireless communication; an image information acquisition unit that acquires image information within the work area as a video; an analysis unit that analyzes the movement of the worker and the work content of the worker based on the position information of the worker acquired by the position information acquisition unit and the image information acquired by the image information acquisition unit; and The analysis unit analyzes the position information of the worker acquired by the position information acquisition unit to grasp the work flow of the worker over time, analyzes the image information acquired by the image information acquisition unit to extract the position of the worker and grasp the worker's posture and work status, and determines the work content of the worker from the work flow, the position and posture of the worker extracted from the image information, and the worker's work status, and classifies the work content.

2. 2. The dynamic analysis system according to claim 1, wherein the image information acquisition unit has a plurality of cameras that acquire images of the work area as video.

3. 2. The dynamic analysis system according to claim 1, wherein the position information acquisition unit includes a transmitter attached to the worker and a receiving unit having a fixedly installed receiver.

4. 4. The dynamic analysis system according to claim 3, wherein the transmitter is a beacon and the receiver is a locator.

5. The analysis unit a position information analysis unit that analyzes the position information of the worker acquired by the position information acquisition unit and grasps the work flow line of the worker over time; an image information analysis unit that analyzes the video acquired by the image information acquisition unit, extracts the position of the worker, and grasps the working state of the worker; a work content determination unit that determines the work content of the worker based on the position and posture of the worker obtained by the position information analysis unit and the image information analysis unit, and the work state of the worker, and classifies the work content; an output information creation unit that creates output information including the work flow line trajectory of the worker and the movement distance of the worker grasped by the position information analysis unit, and the work classification obtained by the work content determination unit; The dynamic analysis system according to any one of claims 1 to 4, further comprising:

6. The dynamic analysis system according to claim 5, characterized in that the analysis unit further includes a linking unit that links the position information of the worker obtained by the position information analysis unit with the position of the worker extracted from the video by the image information analysis unit.

7. The dynamic analysis system according to claim 5 , wherein the work content determination unit performs machine learning of the image information using AI.

8. A movement analysis method for analyzing the movement of workers working in a work area at a production site, comprising: a step in which a location information acquisition unit acquires location information of the worker by wireless communication; an image information acquisition unit acquiring image information within the work area as a video; an analysis unit analyzing the movement of the worker and the work content of the worker based on the position information and the image information of the worker, The analyzing step includes analyzing the position information of the worker acquired by the position information acquisition unit to grasp the work flow of the worker over time, analyzing the image information acquired by the image information acquisition unit to extract the position of the worker and grasp the worker's posture and work status, and determining the work content of the worker from the work flow, the position and posture of the worker extracted from the image information, and the worker's work status, and classifying the work content.

9. The analyzing step includes: analyzing the location information; analyzing the image information; determining the work content of the worker based on the analysis result of the position information and the analysis result of the image information, and classifying the work content; creating output information including the work flow path trajectory of the worker and the movement distance of the worker ascertained by analyzing the position information, and a classification of the work content; The dynamic analysis method according to claim 8, further comprising:

10. The dynamic analysis method according to claim 9, further comprising the step of linking the position information of the worker with the position of the worker extracted from the video.

11. The dynamic analysis method according to claim 9, wherein the step of determining the work content of the worker and classifying the work content is performed by machine learning the image information using AI.

Images