Work recognition device, work recognition method, and work recognition program

Abstract

To provide a work recognition system capable of easily obtaining work time for each task in a series of tasks performed by a worker by comparing the case when using machine learning.SOLUTION: The work recognition system includes: a total working time acquisition unit that acquires the total working time of a series of tasks performed by a worker; a standard time information acquisition unit that acquires standard time information relevant to the standard time for each task in a series of tasks; a working time calculation unit that calculates the standard time of each work done by the worker based on the total working time and the standard time information; a breakpoint setting unit that sets a breakpoint in the series of tasks based on the standard time for each work done by the worker; and an output unit that outputs the breakpoint information regarding the breakpoints in the set tasks.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The disclosed technology relates to a work recognition device, a work recognition method, and a work recognition program.

Background Art

[0002] Identifying bottlenecks in work at a factory and discovering processes where abnormalities are likely to occur are important in quality improvement. Manually measuring the working time, which is fundamental when analyzing these, is very laborious.

[0003] For this reason, technologies have been proposed that automatically identify working time using a learned model learned using machine learning (see, for example, Patent Documents 1 and 2).

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, the technology described in Patent Document 1 has a problem in that a large error may occur depending on the accuracy of the learning model.

[0006] Also, the technology described in Patent Document 2 has a problem in that a large amount of learning data is required for use in machine learning.

[0007] Also, when not using machine learning, there is a problem in that a person has to watch a video and manually determine and set where the work segmentation is.

[0008] The disclosed technology was developed in view of the above points, and aims to provide a work recognition device, a work recognition method, and a work recognition program that can easily obtain the work time for each task in a series of tasks performed by an operator, compared to using machine learning. [Means for solving the problem]

[0009] A first aspect of the disclosure is a work recognition device comprising: a total work time acquisition unit that acquires the total work time for a series of tasks performed by an operator; a standard time information acquisition unit that acquires standard time information relating to the standard time for each task in the series of tasks; a work time calculation unit that calculates the work time for each task performed by the operator based on the total work time and the standard time information; a delimiter setting unit that sets the delimiters between tasks in the series of tasks based on the work time for each task performed by the operator; and an output unit that outputs delimiter information relating to the set delimiters between tasks.

[0010] This makes it possible to display potential work completion points. Users only need to approve or make minor adjustments to these points, thus reducing the effort required from the user. Furthermore, it does not require a large amount of training data compared to methods using machine learning.

[0011] In the first embodiment described above, the work time calculation unit may calculate the work time for each task based on the ratio of the total standard time, which is the sum of the standard times for each task, to the total work time.

[0012] In the first embodiment described above, the work time calculation unit may calculate the work time for each task by multiplying the ratio by the standard time for each task.

[0013] In the first embodiment described above, the total work time acquisition unit may determine the start time of the series of operations based on the output signal of a proximity sensor provided on the workbench where the first operation of the series of operations is performed.

[0014] In the first embodiment described above, the total work time acquisition unit may determine the completion time of the series of tasks based on the output signal of a proximity sensor provided on the workbench where the last task of the series of tasks is performed.

[0015] In the first embodiment described above, the work time calculation unit may calculate the start time of the first task in the series of tasks as the time obtained by subtracting the total work time of the series of tasks from the end time of the last task in the series of tasks.

[0016] A second aspect of the disclosure is a work recognition method, the computer which performs a process including obtaining the total work time for a series of tasks performed by an worker, obtaining standard time information relating to the standard time for each task in the series of tasks, calculating the work time for each task performed by the worker based on the total work time and the standard time information, setting boundaries between tasks in the series of tasks based on the work time for each task performed by the worker, and outputting boundary information relating to the set boundaries between tasks.

[0017] A third aspect of the disclosure is a work recognition program that causes a computer to execute a process including obtaining the total work time for a series of tasks performed by an worker, obtaining standard time information relating to the standard time for each task in the series of tasks, calculating the work time for each task performed by the worker based on the total work time and the standard time information, setting boundaries between tasks in the series of tasks based on the work time for each task performed by the worker, and outputting boundary information relating to the set boundaries between tasks. [Effects of the Invention]

[0018] According to the disclosed technology, the time taken for each task in a series of tasks performed by an operator can be easily obtained compared to using machine learning. [Brief explanation of the drawing]

[0019] [Figure 1] This is a diagram illustrating the configuration of the work recognition system. [Figure 2]It is a diagram showing how an operator moves multiple workbenches to perform work as seen from information. [Figure 3] It is a block diagram showing the hardware configuration of the work recognition device. [Figure 4] It is a functional block diagram of the work recognition device. [Figure 5] It is a diagram for explaining the case where a proximity sensor is provided on the workbench. [Figure 6] It is a diagram showing the output waveform of the proximity sensor. [Figure 7] It is a diagram showing an example of standard time information. [Figure 8] It is a diagram showing the relationship between the work times of beginners and skilled workers and the standard time. [Figure 9] It is a diagram showing the relationship between the standard time and the work time calculated by beginners. [Figure 10] It is a diagram showing the relationship between the actual work time of beginners and the calculated work time. [Figure 11] It is a diagram for explaining the error between the actual work time of beginners and the calculated work time. [Figure 12] It is a diagram showing the relationship between the standard time and the work time calculated by skilled workers. <000,0103>It is a diagram showing the relationship between the actual work time of skilled workers and the calculated work time. [Figure 14] It is a diagram for explaining the error between the actual work time of skilled workers and the calculated work time. [Figure 15] It is a diagram showing an example of delimiter information. [Figure 16] It is a diagram showing the work time of each work in each cycle. [Figure 17] It is a flowchart of the work recognition process. [Figure 18] It is a diagram showing an example of a menu screen. [Figure 19] It is a diagram showing an example of a selection screen for the standard time file. [Figure 20] It is a diagram showing an example of delimiter information.

Mode for Carrying Out the Invention

[0020] Hereinafter, an example of an embodiment of the present invention will be described with reference to the drawings. In each drawing, identical or equivalent components and parts are given the same reference numerals. Also, the dimensional ratios in the drawings may be exaggerated for illustrative purposes and may differ from the actual ratios.

[0021] Figure 1 shows the configuration of the work recognition system 10. The work recognition system 10 includes a work recognition device 20 and a camera 30.

[0022] The work recognition device 20 calculates the work time for each task in a series of tasks performed by worker W based on the images captured by the camera 30.

[0023] For example, worker W takes the object M to be worked on, which is placed on the workbench TB, and performs the prescribed work on the work space S.

[0024] Specifically, as shown in Figure 2, worker W moves sequentially between multiple workbenches TB and performs a predetermined task at each workbench TB. In the example in Figure 2, eight workbenches TB1 to TB8 are arranged to surround worker W. Worker W moves sequentially from workbenches TB1 to TB8 and performs tasks 1 to 14 in sequence. Tasks 1 to 14 are examples of the following tasks, but the content of the tasks is not limited to these.

[0025] Task 1: Combine part A and part B. Task 2: Tightening screws Task 3: Inserting the circuit board Task 4: Crimping Task 5: Electrical Inspection Task 6: Installing part C Task 7: Installing part D Task 8: Airbrushing Task 9: Inspection Task 10: Packaging the instruction manual Task 11: Packaging products into boxes Task 12: Label Printing Task 13: Labeling Task 14: Store in transport box

[0026] As shown in Figure 2, worker W performs tasks 1 and 2 at workbench TB1, tasks 3 and 4 at workbench TB2, task 5 at workbench TB3, tasks 6 and 7 at workbench TB4, tasks 8 and 9 at workbench TB5, tasks 10 and 11 at workbench TB6, tasks 12 and 13 at workbench TB7, and task 14 at workbench TB8.

[0027] In the following, if multiple workbenches are not distinguished, they may simply be referred to as workbench TB. Note that the arrangement and number of workbenches TB, as well as the types and number of tasks, are not limited to the example in Figure 2.

[0028] Camera 30 is a recording device capable of capturing, for example, RGB color video. Camera 30 is installed in a position that makes it easy to recognize the movements of worker W and the entire workbench TB1 to TB8. Specifically, in this embodiment, as an example, we will describe the case in which camera 30 is installed in a position that looks down on worker W and workbench TB1 to TB8 from above, as shown in Figure 2. However, if workbenches TB1 to TB8 are arranged in a single row, camera 30 may be placed in a position that allows for frontal shots of worker W and workbench TB1 to TB8.

[0029] Furthermore, although this embodiment describes the case where there is one camera 30, a configuration with multiple cameras 30 may also be used.

[0030] Figure 3 is a block diagram showing the hardware configuration of the work recognition device 20 according to this embodiment. As shown in Figure 3, the work recognition device 20 includes a controller 21. The controller 21 is composed of a device including a general-purpose computer.

[0031] As shown in Figure 3, the controller 21 comprises a CPU (Central Processing Unit) 21A, a ROM (Read Only Memory) 21B, a RAM (Random Access Memory) 21C, and an input / output interface (I / O) 21D. The CPU 21A, ROM 21B, RAM 21C, and I / O 21D are connected to each other via a bus 21E. The bus 21E includes a control bus, an address bus, and a data bus.

[0032] Furthermore, the I / O21D is connected to the operation unit 22, the display unit 23, the communication unit 24, and the storage unit 25.

[0033] The operating unit 22 is comprised of, for example, a mouse and a keyboard.

[0034] The display unit 23 is composed of, for example, a liquid crystal display.

[0035] The communication unit 24 is an interface for data communication with external devices such as the camera 30.

[0036] The storage unit 25 is composed of a non-volatile external storage device such as a hard disk. As shown in Figure 3, the storage unit 25 stores the work recognition program 25A, standard time information 25B, and delimiter information 25C, etc.

[0037] CPU21A is an example of a computer. Here, "computer" refers to a processor in a broad sense, including general-purpose processors (e.g., CPUs) or specialized processors (e.g., GPUs: Graphics Processing Units, ASICs: Application Specific Integrated Circuits, FPGAs: Field Programmable Gate Arrays, programmable logic devices, etc.).

[0038] The work recognition program 25A may also be implemented by storing it on a non-volatile, non-transitory recording medium or by distributing it via a network and installing it appropriately on the work recognition device 20.

[0039] Examples of non-volatile, non-transitional recording media include CD-ROMs (Compact Disc Read Only Memory), magneto-optical disks, HDDs (Hard Disk Drives), DVD-ROMs (Digital Versatile Disc Read Only Memory), flash memory, and memory cards.

[0040] Figure 4 is a block diagram showing the functional configuration of the CPU 21A of the work recognition device 20. As shown in Figure 4, the CPU 21A functionally comprises a total work time acquisition unit 40, a standard time information acquisition unit 41, a work time calculation unit 42, a delimiter setting unit 43, and an output unit 44. The CPU 21A functions as each of these functional units by reading and executing the work recognition program 25A stored in the storage unit 25.

[0041] The total work time acquisition unit 40 acquires the total work time for a series of tasks performed by the worker. Specifically, in the example in Figure 2, it acquires the total work time from when task W starts task 1 until task 14 is completed. In order to acquire the total work time, it is necessary to identify the start time when task 1 is started and the end time when task 14 is completed.

[0042] For example, camera 30 acquires motion information based on video footage of worker W and workbenches TB1 to TB8. Based on the acquired motion information, the timing at which worker W makes the movement to start work 1 is identified and set as the start time of work 1. Similarly, based on the motion information, the timing at which worker W makes the movement to finish work 14 is identified and set as the end time of work 14.

[0043] As a method for acquiring movement information of worker W, a known method called OpenPose, described in Reference 1 below, can be used. OpenPose makes it possible to detect the skeletal information of worker W from captured images. Specifically, the skeletal information includes the coordinates of feature points such as body parts and joints of worker W, link information that defines links connecting each feature point, and labels that represent the body parts of the feature points. For example, feature points include facial parts such as the eyes and nose of worker W, and joints such as the neck, shoulders, elbows, wrists, waist, knees, and ankles.

[0044] OpenPose uses a pre-trained model that takes captured images as input and outputs skeletal information, trained using a large number of captured images as training data. For example, well-known methods such as CNN (Regions with Convolutional Neural Networks) are used to obtain such a pre-trained model.

[0045] (Reference 1) "OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields", Zhe Cao, Student Member, IEEE, Gines Hidalgo, Student Member, IEEE, Tomas Simon, Shih-En Wei, and Yaser Sheikh, IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE.

[0046] Alternatively, instead of the camera 30, motion sensors or the like may be used to acquire information about the worker W's movements.

[0047] Alternatively, as shown in Figure 5, a proximity sensor S1 may be provided on the workbench TB1, and the start time of task 1 may be determined based on the output signal of the proximity sensor S1. For example, the time when the proximity sensor S1 switches from off to on may be used as the start time of task 1. Specifically, as shown in Figure 6, the time T1 when the sensor output of the proximity sensor S1 exceeds a threshold is set as the start time of task 1.

[0048] Alternatively, as shown in Figure 5, a proximity sensor S2 may be provided on the workbench TB8, and the end time of task 14 may be determined based on the output signal of the proximity sensor S2. For example, the end time of task 14 may be determined as the time when the proximity sensor S2 switches from on to off. Specifically, as shown in Figure 6, the end time of task 14 is defined as the time T2 when the sensor output of the proximity sensor S2 falls below a threshold. The time T1 when the sensor output of the proximity sensor S2 rises above the threshold can be considered as the time it takes to move from the adjacent workbench TB7 to workbench TB8. Therefore, the work time T of task 14 can be calculated as T2 - T1. In order to accurately determine that task 14 has finished, it may be determined that task 14 has finished only when the work time T of task 14 is within a certain range.

[0049] For example, the work 14 may be determined to be completed only if the work time T falls within the following range.

[0050] a × Ts ≤ T ≤ b × Ts ... (1)

[0051] Here, Ts represents the standard time for task 14. Also, a and b are predetermined coefficients; for example, a=0.6 and b=2.0, but are not limited to these.

[0052] Standard time, for example, is the time it takes for a worker with a standard level of proficiency to perform a task under standard procedures, methods, and conditions, plus any buffer time. In other words, standard time is the time it takes for an average person to perform a task under normal circumstances.

[0053] The standard time information acquisition unit 41 acquires standard time information for each task in a series of operations. Figure 7 shows an example of standard time information 25B. As shown in Figure 7, standard time information 25B is table data that shows the correspondence between task number and standard time information. Standard time information 25B is prepared for each type of operation in the series.

[0054] The work time calculation unit 42 calculates the work time for each task performed by worker W based on the total work time acquired by the total work time acquisition unit 40 and the standard time information acquired by the standard time information acquisition unit 41. Specifically, the work time calculation unit 42 calculates the work time for each task based on the ratio of the total standard time, which is the sum of the standard times for each task, to the total work time. The ratio of the total standard time to the total work time is, for example, the value obtained by dividing the total work time by the total standard time.

[0055] In the following explanation, for the sake of simplicity, we will describe the case where worker W performs six tasks, and both a beginner and an experienced worker perform tasks 1 through 6.

[0056] Figure 8 shows an example of the actual work time and total work time for tasks 1 to 6 when worker W is a beginner, and the actual work time and total work time for tasks 1 to 6, as well as the standard time and total standard time for tasks 1 to 6 when worker W is a skilled worker.

[0057] In the example shown in Figure 8, the total standard time is 48.3 seconds, and the total work time for beginners is 60.3 seconds. The ratio R of the total standard time TS to the total work time TW, that is, the value obtained by dividing the total work time TW by the total standard time TS (=TW / TS), is 60.3 / 48.3 = 1.249.

[0058] Then, assuming that the working time for beginners in tasks 1 to 6 is Tn (n=1 to 6) and the standard time for tasks 1 to 6 is TSn (n=1 to 6), the working times T1 to T6 for tasks 1 to 6 are calculated using the following formula.

[0059] Tn = TSn × R ... (2)

[0060] In other words, the work time Tn for each task is calculated by multiplying the standard time TSn for each task by the ratio R.

[0061] Figure 9 shows the calculation results of the work time (matching time) for tasks T1 to T6 when worker W is a beginner. Note that in the example in Figure 9, the values ​​are rounded to two decimal places.

[0062] Figure 10 shows the correspondence between the actual work time (correct answer) for tasks 1 to 6 when worker W, as shown in Figure 8, is a beginner, and the matching time for tasks 1 to 6, as shown in Figure 9.

[0063] As shown in Figure 10, the matching times for tasks 1 through 6 are generally close to the correct task times.

[0064] Figure 11 shows the error in the timing of switching between tasks, comparing the matching time for tasks 1 to 6 with the work time for tasks 1 to 6 when worker W is a beginner. As shown in Figure 11, the error in switching from task 1 to task 2 is 1.3 seconds, the error in switching from task 2 to task 3 is 0.9 seconds, the error in switching from task 3 to task 4 is 1.3 seconds, the error in switching from task 4 to task 5 is 0.9 seconds, and the error in switching from task 5 to task 6 is 0.4 seconds. Thus, it can be seen that the error in the timing of switching between tasks is not very large.

[0065] Similarly, if worker W is a skilled worker, the work time for tasks 1 through 6 is calculated.

[0066] In the example shown in Figure 8, the total standard time is 48.3 seconds, and the total working time for skilled workers is 41.3 seconds. The ratio R of the total standard time TS to the total working time TW, i.e., the value obtained by dividing the total working time TW by the total standard time TS (=TW / TS), is 41.3 / 48.3 = 0.855.

[0067] Then, the working time Tn for each task is calculated using the above equation (2) based on the working time of skilled workers for tasks 1 to 6.

[0068] Figure 12 shows the calculation results of the work time (matching time) for tasks T1 to T6 when worker W is a skilled worker. Note that in the example in Figure 12, the values ​​are rounded to two decimal places.

[0069] Figure 13 shows the correspondence between the actual work time (correct answer) for tasks 1 to 6 when worker W, as shown in Figure 8, is a skilled worker, and the matching time for tasks 1 to 6, as shown in Figure 12.

[0070] As shown in Figure 13, the matching times for tasks 1 through 6 are generally close to the correct task times.

[0071] Figure 14 shows the error in the timing of switching between tasks, comparing the matching time for tasks 1 to 6 with the work time for tasks 1 to 6 when worker W is a skilled worker. As shown in Figure 14, the error in switching from task 1 to task 2 is 0.3 seconds, the error in switching from task 2 to task 3 is 0.2 seconds, the error in switching from task 3 to task 4 is 0.6 seconds, the error in switching from task 4 to task 5 is 0.5 seconds, and the error in switching from task 5 to task 6 is 0.6 seconds. Thus, it can be seen that the error in the timing of switching between tasks is not very large.

[0072] The delimiter setting unit 43 sets the delimiters between tasks in a series of tasks based on the work time of each task performed by worker W. Here, the delimiters between tasks refer to the start time and end time of each task. Specifically, as shown in Figure 15, the delimiter setting unit 43 records the work time of each task calculated by the work time calculation unit 42 in the delimiter information 25C.

[0073] Here, for example, if we only determine the end time of task 6, which is the last task in a series of tasks, the start time of task 1 in the second cycle and beyond is unknown. In this case, the time obtained by subtracting the total work time of the series from the end time of the last task in the series may be recorded in the delimiter information 25C as the start time of the first task in the series.

[0074] For example, as shown in Figure 16, suppose the total work time for the second cycle was 41.3 seconds. And, as shown in Figure 15, suppose the end time for the last task 6 of the second cycle was 92.9 seconds. In this case, as shown in Figure 15, the start time for task 1 of the second cycle is recorded in the delimiter information 25C as 92.9 - 41.3 = 51.3 seconds.

[0075] The output unit 44 outputs the delimiter information 25C related to the set delimiters between tasks to, for example, the storage unit 25 for storage.

[0076] Next, the work recognition process performed by the CPU 21A of the work recognition device 20 will be explained with reference to the flowchart shown in Figure 17. The following explanation will describe the case where worker W performs a series of tasks 1 through 14.

[0077] In step S100, the CPU 21A acquires standard time information 25B. For example, it displays a menu screen G1 on the display unit 23, as shown in Figure 18. The menu screen G1 includes a button B1 for selecting a standard time file in which the standard time information 25B is recorded, a button B2 for starting the measurement of the operator W's movements, a button B3 for editing annotations, and a button B4 for instructing the end of processing.

[0078] If the operator presses button B1, a selection screen G2 for selecting a standard time file, as shown in Figure 19, is displayed on the display unit 23. The operator then selects a standard time file corresponding to the series of tasks performed by worker W. This allows the standard time information 25B to be obtained.

[0079] In step S101, the CPU 21C starts measuring the movements of worker W. For example, when the operator presses button B2 on the menu screen G, the measurement of worker W's movements begins. Specifically, it starts acquiring video footage captured by camera 30.

[0080] In step S102, the CPU 21A determines, based on the acquired video footage, whether or not worker W has made the movement to start task 1, which is the first task in a series of tasks. If it determines that worker W has made the movement to start task 1, the process proceeds to step S103. On the other hand, if worker W has not made the movement to start task 1, the process of determining whether or not worker W has made the movement to start task 1 is repeated.

[0081] In step S103, CPU21A starts measuring time.

[0082] In step S104, the CPU 21A determines, based on the acquired video footage, whether or not the worker W performed the action to complete task 14, which is the last task in the series. If it determines that the worker W performed the action to complete task 14, the process proceeds to step S105. On the other hand, if the worker W did not perform the action to complete task 14, the process of determining whether or not the worker W performed the action to complete task 14 is repeated.

[0083] In step S105, CPU 21A obtains the total work time. Specifically, it calculates the total work time as the difference between the end time of task 14 and the start time when time measurement began in step S103.

[0084] In step S106, the CPU 21A calculates the work time for each of the tasks 1 to 14 performed by worker W, based on the standard time information 25B obtained in step S100 and the total work time obtained in step S105.

[0085] In step S107, the CPU 21A records the work time for each task calculated in step S106 in the segmentation information 25C.

[0086] In step S108, the CPU 21A determines whether the operator has instructed the end of the measurement. If the operator has instructed the end of the measurement, the process proceeds to step S109. If the operator has not instructed the end of the measurement, the process proceeds to step S102 and the above process is repeated.

[0087] In step S109, the CPU 21A outputs delimiter information 25C, which contains the start and end times of all operations, to the storage unit 25 and stores it, as shown in Figure 20.

[0088] In step S110, the CPU 21A accepts the editing process for the operator to add annotations to the video acquired in step S100. For example, when button B3 is pressed on the menu screen G1 shown in Figure 18, the CPU executes an editing process to edit the video according to the operator's operation. At this time, by using the delimiter information 25C, the playback position of the video can be easily switched to the start time of each operation, thus reducing the burden of the annotation editing work.

[0089] Thus, in this embodiment, the work time for each task is calculated based on the total work time for a series of tasks performed by the worker and the standard time for each task in the series. Therefore, the work time for each task in a series of tasks performed by the worker can be easily obtained.

[0090] Although this embodiment describes a case where work is performed on multiple workbenches TB, the disclosed technology can also be applied when multiple tasks are performed on a single workbench.

[0091] Furthermore, the above embodiments are merely illustrative examples illustrating the configuration of the present invention. The present invention is not limited to the above-described specific forms, and various modifications are possible within the scope of its technical concept.

[0092] Furthermore, the work recognition processing that the CPU reads and executes in each of the above embodiments may be executed by various processors other than the CPU. Examples of such processors include PLDs (Programmable Logic Devices) such as FPGAs (Field-Programmable Gate Arrays) whose circuit configuration can be changed after manufacturing, and dedicated electrical circuits that are processors with circuit configurations specifically designed to execute recognition processing, such as ASICs (Application Specific Integrated Circuits). The work recognition processing may be executed by one of these various processors, or by a combination of two or more processors of the same or different types (for example, multiple FPGAs, and a combination of a CPU and an FPGA). More specifically, the hardware structure of these various processors is an electrical circuit that combines circuit elements such as semiconductor elements. [Explanation of symbols]

[0093] 10. Work Recognition System 20 Work recognition device 21 Controllers 22 Control section 23 Display section 24 Communications Department 25 Memory section 25A Work Recognition Program 25B Standard time information 25C Separation Information 30 Cameras 40 Total work time acquisition unit 41 Standard Time Information Acquisition Unit 42. Work Time Calculation Unit 43 Settings section 44 Output section

Claims

1. A total work time acquisition unit that acquires the total work time for a series of tasks performed by an operator, A standard time information acquisition unit that acquires standard time information relating to the standard time of each task in the aforementioned series of tasks, A work time calculation unit calculates the work time for each task performed by the worker by multiplying the ratio of the total standard time (which is the sum of the standard times for each task) to the total work time for each task by the standard time for each task. A delimiter setting unit sets the delimiters between tasks in the series of tasks based on the time taken for each task performed by the worker, An output unit that outputs delimiter information regarding the set boundaries between tasks, A work recognition device equipped with the following features.

2. The total work time acquisition unit determines the start time of the series of tasks based on the output signal of a proximity sensor installed on the workbench where the first task of the series is performed. The work recognition device according to claim 1.

3. The total work time acquisition unit determines the completion time of the series of tasks based on the output signal of a proximity sensor installed on the workbench where the last task of the series is performed. The work recognition device according to claim 1 or claim 2.

4. If the start time of the first task in the series of tasks is unknown, the work time calculation unit calculates the start time of the first task in the series by subtracting the total work time of the series from the end time of the last task in the series. The work recognition device according to claim 1.

5. Computers A step to obtain the total working time for a series of tasks performed by the worker, The steps include obtaining standard time information relating to the standard time of each of the aforementioned tasks by reading it from the storage unit, The steps include: calculating the work time for each task performed by the worker by multiplying the ratio of the total standard time (which is the sum of the standard times for each task) to the total work time for each task by the standard time for each task; The steps include setting boundaries between tasks in the series of tasks based on the time taken for each task performed by the worker, The steps include outputting and storing delimiter information regarding the set boundaries between tasks in the storage unit, A method for recognizing tasks that include performing a process.

6. On the computer, A step to obtain the total working time for a series of tasks performed by the worker, The steps include obtaining standard time information relating to the standard time of each of the aforementioned series of operations by reading it from the storage unit, The steps include: calculating the work time for each task performed by the worker by multiplying the ratio of the total standard time (which is the sum of the standard times for each task) to the total work time for each task by the standard time for each task; The steps include setting boundaries between tasks in the series of tasks based on the time taken for each task performed by the worker, The steps include outputting and storing delimiter information regarding the set boundaries between tasks in the storage unit, A task recognition program that performs a process that includes the following.

Images