Work analysis device, work analysis method, and recording medium

Abstract

A work analysis device according to the present invention is provided with an acquisition unit, a first processing unit, and a second processing unit. The acquisition unit acquires a plurality of images generated by a plurality of photography devices individually photographing a work area in which a plurality of persons perform work. The first processing unit generates work information related to the work performed by each of the plurality of persons by processing the plurality of images. The second processing unit generates improvement information for improving work by using the work information and outputs the improvement information.

Description

Work analysis device, work analysis method, and recording medium

[0001] The present invention relates to a task analysis device, a task analysis method, and a recording medium.

[0002] Analyzing and visualizing the actions of workers has been studied. For example, Patent Literature 1 describes a device that performs the following process. This device recognizes and acquires the types of objects handled by a worker based on video footage of the worker's work, and also recognizes and acquires the types of actions that constitute the worker's work. This device then outputs information that represents the implementation status of actions for each type of object in chronological order.

[0003] JP 2023-140036 A

[0004] The device described in Patent Document 1 outputs information that expresses the implementation status of actions for each type of target object in chronological order. However, even using this information, it is difficult for, for example, a supervisor or worker to recognize content that can lead to improvements in the work.

[0005] The work analysis device of the present disclosure includes an acquisition means that acquires a plurality of images generated by a plurality of image capture devices capturing an image of a work area where a plurality of people are working; a first processing means that processes the plurality of images to generate work information related to the work performed by each of the plurality of people; and a second processing means that uses the work information to generate and output improvement information for improving the work.

[0006] The work analysis method disclosed herein involves a computer acquiring a plurality of images generated by a plurality of image capture devices capturing an image of a work area where a plurality of people are working, processing the plurality of images to generate work information regarding the work performed by each of the plurality of people, and using the work information to generate and output improvement information for improving the work.

[0007] The recording medium in the present disclosure records a program that causes a computer to have: an acquisition means that acquires a plurality of images generated by a plurality of photographing devices each capturing an image of a work area where a plurality of people are working; a first processing means that processes the plurality of images to generate work information related to the work performed by each of the plurality of people; and a second processing means that uses the work information to generate and output improvement information for improving the work.

[0008] According to the present disclosure, for example, a person supervising a work or a person performing the work can easily recognize information for improving the work.

[0009] 1 is a diagram illustrating an example of a usage environment of a work analysis device according to the present disclosure; FIG. 2 is a diagram illustrating an example of a functional configuration of a work analysis device; FIG. 3 is a diagram illustrating an example of a hardware configuration of a work analysis device; FIG. 4 is a flowchart illustrating an example of a processing operation of a work analysis device; FIG. 5 is a diagram illustrating an example of a usage environment of a work analysis device; FIG. 6 is a diagram illustrating an example of a screen displayed on a display by a communication device; FIG. 7 is a diagram illustrating an example of a screen displayed on a display by a communication device;

[0010] Hereinafter, in this disclosure, the drawings relate to one or more embodiments. In addition, in all drawings, similar components are given similar reference numerals and descriptions thereof will be omitted as appropriate.

[0011] As shown in FIG. 1 , the work analysis device 10 is used in conjunction with multiple imaging devices 20. The imaging devices 20 capture images of a work area and generate them. A work area is an area where multiple people work simultaneously. As an example, a work area may be, but is not limited to, a location where construction or civil engineering work is taking place, or inside a facility or building such as a factory or warehouse. There may be one type of work or multiple types of work being performed in a single work area. Furthermore, one type of work may be a collection of multiple types of sub-work. As such, there are various definitions of one type of work.

[0012] For example, taking items from a warehouse, placing them in a tray or cardboard box, and carrying them to a designated location may be defined as one type of work. Also, taking items from a warehouse and placing them in a tray or cardboard box and carrying the container to a designated location may be defined as two different types of work.

[0013] The frame rate of images generated by the imaging devices 20 is arbitrary, but is, for example, 5 frames per second (5 fps) or higher. The imaging ranges of the multiple imaging devices 20 may partially overlap or may differ. Furthermore, there may be areas in the work area that are not included in the imaging ranges of any of the imaging devices 20, or there may be no such areas. Note that, for example, if the work area is a warehouse, there may be an obstruction 30, such as a shelf, within the work area. In this case, it is preferable to determine the positions of the multiple imaging devices 20 so that no areas are hidden by the obstruction 30.

[0014] The work analysis device 10 analyzes work performed by multiple people in a work area by processing images generated by multiple image capture devices 20. The work analysis device 10 then generates and outputs improvement information for improving the work. The improvement information is, for example, information for improving work efficiency, and indicates changes to work allocation or improvements to work procedures. The improvement information is output in a manner that can be recognized by, for example, at least one of the people performing the work or at least one of the people managing the work.

[0015] As shown in FIG. 2 , the work analysis device 10 includes an acquisition unit 110, a first processing unit 120, and a second processing unit 130. The acquisition unit 110 acquires images generated by each of the multiple imaging devices 20. The first processing unit 120 processes these multiple images to generate work information. The work information relates to work performed by each of multiple people. The work information may be generated for each of the multiple people, or may collectively represent information about the multiple people. The second processing unit 130 uses the work information to generate and output improvement information.

[0016] The work analysis apparatus 10 can use an internal information storage unit 40. The internal information storage unit 40 stores various types of information used by the work analysis apparatus 10. For example, the internal information storage unit 40 stores images generated by multiple imaging devices 20. The acquisition unit 110 may acquire images from the internal information storage unit 40. The acquisition unit 110 may also store images acquired from the imaging devices 20 in the internal information storage unit 40.

[0017] The work analysis device 10 has, as a hardware configuration, for example, as shown in FIG. 3, a bus 1010, a processor 1020, a memory 1030, a storage device 1040, an input / output interface 1050, and a network interface 1060.

[0018] The bus 1010 is a data transmission path for transmitting and receiving data among the processor 1020, memory 1030, storage device 1040, input / output interface 1050, and network interface 1060. However, the method of connecting the processor 1020 and the like to each other is not limited to bus connection.

[0019] The processor 1020 is implemented by a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or the like.

[0020] The memory 1030 is a main storage device realized by a RAM (Random Access Memory) or the like.

[0021] The storage device 1040 is an auxiliary storage device realized by removable media such as a hard disk drive (HDD), a solid state drive (SSD), or a memory card, or read-only memory (ROM), and has a recording medium. The recording medium of the storage device 1040 stores program modules that realize each function of the work analysis apparatus 10 (e.g., the acquisition unit 110, the first processing unit 120, and the second processing unit 130). The processor 1020 loads each of these program modules into the memory 1030 and executes them, thereby realizing each function corresponding to the program module. The storage device 1040 may also function as a memory unit that stores various types of information (e.g., at least one of the internal information memory unit 40 and the external information memory unit 60 described below).

[0022] The input / output interface 1050 is an interface for connecting the work analysis device 10 to various input / output devices.

[0023] The network interface 1060 is an interface for connecting the work analysis device 10 to a network. This network may be, for example, a local area network (LAN) or a wide area network (WAN). The network interface 1060 may connect to the network wirelessly or via a wired connection. The work analysis device 10 may communicate with a communication device 50 (described later) via the network interface 1060.

[0024] The work analysis device 10 may be realized by a plurality of devices each having the configuration shown in FIG.

[0025] The work analysis device 10 operates, for example, as shown in Fig. 4 . First, the acquisition unit 110 acquires multiple images generated by multiple imaging devices 20. For example, the acquisition unit 110 acquires multiple frame images generated by each of the multiple imaging devices 20 (step S10). Next, the first processing unit 120 processes these multiple images to generate work information (step S20). Next, the second processing unit 130 generates improvement information using the work information (step S30) and outputs the generated improvement information (step S40).

[0026] The work analysis device 10 may perform processing in real time, i.e., while multiple people are working in the work area, or may perform processing using images captured and stored after multiple people have worked in the work area.

[0027] In this way, the work analysis device 10 outputs improvement information. The improvement information is information for improving work. Therefore, for example, the person performing the work can improve the work by recognizing this improvement information. Furthermore, the person managing the work can improve the work plan or provide guidance to the person performing the work to improve the work by recognizing this improvement information.

[0028] Below, detailed examples of the processes performed by the first processing unit 120 and the second processing unit 130, as well as detailed examples of the work information and improvement information, will be described.

[0029] First, a detailed example of the processing performed by the first processing unit 120 and a detailed example of the work information will be described.

[0030] As described above, the first processing unit 120 generates task information by processing images generated by each of the multiple imaging devices 20. The task information relates to tasks performed by each of the multiple people.

[0031] For example, the first processing unit 120 processes images generated by the imaging devices 20 separately for each of the multiple imaging devices 20 to identify each of the multiple people and to identify the type of work each person is performing. The first processing unit 120 then integrates the processing results for each of the imaging devices 20. In this manner, the first processing unit 120 generates work information. The work information includes, for example, work type information indicating the content of the work a person is performing, i.e., the type of work, and the time the person started the work. If the work has been completed, the work information may further include the time the person finished the work. In this case, the work information includes information indicating, for each person, the type of work performed by that person in chronological order. Hereinafter, this information will be referred to as chronological information.

[0032] [Person Identification] The first processing unit 120 identifies each of the multiple people, for example, using at least one of the following methods (1-1) to (1-6), and determines whether the people included in each of the multiple images generated by the multiple imaging devices 20 are the same person.

[0033] (1-1) The first processing unit 120 identifies a person using appearance, such as at least one of a face, a figure, and an attached item. An example of an attached item is at least one of clothing and a tool. In this case, the first processing unit 120 may identify a person by recognizing features of the appearance. Using this method, the first processing unit 120 can determine whether a person included in an image generated by the first imaging device 20 is the same as a person included in an image generated by the second imaging device 20.

[0034] (1-2) When a code such as a barcode or a two-dimensional code is attached to an item worn by a person, such as clothing, a bib, or a helmet, the first processing unit 120 identifies the person by recognizing the code. Using this method, the first processing unit 120 can determine whether the person included in the image generated by the first imaging device 20 is the same as the person included in the image generated by the second imaging device 20.

[0035] (1-3) The first processing unit 120 identifies the type of work being performed by the person and uses this type of work to determine the identity of the person. For example, if the type of work being performed by the person included in the image generated by the first imaging device 20 is the same as the type of work being performed by the person included in the image generated by the second imaging device 20, the first processing unit 120 determines that there is a high possibility that the people included in these images are the same.

[0036] (1-4) The first processing unit 120 identifies the position of the person in the image and converts this position into a position in real space, i.e., a position in the world coordinate system, by converting this position according to a predetermined conversion rule. Then, using the identity of this position, it determines whether the person included in the image generated by the first imaging device 20 is the same as the person included in the image generated by the second imaging device 20. This process is effective when at least a portion of the imaging area of ​​the first imaging device 20 overlaps with the imaging area of ​​the second imaging device 20.

[0037] (1-5) The first processing unit 120 uses a rule based on feasible movement lines in the work area to determine whether a person included in an image generated by the first imaging device 20 is the same as a person included in an image generated by the second imaging device 20. For example, if there is a passage in the work area, and the first imaging device 20 captures an image of the entrance of the passage and the second imaging device 20 captures an image of the exit of the passage, there is a rule that a person who enters through the entrance will exit through the exit or the entrance. The first processing unit 120 uses this rule to determine whether a person included in an image generated by the first imaging device 20 is the same as a person included in an image generated by the second imaging device 20.

[0038] (1-6) When multiple people each have a transmitting device, such as a beacon or a wireless communication tag, that transmits different identification information over a short communication distance, and multiple receiving devices are located in the work area, the first processing unit 120 may use the identification information received by the multiple receiving devices to identify the position of each person in the world coordinate system.The first processing unit 120 then uses this position to identify which image capture device 20 generated the image that includes each of the multiple people.

[0039] [Method for Identifying Task Type] The first processing unit 120 generates task type information using, for example, at least one of the person's posture and the tools the person is using. The first processing unit 120 identifies the task type using, for example, at least one of the following methods (2-1) to (2-3). For example, if the task area is a warehouse, task types include stocking, picking, transporting, inspection, packing, and rest. In each of methods (2-1) to (2-3), the first processing unit 120 also calculates a value indicating the likelihood that the task is the task type, i.e., a reliability value.

[0040] (2-1) The first processing unit 120 processes multiple images, for example, multiple frame images generated by the same image capture device 20, to obtain information on a time series of a person's posture, i.e., the person's movement. The first processing unit 120 then uses this movement to identify the type of work and the start time of the work. For example, information indicating the movements corresponding to each type of work is registered in advance in the work analysis device 10 or an external storage device. The first processing unit 120 then compares this information with the person's movement identified by image processing to identify the type of work and the start time of the work. Note that if two or more image capture devices 20 capture the same area but are oriented differently relative to the area, the first processing unit 120 may use images generated by the two or more image capture devices 20 at the same time when identifying the posture.

[0041] (2-2) The first processing unit 120 processes at least one image to identify the tool used by at least one person. The first processing unit 120 then determines the task using this tool as the task being performed by that person. Note that information indicating the task using each of multiple tools is registered in advance in the work analysis device 10 or an external storage device. The first processing unit 120 uses this information. Note that if two or more image capture devices 20 capture images of the same area but are oriented differently relative to this area, the first processing unit 120 may use images generated by these two or more image capture devices 20 at the same time when identifying the tool.

[0042] (2-3) When using both (2-1) and (2-2) above, the first processing unit 120 differentiates the imaging device 20 to which (2-1) is applied from the imaging device 20 to which (2-2) is applied. For example, when the same area is photographed by two or more imaging devices 20 and the orientations of these two or more imaging devices 20 relative to this area are different, an image that makes it easy to identify the posture and an image that makes it easy to identify the tool may differ. In such a case, it is preferable that the first processing unit 120 differentiates the imaging device 20 to which (2-1) is applied from the imaging device 20 to which (2-2) is applied.

[0043] The first processing unit 120 also processes the images to identify, for each of the multiple people, a time period during which that person is not working. Hereinafter, this time period will be referred to as a non-work time period. A non-work time period may occur due to waiting time caused by the absence of an item to be worked on, a break between tasks, or the like. For example, the first processing unit 120 determines that a person is not working if the person's movements deviate from those of a working person. Here, the first processing unit 120 may further add a determination criterion of whether the person's movements are infrequent. As an example, the first processing unit 120 determines that a person is not working if the person is talking to others but has few other movements. The first processing unit 120 includes the non-work time period in at least a portion of the work information.

[0044] [Integrating the type of work for each imaging device 20] The same person may appear at the same time on two or more imaging devices 20. In this case, the type of work that the person does is identified for each of the two or more imaging devices 20. The first processing unit 120 integrates these multiple identification results into a single type of work, for example, using at least one of the following methods (3-1) to (3-3).

[0045] In other words, the first processing unit 120 identifies the type of work performed by the same person at the same time from each of the images generated by at least two image capture devices 20, and if at least one of the identified work types is different from the others, generates work type information according to a predetermined rule. For example, this rule may relate to the reliability of the work type or to consistency with external information generated by a sensor used in the work area.

[0046] (3-1) When the types of work are different from each other, the first processing unit 120 adopts the type of work with the highest reliability.

[0047] (3-2) When the types of work are different from one another, the first processing unit 120 adds up the reliability for each type of work and adopts the type of work with the highest reliability after addition. At this time, the reliability may be weighted depending on, for example, the image capture device 20. This weighting is set depending on, for example, the position of the image capture device 20.

[0048] (3-3) As illustrated in FIG. 5 , a sensor 22 may be used within the work area, and predetermined information, i.e., external information, may be generated based on the detection results of the sensor 22. As illustrated in FIG. 6 , this external information is stored in the external information storage unit 60. Using this external information, it may be possible to identify the type of work performed in the work area, the start time of that work, and the end time of that work. If the type of work based on at least one imaging device 20 differs from the types of work based on other imaging devices 20, the first processing unit 120 selects a type of work that is consistent with the information stored in the external information storage unit 60. As an example, if the work area is a warehouse and the sensor 22 is a reading device that reads codes attached to items, the external information storage unit 60 may be, for example, a database used in a WMS (Warehouse Management System) for inventory management of items. For example, if the first processing unit 120 determines, using the information stored in the external information storage unit 60, that an inspection was being performed at a certain time, it selects a type of work corresponding to inspection from among multiple types of work.

[0049] [Generation of chronological information of task type] When the first processing unit 120 can identify task type information, the time when the person started the task, and the time when the person finished the task, the first processing unit 120 generates chronological information of task type as at least a part of the task information. This chronological information indicates the type of task performed by a certain person, the time when the person started the task, and the time when the person finished the task in chronological order.

[0050] For some people, it may be impossible to identify the type of work they were doing during a certain time period. This occurs, for example, when there is a time period when the person is not captured by any of the image capture devices 20. In this case, the first processing unit 120 estimates the type of work they were doing during that time period using at least one of the types of work they did before that time period, the types of work they did after that time period, the person's location during that time period, and a predetermined work flow.

[0051] For example, the first processing unit 120 may determine the type of work before that time period, such as the type of the immediately preceding work, as the type of work for that time period, or may determine the type of work after that time period, such as the type of the immediately succeeding work, as the type of work for that time period.Furthermore, if the type of work before that time period and the type of work immediately succeeding that time period are the same, the first processing unit 120 may determine the type of work for that time period.

[0052] In addition, each type of work may have a specific location where the work should be performed. In this case, the first processing unit 120 may identify the person's location during that time period and estimate the type of work that the person was performing during that time period based on the identified location.

[0053] In addition, the workflow, i.e., the order of tasks, may be predetermined. In this case, the first processing unit 120 may estimate the type of task for that time period using the type of task that occurred before that time period, the type of task that occurred after that time period, and the workflow. For example, the first processing unit 120 identifies the type of task that occurred before that time period. Then, the first processing unit 120 identifies the type of task that should be performed next according to the workflow. The first processing unit 120 estimates this type of task as the type of task for that time period. As another example, the first processing unit 120 identifies the type of task that will occur after that time period. Then, the first processing unit 120 performs the type of task that should be performed before that according to the workflow. The first processing unit 120 estimates this type of task as the type of task for that time period.

[0054] Next, a detailed example of the processing performed by the second processing unit 130 and a detailed example of the improvement information will be described. When the improvement information is generated in real time, i.e., while the work is being performed, the second processing unit 130 may generate the improvement information when it becomes highly likely that the estimated completion time of the work will be significantly delayed from the work plan. The timing for this determination is, for example, when half of the scheduled work time has passed.

[0055] As described above, the improvement information is information for improving a task, and may be, for example, at least one of task change information regarding changes in the task and the person in charge, task assignment information for informing each of multiple people of the task they will be responsible for before the task begins, information indicating improvements to the task procedure, and information indicating task items to be added. To generate the improvement information, the second processing unit 130 performs, for example, at least one of the following processes.

[0056] [First process for generating person-in-charge change information]

[0057] In this example, multiple people are performing multiple types of work. The second processing unit 130 generates responsibility change information, which is an example of work information, during the work and transmits the generated responsibility change information to, for example, the communication device 50 shown in FIG. 6 . The communication device 50 is operated by at least one of the person performing the work and the person managing the work. An example of the communication device 50 is a portable communication device such as a smartphone or tablet terminal. The person operating the communication device 50 can recognize the change in responsibility of the person by checking the responsibility change information using the communication device 50. Note that, when the communication device 50 receives the responsibility change information, it may notify the person operating the communication device 50 that the responsibility change information has been received by outputting a human-perceptible signal. Examples of the human-perceptible signal include at least one of sound output, vibration, light emission from a light-emitting element, and a change in the display state of a display.

[0058] The second processing unit 130 acquires a work plan. This work plan is stored, for example, in the internal information storage unit 40, and indicates the scheduled start time and scheduled end time for each of a plurality of work types.

[0059] The work information also includes information that can identify the type of work that has been completed. For example, if the work information includes the type of work, the start time of the work, and the end time of the work, the second processing unit 130 can identify the type of work that has been completed by a certain time by tallying up the types of work that have been indicated as having been completed by the work information.

[0060] The second processing unit 130 then uses the types of tasks completed up to that time to determine the degree of progress toward the work plan for each type of task at that time. The degree of progress may indicate, for example, the ratio of the amount of work of that type completed up to that time to the amount of work of that type scheduled to be completed by that time in the work plan. The degree of progress may also indicate the ratio of the amount of work of that type completed up to that time to the amount of work of that type to be performed on that day. When packing items in a warehouse, the amount of work can be determined by the number of boxes packed. As another example, when picking a predetermined number of items in a warehouse, the number of items picked may be calculated by multiplying the number of picks by a reference value (e.g., average) for the number of items picked per pick, or by multiplying the length of time the picking was performed by a reference value (e.g., average) for the number of items picked per unit time.

[0061] The second processing unit 130 then generates responsibility change information using the calculated progress. For example, if the first task is progressing faster than planned and the second task is behind schedule, the second processing unit 130 generates responsibility change information so that at least some of the people performing the first task will perform the second task.

[0062] The second processing unit 130 may use the calculated progress to calculate a predicted completion time for each of the multiple types of tasks, and generate responsibility change information using these predicted completion times. For example, if the scheduled completion time of a first task is earlier than the scheduled completion time of a second task by a reference time or more, the second processing unit 130 generates responsibility change information so that at least some of the people performing the first task will perform the second task.

[0063] When there are multiple people performing a first task and only some of the people perform a second task, the second processing unit 130 may use skill information to identify the person who should perform the second task. The skill information indicates the skill level of each person for each of multiple people and is stored in advance in the internal information storage unit 40. The skill level indicates the person's proficiency with each of multiple types of tasks. The higher the proficiency level, the faster the person can perform that task. Therefore, the second processing unit 130 selects the person to perform the second task, for example, in descending order of proficiency in the second task.

[0064] In this case, the second processing unit 130 may identify the communication device 50 operated by the person who is to perform the second task, i.e., the person whose responsibility will be changed if the responsibility change information is followed, and transmit the responsibility change information or information indicating the changes in the person's responsibility if the responsibility change information is followed to the communication device 50. For example, the internal information storage unit 40 stores information identifying the communication device 50 operated by each of multiple people, such as information equivalent to an SNS account or email address. The second processing unit 130 uses this information to identify the communication device 50 to which information should be sent.

[0065] The skill information may be generated by the first processing unit 120. For example, the first processing unit 120 may calculate the actual amount of work per unit time for each person and each type of work, and generate the skill information using this amount of work.

[0066] [Second Process for Generating Responsibility Change Information] The second processing unit 130 calculates the length of time that each person is not performing work using the non-working time periods included in the work information. Hereinafter, this length will be referred to as the first time. The second processing unit 130 uses the first time calculated for each person to identify the person whose work responsibility will be changed. In this case, the second processing unit 130 uses, for example, at least one of the following (4-1) to (4-2). (4-1) and (4-2) are executed, for example, in real time.

[0067] (4-1) The second processing unit 130 generates responsibility change information so that a person whose first time exceeds a first reference value is assigned to another task. The second processing unit 130 may set the task to be assigned to a person whose first time is less than a second reference value after the change. The second reference value is smaller than the first reference value.

[0068] (4-2) When multiple types of work are being performed in parallel in a work area and multiple people are responsible for each type of work, the second processing unit 130 adds up the first times of the multiple people responsible for that work, for each type of work. The second processing unit 130 then generates responsibility change information so that at least some of the people responsible for a work whose first time after the addition exceeds a third reference value are assigned to another work. The second processing unit 130 may determine that a work whose first time after the addition is less than a fourth reference value is the changed work. The fourth reference value is smaller than the third reference value. Note that the area in which each type of work is performed may be determined. In this case, "type of work" may be replaced with "area" in this process.

[0069] [Process for generating responsible information]

[0070] As described above, responsibility information is information used to inform each of multiple people of the tasks they are responsible for before starting work. An example of responsibility information is a shift schedule. When responsibility information is generated, multiple people share multiple types of work. The second processing unit 130 generates responsibility information, which is an example of work information, when the person performing the work is replaced, i.e., when the shift changes, and transmits the generated responsibility information to, for example, the communication device 50 shown in FIG. 6. The person operating the communication device 50 can confirm the tasks that the person is responsible for by checking the responsibility information using the communication device 50. When generating responsibility information, the second processing unit 130 uses, for example, at least one of the following methods (5-1) to (5-4).

[0071] (5-1) When the person performing the work is changed, the second processing unit 130 determines the degree of progress with respect to the work plan for each of the multiple types of work. Specific examples of the degree of progress are the same as when generating the responsibility change information. The second processing unit 130 then generates responsibility information using the calculated degree of progress. For example, when a first work is progressing ahead of schedule and a second work is behind schedule, the second processing unit 130 generates responsibility information so that at least some of the people scheduled to perform the first work will perform the second work. Here, the second processing unit 130 may use skill information to identify the person who should perform the second work, as in the case of generating the responsibility change information.

[0072] (5-2) The second processing unit 130 processes images captured on or before the previous day to calculate cumulative values ​​of the first time for each type of work during a predetermined period of time up to the previous day. The second processing unit 130 then uses these cumulative values ​​of the first time to identify the number of people to be in charge of each type of work, or the people to be in charge. For example, the second processing unit 130 reduces the number of people in charge of work with a large cumulative value of the first time compared to the previous day, and instead increases the number of people in charge of work with a small cumulative value of the first time. The second processing unit 130 further identifies the people to be in charge of each type of work based on the revised number of people. Here, the second processing unit 130 may calculate the difference in the amount of work for each type of work between the previous day and the current day, and further use this difference to identify the number of people to be in charge of each type of work, or the people to be in charge.

[0073] When generating the responsibility information, the second processing unit 130 may generate improvement information using the skill information stored in the internal information storage unit 40. As described above, the skill information indicates the skill levels of multiple people. In this case, the second processing unit 130 uses, for example, at least one of the following (5-3) to (5-4).

[0074] (5-3) The second processing unit 130 calculates the time required to complete a task for each of multiple people. In this process, the second processing unit 130 uses skill information. For example, the second processing unit 130 shortens the time required by people with high skill levels compared to the time required by people with low skill levels. Then, the second processing unit 130 uses the time calculated using the skill information to identify the number of people to be in charge of each type of task, or the people to be in charge.

[0075] (5-4) In the skill information, skill levels may be set for each person and each type of work. In this case, when deciding who will be in charge of a certain type of work, the second processing unit 130 gives priority to assigning people with a high skill level for that type of work.

[0076] [Other Examples of Improvement Information] The second processing unit 130 may further include the following information (6-1) to (6-2) as at least part of the improvement information. Here, (6-1) is preferably executed in real time. On the other hand, (6-2) to (6-5) are preferably executed when creating a work plan including personnel allocation.

[0077] (6-1) If there is a person whose first time exceeds a first reference value, the second processing unit 130 includes information indicating this as at least part of the improvement information. Note that the reference value used here may be different from the first reference value. In this regard, in the output process described below, the second processing unit 130 transmits this information to at least one of the communication device 50 of the person managing the work and the communication device 50 operated by the person whose first time exceeded the first reference value. Note that in the former case, the second processing unit 130 preferably transmits to the communication device 50 information that can identify the person whose first time exceeded the first reference value. Furthermore, in the latter case, the second processing unit 130 may transmit to the communication device 50 information indicating that support for the other person should be provided.

[0078] (6-2) If the first time exceeds the first reference value for any person, the second processing unit 130 performs processing to estimate the cause and uses information indicating the estimated result as at least part of the improvement information. The reference value used here may be a value different from the first reference value. The second processing unit 130 may further generate information indicating a work process improvement proposal to eliminate the cause, and use this information as at least part of the improvement information. Note that if the cause is due to personnel allocation, the second processing unit 130 may generate information indicating a personnel allocation improvement proposal, and use this information as at least part of the improvement information.

[0079] If no inferred cause is found in (6-2), it is highly likely that the problem lies with the person in charge, and therefore information recommending that some kind of action be taken against that person may be output to the communication device 50 of the person in charge of the work. This information may also be considered as improvement information.

[0080] (6-3) At least two people may form a group and work on this group basis. In this case, the compatibility between the people in the group may affect the efficiency of the work. The internal information storage unit 40 stores information indicating this compatibility. An example of this information is information indicating combinations of people who have good compatibility. The second processing unit 130 then uses this information when forming groups in the work plan.

[0081] (6-4) The work procedures of people with high processing capabilities often include content that others should emulate. The second processing unit 130 includes information about this work performed by that person, i.e., a specific person, as at least part of the improvement information. This information can also be considered know-how information. For example, the second processing unit 130 may include a video showing the person's movements as at least part of the improvement information. Furthermore, when a single work type includes multiple sub-tasks, the second processing unit 130 may include information indicating the order in which the sub-tasks are performed by that person as at least part of the improvement information. For example, this method is applicable when a single work type in a warehouse involves picking items and storing them in a container, and the picking, transporting them to the storage location, and storing them in the container are each sub-tasks. Furthermore, the second processing unit 130 may identify the person's movement path and include this movement path as at least part of the improvement information.

[0082] The second processing unit 130 may use the content of the instruction that a person with a high skill level gives to another person as at least a part of the improvement information. This content is generated by the first processing unit 120, for example.

[0083] (6-5) Depending on the type of work, work procedures may be predefined. The first processing unit 120 can detect actions that deviate from the work procedures through image processing. As an example, the internal information storage unit 40 pre-stores information indicating actions that would be performed if the work procedures were followed. The first processing unit 120 then uses this information to detect actions that deviate from the work procedures. When the same action that deviates from the work procedures is repeatedly detected in a person with a high skill level, this action may be an action that should be included in the work procedures. Examples of such actions include organizing and cleaning. The second processing unit 130 may include information about this action in the improvement information. As an example, the second processing unit 130 may include an image, such as a video, that includes this action in the improvement information.

[0084] As described above, the second processing unit 130 of the work analysis apparatus 10 outputs the improvement information to, for example, the communication device 50. The communication device 50 displays this improvement information on, for example, a display. For example, when the communication device 50 transmits improvement information to a communication device 50 operated by a work manager, the work analysis apparatus 10 may cause the communication device 50 to display one of the screens shown in Figures 7 to 9. Each of these screens includes work information, an image generated by at least one imaging device 20, and information in which predetermined information is superimposed on a map of the work area.

[0085] The screen shown in Fig. 7 is displayed while work is being performed in the work area. The second processing unit 130 causes the communication device 50 to display an area 502 that displays images generated by each of the multiple image capture devices 20, an area 504 that displays an image selected from area 502 in a high-resolution enlarged state, an area 506 that displays a map of the work area, and an area 508 that displays work information. In this example, real-time images are displayed in areas 502 and 504. Note that the image displayed in area 502 is generated, for example, by downsampling or reducing the resolution of the image displayed in area 504.

[0086] The second processing unit 130 displays the recognition results of the person and the object being detected superimposed on the image displayed in the area 504. As an example, the second processing unit 130 surrounds the area recognized as a person with a rectangular frame, and surrounds the area recognized as an object with a rectangular frame. These two types of frames are displayed in a manner that allows them to be distinguished from each other. An example of a manner in which they can be distinguished from each other is by using different line colors, thicknesses, and / or solid, dotted, or dashed lines.

[0087] Area 506 displays an image in which predetermined information is superimposed on a map of the work area. One example of the predetermined information is the movement lines of people working. When multiple people are working, movement lines are generated for each person and are displayed in a manner that allows them to be distinguished from one another. Examples of ways to allow them to be distinguished from one another include by using different line colors, thicknesses, and / or solid, dotted, or dashed lines.

[0088] The task information displayed in area 508 includes, for example, information indicating task time for each type of task for each of multiple people. In the example shown in the figure, second processing unit 130 groups people captured by each image capture device 20, and displays information indicating task time for each person and task type for each group in area 508.

[0089] 8 is displayed after a task has been performed. The second processing unit 130 causes the communication device 50 to display areas 502, 504, and 506, as well as area 512 for displaying task information. The task information displayed here is, for example, the result of statistical processing of task time. An example of statistical processing is task time for each task type for each time period.

[0090] 9 is also displayed, for example, after work has been performed. In addition to area 506 displaying a map of the work area, second processing unit 130 causes communication device 50 to display area 522 displaying images of areas where work is progressing faster than planned, area 524 displaying images of areas where work is lagging behind plan, and area 526 displaying work information. The work information displayed here includes, for example, analysis results of work in the work area displayed in area 522 and analysis results of work in the work area displayed in area 524. This may enable a viewer of this screen to understand the cause of the delay in area 524.

[0091] As described above, according to this embodiment, the second processing unit 130 outputs improvement information. Therefore, the person performing the work can improve the work by recognizing this improvement information. Furthermore, the person managing the work can improve the work plan or provide guidance to the person performing the work to improve the work by recognizing this improvement information.

[0092] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0093] In addition, although the flowcharts used in the above description show a number of steps (processes) in a sequential order, the order of the steps executed in each embodiment is not limited to the order shown in the flowcharts. In each embodiment, the order of the steps shown in the diagrams can be changed as long as it does not cause any problems in terms of the content.

[0094] Some or all of the above embodiments can be described as, but are not limited to, the following supplementary notes: 1. A task analysis device comprising: an acquisition means for acquiring a plurality of images generated by a plurality of image capture devices capturing an area where a plurality of people are performing tasks; a first processing means for generating task information related to the tasks performed by each of the plurality of people by processing the plurality of images; and a second processing means for generating and outputting improvement information for improving the tasks using the task information. 2. The task analysis device described in above 1, wherein the task information includes, for each of the plurality of people, task type information indicating the type of task being performed by that person, and the time that that person started the task. 3. The task analysis device described in above 2, wherein the first processing means generates the task type information using at least one of the person's posture and the tool being used by that person. 4. 5. The task analysis device described in any one of 2 or 3 above, wherein the first processing means identifies the type of task performed by the same person at the same time from each of the images generated by at least two of the image capture devices, and generates the task type information in accordance with a predetermined rule if at least one of the identified task types is different from the others. 5. The task analysis device described in 4 above, wherein the first processing means calculates the reliability of the task type when identifying the task type using the images, and the rule relates to the reliability. 6. The task analysis device described in 4 above, wherein the rule relates to consistency with external information generated using sensors used in the task area. 7. The task analysis device described in any one of 1 to 6 above, wherein the first processing means, when there is a time period during which the task type cannot be identified for at least one person, estimates the task type for that time period using at least one of the task type before that time period, the task type after that time period, the person's position during that time period, and a predetermined workflow. 8. 8. The work analysis apparatus according to any one of claims 1 to 7, wherein the improvement information includes responsibility change information relating to a change in the person's responsibilities.9. The work analysis device described in any one of above 8 to 10, wherein the second processing means transmits, to a communication device operated by the person whose responsibility will be changed when the responsibility change information is followed, information indicating a change in the responsibility of that person. 12. The work analysis device described in any one of above 8 to 10, wherein the second processing means transmits, for each of the plurality of people, a first time period indicating the length of time that that person has not performed the work, and uses the first time period to identify the person whose responsibility should be changed. 13. The work analysis device described in any one of above 8 to 10, wherein the second processing means transmits, to a communication device operated by the person whose responsibility will be changed when the responsibility change information is followed, information indicating a change in the responsibility of that person. 13. The work analysis device described in any one of claims 1 to 12 above, wherein a work procedure is defined for the work, and when the second processing means detects an action not specified in the work procedure, it includes information about the action in the improvement information. 14. The work analysis device described in any one of claims 1 to 13, wherein the improvement information includes information about the work performed by a specific person. 15. The work analysis device described in any one of claims 1 to 14, wherein the second processing means displays the work information, the image generated by at least one of the imaging devices, and a map of the work area on a display device. 16. A work analysis method in which a computer acquires a plurality of images generated by a plurality of image capturing devices photographing a work area where a plurality of people are working, processes the plurality of images to generate work information related to the work performed by each of the plurality of people, and uses the work information to generate and output improvement information for improving the work.17. A recording medium having recorded thereon a program for causing a computer to have: an acquisition means for acquiring a plurality of images generated by a plurality of image capture devices photographing a work area where a plurality of people are working, a first processing means for generating work information related to the work performed by each of the plurality of people by processing the plurality of images, and a second processing means for using the work information to generate and output improvement information for improving the work. 18. The program described in 17 above.

[0095] Furthermore, some or all of the configurations described in Supplementary Notes 2 to 15, which are dependent on Supplementary Note 1, may also be dependent on Supplementary Notes 16, 17, and 18 in the same dependent relationship as Supplementary Notes 2 to 15. Furthermore, not limited to Supplementary Notes 1, 16, 17, and 18, some or all of the configurations described as Supplements may be made dependent on various hardware, software, various recording means for recording software, or systems, within the scope of each of the above-mentioned embodiments.

[0096] REFERENCE SIGNS LIST 10 Work analysis device 20 Imaging device 22 Sensor 30 Shielding object 40 Internal information storage unit 50 Communication device 60 External information storage unit 110 Acquisition unit 120 First processing unit 130 Second processing unit

Claims

1. A work analysis device comprising: an acquisition means for acquiring a plurality of images generated by a plurality of image capture devices of a work area where a plurality of people are working; a first processing means for generating work information relating to the work performed by each of the plurality of people by processing the plurality of images; and a second processing means for generating and outputting improvement information for improving the work using the work information.

2. A work analysis device according to claim 1, wherein the work information includes, for each of the plurality of people, work type information indicating the type of work being performed by that person, and the time at which that person started that work.

3. A task analysis device according to claim 2, wherein the first processing means generates the task type information using at least one of the posture of the person and a tool used by the person.

4. A work analysis device according to claim 2 or 3, wherein the first processing means identifies the type of work performed by the same person at the same time from each of the images generated by at least two of the photographing devices, and, if at least one of the identified multiple work types is different from the others, generates the work type information in accordance with a predetermined rule.

5. A work analysis device according to claim 4, wherein the first processing means, when identifying the type of work using the image, calculates the reliability of the type of work, and the rule relates to the reliability.

6. A work analysis device according to claim 4, wherein the rules relate to consistency with external information generated using sensors used in the work area.

7. A work analysis device according to any one of claims 1 to 6, wherein, when there is a time period during which the type of work cannot be identified for at least one person, the first processing means estimates the type of work during that time period using at least one of the type of work before that time period, the type of work after that time period, the person's location during that time period, and a predetermined work flow.

8. A work analysis device according to any one of claims 1 to 7, wherein the improvement information includes responsibility change information relating to a change in the person's responsibilities.

9. A work analysis device as described in claim 8, wherein there are multiple types of work, the work information includes information that can identify the type of work that has been completed, and the second processing means uses the work information to identify the degree of progress against a pre-set work plan for each of the multiple types of work, and generates the responsibility change information using the degree of progress.

10. A work analysis device according to claim 8 or 9, wherein the second processing means transmits information indicating the changes in the person's responsibilities when the responsibility change information is followed to a communication device operated by the person whose responsibilities will be changed when the responsibility change information is followed.

11. A work analysis device according to any one of claims 8 to 10, wherein the second processing means identifies, for each of the plurality of people, a first time period indicating the length of time that the person has not performed the work, and identifies the person whose responsibilities should be changed using the first time period.

12. A work analysis device according to any one of claims 8 to 11, wherein the second processing means uses skill information indicating the skill level of each of the plurality of people to identify the person whose responsibilities should be changed.

13. A work analysis device according to any one of claims 1 to 12, wherein a work procedure is defined for the work, and when the second processing means detects an action not specified in the work procedure, the second processing means includes information about the action in the improvement information.

14. A work analysis device according to any one of claims 1 to 13, wherein the improvement information includes information about the work performed by a specific person.

15. A work analysis device according to any one of claims 1 to 14, wherein the second processing means causes a display device to display the work information, the image generated by at least one of the imaging devices, and a map of the work area.

16. A work analysis method in which a computer acquires a plurality of images generated by each of a plurality of image capturing devices of a work area where a plurality of people are working, processes the plurality of images to generate work information regarding the work performed by each of the plurality of people, and uses the work information to generate and output improvement information for improving the work.

17. A recording medium having recorded thereon a program that causes a computer to have: an acquisition means for acquiring a plurality of images generated by each of a plurality of photographing devices photographing a work area where a plurality of people are working; a first processing means for generating work information relating to the work performed by each of the plurality of people by processing the plurality of images; and a second processing means for generating and outputting improvement information for improving the work using the work information.

Images