Operation Analysis Device

Abstract

This task analysis device generates information pertaining to a plurality of tasks which are carried out by one or more workers at a workplace. The task analysis device comprises: a storage unit that stores map information indicating regions of the workplace which are associated with the respective tasks; an acquisition unit that acquires position information including the positions of the workers in the workplace at each time; and a control unit that carries out, on the basis of the position information and the map information, a computation process (S3) for determining tasks for the workers for each time. The control unit generates, on the basis of the position information, probability information which indicates the probability that a task associated with a region including the position of a worker for each time in the map information will be carried out by that worker (S12, S13), and corrects the probability information in accordance with task tendency information which indicates the tendency of tasks to be carried out by workers at the workplace (S14, S15).

Description

[[Technical Field]]

[0001] The present disclosure relates to a work analysis apparatus and method. [[Background Art]]

[0002] Patent Literature 1 discloses an analysis apparatus that analyzes work content during preparation work time before the start of operation of a paper converting machine. The analysis apparatus of Patent Literature 1 detects the work position of an operator of the paper converting machine, and creates an operator's motion diagram based on the detection result. Further, the analysis apparatus of Patent Literature 1, based on work process data and paper converting machine operation data, as a table that represents the work content in preparation work time by item, creates a graph showing work time for each separate item of the operation content of the paper converting machine and the corresponding work content of the operator. In the analysis apparatus of Patent Literature 1, based on these creation results, improvement items for improving production efficiency, such as work time being longer than the standard time, are selected for the work process in the preparation work time. [[Prior Art Documents]] [[Patent Documents]]

[0003] [[Patent Document 1]] International Publication No. WO2019 / 064398 [[Summary of the Invention]] [[Problem to be Solved by the Invention]]

[0004] The present disclosure provides a work analysis apparatus capable of estimating the work performed by a worker when a plurality of works are performed by one or more workers. [[Means for Solving the Problem]]

[0005] A work analysis device according to one aspect of the present disclosure generates information about multiple tasks performed by one or more workers in a workplace. The work analysis device comprises a storage unit, an acquisition unit, and a control unit. The storage unit stores map information indicating areas associated with each task in the workplace. The acquisition unit acquires location information, including the worker's position at each time in the workplace. The control unit performs calculation processing to determine the worker's task at each time based on the location information and the map information. Based on the location information, the control unit generates probability information indicating the probability that the task associated with the area including the worker's position at each time in the map information is performed by that worker, and corrects the probability information according to work trend information indicating the tendency for workers to perform tasks in the workplace.

[0006] These general and specific embodiments may be implemented by systems, methods, and computer programs, or combinations thereof. [Effects of the Invention]

[0007] According to the work analysis apparatus and method described herein, when multiple tasks are performed by one or more workers, it is possible to estimate the tasks performed by each worker. [Brief explanation of the drawing]

[0008] [Figure 1] Diagram showing an overview of the work analysis system according to Embodiment 1. [Figure 2] Block diagram illustrating the configuration of the work analysis device in a work analysis system. [Figure 3] A diagram illustrating map data in a work analysis device. [Figure 4] Diagram illustrating work area information and assigned personnel information in a work analysis device. [Figure 5] A diagram illustrating the challenges related to work analysis equipment. [Figure 6] A diagram illustrating the challenges related to work analysis equipment. [Figure 7] Flowchart to explain the overall operation of the work analysis device [Figure 8] A flowchart illustrating the task determination process. [Figure 9] Diagram to explain the task discrimination process. [Figure 10] A flowchart illustrating the correction process for each worker. [Figure 11] A flowchart illustrating the process of corrections between workers. [Figure 12] This figure shows an example of the display in the information presentation device of the work analysis system according to Embodiment 2. [Figure 13] Block diagram illustrating the configuration of the information presentation device in the work analysis system of Embodiment 2. [Figure 14] Flowchart for explaining the overall operation of the work analysis device according to Embodiment 2 [Figure 15] A flowchart illustrating the operation of an information display device. [Modes for carrying out the invention]

[0009] The embodiments will be described in detail below, with reference to the drawings as appropriate. However, unnecessary details may be omitted. For example, detailed explanations of already well-known matters or redundant explanations of substantially identical configurations may be omitted. This is to avoid the following explanation becoming unnecessarily verbose and to facilitate understanding by those skilled in the art. The inventors provide the accompanying drawings and the following explanation so that those skilled in the art can fully understand this disclosure, and do not intend to limit the subject matter described in the claims by means of these.

[0010] (Embodiment 1) 1-1. Composition The work analysis system according to Embodiment 1 will be described with reference to Figure 1. Figure 1 is a diagram showing an overview of the work analysis system 1 according to this embodiment.

[0011] 1-1-1. System Overview The present system 1 comprises a camera 2 and a work analysis device 5, as shown in FIG. 1. The present system 1 is applied to the use of analyzing the efficiency and the like of workers W1, W2 and W3 who perform a plurality of works in a work site 6 such as a distribution warehouse. The present system 1 may comprise a monitor 4 for presenting an analysis chart 7 related to a predetermined analysis period to a user 3 such as an administrator of the work site 6 or an analyst, for example. The analysis period is a period to be analyzed by image recognition or the like using the camera 2 in the present system 1, and is set in advance to, for example, one day to several months.

[0012] In the example of FIG. 1, a conveyance line 61 and a shelf 62 are installed in the work site 6. In this example, the plurality of works performed by each of the workers W1 to W3 while moving in the work site 6 include "picking" for taking out products from the shelf 62, "packing" for packing products into boxes on the conveyance line 61 and conveying the boxes, and "box preparation" for preparing the boxes.

[0013] The analysis chart 7 of the present system 1 shows the ratio of each item in the analysis period for each of the workers W1 to W3 by items obtained by classifying each work into "main work", "sub work" and "non-work" according to the magnitude of added value of the work, for example. In the example of FIG. 1, packing is the main work, and picking related to the main work, box preparation, movement toward the conveyance line 61 or the shelf 62, other auxiliary works and the like are sub works. Waiting states and the like not related to the main work are classified into non-work. As described above, the works to be analyzed in the work analysis device 5 include not only main work and sub work but also non-work.

[0014] According to the work analysis system 1 according to the present embodiment, by presenting the analysis chart 7, the user 3 can analyze the work content of each of the workers W1 to W3, for example, in order to study the improvement of work efficiency in the work site 6.

[0015] Camera 2 of this system 1 is positioned, for example, to capture the entire area in the workspace 6 where workers W1 to W3 move. Camera 2 repeatedly performs an imaging operation at a predetermined interval in the workspace 6, for example, and generates image data showing the captured image. Camera 2 is connected to the work analysis device 5, for example, so that the image data is transmitted to the work analysis device 5. Although Figure 1 shows one camera 2 as an example, the camera 2 included in this system 1 is not limited to one camera, but may be two or more cameras.

[0016] The work analysis device 5 is composed of information processing equipment, such as a server device. The work analysis device 5 is connected to an external information processing equipment, such as a PC including a monitor 4, in a communicative manner. The configuration of the work analysis device 5 will be explained using Figure 2.

[0017] 1-1-2. Configuration of the Working Analyzer Figure 2 is a block diagram illustrating the configuration of the work analysis device 5. The work analysis device 5 illustrated in Figure 2 comprises a control unit 50, a storage unit 52, an operation unit 53, an equipment interface 54, and an output interface 55. Hereinafter, interfaces will be abbreviated as "I / F".

[0018] The control unit 50 includes, for example, a CPU or MPU that works in cooperation with software to realize predetermined functions, and controls the overall operation of the work analysis device 5. The control unit 50 reads data and programs stored in the storage unit 52, performs various calculations, and realizes various functions. For example, the control unit 50 includes an image recognition unit 51 as part of its functional configuration.

[0019] The image recognition unit 51 applies various image recognition techniques to the image data to recognize the positions of pre-defined processing targets, such as workers W1 to W3, in the image data, and outputs the recognition result. The recognition result may include information indicating the time at which the positions of the processing targets were recognized. The recognition result is an example of position information in this embodiment. The image recognition unit 51 performs image recognition processing using a trained model of a neural network, such as a convolutional neural network. The image recognition processing may be performed using various image recognition algorithms.

[0020] The control unit 50 executes a program that includes a set of instructions for realizing the functions of the work analysis device 5, for example. This program may be provided via a communication network such as the Internet, or it may be stored on a portable recording medium. The control unit 50 may also be equipped with internal memory as a temporary storage area for holding various data and programs.

[0021] The control unit 50 may be a dedicated electronic circuit or a hardware circuit such as a reconfigurable electronic circuit designed to realize a predetermined function. The control unit 50 may be composed of various semiconductor integrated circuits such as a CPU, MPU, GPU, GPGPU, TPU, microcontroller, DSP, FPGA, and ASIC.

[0022] The storage unit 52 is a storage medium that stores the programs and data necessary to realize the functions of the work analysis device 5. The storage unit 52 is composed of, for example, a hard disk drive (HDD) or a semiconductor storage device (SSD). For example, the storage unit 52 stores the above-mentioned programs, as well as various types of information such as map data D1, work area information D2, and assigned information D3.

[0023] Map data D1 shows the arrangement of various equipment such as conveyor lines 61 and shelves 62 in the workspace 6 in a predetermined coordinate system. Work area information D2 is information that associates location with work in the workspace 6. Assignment information D3 is information that shows the area of ​​responsibility for each worker W1 to W3 in the workspace 6. Map data D1 and work area information D2 are examples of map information in the work analysis device 5 of this embodiment. Assignment information D3 is an example of work trend information in the work analysis device 5 of this embodiment. Details of each piece of information will be described later.

[0024] The memory unit 52 may include temporary memory elements, such as DRAM or SRAM, and may function as a work area for the control unit 50. For example, the memory unit 52 may temporarily store image data received from the camera 2 and recognition results from the image recognition unit 51.

[0025] The operation unit 53 is a general term for the operating components that receive user input. The operation unit 53 is composed of, for example, a keyboard, mouse, trackpad, touchpad, buttons, and switches, or a combination thereof. The operation unit 53 acquires various information input by the user.

[0026] The device interface 54 is a circuit for connecting external devices such as the camera 2 to the work analysis device 5. The device interface 54 communicates according to a predetermined communication standard. The predetermined standards include USB, HDMI (registered trademark), IEEE 1395, IEEE 802.11, Bluetooth (registered trademark), etc. The device interface 54 is an example of an acquisition unit that receives various information from an external device in the work analysis device 5. In the work analysis system 1, the work analysis device 5 acquires image data showing a video captured by the camera 2, for example, via the device interface 54.

[0027] Output I / F55 is a circuit for outputting information. Output I / F55 outputs video signals and other information to external display devices such as monitors and projectors, in accordance with standards such as HDMI, for example.

[0028] The configuration of the work analysis device 5 described above is just one example, and the configuration of the work analysis device 5 is not limited to this. The work analysis device 5 may be composed of various types of computers, including a PC (personal computer). In addition to the output I / F 55, or in its place, the work analysis device 5 may be equipped with a display unit, for example, a liquid crystal display or an organic EL display as a built-in display device. Furthermore, the work analysis method of this embodiment may be executed in a distributed computing environment.

[0029] Furthermore, the work analysis device 5 may have a configuration that allows it to communicate with an external information processing device via a communication network, in addition to or instead of the above configuration. For example, the operation unit 53 may be configured to accept operations from an external information processing device connected via a communication network. Also, the output I / F 55 may transmit various types of information to an external information processing device via a communication network.

[0030] Furthermore, the acquisition unit in the work analysis device 5 may be realized through cooperation with various software in the control unit 50, etc. The acquisition unit in the work analysis device 5 may acquire various information by reading various information stored in various storage media (for example, storage unit 52) ​​into the work area of ​​the control unit 50.

[0031] 1-1-3. About various data structures

[0032] The work analysis device 5 of this embodiment stores map data D1, work area information D2, and assigned information D3 in the storage unit 52 as described above. An example of the structure of the various data D1, D2, and D3 will be explained using Figures 3 and 4.

[0033] Figure 3 is a diagram illustrating map data D1. Map data D1 manages data that shows the coordinate system of a map, such as the layout of various facilities viewed from above in the workshop 6, by associating it with the arrangement of sections and work areas, which will be described later. Hereinafter, the two mutually orthogonal directions on the horizontal plane of the workshop 6 will be referred to as the X direction and the Y direction. The position in the workshop 6 is defined, for example, by the X coordinate indicating the position in the X direction and the Y coordinate indicating the position in the Y direction.

[0034] In the map data D1 of Figure 3, a conveyor line 61 and shelves 62 are shown, spaced apart in the X direction, corresponding to the workspace 6 shown in Figure 1. In the example of Figure 3, the conveyor line 61 extends in the Y direction and conveys boxes in the direction from positive to negative in the Y direction. In this example, the map data D1 divides the workspace 6 into multiple sections in the Y direction for management. Figure 3 shows an example where the workspace 6 is divided into sections Z1 and Z2. Each section Z1 and Z2 is pre-set, for example, as a unit section to which workers are assigned in the workspace 6.

[0035] Each section Z1 and Z2 includes a work area that indicates the area where workers W1 to W3, etc., work in the workspace 6. Section Z1 shown in Figure 3 includes work area A1 near the conveyor line 61 and work area A2 near the shelves 62. Each work area A1 and A2 is pre-set as an area within the workspace 6 where work related to the conveyor line 61 or shelves 62 is expected to be performed, respectively.

[0036] Figure 4 is a diagram illustrating the work area information D2 and the assigned information D3 in the work analysis device 5 of this embodiment.

[0037] The work area information D2 manages the "work area" and the "tasks" performed in each "section" of the work area 6, as shown in Figure 4(A), for example. For example, "packing" and "box preparation" tasks are performed in work area A1 near the conveyor line 61 in section Z1, and "collection" tasks are performed in work area A2 near the shelf 62 in section Z1. The work analysis device 5 can manage the correspondence between location and tasks in the work area 6 using the work area information D2.

[0038] The assignment information D3 manages the relationship between "workers" and "assigned areas," which are the areas where each worker primarily works, as shown in Figure 4(B), for example. In the example in Figure 4(B), worker W1's assigned area is area Z2, and worker W2's assigned area is area Z1. The assignment information D3 may be updated sequentially according to information indicating worker assignments, such as a daily work plan in the workplace 6. In addition, in the assignment information D3, the areas where each worker frequently stays may be set as their assigned area, for example, based on past recognition results by the image recognition unit 51.

[0039] Although not shown in the diagram, the work analysis device 5 of this embodiment stores, for example, work trend information related to the workplace 6 in the memory unit 52, in addition to the above-mentioned assignment information D3. The work trend information includes, for example, information such as the standard work period set for each worker's work, the maximum number of people for each work in each work area, and the work order, which indicates the temporal or spatial execution order in combinations of work. The work trend information may also include information indicating various trends in the types of work performed by the workers being analyzed in the workplace 6. Furthermore, the work trend information may also include information indicating classifications such as main work and sub-work in the analysis chart 7. The operation of the work analysis device 5 using this various information will be described later.

[0040] 1-2.Operation The operation of the work analysis system 1 and work analysis device 5, which are configured as described above, will be explained below.

[0041] The work analysis system 1 illustrated in Figure 1 recognizes the positions of workers W1 to W3 at each time point in the work area 6 using image recognition processing, and estimates the tasks performed by each worker W1 to W3 at each time point. This system 1 stores information showing the estimation results and generates an analysis chart 7 that visualizes the tasks performed by each worker W1 to W3 during the analysis period based on the stored information.

[0042] In this embodiment, the work analysis device 5, for example, uses an image recognition unit 51 to perform image recognition on images of the work area 6 captured by the camera 2 and recognize the positions of each worker W1 to W3. For example, in the area Z1 shown in Figure 3, the work analysis device 5 first determines the work being performed by each worker based on whether the positions of each worker included in the recognition results of the image recognition unit 51 are in work area A1, A2, or another area.

[0043] Here, for example, in work area A1 where multiple tasks are expected, as shown in work area information D2 in Figure 4(A), even if each worker W1 to W3 can be identified by image recognition processing based on images captured from camera 2, it may be difficult to distinguish the task that each worker is performing.

[0044] In this embodiment, the work analysis system 1 provides a work analysis device 5 that, in addition to image recognition processing, can estimate the work performed by each worker W1 to W3 based on, for example, pre-stored work trend information. According to the work analysis device 5 of this system 1, an analysis chart 7 is generated by determining the work performed based on the estimation results.

[0045] 1-2-1. About the Issues In the work analysis system 1 of this embodiment, the challenges in determining the work performed by each worker will be explained using Figures 5 and 6.

[0046] Figures 5 and 6 are diagrams illustrating the problems related to the work analysis device 5, and show workers W1 and W2 in the work area 6 viewed from above. Figures 5 and 6 show workers W1 and W2 working in section Z1 of the work area 6.

[0047] Figure 5(A) shows worker W1 "moving" and worker W2 "collecting". Figure 5(B) shows worker W1 arriving at work area A2 from Figure 5(A), and workers W1 and W2 each "collecting". Figure 5(C) shows worker W1 moving to work area A1 from Figure 5(B), and worker W1 "packing" and worker W2 "collecting". Figure 5(D) shows the scene after Figure 5(C), with worker W1 "preparing boxes" and worker W2 "collecting".

[0048] In the example in Figure 5(A), worker W1 is located in the area between work area A1 and work area A2, so worker W1's task can be identified as movement. On the other hand, worker W2 is located in work area A2 near shelf 62, so their task can be identified as collection. Also, in the example in Figure 5(B), both workers W1 and W2 are located in work area A2, so both of their tasks can be identified as collection.

[0049] In the example in Figure 5(C), worker W1 is located in work area A1 near the transport line 61, after work area A2 (Figure 5(B)) which corresponds to collection, so the work being performed can be identified as boxing. In the example in Figure 5(D), worker W2 is located in work area A2, so the work being performed can be identified as collection.

[0050] However, in the scene shown in Figure 5(D), it is difficult to determine that worker W1 is performing a different task, "box preparation," from the "box packing" task performed in Figure 5(C), even if it is recognized that worker W1 is located in the same work area A1 as in Figure 5(C). In other words, in work area A1 where multiple tasks are expected, it is difficult to determine from image recognition of worker W1's position whether worker W1 is continuing with box packing or has moved on to box preparation in the state shown in Figure 5(D), which is some time after Figure 5(C).

[0051] Furthermore, Figure 6 shows a scene where worker W1 is "preparing boxes" and worker W2 is "packing boxes." In the example in Figure 6, workers W1 and W2 are located in work area A1. In this way, even in a scene where workers W1 and W2 are working side by side in work area A1 where multiple tasks are expected, it is difficult to determine whether each of them is packing boxes or preparing boxes.

[0052] As described above, a potential problem is that relying solely on image recognition of workers W1 and W2 may make it difficult to distinguish the tasks being performed by each worker W1 and W2 in the work area 6, as these tasks change moment by moment.

[0053] Therefore, in the work analysis device 5 of this embodiment, in addition to the positions of workers W1 and W2, etc., the device performs probabilistic calculation processing to estimate the work performed by each worker based on work trend information such as assigned information D3. As a result, even in situations where multiple tasks are performed in a specific area such as work area A1, as shown in Figures 5(D) and 6, and it is difficult to distinguish the tasks based solely on the positions of each worker W1 and W2, the work performed by each worker W1 and W2 can be determined from the estimation results.

[0054] For example, in the situation shown in Figure 5(D), by using information about the elapsed time since Figure 5(C), it is possible to estimate that worker W1's work has shifted from boxing to box preparation. Also, in the situation shown in Figure 6, it is possible to estimate that the work performed by workers W1 and W2 is box preparation and boxing, respectively, based on the assigned areas of each worker W1 and W2, or based on the relationship between upstream and downstream processes in a combination of multiple tasks.

[0055] 1-2-2. Overall Operation The overall operation of the work analysis device 5 in the work analysis system 1 will be explained using Figure 7.

[0056] Figure 7 is a flowchart illustrating the overall operation of the work analysis device 5. The processes shown in this flowchart are executed, for example, by the control unit 50 of the work analysis device 5.

[0057] First, the control unit 50 acquires image data from the camera 2, for example via the equipment I / F 54 (S1). For example, while workers W1 to W3 are working in the workplace 6, the camera 2 captures a video and generates image data showing the captured image at each time point at a predetermined period, such as the frame period of the video, and transmits it to the work analysis device 5.

[0058] Next, the control unit 50 selects one section in the workspace 6 by referring to the map data D1 (S2). For example, from sections Z1 and Z2 shown in Figure 3, section Z1 is selected first.

[0059] The control unit 50 determines the task being performed for each worker who appears in the area corresponding to the section selected in step S2 in the image shown by the acquired image data (S3). In this task determination process (S3), the control unit 50 performs calculations to probabilistically estimate which tasks will be performed when multiple tasks are performed by multiple workers. In this embodiment, the control unit 50 performs the calculations in step S3 using the worker's position based on the image as well as task tendency information such as the aforementioned assignment information D3. Details of the task determination process (S3) will be described later.

[0060] The control unit 50 refers to the map data D1 to determine whether all sections in the workspace 6 have been selected (S4), and repeats steps S2 to S3 until all sections are selected per frame (NO in S4). For example, in the map data D1 of Figure 3, section Z1 is selected, followed by section Z2.

[0061] If all sections are selected (YES in S4), the control unit 50 determines whether a predetermined number of frames of work have been identified (S5). The predetermined number of frames is, for example, the number of frames captured by the camera 2 during the analysis period to be visualized in the analysis chart 7. The control unit 50 repeats steps S1 to S4 until a predetermined number of frames of work have been identified (NO in S5).

[0062] When a predetermined number of tasks are identified (YES in S5), the control unit 50 performs visualization processing (S6) to generate the analysis chart 7. For example, for each worker in the workspace 6, the control unit 50 counts the number of times the tasks identified by the task identification process (S3) are performed at each time interval, such as the duration of one frame. Once the total number of times each task is performed during the analysis period is calculated for each worker, the control unit 50 calculates the ratio of each task for each worker and generates the analysis chart 7. In the analysis chart 7, the ratio of each task is shown, for example, as the proportion of time each task spends in the analysis period.

[0063] The control unit 50, for example, stores the analysis chart 7 generated by the visualization process (S6) in the storage unit 52, and terminates the process shown in this flowchart.

[0064] According to the above process, the work performed by each worker is estimated for each section of the work area 6 by the work determination process (S3) (S3), and the work performed is determined based on the estimation results for the analysis period of all sections, thereby generating the analysis chart 7 (S6). According to the work determination process (S3) of this embodiment, even if it is difficult to determine the work performed at a specific time interval corresponding to the scenes shown in Figures 5(D) and 6 during the analysis period, for example, an analysis chart 7 that reflects the work performed at all time intervals during the analysis period can be obtained.

[0065] In step S1 described above, video data recorded during the analysis period may be acquired from camera 2. For example, after step S1, the control unit 50 may select image data for each frame and perform the processing from step S2 onward, and repeat these processes until all frames are selected, instead of step S5.

[0066] 1-2-3. About the task determination process (S3) The details of the task determination process in step S3 of Figure 7 will be explained using Figures 8 and 9.

[0067] Figure 8 is a flowchart illustrating the work discrimination process (S3 in Figure 7) in the work analysis device 5 of this embodiment. The process shown in the flowchart of Figure 8 starts, for example, with one section selected in step S2 in Figure 7. Below, we will explain using an example in which section Z1 in the work area 6, as shown in map data D1 in Figure 3, is selected.

[0068] Figure 9 is a diagram illustrating the task discrimination process (S3). In this embodiment, the task analysis device 5 generates a task probability table T1 for storing the probability of each task being assigned to each worker during the task discrimination process (S3). Figure 9(A) illustrates a task probability table T1 with items set corresponding to the captured images of the scene shown in Figure 6. Figures 9(B) and (C) illustrate a task probability table T1 whose values ​​have changed due to the process shown in the flowchart of Figure 8, respectively. The task probability table T1 is an example of probability information in this embodiment.

[0069] The work analysis device 5 of this embodiment maintains the probability for each worker's task, which can be calculated from the determination of the work area, based on the recognition result of each worker's position and the work area information D2, using the work probability table T1. Furthermore, the work analysis device 5 of this embodiment realizes the estimation of the work to be performed by performing calculation processing to correct the probabilities in the work probability table T1 based on work tendency information such as assignment information D3.

[0070] In the flowchart of Figure 8, first, the control unit 50 functions as an image recognition unit 51 and recognizes the positions of workers W1, W2, etc., in the image shown by the image data acquired in step S1 of Figure 7, and obtains the recognition result (S11). At this time, the control unit 50 calculates a coordinate transformation to convert the recognized position in the image into a coordinate system that shows the position in the workplace 6 based on the map data D1.

[0071] Next, the control unit 50 creates a work probability table T1 according to the area selected in step S2 of Figure 7 (S12). In the work probability table T1, the control unit 50 sets the items for the work and workers in the selected area by referring to, for example, the map data D1 and work area information D2 stored in the storage unit 52, and the acquired recognition results. The control unit 50 also sets, for example, the maximum number of people for each work that is previously stored in the storage unit 52.

[0072] In the work probability table T1 in Figure 9(A), "packing," "box preparation," and "collection" are set as tasks in section Z1 based on the work area information D2 in Figure 4(A), and "movement" is set as a task common to all sections, for example. Also, in the scene in Figure 6, for example, "worker W1" and "worker W2" are set based on the recognition result in the image region corresponding to section Z1. In the example in Figure 9(A), the maximum number of people for packing and box preparation is set to "1". The maximum number of people for each task is predetermined according to, for example, the spatial constraints in the work area of ​​each task or the nature of the task, and is stored in the memory unit 52. Packing and box preparation are examples of the second tasks in this embodiment.

[0073] Next, the control unit 50 allocates probabilities in the work probability table T1 based on the worker's position recognized in step S11 (S13). The control unit 50 compares, for example, the coordinates indicating the worker's position with the coordinates of the work area in the map data D1 to determine the work area to which each worker's position belongs. Based on, for example, the work area information D2, the control unit 50 allocates probabilities for each worker to the work in the determined work area.

[0074] Figure 9(B) illustrates the task probability table T1, in which probabilities are assigned in step S13 based on the recognition results in the image of the scene shown in Figure 6. In the example in Figure 6, the positions of workers W1 and W2 are recognized in work area A1. Also, as shown in the work area information D2 in Figure 4(A), two tasks, boxing and box preparation, correspond to work area A1. Therefore, in the task probability table T1 in Figure 9(B), a probability of "50%", considered equal, is assigned to both boxing and box preparation for worker W1. The same probability is assigned to worker W2 as to worker W1.

[0075] Next, the control unit 50 performs a worker-specific correction (S14) in the work probability table T1, where probabilities are assigned based on the worker's position. The processing in step S14 is performed based, for example, on the results of past work determination, the standard work period for each worker's work, and information on the temporal work sequence. In the example in Figure 5(D), if the control unit 50 determines, for example, from the past determination results that the standard work period for worker W1's boxing has elapsed, it performs a correction in the work probability table T1 to reduce the probability of worker W1's boxing by a predetermined value. The predetermined value is set as a positive value in a range smaller than the probability divided equally according to the number of workers. Details of the worker-specific correction process (S14) will be described later.

[0076] Next, the control unit 50 performs adjustments between workers in the work probability table T1 according to the relationships between multiple workers (S15). The processing in step S15 is performed based on, for example, work area information D2, assignment information D3, positional work order, and information on the time each worker was recognized by the image recognition unit 51. In the example in Figure 6, the control unit 50 determines, for example, that worker W2's assigned area is area Z1 based on the assignment information D3 in Figure 4(B), and performs adjustments in the work probability table T1 to increase the probability of packing, which is worker W2's main task, by a predetermined value. The predetermined value is, for example, the same as in step S14. Figure 9(C) shows an example in which adjustments between workers have been performed (S15) in the work probability table T1 before adjustment shown in Figure 9(B).

[0077] Next, the control unit 50 determines the task to be performed by each worker based on the corrected task probability table T1 (S16). In step S16, the control unit 50 determines that the task with the highest probability among multiple tasks in the task probability table T1 is the task to be performed for each worker. If the worker's highest probability does not exceed a predetermined threshold, the control unit 50 determines that the worker's task is a predetermined task (e.g., waiting). The control unit 50 stores the determination result in, for example, the storage unit 52. The predetermined threshold is set to a sufficiently large value, for example, from the viewpoint of excluding tasks that are unlikely to apply to each worker.

[0078] For example, in step S16, the work probability table T1 in Figure 9(C) indicates that the tasks performed by workers W1 and W2 are box preparation and box packing, respectively.

[0079] After determining the task performed by each worker (S16), the control unit 50 stores, for example, the corrected task probability table T1 in the storage unit 52, and terminates the process shown in this flowchart. Then, the process proceeds to step S4 in Figure 7.

[0080] According to the above task determination process (S3), even if the probability allocated from the worker's position (S13) cannot determine the task to be performed by each worker, a task probability table T1 corrected based on the task trend information is obtained (S14, S15). Based on this task probability table T1 corrected by the calculation process for estimating the task to be performed by each worker, the task to be performed is determined (S16), and one task is reliably assigned to each worker.

[0081] 1-2-4. Processing of corrections for each worker The process of step S14 in the task determination process described above (Figure 8) will be explained using Figure 10.

[0082] Figure 10 is a flowchart illustrating the worker-specific correction process (S14 in Figure 8) in the work analysis device 5 of this embodiment. The process shown in the flowchart of Figure 10 starts, for example, with probabilities allocated based on the worker's position in the work probability table T1.

[0083] First, the control unit 50 selects a worker from the work probability table T1 (S140). For example, in the work probability table T1 set up to correspond to the scene in Figure 5(D), worker W1 is selected from among workers W1 and W2.

[0084] The control unit 50, for the selected worker, refers to, for example, the information on the standard work period stored in the memory unit 52 and the results of the discrimination of past work, and performs a correction based on the standard work period (S141). The control unit 50 determines whether there is work that continues beyond the standard work period, and if there is such work, it reduces the probability of that work in the work probability table T1. The standard work period is set, for example, based on the time required for each worker's work, which has been measured in advance.

[0085] In the example in Figure 5(D), since worker W1 is located in work area A1, a 50% probability is assigned to worker W1's boxing and box preparation in the work probability table T1, similar to Figure 9(A) (S13 in Figure 8). For example, if the work determination process for the scene in Figure 5(C) determines that worker W1's work is boxing, and the standard work period for worker W1's boxing has elapsed since Figure 5(C) at the time of Figure 5(D), the probability of worker W1's work being boxing is reduced (S141). Boxing is an example of the first work in this embodiment.

[0086] Subsequently, the control unit 50 normalizes the probabilities of multiple tasks in the task probability table T1, for example, for the selected worker W1. In the example of Figure 5(D) described above, for the two tasks of boxing and box preparation, for example, the probability of worker W1 performing box preparation is increased by the amount by which the probability of boxing is reduced. Also, for example, if the probability of a task for which a maximum number of people is set is corrected, normalization may be performed to increase the probability of that task for workers other than the selected worker.

[0087] Furthermore, the control unit 50 refers to information indicating the temporal order of operations from, for example, the storage unit 52, and performs correction based on the temporal order (S142). The control unit 50 reduces the probability that an operation does not follow the operation determined in the immediately preceding operation determination process (Figure 8) for the operator selected in step S140.

[0088] For example, in the scenario shown in Figure 5(C), similar to the example in Figure 5(D), the probabilities of worker W1 performing box packing and box preparation are each allocated to "50%" in the work probability table T1 (S13 in Figure 8). For example, if the work immediately preceding worker W1, selected in step S140, is collection, then a correction is made to increase the probability of worker W1 performing box packing based on the information of the temporal work sequence, which is set from the knowledge that workers who carry packages during collection perform box packing (S142). Subsequently, similar to step S141, for example, the probabilities of multiple tasks for the selected worker W1 are normalized.

[0089] The control unit 50 repeats the process in steps S140 to S142 until all workers in the work probability table T1 are selected (NO in S143). Once all workers are selected (YES in S143), the control unit 50 terminates the correction process for each worker (S14 in Figure 8).

[0090] Based on the above processing, the probability for each worker in the work probability table T1 is corrected based on the information of the standard work period and the temporal order of work for each worker (S141-S142). As a result, even in a scenario where worker W1 is staying in work area A1 where multiple tasks are performed, as in Figure 5(D), the task of worker W1 can be determined by, for example, the correction process based on the information of the standard work period (S141) (S16 in Figure 8).

[0091] Furthermore, the correction process based on the temporal order of work (S142) may not be limited to step S14 in Figure 8, but may also be performed when allocating probabilities in the work probability table T1 (S13 in Figure 8). Also, the standard work period in step S141 may be calculated, for example, by measuring the period from start to completion multiple times for each worker's work, and then determining the period that includes a predetermined percentage (for example, 95% of the total number of measurements) in the frequency distribution of the measured periods.

[0092] 1-2-5. Processing of corrections between workers The process of step S14 in Figure 8 will be explained using Figure 11.

[0093] Figure 11 is a flowchart illustrating the processing of inter-worker corrections in the work analysis device 5 of this embodiment (S15 in Figure 8). The processing shown in the flowchart of Figure 11 starts, for example, when individual worker corrections have been performed in the work probability table T1 (S14 in Figure 8).

[0094] First, the control unit 50 selects one task from among several tasks in the task probability table T1 (S150). For example, in the task probability table T1 shown in Figure 9(B), boxing is selected first.

[0095] Next, the control unit 50 determines whether the selected task meets a predetermined correction condition (S151). The predetermined correction condition is set, for example, to correct the probability based on the relationship between multiple workers for a particular task. For example, the correction condition is that when the number of workers for whom the selected task has the highest probability is counted in the task probability table T1, the number of workers with the highest probability exceeds the maximum number of workers for that task. If the selected task does not meet the correction condition (NO in S151), the control unit 50 proceeds to step S155.

[0096] If the selected task meets the correction conditions (YES in S151), the control unit 50 performs a correction for that task based on the assigned information D3 (S152). For example, in the task probability table T1 in Figure 9(B), the number of workers for whom boxing has the highest probability is two, workers W1 and W2, which exceeds the maximum number of "1", so a correction is performed for boxing.

[0097] In step S152, the control unit 50 refers to the assignment information D3 and increases the probability of the main task for workers whose assigned section is the section selected in step S2 in Figure 7, i.e., the section targeted for the task discrimination process (S3). In this embodiment, for example, corresponding to the task classification in the analysis chart 7 in Figure 1, the main task is boxing. For example, in the task probability table T1 in Figure 9(B), since the assigned section for worker W2 is section Z1 in the assignment information D3 in Figure 4(B), a correction is made to increase the probability of boxing, which is worker W2's main task.

[0098] Subsequently, the control unit 50 performs a normalization process for each of the corrected workers and tasks, that is, for each row and column of the task probability table T1. In the example in Figure 9(B), after increasing the probability of worker W2 packing boxes through correction, normalization is performed to decrease the probabilities of worker W2 preparing boxes and worker W1 packing boxes, respectively. Furthermore, the control unit 50 increases the probability of worker W1 preparing boxes through normalization, for example, in worker W1.

[0099] In addition, in the correction based on the assignment information D3 in step S152, for example, the assigned tasks for each worker may be set in advance, and the probability of the assigned tasks may be increased instead of the main tasks in the example above. In this case, the assignment information D3 may include information indicating the assigned tasks. Alternatively, for example, the main tasks may be set in advance for each section or work area, and the work area information D2 may include information indicating the main tasks. In this case, the work area information D2 is referenced in step S152.

[0100] Next, the control unit 50 performs positional order correction based on the relationship of work positions in a combination of multiple tasks, including the selected task (S153). The control unit 50 performs the process in step S153 by referring, for example, the positional work order information stored in the memory unit 52 and the recognition result obtained in step S11 in Figure 8.

[0101] For example, in the scene in Figure 6, which corresponds to the work probability table T1 in Figure 9, in the work area A1 corresponding to the two tasks of boxing and box preparation, the position of worker W1 is recognized as being in the +Y direction relative to worker W2, i.e., upstream of the conveyor line 61 (S11 in Figure 8). In this case, the control unit 50 performs a correction to reduce the probability of worker W1 not being assigned to the task "boxing" (S153), based on positional work sequence information such as box preparation being upstream of the conveyor line 61 and boxing being downstream of the conveyor line 61. Subsequently, for example, the probabilities for the corrected boxing and worker W1 are normalized in the same way as in step S152.

[0102] Next, the control unit 50 performs a correction based on the order of arrival at the work area corresponding to the selected task (S154). Based on, for example, the work area information D2 and the recognition results from past image recognition unit 51, the control unit 50 compares the time each worker was recognized for multiple workers in the work area corresponding to the selected task. The control unit 50 increases the probability of the selected task for, for example, the worker who was recognized first in the work area among workers whose standard work period does not exceed that of the selected task, i.e., the worker who can be considered to have arrived at the work area earliest and started the selected task earliest. After that, normalization is performed on the corrected tasks and workers, for example, in the same way as in step S152.

[0103] The control unit 50 repeats the process from step S150 onward until all tasks in the task probability table T1 are selected (NO in S155). Once all tasks are selected (YES in S155), the control unit 50 terminates the processing of inter-worker adjustments (S15).

[0104] Based on the above processing, the probability for each task in the task probability table T1 is corrected based on the assigned information D3, the positional work order information, and the order of arrival at the work area (S152~S154). For example, in the scenario in Figure 6 where multiple workers W1 and W2 are working in work area A1 which corresponds to multiple tasks, the corrected task probability table T1 is obtained from the uncorrected probability in Figure 9(B) as shown in Figure 9(C). As a result, even if it is difficult to distinguish tasks based on the probabilities allocated to each worker W1 and W2 from their positions, the tasks performed by each worker can be determined based on the corrected task probability table T1 (S16 in Figure 8).

[0105] In addition, the corrections in steps S152 to S154 may be performed in a different order than the example described above, and only some of the corrections in steps S152 to S154 may be performed. Furthermore, the predetermined values ​​used to increase or decrease the probability by the correction in the work probability table T1 may be random numbers generated as positive numbers within a range smaller than the probability divided equally according to the number of workers.

[0106] 1-3. Effects, etc. As described above, the work analysis device 5 in this embodiment generates information about multiple tasks performed by one or more workers, namely workers W1 to W3, in a workplace 6, which is an example of a workplace. The work analysis device 5 comprises a storage unit 52, an equipment interface 54, which is an example of an acquisition unit, and a control unit 50. The storage unit 52 stores map data D1 and work area information D2 as an example of map information showing work areas A1, A2, etc., which are examples of areas associated with each task in the workplace 6. The equipment interface 54 acquires image data of captured images from the camera 2 as an example of location information including the location of workers at each time in the workplace 6 (S1). The control unit 50 performs calculation processing to determine the work performed by the workers at each time based on the location information and map information (S3). Based on the location information, the control unit 50 generates a work probability table T1, which is an example of probability information showing the probability that a task associated with an area including the worker's location at each time in the map information is performed by that worker (S12, S13). The control unit 50 corrects the work probability table T1 according to the work tendency information D3, which is an example of work tendency information that shows the tendency for work to be performed by workers in the workplace 6 (S14, S15).

[0107] According to the work analysis device 5 described above, the work probability table T1 generated based on location information is corrected according to work trend information such as assigned information D3. This makes it possible to estimate the work performed by a worker when multiple tasks are performed by one or more workers. In the work analysis device 5, the control unit 50 functions as an acquisition unit, and the recognition result of the image recognition unit 51 may be acquired as an example of location information.

[0108] In this embodiment, when the worker's location is included in a specific area such as work area A1 where two or more tasks are associated in the map information, the control unit 50 corrects the work probability table T1 so that the probabilities for those two or more tasks are different from each other, according to the work tendency information (S14, S15). As a result, even if two or more tasks are assigned equal probabilities based on location information in the work probability table T1, the work performed by the worker can be determined from the corrected work probability table T1 obtained as an estimation result (see Figures 9(B), (C)).

[0109] In this embodiment, when the positions of multiple workers are included in a specific area such as work area A1 where two or more tasks are associated in the map information, the control unit 50 corrects the probability of each worker's task among the multiple workers according to the work trend information (S15). This makes it possible to estimate the tasks performed by each worker through corrections among the workers, even when it is not possible to determine the tasks performed by each worker from a work area that includes the positions of multiple workers, such as in the scene in Figure 6.

[0110] In this embodiment, the work trend information includes information indicating the standard work period set for the first task in a plurality of tasks. When the period during which the worker's position is included in the area associated with the first task exceeds the standard work period, the control unit 50 reduces the probability related to the first task (S141). As a result, even if the worker W1's position is continuously included in work area A1, which is an example of an area associated with boxing (an example of the first task), as shown in Figures 5(C) and (D), the work performed by worker W1 can be estimated based on the standard work period for boxing.

[0111] In this embodiment, the work trend information includes information indicating the maximum number of workers performing a second task in parallel across multiple tasks. When the number of workers in a location included in the area associated with the second task exceeds the maximum number (YES in S151), the control unit 50 changes the probability of each worker performing the second task (S152-S154). This allows for adjustments to be made between workers to satisfy the maximum number of workers for each task, such as boxing and box preparation (an example of a second task) in the work probability table T1 in Figure 9.

[0112] In this embodiment, the work tendency information includes assignment information D3 (an example of assignment information) which associates a worker with a section Z1, which is an example of an area related to the second work. The control unit 50 corrects the probability of the work associated with the area when the worker's position is included in the area associated in the assignment information D3 (152). This allows the probability to be corrected to reflect the tendency of the workplace 6 in which each worker is likely to perform work in the work area included in the assigned section associated in the assignment information D3. The assignment information D3 may be generated based on the frequency with which the worker stays in the section.

[0113] In this embodiment, the recognition result of the image recognition unit 51 (an example of location information) includes information indicating the time when multiple workers arrived at a work area, which is an example of a region. When the number of workers at a location included in the work area associated with the second task exceeds the maximum number (YES in S151), the control unit 50 increases the probability of workers who arrived at the region earlier among the multiple workers (S154). This allows for correction to increase the probability of workers who arrived at the work area earlier and can be considered to have an earlier start time for the task corresponding to that work area.

[0114] In this embodiment, the work trend information includes information indicating the order of two or more tasks in a combination of multiple tasks. The control unit 50 corrects the probability for each task in the combination according to the order (S142, S153). This makes it possible to estimate the tasks performed by the worker based on the order, even when the worker's position is included in the work area A1 corresponding to two or more tasks, as shown in Figures 5(D) and 6. In this embodiment, the information indicating the order includes, for example, information on the temporal or spatial order of tasks. In the example of Figure 5(D), the tasks performed by worker W1 are estimated from the temporal order of tasks, and in the example of Figure 6, the tasks performed by workers W1 and W2 are estimated from the spatial order of tasks.

[0115] In this embodiment, the control unit 50 generates an analysis chart 7, which is an example of information showing the ratio of multiple tasks performed over a predetermined period, for each worker based on a work probability table T1 (an example of probability information) for the analysis period (an example of a predetermined period) (S6). This makes it possible to present the estimated results of the tasks performed by each worker over the analysis period to, for example, the user 3 of the work analysis system 1.

[0116] The work analysis method of this embodiment is a method for generating information on multiple tasks performed by one or more workers in a workplace 6. The storage unit 52 of the work analysis device 5, which is an example of a computer, stores map data D1 and work area information D2 (an example of map information) that indicate the area associated with each task in the workplace 6. This method includes the steps of the computer's control unit 50 acquiring location information including the position of workers at each time in the workplace 6 (S1, S11), generating a work probability table T1 (an example of probability information) that indicates the probability that a task associated with the area including the worker's position at each time in the map information is performed by the worker (S12, S13) based on the location information, and correcting the probability information according to work tendency information such as assignment information D3 that indicates the tendency for workers to perform tasks in the workplace 6 (S14, S15).

[0117] In this embodiment, a program is provided to cause a computer's control unit to execute the work analysis method described above. According to the work analysis method of this embodiment, when multiple tasks are performed by one or more workers, it is possible to estimate the tasks performed by each worker.

[0118] (Embodiment 2) Embodiment 2 of this disclosure will be described below with reference to Figures 12 to 15. Embodiment 1 described a work analysis system 1 in which a work analysis device 5 generates an analysis chart 7 over an analysis period (S6 in Figure 7). In this embodiment, a work analysis system 1A is described which includes an information display device capable of displaying the analysis results of work content in response to user operations specifying a particular time and workers W1 to W3.

[0119] Hereinafter, descriptions of the configuration and operation similar to that of the work analysis system 1 according to Embodiment 1 will be omitted as appropriate, and the work analysis system 1A according to this embodiment will be described.

[0120] 2-1. System Overview Figure 12 shows an example of the display in the information display device of the work analysis system 1A of this embodiment. The information display device in the work analysis system 1A is composed of an information processing device such as a PC including a monitor 4.

[0121] In the example shown in Figure 12, the monitor 4 displays an image 40 showing a video of the workspace 6 captured by the camera 2, a progress bar 41 showing the playback status during the video recording period, and estimated work information 9 showing the results of the analysis of the work content at a specific time.

[0122] In this system 1A, for example, while playing a video of the workspace 6 on monitor 4, estimated work information 9 can be displayed by user operation specifying workers W1 to W3 and the time in the video. In the example in Figure 12, for example, by user operation specifying the playback time on the progress bar 41 and selecting worker W1 on image 40, estimated work information 9 for worker W1 at the specified time is displayed. The estimated work information 9 in Figure 12 indicates that the work performed by worker W1 at the time "13:54" is estimated to be packing with a probability of "30%", preparing boxes with a probability of "70%", and other work with a probability of "0%".

[0123] According to this estimated work information 9, for example, a user of this system 1A can check the estimated results of the work performed by desired workers W1 to W3 at a specific time, and can analyze in detail the work performed by each worker W1 to W3.

[0124] 2-2. Configuration of the Information Display Device The configuration of the information display device, which includes a monitor 4 capable of displaying the estimated work information 9 described above, will be explained using Figure 13. Figure 13 is a block diagram illustrating the configuration of the information display device 8 in the work analysis system 1A of this embodiment.

[0125] The information display device 8 illustrated in Figure 13 comprises a control unit 80, a storage unit 82, an operation unit 83, a device interface 84, and a monitor 4.

[0126] The control unit 80 includes, for example, a CPU or MPU that works in cooperation with software to realize predetermined functions, and controls the overall operation of the information presentation device 8. The control unit 80 reads data and programs stored in the storage unit 82, performs various calculations, and realizes various functions. The above-mentioned programs may be provided from a communication network such as the Internet, or they may be stored on a portable recording medium. The control unit 80 may be equipped with internal memory as a temporary storage area for holding various data and programs. The control unit 80 may be implemented with various circuits, not limited to a CPU, for example, similar to the control unit 50 of the work analysis device 5.

[0127] The memory unit 82 is a storage medium that stores the programs and data necessary to realize the functions of the information presentation device 8. The memory unit 82 is composed of, for example, an HDD or an SSD. For example, the memory unit 82 stores the above-mentioned programs, as well as various information such as image data from the camera 2 and the work probability table T1 acquired from the work analysis device 5, as described later. The memory unit 82 may also include temporary memory elements composed of, for example, DRAM or SRAM, and may function as a work area for the control unit 80.

[0128] The operation unit 83 is a general term for the operating components that receive user input. The operation unit 83 is composed of, for example, a keyboard, mouse, trackpad, touchpad, buttons, and switches, or a combination thereof. The operation unit 83 acquires various information input by the user.

[0129] The device interface 84 is a circuit for connecting external devices, such as the work analysis device 5, to the information display device 8. The device interface 84 communicates according to a predetermined communication standard, similar to the device interface 54 of the work analysis device 5, for example. The device interface 84 is an example of an acquisition unit that receives various information from external devices in the information display device 8. In the work analysis system 1, the information display device 8 acquires image data from camera 2 and the corrected work probability table T1 from the work analysis device 5, for example, via the device interface 84.

[0130] Monitor 4 is an example of a display unit that displays various information. For example, Monitor 4 displays an image shown by image data acquired from the work analysis device 5. Monitor 4 also displays, for example, a menu screen for the user of the work analysis system 1 to make various settings. Monitor 4 can be made of, for example, a liquid crystal display device or an organic EL device.

[0131] The configuration of the information presentation device 8 described above is merely an example, and the configuration of the information presentation device 8 is not limited to this. For example, the work analysis device 5 may have a configuration that communicates with an external information presentation device via a communication network, in addition to or instead of the above configuration. Furthermore, the acquisition unit in the information presentation device 8 may be realized through cooperation with various software in the control unit 80, etc., and various information may be acquired by reading various information stored in various storage media (for example, storage unit 82) into the work area of ​​the control unit 80. In addition, the information presentation device 8 is not limited to a PC, but may be configured as a tablet terminal or a smartphone, etc.

[0132] 2-3. Operation of the work analyzer The overall operation of the work analysis device 5 in the work analysis system 1A, which includes the information presentation device 8 described above, will be explained with reference to Figure 14.

[0133] Figure 14 is a flowchart illustrating the overall operation of the work analysis device 5 according to this embodiment. In the work analysis device 5 of this embodiment, in addition to the processing of steps S1 to S6 similar to those in Figure 7 of Embodiment 1, for example, the control unit 50 stores the corrected work probability table T1 (see Figure 9(C)) in the storage unit 52 or the like after the work discrimination processing (S3) (S20).

[0134] According to the work analysis device 5 of this embodiment, for example, by repeating the above process at a predetermined interval and storing the work probability table T1 for each time point, the estimated results of the work performed by each worker W1 to W3 at each time point are accumulated.

[0135] 2-4. Operation of the Information Display Device In the work analysis system 1A, the operation of the information display device 8, which displays estimated work information 9 according to user specifications based on the time-based work probability table T1 described above, will be explained using Figure 15.

[0136] Figure 15 is a flowchart illustrating the operation of the information display device 8. This flowchart is initiated, for example, when a predetermined user operation to start the analysis is input to the information display device 8 after the processing shown in Figure 14 has been performed in the work analysis device 5 over the analysis period. Each process shown in this flowchart is executed, for example, by the control unit 80 of the information display device 8.

[0137] First, the control unit 80 acquires image data showing the video of the workplace 6 from the work analysis device 5 via, for example, the equipment I / F 84, and displays the video on the monitor 4 (S81). For example, the control unit 50 of the work analysis device 5 applies work discrimination processing (S3 in Figure 14) to the image data which is then transmitted via the equipment I / F 54, and the information display device 8 plays back the video based on the received image data. In the example in Figure 12, the monitor 4 displays an image 40 showing the video being played back.

[0138] Next, the control unit 80 determines, for example, whether a user operation specifying the time and workers W1 to W3 for the video being displayed has been input to the operation unit 83 (S82). The control unit 80 controls the operation unit 83 and the monitor 4 to accept, for example, a user operation specifying the time on the progress bar 41 of the video illustrated in Figure 12, and a user operation selecting one of the workers W1 to W3 on the image 40.

[0139] If no user input is entered specifying the time and operator (NO in S82), the control unit 80 repeats the decision in step S82, for example, at a predetermined interval.

[0140] When the user operation is input (YES in S82), the control unit 80 obtains, for example, the corrected work probability table T1 for the specified time from the work analysis device 5 and displays the estimated work information 9 for the specified workers W1 to W3 on the monitor 4 (S83). For example, the control unit 80 transmits information indicating the time and workers W1 to W3 specified by the user operation to the work analysis device 5 and controls the device I / F 54 to receive the corrected work probability table T1 for the time in that information. For example, for the specified worker among the workers W1 to W3, the control unit 80 extracts the probability of each task to be performed from the acquired work probability table T1 and generates the estimated work information 9.

[0141] In the example shown in Figure 12, the user input specifies the time "13:54" and worker W1 (YES in S82), and estimated work information 9 is displayed based on the probability of each task performed by worker W1 at that time (S83).

[0142] After displaying estimated work information 9 corresponding to the user's input (S83), the control unit 80 terminates the processing of this flowchart.

[0143] According to the above process, when a user input specifying the time and workers W1 to W3 is received while the video is being displayed (S81) (YES in S82), the information display device 8 can display estimated work information 9 corresponding to the user input on the monitor 4 (S83).

[0144] In step S82 described above, an example was given of determining whether or not a user operation has been performed to specify both the time and the workers W1 to W3. In step S82, the determination of whether or not a user operation has been performed to specify either the time or the workers W1 to W3 is not limited to the above example. In this case, when a user operation specifying the time is input, the information display device 8 may display the estimated work information 9 for each worker W1 to W3 at that time in step S83. Alternatively, when a user operation specifying workers W1 to W3 is input, the information display device 8 may display the estimated work information 9 for the specified worker at the time of the video being displayed in step S81 in step S83.

[0145] In step S81 described above, an example was explained in which image data of a video over the analysis period is acquired and displayed from the work analysis device 5. Step S81 is not limited to the above example; for example, image data may be acquired sequentially according to the frame period of the video and the image data of each frame may be displayed. In this case, in step S82, it may be determined whether or not a user operation has been entered specifying a time prior to the time corresponding to the currently displayed frame, and if there is no user operation (NO in S82), the processing from step S81 onwards may be repeated. Also, in step S81, the information presentation device 8 may acquire image data from the camera 2 via, for example, the equipment I / F 84.

[0146] In step S83 described above, an example was shown in which estimated work information 9 based on the work probability table T1 acquired from the work analysis device 5 is displayed on the monitor 4. In step S83, the monitor 4 may not be limited to the estimated work information 9 illustrated in Figure 12, but may also display, for example, the acquired work probability table T1. In addition, in step S83, for example, a heat map corresponding to the probability of each work performed in the work probability table T1 may be generated and displayed.

[0147] 2-5. Effects, etc. As described above, the work analysis system 1A in this embodiment comprises a work analysis device 5 and an information presentation device 8 that acquires a corrected work probability table T1 (an example of probability information) from the work analysis device 5 and displays the acquired probability information (S83). With such a work analysis system 1A, the information presentation device 8 can present to the user the estimated results of the work performed by workers W1 to W3 based on the acquired work probability table T1.

[0148] In the work analysis system 1A of this embodiment, the information presentation device 8 comprises an instrument I / F 84 (an example of a communication unit), an operation unit 83, a control unit 80, and a monitor 4 (an example of a display unit). The instrument I / F 84 communicates data with the work analysis device 5. The operation unit 83 receives user inputs indicating at least one of the time in the work area 6 and the workers W1 to W3 (S82). The control unit 80 transmits the specified information to the work analysis device 5 in response to the user input and controls the instrument I / F 84 to receive a corrected work probability table T1 from the work analysis device 5 as an example of probability information corresponding to the specified information, relating to the time and / or workers W1 to W3 specified by the user input (S83). The monitor 4 displays estimated work information 9 based on the corrected work probability table T1 as an example of probability information corresponding to the specified information (S83).

[0149] As described above, in this embodiment, the information display device 8 acquires the corrected work probability table T1 (an example of probability information) from the work analysis device 5 and displays the acquired probability information (S83). With such an information display device 8, probability information corresponding to user operations can be displayed, making it easier to analyze the work being performed.

[0150] (Other embodiments) As described above, Embodiments 1 and 2 have been explained as examples of the technology disclosed in this application. However, the technology in this disclosure is not limited thereto and can be applied to embodiments that have been modified, substituted, added, or omitted as appropriate. Furthermore, it is possible to create new embodiments by combining the components described in each of the above embodiments. Therefore, other embodiments are described below as examples.

[0151] In the embodiments described above, an example was explained in which, in the visualization process (S6 in Figure 7), an analysis chart 7 is generated based on the total number of times each task was identified as being performed by each worker at predetermined time intervals. However, step S6 is not limited to this. For example, the control unit 50 may generate the analysis chart 7 by calculating the sum of the probabilities of each task at each time interval over the analysis period based on the accumulated corrected task probability table T1, and then calculating the ratio of each task for each worker from the sum of the probabilities.

[0152] Furthermore, in the embodiments described above, an example was shown in which image data of the image captured by camera 2 is acquired via the device I / F 54 in step S1 of Figure 7, but step S1 is not limited to this. For example, the work analysis device 5 may read image data that has been stored in the storage unit 52 in advance. Also, in step S1, image data may be acquired in units of multiple frames, or one frame may be acquired for every multiple frames.

[0153] In the above embodiment 2, an example was described in which, after the processing shown in Figure 14 in the work analysis device 5 is executed over the analysis period, the processing shown in Figure 15 is executed in the information presentation device 8 to display the estimated work information 9. In this embodiment, for example, while the processing shown in Figure 14 is being executed at the frame cycle of a video, the processing shown in Figure 15 may be executed each time the corrected work probability table T1 is stored (S20). In this case, in step S81 of Figure 15, for example, image data of each frame may be acquired and displayed on the monitor 4. This makes it possible to display the estimated work information 9 according to the time and worker W1 to W3 in real time (S83).

[0154] Furthermore, in the embodiments described above, an example was explained in which image data is acquired in step S1 of Figure 7 and the worker's position is recognized by image recognition processing in step S11 of Figure 8, but steps S1 and S11 are not limited to this. For example, the work analysis device 5 may acquire the worker's position information via a beacon or GPS through the device I / F 54.

[0155] Furthermore, in each of the embodiments described above, an example was given in which the work analysis system 1 is applied to a workplace 6 such as a logistics warehouse. In this embodiment, the workplace, or site, to which the work analysis system 1 and work analysis device 5 are applied is not limited to the aforementioned workplace 6, but may be various sites such as a factory or a store's sales floor. Also, the work identified by the work analysis system 1 is not limited to the example of boxing described above, but may be various tasks appropriate to various sites. In addition, the worker to be analyzed by the work analysis system 1 is not limited to people such as workers W1 to W3, but may be any mobile object capable of performing various tasks. For example, the worker may be a robot, or various manned or unmanned vehicles.

[0156] As described above, embodiments have been explained as examples of the technology in this disclosure. For this purpose, accompanying drawings and a detailed description have been provided.

[0157] Therefore, the components described in the attached drawings and detailed descriptions may include not only components essential for solving the problem, but also components that are not essential for solving the problem, provided that they illustrate the technology described above. For this reason, the mere presence of these non-essential components in the attached drawings and detailed descriptions should not be immediately assumed to mean that they are essential. [Industrial applicability]

[0158] This disclosure is applicable to data analysis applications that analyze the work of individual workers in various environments such as logistics sites or factories.

Claims

1. A work analysis device that generates information on multiple tasks performed by one or more workers in a workplace, A storage unit that stores map information indicating the area corresponding to each task in the aforementioned workplace, An acquisition unit that acquires location information including the position of the worker at each time in the aforementioned workplace, The system includes a control unit that performs calculation processing to determine the worker's work for each time period based on the location information and the map information, The control unit, Based on the location information, the region containing the worker's position at each time point is determined in the map information, and the probability of each task being performed by the worker is allocated among the one or more tasks associated with the determined region in the map information, thereby generating probability information indicating the probability that each task is performed by the worker. The probability information is corrected according to work trend information that indicates the tendency for the work to be performed by the worker in the aforementioned workplace. The work trend information includes information indicating the maximum number of workers assigned to a task associated with an area in the workplace, assignment information associating the area related to the task with the maximum number of workers with the workers, and information indicating a specific task among the multiple tasks. When the number of workers at a location included in the area associated with the task for which the maximum number of people has been set exceeds the maximum number, the control unit corrects the probability information for workers at that location whose determined area is the area associated with the assigned information, so as to increase the probability of the specific task among the tasks associated with that area according to the map information. Work analysis device.

2. When the worker's position is included in a specific area in the map information where two or more tasks are associated, the control unit corrects the probability information so that the probabilities for the two or more tasks differ from each other, according to the task tendency information. The work analysis apparatus according to claim 1.

3. When the positions of multiple workers are included in the specific area in the map information, the control unit corrects the probability of each worker's work among the multiple workers according to the work trend information. The work analysis apparatus according to claim 2.

4. The aforementioned work trend information includes information indicating the standard work period set for the first work in the plurality of work, The control unit reduces the probability related to the first task when the period during which the worker's position is included in the area associated with the first task exceeds the standard work period. The work analysis apparatus according to any one of claims 1 to 3.

5. The aforementioned maximum number of people is set as the maximum number of workers who perform the second task in parallel with the second task in the aforementioned multiple tasks. The control unit changes the probability of each worker performing the second task when the number of workers in a location included in the area associated with the second task exceeds the maximum number. The work analysis apparatus according to any one of claims 1 to 4.

6. The aforementioned assignment information associates the area related to the second task with the worker, The control unit corrects the probability of the work associated with the area when the worker's position is included in the area associated with the assignment information. The work analysis apparatus according to claim 5.

7. The location information includes information indicating the time when multiple workers arrived in the area. When the number of workers in a location included in the area associated with the second task exceeds the maximum number, the control unit increases the probability of the worker who arrived in the area earlier among the multiple workers. The work analysis apparatus according to claim 5 or 6.

8. The aforementioned work trend information includes information indicating the order of combinations of two or more tasks in the plurality of tasks, The control unit corrects the probability of each operation in the combination according to the order. The work analysis apparatus according to any one of claims 1 to 7.

9. The control unit generates information for each worker indicating the ratio of the multiple tasks over the predetermined period, based on the probability information for the predetermined period. The work analysis apparatus according to any one of claims 1 to 8.

10. A work analysis method that generates information on multiple tasks performed by one or more workers in a workplace, The computer's memory unit stores map information indicating the areas corresponding to each task in the aforementioned workspace. The control unit of the aforementioned computer, The steps include acquiring location information, including the location of workers at each time in the aforementioned workplace, Based on the location information, determine the area in the map information that includes the worker's position at each time, and distribute the probability that each task will be performed by the worker among one or more tasks that correspond to the determined area in the map information, thereby generating probability information that indicates the probability that each task will be performed by the worker. A step of correcting the probability information in accordance with work trend information that indicates the tendency for the work to be performed by the worker in the aforementioned workplace. Includes, The work trend information includes information indicating the maximum number of workers assigned to a task associated with an area in the workplace, assignment information associating the area related to the task with the maximum number of workers with the workers, and information indicating a specific task among the multiple tasks. When the number of workers at a location included in the area associated with the task for which the maximum number of people has been set exceeds the maximum number, the control unit corrects the probability information for workers at that location whose determined area is the area associated with the assigned information, so as to increase the probability of the specific task among the tasks associated with that area according to the map information. Work analysis method.

11. A program for causing a computer control unit to execute the work analysis method described in claim 10.

12. A work analysis apparatus according to any one of claims 1 to 9, The system includes an information presentation device that acquires the probability information from the work analysis device and displays the acquired probability information. Work analysis system.

13. The aforementioned information display device is The aforementioned work analysis device and a communication unit that performs data communication, An operating unit that accepts user input of designated information indicating the time in the workplace and at least one of the worker, A control unit that controls the communication unit to transmit the specified information to the work analysis device in response to the user operation and to receive probability information corresponding to the specified information from the work analysis device, The system includes a display unit that displays probability information corresponding to the specified information. The work analysis system according to claim 12.

14. An information presentation device that acquires probability information from a work analysis device according to any one of claims 1 to 9 and displays the acquired probability information, The aforementioned work analysis device and a communication unit that performs data communication, An operating unit that accepts user input of designated information indicating the time in the workplace and at least one of the worker, A control unit that controls the communication unit to transmit the specified information to the work analysis device in response to the user operation and to receive probability information corresponding to the specified information from the work analysis device, The system includes a display unit that displays probability information corresponding to the specified information. Information presentation device.

Images