Task content identifying system, task content identifying method, and program

Abstract

To efficiently identify task contents of a worker.SOLUTION: A task content identifying system for identifying task contents performed by a worker in a series of tasks consisting of a plurality of consecutive element tasks includes: information acquisition means that acquires sensor information indicating a state of the worker when the worker performs an element task; storage means that stores a determination model of each element task for identifying each element task; task identifying means that identifies an element task performed by the worker by comparing the sensor information of the worker acquired by the information acquisition means with a determination model of each element task stored by the storage means; and priority setting means that sets a priority of the determination model of each element task when the task identifying means performs a comparison.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to a work content identification system, a work content identification method, and a program for identifying work content. [Background technology]

[0002] 2. Description of the Related Art A system is known that identifies the work content of a worker based on sensor information of the worker or the like (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2019-41811 A Summary of the Invention [Problem to be solved by the invention]

[0004] For example, the sensor information of the worker is compared with the judgment model for each task to identify the task that the worker is performing. If the sensor information of the worker is compared with the judgment model for each task in a random order, calculations will be wasted and the efficiency will be poor.

[0005] The present disclosure has been made to solve such problems, and has as its main objective to provide a work content identification system, a work content identification method, and a program that can efficiently identify the work content of a worker. [Means for solving the problem]

[0006] In order to achieve the above object, one aspect of the present disclosure is to A work content identification system for identifying work content being performed by a worker in a series of work operations consisting of a plurality of consecutive elemental work operations, comprising: an information acquiring means for acquiring sensor information indicating a state of the worker when the worker performs the elemental work; a storage means for storing a judgment model for each of the elemental operations for identifying each of the elemental operations; a task identification means for identifying an element task being performed by a worker by comparing the sensor information of the worker acquired by the information acquisition means with a judgment model of each element task stored in the storage means; a priority setting means for setting a priority of a judgment model for each of the elemental operations when the operation specifying means performs the comparison; A work content specification system comprising: It is. In this one aspect, the work identification means may compare the judgment models of the element work with the sensor information of the worker acquired by the information acquisition means, in order of priority set by the priority setting means, and, when the judgment model of the element work matches with the sensor information of the worker, identify the element work of the matching judgment model as the work content being performed by the worker. In this one aspect, a probability value of each of the element tasks to be performed next to each of the element tasks in the series of tasks may be set in advance, and the priority setting means may set the priority of the judgment model of the element task having a high probability value to be high. In order to achieve the above object, one aspect of the present disclosure is to A method for identifying work content being performed by a worker in a series of work operations consisting of a plurality of consecutive elemental work operations, comprising the steps of: acquiring sensor information indicating a state of a worker when the worker performs the elemental work; storing a judgment model for each of the elemental operations for identifying each of the elemental operations; A step of identifying an elemental work being performed by the worker by comparing the acquired sensor information of the worker with each of the stored judgment models of each elemental work; setting a priority of a judgment model for each of the element operations when performing the comparison; A method for identifying the work content, including It is. In order to achieve the above object, one aspect of the present disclosure is to A program for identifying the work content being performed by a worker in a series of work operations consisting of a plurality of consecutive elemental work operations, A process of acquiring sensor information indicating a state of the worker when the worker performs the elemental work; a process of identifying an elemental work being performed by the worker by comparing the acquired sensor information of the worker with a judgment model for identifying each elemental work; A process of setting a priority of a judgment model for each of the element operations when performing the comparison; A program that causes a computer to execute It is. Effect of the Invention

[0007] According to the present disclosure, a main object is to provide a work content identification system, a work content identification method, and a program that can efficiently identify the work content of a worker. [Brief description of the drawings]

[0008] [Figure 1] 1 is a block diagram showing a schematic system configuration of a work content specifying system according to an embodiment of the present invention; [Diagram 2] 4 is a flowchart showing a flow of a task content identification method according to the present embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, the present embodiment will be described with reference to the drawings. FIG. 1 is a block diagram showing a schematic system configuration of a task content identification system according to the present embodiment. The task content identification system 1 according to the present embodiment is a device for identifying task content performed by a worker in a series of tasks consisting of a plurality of consecutive elemental tasks. The elemental tasks include, for example, a removal task for removing parts, a tightening task for tightening bolts, nuts, etc., a fitting task for fitting parts, etc., and a fitting task for fitting parts, etc. The worker is, for example, a worker who performs work on a production line.

[0010] For example, if a series of n cycles of work in the past is observed and the series of work in the n cycles is the same work, the series of work is set as standard work. Then, the work content identification system 1 may identify the work content performed by the worker in the standard work.

[0011] The task content specifying system 1 according to this embodiment includes an information acquiring unit 2, a storage unit 3, a task specifying unit 4, and a priority setting unit 5.

[0012] The work content identification system 1 has a hardware configuration of a typical computer, including, for example, a processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), internal memory such as a RAM (Random Access Memory) or a ROM (Read Only Memory), storage devices such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive), an input / output I / F for connecting peripheral devices such as a display, and a communication I / F for communicating with devices outside the device.

[0013] The information acquisition unit 2 is a specific example of information acquisition means. The information acquisition unit 2 acquires sensor information indicating the state of a worker when the worker performs an element work. For example, the information acquisition unit 2 acquires..., sensor information for element work a at time t-1, sensor information for element work b at time t, sensor information for element work c at time t+1,...

[0014] The information acquiring unit 2 acquires sensor information from, for example, a sensor 6 attached directly to a worker or indirectly via a wearable device or the like, or a sensor 6 attached to the work environment. The information acquiring unit 2 acquires the sensor information via a wired connection such as wiring, or via a wireless connection such as Bluetooth (registered trademark) or Wifi (registered trademark).

[0015] The sensor 6 includes, for example, a camera, a microphone, an acceleration sensor, a biosensor, a temperature sensor, a pressure sensor, etc. The sensor information includes, for example, a still image or a moving image of the worker, the voice of the worker, environmental sounds, and the like.

[0016] The storage unit 3 is a specific example of a storage means. The storage unit 3 stores a judgment model for each element work to identify each element work. The judgment model is information that models actual sensor information when a worker performs an element work. The storage unit 3 is composed of the above-mentioned storage device, etc.

[0017] The task identification unit 4 is a specific example of a task identification means. The task identification unit 4 compares the sensor information of the worker acquired by the information acquisition unit 2 with the judgment models of each task stored in the storage unit 3, thereby identifying the task element being performed by the worker.

[0018] For example, suppose that a worker performs a certain element work at time t-1, and then the worker performs the next element work at time t. The work identification unit 4 identifies the element work at time t. For example, the work identification unit 4 identifies the element work being performed by the worker using pattern matching processing or the like based on the image information of the worker acquired by the information acquisition unit 2 and the image information of the judgment model of each element work stored in the storage unit 3.

[0019] More specifically, the task identification unit 4 calculates the similarity between the image information of the worker acquired by the information acquisition unit 2 and the image information of the judgment model of each element task. The task identification unit 4 identifies the element task corresponding to the image information of the judgment model for which the calculated similarity is equal to or greater than a predetermined value as the task content being performed by the worker.

[0020] Now, for example, suppose that a certain operation is a fitting operation, and the sensor information of the certain operation is compared with the judgment model for the removal operation, the judgment model for the tightening operation, the judgment model for the fitting operation, and the judgment model for the fitting operation, in that order. In this case, it is only at the fourth comparison that it is determined that the certain operation is a fitting operation, and the previous three comparisons are wasteful calculations. Thus, if the sensor information of the worker is compared with the judgment models for each operation in a random order, wasteful calculations occur and efficiency is poor.

[0021] In contrast, in this embodiment, the priority setting unit 5 sets the priority of the judgment model of each element work when the work identification unit 4 performs the above comparison. Thereby, for example, by setting the priority of the judgment model of each element work so as to reduce the above-mentioned wasteful calculations, it is possible to reduce the above-mentioned wasteful calculations and efficiently identify the work content of the worker.

[0022] The priority setting unit 5 is a specific example of a priority setting means. The task identification unit 4 compares the judgment models of element tasks with the highest priority set by the priority setting unit 5 in descending order with the sensor information of the worker acquired by the information acquisition unit 2. Then, when the judgment model of the compared element task matches the sensor information of the worker, the task identification unit 4 identifies the element task of the matching judgment model as the task content being performed by the worker.

[0023] For example, in a series of operations, the probability value of each element operation performed next to each element operation may be preset as probability table information. Specifically, the operation performed next to the removal operation is set to have a 50% probability of being a fastening operation, a 25% probability of being a fitting operation, a 25% probability of being a fitting operation, and so on. In this manner, the probability of the element operation to be performed next is set for each element operation. The probability of each element operation may be set based on accumulated operation data. In addition, the probability of each element operation can be set with higher accuracy by including, for example, information on the operation process and the tools used in the operation in the operation data.

[0024] Based on the probability table, the priority setting unit 5 sets a high priority for the judgment model of an element work with a high probability value. This allows the work identification unit 4 to compare the sensor information of the worker acquired by the information acquisition unit 2 with the judgment models of the element work with a high priority set by the priority setting unit 5 and with a high probability of being performed next. This prevents the above-mentioned unnecessary comparisons and allows the work content of the worker to be identified efficiently, quickly, and accurately.

[0025] Note that the task identification unit 4 may, for example, compare the sensor information of the worker acquired by the information acquisition unit 2 with a randomly selected judgment model only for the first judgment, and identify the task content of the worker. After that, when several cycles of tasks are performed and task information is accumulated, as described above, the task identification unit 4 compares the sensor information of the worker acquired by the information acquisition unit 2 with the judgment models of the element tasks with the highest priorities set by the priority setting unit 5 in order, and identifies the task content of the worker.

[0026] Next, the task content identification method according to this embodiment will be described in detail with reference to Fig. 2. Fig. 2 is a flowchart showing the flow of the task content identification method according to this embodiment.

[0027] The information acquisition unit 2 acquires sensor information when a worker performs each elemental work (step S101).

[0028] The storage unit 3 stores the judgment model for each element work (step S102). The priority setting unit 5 sets the priority of the judgment model for each element work based on the probability table (step S103). Note that the above steps S102 and S103 may be performed before step S101.

[0029] The task identifying unit 4 compares the sensor information of the worker acquired by the information acquiring unit 2 with the judgment models for the element tasks, starting from the one with the highest priority set by the priority setting unit 5 (step S104).

[0030] When the determination model of the elemental work matches the sensor information of the worker (YES in step S105), the work identification unit 4 identifies the elemental work of the matching determination model as the work content being performed by the worker (step S106).On the other hand, when the determination model of the elemental work does not match the sensor information of the worker (NO in step S105), the work identification unit 4 performs the above process (step S104).

[0031] As described above, the task content identification system 1 according to this embodiment includes an information acquisition unit 2 that acquires sensor information when a worker performs each elemental task, a storage unit 3 that stores a judgment model for each elemental task, a task identification unit 4 that identifies an elemental task being performed by a worker by comparing the sensor information of the worker acquired by the information acquisition unit 2 with the judgment model for each elemental task stored in the storage unit 3, and a priority setting unit 5 that sets the priority of the judgment model for each elemental task when the task identification unit 4 makes the comparison. This makes it possible to efficiently identify the task content of a worker.

[0032] Although some embodiments of the present disclosure have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope and spirit of the invention, and are included in the scope of the invention and its equivalents described in the claims.

[0033] The present disclosure can also be implemented by causing a processor to execute a computer program to perform the processes shown in FIG.

[0034] The program can be stored and provided to a computer using various types of non-transitory computer readable media. The non-transitory computer readable media includes various types of tangible storage media. Examples of the non-transitory computer readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / Ws, and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (random access memories)).

[0035] The program may be provided to the computer by various types of transitory computer readable media. Examples of the transitory computer readable medium include an electric signal, an optical signal, and an electromagnetic wave. The transitory computer readable medium can provide the program to the computer via a wired communication path such as an electric wire and an optical fiber, or via a wireless communication path.

[0036] Each component of the work content identification system 1 according to each of the above-described embodiments can be realized not only by a program, but also in whole or in part by dedicated hardware such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field-Programmable Gate Array). [Explanation of symbols]

[0037] 1 Work content identification system, 2 Information acquisition unit, 3 Memory unit, 4 Work identification unit, 5 Priority setting unit, 6 Sensor

Claims

1. A work content identification system for identifying work content being performed by a worker in a series of work operations consisting of a plurality of consecutive elemental work operations, comprising: an information acquiring means for acquiring sensor information indicating a state of the worker when the worker performs the elemental work; a storage means for storing a judgment model for each of the elemental operations for identifying each of the elemental operations; a task identification means for identifying an element task being performed by a worker by comparing the sensor information of the worker acquired by the information acquisition means with a judgment model of each element task stored in the storage means; a priority setting means for setting a priority of a judgment model for each of the elemental operations when the operation specifying means performs the comparison; A work content specification system comprising:

2. 2. The work content specification system according to claim 1, The work identification means compares the sensor information of the worker acquired by the information acquisition means with the judgment models of the element work with the highest priority set by the priority setting means, and when the judgment model of the element work matches the sensor information of the worker, identifies the element work of the matching judgment model as the work content being performed by the worker.

3. 3. The work content specification system according to claim 2, a probability value of each of the elemental tasks to be performed next to each of the elemental tasks in the series of tasks is set in advance, the priority setting means sets the priority of a judgment model of the element work having a high probability value to a high priority. Work content identification system.

4. A method for identifying work content being performed by a worker in a series of work operations consisting of a plurality of consecutive elemental work operations, comprising the steps of: acquiring sensor information indicating a state of a worker when the worker performs the elemental work; storing a judgment model for each of the elemental operations for identifying each of the elemental operations; A step of identifying an elemental work being performed by the worker by comparing the acquired sensor information of the worker with each of the stored judgment models of each elemental work; setting a priority of a judgment model for each of the element operations when performing the comparison; A method for identifying work content, including:

5. A program for identifying a task performed by a worker in a series of tasks consisting of a plurality of consecutive element tasks, comprising: A process of acquiring sensor information indicating a state of the worker when the worker performs the elemental work; a process of identifying an elemental work being performed by the worker by comparing the acquired sensor information of the worker with a judgment model for identifying each elemental work; A process of setting a priority of a judgment model for each of the element operations when performing the comparison; A program that causes a computer to execute the following.

Images