Work state estimation system

Abstract

To provide a work state estimation system for determining a work state of a worker, for achieving efficiency of work by using the determined work state in process control of the work.SOLUTION: A work state estimation system comprises: a work result information acquisition part 60 for acquiring work result information including information of a work item, information of work start time and work finish time of the work item, and information of a worker who performs the work item, the information being input to a work manager terminal 50 by a work manager; a master information database 100 for storing work plan information including information of the work item, information of work start scheduled time and work completion scheduled time of the work item, and information of a work scheduled area of the work item, and section information including information of the work area and positional information of the work area; and a work state determination part 110 for collating the positional information of the worker acquired from the positional information acquisition part 20, work result information acquired from the work result information acquisition part 60, work plan information and section information acquired from the master information database 100, for determining the work state of the worker.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to an operation state inference system. [Background technology]

[0002] Conventionally, a worker monitoring system includes a mobile terminal carried by a worker and a monitoring device that monitors the activity status of the worker. the mobile terminal has a location information acquisition unit that acquires location information of the mobile terminal itself, an acceleration sensor that measures acceleration of the mobile terminal itself, an activity state determination unit that determines that the worker is engaged in work activity when the location information of the mobile terminal has moved by a predetermined location information threshold or more within a preset first time period, or when acceleration equal to or greater than a predetermined first acceleration threshold is measured by the acceleration sensor within the first time period, and generates activity state information based on the determination result, and a communication unit that transmits the activity state information generated by the activity state determination unit to the monitoring device, The monitoring device has an output unit that acquires and outputs activity status information transmitted from the mobile terminal (see Patent Document 1 below). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2020-14124 A Summary of the Invention [Problem to be solved by the invention]

[0004] The aforementioned Patent Document 1 is a system that determines the activity state of a worker using a location information acquisition unit and an acceleration sensor, and does not aim to improve work efficiency by determining the worker's work state (working, taking a break, etc.) and using the determination results in a production management tool used to manage the work process.

[0005] The present disclosure discloses technology for solving the above-mentioned problems, and provides a work status inference system that determines the work status of a worker and can be used for work process management to improve work efficiency. [Means for solving the problem]

[0006] The work state inference system of the present disclosure includes: a position information acquisition unit that acquires position information of a worker from a position information sensor of the worker; a work performance information acquisition unit that acquires work performance information including information on work items, information on work start times and work completion times for the work items, and information on the workers engaged in the work items, which are input to the work manager's terminal by a work manager; a master information database that stores work plan information including information on the work items, information on the scheduled work start times and scheduled work completion times for the work items, and information on the scheduled work areas for the work items, and area information including information on the work areas and location information of the work areas; The system is provided with a work status determination unit which determines the work status of the worker by comparing the worker's location information obtained from the location information acquisition unit, the work performance information obtained from the work performance information acquisition unit, and the work plan information and area information obtained from the master information database. Effect of the Invention

[0007] According to the work state inference system of the present disclosure, the work state of a worker can be determined, and this can be used for work process management to improve work efficiency. [Brief description of the drawings]

[0008] [Figure 1] 1 is a block diagram showing a configuration of an operation state inference system according to a first embodiment. [Diagram 2] 4 is a flowchart showing location information acquisition steps according to the first embodiment. [Diagram 3]4 is a flowchart showing work performance information acquisition steps according to the first embodiment. [Figure 4] 4 shows an example of a screen for inputting information into the operator terminal according to the first embodiment. [Diagram 5] FIG. 4 is a diagram showing an example of work performance information according to the first embodiment. [Figure 6] FIG. 4 is a diagram showing work plan information stored in a master information database according to the first embodiment. [Figure 7] FIG. 4 is a diagram showing area information stored in a master information database according to the first embodiment. [Figure 8] 4 is a flowchart showing work state determination steps performed by a work state determination unit according to the first embodiment. [Figure 9] 4 is a time chart screen showing a working state of a worker outputted by an output control unit according to the first embodiment. [Figure 10] 4 is a time chart screen showing a working state of a worker outputted by an output control unit according to the first embodiment. [Figure 11] 4 is an analysis screen showing the working states of workers output by an output control unit according to the first embodiment. [Figure 12] 13 is an analysis screen showing the position information of a worker output by an output control unit according to the first embodiment. [Figure 13] FIG. 11 is a block diagram showing a first learning device in an activity state determination unit according to the second embodiment. [Figure 14] FIG. 11 is a diagram showing an example of a neural network in an operation state determining unit according to the second embodiment. [Figure 15] 11 is a flowchart relating to a learning process of a first learning device according to embodiment 2. [Figure 16] FIG. 11 is a block diagram showing a first inference device in an activity state determination unit according to embodiment 2. [Figure 17] 11 is a flowchart showing processing by a first inference device according to embodiment 2. [Figure 18]13 is a time chart screen showing the working state of a worker outputted by an output control unit according to the second embodiment. [Figure 19] 13 is a time chart screen showing the working state of a worker outputted by an output control unit according to the second embodiment. [Figure 20] FIG. 2 is a configuration diagram showing a first example of a processing circuit for realizing each function of the work state inference system according to the first and second embodiments. [Figure 21] FIG. 13 is a diagram illustrating a second example of the processing circuit for realizing each function of the work state inference system according to the first and second embodiments. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Embodiment 1 FIG. 1 is a block diagram showing the configuration of an operation state inference system according to the first embodiment. As shown in FIG. 1, the activity state inference system 1000 according to the first embodiment includes: a position information acquisition unit 20 that acquires position information of each worker from a position information sensor 10 of each worker; a position information database 30 for storing the position information of each worker obtained by the position information acquisition unit 20; a work performance information acquisition unit 60 that acquires work performance information including information on work items, information on work start times and work completion times for the work items, and information on each worker engaged in the work items, which are input to the work manager's terminal 50 by the work manager; A work performance information database 70 for storing the work performance information obtained by the work performance information acquisition unit 60; a master information database 100 for storing work plan information including information on work items, information on the scheduled work start times and scheduled work completion times for the work items, and information on the scheduled work areas for the work items, and area information including information on the work areas and location information of the work areas; a work status determination unit 110 for determining the work status of each worker by collating the location information of each worker obtained from the location information acquisition unit 20, the work performance information obtained from the work performance information acquisition unit 60, and the work plan information and area information obtained from the master information database 100; a work state database 120 that stores the work state of the worker determined by the work state determination unit 110 as a work status; and an output control unit 150 that outputs at least the work status of each worker based on information on the work status of each worker determined at least by the work status determination unit 110.

[0010] FIG. 2 is a flowchart showing location information acquisition steps according to the first embodiment. Each worker carries a position information sensor 10 shown in Fig. 1. The position information sensor 10 may be, for example, a GPS (Global Positioning System) sensor. In step S10, a position information signal is transmitted from the position information sensor 10 carried by each worker. In step S11, the position information acquisition unit 20 receives a signal from the position information sensor 10 carried by each worker, and acquires the position information of each worker. In step S12, the position information acquisition unit 20 stores the acquired position information of each worker in the position information database 30.

[0011] FIG. 3 is a flowchart showing the work performance information acquisition steps according to the first embodiment. The worker in charge of work has a worker terminal 50 shown in Fig. 1. The worker terminal 50 is, for example, a tablet PC (Tablet Personal Computer). In step S20, the worker inputs work performance information to the worker terminal 50. The work performance information input to the worker terminal 50 includes information on the work items, the work start times and work completion times for the work items, and information on each worker engaged in the work items.

[0012] FIG. 4 shows an example of a screen on which the worker inputs information into the worker terminal according to the first embodiment. 4, the work manager selects a specific work item from the work items of the work plan information stored in the master information database 100. In the example of FIG. 4, the work item W1 is selected as the work item. Then, the worker in charge of the work selects the workers who will be engaged in the specific work item. In the example of Fig. 4, workers P1 and P2 are selected as workers who will be engaged in the work item W1. The work manager also inputs the work start time and work completion time for a specific work item. In the example of Figure 4, the work start time is input by pressing the "Start button" when work item W1 starts, and the work completion time is input by pressing the "Complete button" when work item W1 is completed. By inputting the work start time and work completion time of work item W1, the work status indicating the work state of workers P1 and P2 becomes "in work" from the work start time to the work completion time. Furthermore, when work item W1 is interrupted, the time when the work is interrupted is input by pressing the "Interrupt button," and when work item W1 is resumed, the time when the work is resumed is input by pressing the "Resume button." In this case, the reason for interruption is entered in the "Reason for interruption" text box. As shown in the individual performance in Figure 9 described later, the section where the "Work Status" is interrupted around 12 o'clock reflects the process of entering "Meal Break" as the "Reason for Interruption" before 12 o'clock, pressing the "Pause Button," and then pressing the "Resume Button" at 12:30.

[0013] When the work of inputting the work performance information into the worker's terminal 50 in step S20 is completed, in step S21, the work performance information acquisition unit 60 receives the work performance information transmitted from the worker's terminal 50 and acquires the work performance information.

[0014] FIG. 5 shows an example of the work performance information according to the first embodiment. In FIG. 5, the work performance information includes, for each work item, the work start time and work completion time of each work item, and the worker engaged in each work item. That is, in the example of Figure 5, the work items are work item W1, work item W2, work item W3, and report creation WP, and the work start time and work completion time for each work item, as well as the workers P1, P2, P3, and PM responsible for the work who are engaged in each work item, are recorded. Although not shown in FIG. 5, in the work performance information, the work status indicating the work state of each worker for each work item is recorded as "in progress" from the work start time to the work completion time.

[0015] Returning to the flowchart of FIG. 3, in step S22, the work performance information acquisition unit 60 stores the acquired work performance information (for example, the work performance information in FIG. 5) in the work performance information database .

[0016] FIG. 6 is a diagram showing the work plan information stored in the master information database according to the first embodiment. In FIG. 6, the work plan information is information that is planned in advance and registered in the master information database 100, and for each work item, the scheduled start time and scheduled completion time for each work item, and the scheduled work area where the worker will be present for each work item are recorded. That is, in the example of Figure 6, the work items are work item W1, work item W2, work item W3, and report creation WP, and the scheduled start time and scheduled completion time for each work item are registered, and the scheduled work areas for each work item are work area A1, work area A2, and office A0.

[0017] FIG. 7 is a diagram showing area information stored in the master information database according to the first embodiment. In FIG. 7, the area information is information that is registered in advance in the master information database 100, and includes the name of each work area, location information of the work area that can identify the location of the building, number, room, etc., such as the (X, Y, Z) coordinates for each work area, a replacement flag (true or false) indicating whether the work status indicating the work state needs to be replaced, and a replacement status when the replacement flag is true. That is, in the example of FIG. 7, the work area names include work area A1, work area A2, rest room AR, and office A0, and the (X, Y, Z) coordinate information of each area is registered as the position information of the work area. The replacement flag and replacement destination status are flags and information used by the work state determining unit 110 when determining the work state. The replacement flag indicates whether the work status (working, taking a break, etc.), which is the state of the worker entered by the work manager on the work manager terminal 50, needs to be replaced with another work status in the work status determination unit 110 (true) or not (false). When the work area in which the worker is staying is determined from the position information of the worker and the replacement flag of the work area is true, the work state determination unit 110 replaces the work status, which is the state of the worker, with the replacement status.

[0018] FIG. 8 is a flowchart showing work state determination steps performed by the work state determination unit according to the first embodiment. In step S30, the work state determination unit 110 acquires area information from the master information database 100. In step S31, the work status determination unit 110 acquires work items that the worker is in charge of from the work performance information in the work performance information database . In step S32, the work status determination unit 110 acquires the planned work area of ​​the work item from the work plan information in the master information database 100. In step S33, the work state determination unit 110 identifies a work area from the position information of the worker in the position information database 30, and determines the work state of the worker according to the work area. In step S34, the work state determination unit 110 stores the work state of the worker determined in step S33 in the work state database 120 as a work status.

[0019] Returning to Fig. 1, the output control unit 150 receives work performance information from the work performance information database 70, worker position information from the position information database 30, work plan information and area information from the master information database 100, and the work status of the worker determined by the work status determination unit 110 from the work status database 120, and outputs an analysis screen including the work status of the worker described below. Note that although the output control unit 150 is configured to display on a screen, it may also be output on paper or the like.

[0020] Figures 9 and 10 are time chart screens showing the work status of a worker output by the output control unit according to embodiment 1, where Figure 9 shows the time chart screen before the work status is determined by the work status determination unit 110, and Figure 10 shows the time chart screen after the work status is determined by the work status determination unit 110. On the screens of FIGS. 9 and 10, work item W1 is selected as the work item as indicated in pull-down box G1. 9 and 10, time chart G2 shows the status of work item W1 according to work plan information (upper row) and the status of the work item according to work performance information (lower row). That is, in Fig. 9 and Fig. 10, the work plan information shows that the work started at 9:20 and was completed at 14:00, while the work performance information shows that the work started at 9:30 and was completed at 13:55.

[0021] 9 and 10, the time chart G3 shows the location information and work status of each worker in charge of the work item W1. In this example, the workers in charge of the work item W1 are workers P1 and P2, so the location information and work status of workers P1 and P2 are shown.

[0022] Here, the steps of determining the work state by the work state determining unit 110 will be described in accordance with the changes in the position information and work status of each worker on the screens of FIG. 9 and FIG. As shown in FIG. 9, before the work state determination unit 110 determines the work state, as shown in time chart G5, the position information of worker P1 changes from work area A1 to rest room AR to work area A1, but the work status remains in a working state. Also, before the work state determination unit 110 determines the work state, as shown in the time chart G5, the location information of the worker P2 changes from work area A1 to break room AR to work area A1, but the work status remains "working." Furthermore, as shown in the time chart G6, the location information of the worker P2 changes from office A0 to work area A1, but the work status remains "working."

[0023] As shown in FIG. 10, after the work state is determined by the work state determination unit 110, as shown in the time chart G7, the position information of the worker P1 is work area A1 → rest room AR → work area A1, and since the position information of the worker P1 is the rest room AR and not the work area A1, the work state determination unit 110 changes the work status of the worker P1 from “working” to “taking a break” in the time chart G7. Similarly, the location information of worker P2 is work area A1 → rest room AR → work area A1, and in time chart G7, the location information of worker P1 is the rest room AR rather than work area A1, so the work status determination unit 110 changes the work status of worker P2 from “working” to “taking a break” in time chart G7. Furthermore, in time chart G8, the location information of worker P2 is office A0 → work area A1, and since the location information of worker P2 is office A0 and not work area A1, the work status determination unit 110 changes the work status of worker P2 from “working” to “not assigned” in time chart G8.

[0024] As described above, in the first embodiment, the work status determination unit 110 determines the work status of a worker (working, on break, off assignment, etc.) based on the location information of the worker obtained from the location information acquisition unit 20 and the location information of the work area obtained from the work plan information and area information for the work item in which the worker is engaged obtained from the work performance information acquisition unit 60. In the first embodiment, the status of the worker is determined on a one-to-one basis, such that if the location information of the worker obtained from the location information acquisition unit 20 is a "work area", the status of the worker is "working", and if the location information of the worker is a "rest room", the status of the worker is "taking a break".

[0025] FIG. 11 shows an analysis screen showing the working states of workers output by the output control unit according to the first embodiment. The analysis screen in FIG. 11 displays the working and non-working states of the workers in a pie chart by tallying up the working states of the workers determined by the working state determining unit 110. According to the analysis screen in Figure 11, "unassigned work" that is in a work area different from the work plan information, "working," "meal break," "blank," "break," etc. that is in the work area of ​​the work plan information are visualized. In this case, the proportion of "unassigned work" was high, and it can be inferred that temporary work such as responding to problems occurred.

[0026] FIG. 12 is an analysis screen showing the position information of the worker output by the output control unit according to the first embodiment. The analysis screen in Figure 12 displays the proportion of worker location information in the form of a heat map. According to the analysis screen in Figure 12, as shown in heat map G10, the person returned to office A0 around noon, and it is possible that he performed clerical work without taking lunch, and it is inferred that he was engaged in temporary work such as responding to a problem.

[0027] As described above, according to the first embodiment, a position information acquisition unit that acquires position information of a worker from a position information sensor of the worker; a work performance information acquisition unit that acquires work performance information including information on work items, information on work start times and work completion times for the work items, and information on the workers engaged in the work items, which are input to the work manager's terminal by a work manager; a master information database that stores work plan information including information on the work items, information on the scheduled work start times and scheduled work completion times for the work items, and information on the scheduled work areas for the work items, and area information including information on the work areas and location information of the work areas; The present invention further includes a work status determination unit that determines the work status of the worker by collating the location information of the worker obtained from the location information acquisition unit, the work performance information obtained from the work performance information acquisition unit, and the work plan information and the area information obtained from the master information database, It is possible to determine the working status of workers (working, taking a break, etc.), which can be used to manage work processes and improve work efficiency.

[0028] In addition, the work state determination unit determines the work state of the worker based on the position information of the worker obtained from the position information acquisition unit and the position information of the work area obtained from the work plan information and the area information for the work item in which the worker is engaged, which are obtained from the work performance information acquisition unit. It is possible to easily determine the working status of a worker (working, taking a break, etc.), which can be used for work process management to improve work efficiency.

[0029] Furthermore, an output control unit is provided that outputs at least the work status of each of the workers based on at least the information on the work status of each of the workers determined by the work status determination unit among the position information of each of the workers obtained from the position information acquisition unit, the work performance information obtained from the work performance information acquisition unit, the work plan information and the area information obtained from the master information database, and the information on the work status of each of the workers determined by the work status determination unit. The working status of the worker (working, taking a break, etc.) can be determined, and this can be used for work process management to improve work efficiency.

[0030] In addition, the output control unit outputs, for each of the work items, a time chart screen showing the position information of each worker in charge of the work item and the work status of each worker. The work status of each worker (working, taking a break, etc.) can be easily determined.

[0031] Embodiment 2 In embodiment 1, the work status determination unit determines the work status of a worker (working, on break, off assignment, etc.) based on the worker's location information obtained from the location information acquisition unit and the location information of the work area obtained from the work plan information and area information for the work item in which the worker is engaged, obtained from the work performance information acquisition unit. That is, in embodiment 1, the worker's status is determined in a one-to-one correspondence with the worker's location information, such that if the worker's location information obtained from the location information acquisition unit is in a "work area", the worker's status is determined to be "working", and if the worker's location information is in a "rest room", the worker's status is determined to be "taking a break".

[0032] In the second embodiment, the work status of a worker (working, on break, off assignment, etc.) is determined based on transition data of the worker's location information obtained from the location information acquisition unit and location information of the work area obtained from the work plan information and area information for the work item in which the worker is engaged, obtained from the work performance information acquisition unit.

[0033] That is, in the second embodiment, for example, consider a case where the position information of the worker P1 transitions from the work area A1 to the break room AR to the warehouse AW to the break room AR to the work area A1. In this case, in the first embodiment, the work state of the worker may be determined as working → resting → working → resting → working. However, it is conceivable that the worker P1 goes from the work area A1 to the break room AR to the warehouse AW, picks up a tool, returns to the work area A1 via the break room AR, and performs work. In this case, by having the transition data of the position information of the worker P1 learned in advance, the work state of the worker P1 can be determined as "working".

[0034] For example, when performing a "test in the presence of a customer" task, the worker P1 may leave the work area A1, go to the office A0, and return to the work area A1 with the customer, and perform the "test work" in the presence of the customer. In this case, by having the transition data of the location information of the worker P1 learn in advance, the task of the worker P1 going to the office A0 → returning to the work area A1 with the customer → performing the test work in the presence of the customer can be determined as a "test in the presence of the customer."

[0035] [Supervised learning using neural networks] Next, a description will be given of supervised learning using a neural network for determining the state of a worker by the work state determining unit of the second embodiment.

[0036] As input B1 of the neural network, transition data of the worker's position information obtained from the position information acquisition unit 20 is input. Also, as input B2 (correct answer), correct answer data of the working state of the worker is input. For example, as input B1, the transition data of the work position information, work area A1 → break room AR → warehouse AW → break room AR → work area A1, is input. Then, as input B2 (correct answer), the work status of worker P1, "working", is input. Then, according to the learning data created based on a combination of input B1 and input B2, correct data on the working state of the worker, which is output C, is learned by so-called supervised learning.

[0037] Also, for example, as input B1, the transition data of the work location information, work area A1 → office A0 → work area A1, is input. Then, as input B2 (correct answer), the work status of worker P1, "witness test", is input. Then, according to the learning data created based on a combination of input B1 and input B2, correct data on the working state of the worker, which is output C, is learned by so-called supervised learning.

[0038] Hereinafter, the determination of the work state by the work state determining unit according to the second embodiment will be specifically described with reference to the drawings.

[0039] <Learning Phase> 13 is a block configuration diagram showing a first learning device 500B in the work state determination unit 110. The first learning device 500B includes a first data acquisition unit 510B, a first model generation unit 520B, and a first trained model storage unit 530B.

[0040] The first data acquiring unit 510B acquires the input B1 and the input B2 (correct answer) as learning data. As described above, the input B1 is transition data of the worker's location information obtained from the location information acquisition unit 20. The input B2 is correct data on the working status of the worker.

[0041] The first model generation unit 520B learns the C output (the working state of the worker) based on the learning data created based on a combination of the input B1 and the input B2 (correct answer) output from the first data acquisition unit 510B. That is, it generates a learned model that infers the optimal C output from the input B1 and the input B2 (correct answer) of the first learning device 500B. Here, the learning data is data in which the input B1 and the input B2 (correct answer) are associated with each other.

[0042] The first model generation unit 520B learns the C output by so-called supervised learning, for example, according to a neural network model. Here, supervised learning refers to a method of providing a learning device with a set of input and result (label) data, learning the features of the learning data, and inferring the result from the input.

[0043] A neural network is composed of an input layer made up of multiple neurons, an intermediate layer (hidden layer) made up of multiple neurons, and an output layer made up of multiple neurons. The intermediate layer may be one layer, or two or more layers.

[0044] For example, in a three-layered neural network as shown in Figure 14, when multiple inputs are input to the input layer (X1-X3), the values ​​are multiplied by weight W1 (w11-w16) and input to the intermediate layer (Y1-Y2), and the result is further multiplied by weight W2 (w21-w26) and output from the output layer (Z1-Z3). This output result changes depending on the values ​​of weights W1 and W2.

[0045] In this embodiment, the neural network learns the C output by so-called supervised learning according to learning data created based on a combination of input B1 and input B2 (correct answer) acquired by first data acquisition unit 510B.

[0046] In other words, the neural network learns by inputting an input B1 to the input layer and adjusting the weights W1 and W2 so that the result output from the output layer approaches the input B2 (correct answer).

[0047] The first model generation unit 520B executes the above-mentioned learning to generate and output a trained model.

[0048] The first trained model storage unit 530B stores the trained model output from the first model generation unit 520B.

[0049] Next, the learning process of the first learning device 500B will be described with reference to Fig. 15. Fig. 15 is a flowchart relating to the learning process of the first learning device 500B.

[0050] In step S510B, the first data acquisition unit 510B acquires the input B1 and the input B2 (correct answer). Note that, although the input B1 and the input B2 (correct answer) are acquired simultaneously, it is sufficient that the input B1 and the input B2 (correct answer) are associated with each other and the data of the input B1 and the input B2 (correct answer) may be acquired at different times.

[0051] In step S520B, the first model generation unit 520B learns the C output by so-called supervised learning according to learning data created based on a combination of input B1 and input B2 (correct answer) acquired by the first data acquisition unit 510B, and generates a learned model.

[0052] In step S530B, the first trained model storage unit 530B stores the trained model generated by the first model generation unit 520B.

[0053] <Utilization phase> 16 is a block diagram showing a first inference device 600B in work state determination unit 110. First inference device 600B includes a second data acquisition unit 610B and a second inference unit 620B. A C output from first inference device 600B is output to an output unit 630 in work state determination unit 110.

[0054] The second data acquisition unit 610B acquires the input B1 (transition data of the worker's position information).

[0055] The second inference unit 620B infers the C output (the working state of the worker) obtained by using the trained model in the first trained model storage unit 530B. That is, by inputting the input B1 acquired by the second data acquisition unit 610B to this trained model, it is possible to output the C output inferred from the input B1.

[0056] In this embodiment, the C output is described as being output using a trained model trained by the first model generation unit 520B of the work state determination unit 110, but it is also possible to obtain a trained model from an external source, such as another work state determination unit, and output the C output based on this trained model.

[0057] Next, the process for obtaining output C (working state of the worker) using first inference device 600B will be described with reference to FIG.

[0058] In step S610B, the second data acquisition section 610B acquires an input B1.

[0059] In step S620B, the second inference unit 620B inputs the input B1 to the learned model stored in the first learned model storage unit 530B, and obtains the C output.

[0060] In step S630B, the second inference unit 620B outputs the C output obtained by the learned model to the output unit 630 in the work state determination unit 110. The C output output to the output unit 630 in the work state determination unit 110 is stored in the work state database 120.

[0061] In the present embodiment, the case where supervised learning is applied to the learning algorithm used by the first model generating unit 520B has been described, but the present invention is not limited to this. As for the learning algorithm, reinforcement learning and the like can also be applied in addition to supervised learning.

[0062] The first model generation unit 520B may learn the C output according to learning data created for a plurality of work state estimation systems. The first model generation unit 520B may acquire learning data from a plurality of work state estimation systems used in the same area, or may learn the C output using learning data collected from a plurality of work state estimation systems operating independently in different areas. It is also possible to add or remove a work state estimation system that collects learning data from the target midway. Furthermore, a learning device that has learned the C output for a certain work state estimation system may be applied to another work state estimation system, and the C output for the other work state estimation system may be re-learned and updated.

[0063] In addition, the learning algorithm used in the first model generation unit 520B can be deep learning, which learns to extract the features themselves, or machine learning can be performed according to other well-known methods, such as genetic programming, functional logic programming, and support vector machines.

[0064] Figures 18 and 19 are time chart screens showing the work status of a worker output by the output control unit in embodiment 2, where Figure 18 shows the time chart screen before the work status is determined by the work status determination unit 110, and Figure 19 shows the time chart screen after the work status is determined by the work status determination unit 110.

[0065] 18, before the work state is determined by the work state determination unit 110, the position information of the worker P1 changes as follows, as shown in the time chart G20: work area A1 → break room AR → warehouse AW → break room AR → work area A1. However, since the work state has not yet been determined, the work status remains in a working state.

[0066] As shown in FIG. 19, after the work state is determined by the work state determination unit 110, as shown in the time chart G21, the position information of the worker P1 progresses from work area A1 → rest room AR → warehouse AW → rest room AR → work area A1, so the work state determination unit 110 determines that the worker P1 goes from the work area A1 to the rest room AR and then to the warehouse AW, picks up tools, and returns to the work area A1 via the rest room AR, and determines that the work status of the worker P1 remains “working” in the time chart G21.

[0067] In addition, in Figure 19, the position information of worker P2 in time chart G22 is work area A1 → rest room AR → work area A1, and since the position information of worker P1 is the rest room AR and not the work area A1, the work status determination unit 110 changes the work status of worker P2 from "working" to "taking a break" in time chart G22, as in Figure 10 of embodiment 1. Furthermore, in time chart G23, the location information of worker P2 is office A0 → work area A1, and therefore it is office A0 and not work area A1, so the work status determination unit 110 changes the work status of worker P2 from “working” to “not assigned” in time chart G23, as in FIG. 10 of embodiment 1.

[0068] As described above, in the second embodiment, the work state determination unit determines the work state of the worker based on transition data of the location information of the worker obtained from the location information acquisition unit, and the location information of the work area obtained from the work plan information and the area information for the work item in which the worker is engaged, which is obtained from the work performance information acquisition unit. This makes it possible to more accurately determine the working status of workers (working, taking a break, etc.), and can be used to manage work processes to improve work efficiency.

[0069] In addition, the work state determination unit a first data acquisition unit that acquires transition data of the position information of the worker and data of the working state of the worker as learning data; a first model generation unit that generates a trained model for inferring data on the working state of the worker from transition data of the position information of the worker by using the learning data; Since the first learning device has the following structure, It is possible to learn the working status of workers (working, taking a break, etc.) more accurately, and this can be used to manage work processes and improve work efficiency.

[0070] In addition, the work state determination unit A second data acquisition unit that acquires transition data of the worker's position information; a second inference unit that outputs data on the work state of the worker from the transition data of the position information of the worker, using a trained model for inferring data on the work state of the worker from the transition data of the position information of the worker; Since the first inference device has This makes it possible to more accurately infer the working status of workers (working, taking a break, etc.), which can be used to manage work processes and improve work efficiency.

[0071] Each function of the work state inference system of this embodiment is realized by a processing circuit. Fig. 20 is a configuration diagram showing a first example of a processing circuit that realizes each function of the work state inference system of this embodiment. The processing circuit 700 of the first example is dedicated hardware.

[0072] The processing circuit 700 corresponds to, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a combination thereof. Each function of the work state inference system 1000 may be realized by an individual processing circuit 700. Alternatively, each function of the work state inference system 1000 may be realized by the processing circuit 700 collectively.

[0073] 21 is a diagram showing a second example of a processing circuit for realizing each function of the activity state inference system according to the embodiment. The processing circuit 800 of the second example includes a processor 810 and a memory 820.

[0074] In the processing circuit 800, each function of the working state inference system 1000 is realized by software, firmware, or a combination of software and firmware. The software and firmware are written as programs. The software and firmware are stored in the memory 820. The processor 810 realizes the function of each part by reading and executing the programs stored in the memory 820.

[0075] It can be said that the programs stored in the memory 820 cause the computer to execute the procedures or methods of each of the above-mentioned sections. Here, the memory 820 corresponds to non-volatile or volatile semiconductor memories such as RAM (Random Access Memory), ROM (Read Only Memory), flash memory, EPROM (Erasable Programmable Read Only Memory), EEPROM (Electrically Erasable and Programmable Read Only Memory), etc. In addition, the memory 820 also corresponds to magnetic disks, flexible disks, optical disks, compact disks, mini disks, DVDs, etc.

[0076] The functions of each of the above-mentioned units may be partially realized by dedicated hardware and partially realized by software or firmware.

[0077] In this manner, the processing circuitry can realize the functions of each of the above-described units through hardware, software, firmware, or a combination of these.

[0078] Although the present disclosure describes various exemplary embodiments and examples, the various features, aspects, and functions described in one or more embodiments are not limited to application to a particular embodiment, but may be applied to the embodiments alone or in various combinations. Therefore, countless modifications not illustrated are assumed within the scope of the technology of the present disclosure, including, for example, modifying, adding, or omitting at least one component, and further, extracting at least one component and combining it with a component of another embodiment.

[0079] Various aspects of the present disclosure are summarized below as appendices. [Appendix 1] a position information acquisition unit that acquires position information of a worker from a position information sensor of the worker; a work performance information acquisition unit that acquires work performance information including information on work items, information on work start times and work completion times for the work items, and information on the workers engaged in the work items, which are input to the work manager's terminal by a work manager; a master information database that stores work plan information including information on the work items, information on the scheduled work start times and scheduled work completion times for the work items, and information on the scheduled work areas for the work items, and area information including information on the work areas and location information of the work areas; A work status inference system comprising a work status determination unit that determines the work status of the worker by comparing the worker's location information obtained from the location information acquisition unit, the work performance information obtained from the work performance information acquisition unit, and the work plan information and the area information obtained from the master information database. [Appendix 2] The work state estimation system described in Appendix 1, wherein the work state determination unit determines the work state of the worker based on the location information of the worker obtained from the location information acquisition unit and the location information of the work area obtained from the work plan information and the area information for the work item in which the worker is engaged, which are obtained from the work performance information acquisition unit. [Appendix 3] The work state inference system of claim 1 or 2, wherein the work state determination unit determines the work state of the worker based on transition data of the worker's location information obtained from the location information acquisition unit and location information of the work area obtained from the work plan information and the area information for the work item in which the worker is engaged, which is obtained from the work performance information acquisition unit. [Appendix 4] The work state determination unit is a first data acquisition unit that acquires transition data of the position information of the worker and data of the working state of the worker as learning data; a first model generation unit that generates a trained model for inferring data on the working state of the worker from transition data of the position information of the worker by using the learning data; An operation state prediction system as described in Appendix 3, comprising a first learning device having the above-mentioned. [Appendix 5] The work state determination unit is A second data acquisition unit that acquires transition data of the worker's position information; a second inference unit that outputs data on the work state of the worker from the transition data of the position information of the worker, using a trained model for inferring data on the work state of the worker from the transition data of the position information of the worker; 5. An operation state inference system as described in claim 4, comprising a first inference device having the above-mentioned. [Appendix 6] 6. A work state estimation system according to any one of Supplementary Note 1 to Supplementary Note 5, further comprising an output control unit that outputs at least the work state of each of the workers based on at least information of the work state of each of the workers determined by the work state determination unit among the location information of each of the workers obtained from the location information acquisition unit, the work performance information obtained from the work performance information acquisition unit, the work plan information and the area information obtained from the master information database, and information of the work state of each of the workers determined by the work state determination unit. [Appendix 7] 7. The work status inference system according to claim 6, wherein the output control unit outputs, for each of the work items, location information of each worker in charge of the work item and a time chart screen showing the work status of each worker. [Explanation of symbols]

[0080] 10 location information sensor, 20 location information acquisition unit, 30 location information database, 50 work manager terminal, 60 work performance information acquisition unit, 70 work performance information database, 100 master information database, 110 work status determination unit, 120 Working state database, 150 Output control unit, 500B First learning device, 510B first data acquisition unit, 520B first model generation unit, 530B first trained model storage unit, 600B first inference device, 610B second data acquisition unit, 620B second inference unit, 630 output unit, 1000 working condition prediction system.

Claims

1. a position information acquisition unit that acquires position information of a worker from a position information sensor of the worker; a work performance information acquisition unit that acquires work performance information including information on work items, information on work start times and work completion times for the work items, and information on the workers engaged in the work items, which are input to the work manager's terminal by a work manager; a master information database that stores work plan information including information on the work items, information on the scheduled work start times and scheduled work completion times for the work items, and information on the scheduled work areas for the work items, and area information including information on the work areas and location information of the work areas; A work status inference system comprising a work status determination unit that determines the work status of the worker by comparing the worker's location information obtained from the location information acquisition unit, the work performance information obtained from the work performance information acquisition unit, and the work plan information and the area information obtained from the master information database.

2. 2. The work state inference system according to claim 1, wherein the work state determination unit determines the work state of the worker based on the location information of the worker obtained from the location information acquisition unit and the location information of the work area obtained from the work plan information and the area information for the work item in which the worker is engaged, which is obtained from the work performance information acquisition unit.

3. 3. The work state inference system according to claim 1 or claim 2, wherein the work state determination unit determines the work state of the worker based on transition data of the worker's location information obtained from the location information acquisition unit and location information of the work area obtained from the work plan information and the area information for the work item in which the worker is engaged, which is obtained from the work performance information acquisition unit.

4. The work state determination unit is a first data acquisition unit that acquires, as learning data, transition data of the position information of the worker and data of the working state of the worker; a first model generation unit that generates a trained model for inferring data on a working state of the worker from transition data of the worker's position information by using the learning data; The task state inference system according to claim 3, further comprising a first learning device having:

5. The work state determination unit is A second data acquisition unit that acquires transition data of the worker's position information; a second inference unit that outputs data on the working state of the worker from the transition data of the position information of the worker, using a trained model for inferring data on the working state of the worker from the transition data of the position information of the worker; 5. The task state inference system according to claim 4, further comprising a first inference device having:

6. 3. A work state inference system as described in claim 1 or claim 2, further comprising an output control unit that outputs at least the work state of each of the workers based on at least information of the work state of each of the workers determined by the work state determination unit, among the location information of each of the workers obtained from the location information acquisition unit, the work performance information obtained from the work performance information acquisition unit, the work plan information and the area information obtained from the master information database, and information of the work state of each of the workers determined by the work state determination unit.

7. 7. The work status inference system according to claim 6, wherein the output control unit outputs, for each of the work items, a time chart screen showing location information of each worker in charge of the work item and the work status of each worker.

Images