JP7614997B2 - Skill learning support device and skill learning support method - Google Patents

Description

The present invention relates to a skill mastery support device and a skill mastery support method that support the mastery of a skill.

In Japan, the productive population is decreasing due to the low birthrate and aging population. In the manufacturing industry, while ensuring productivity through automation, the utilization of labor, including elderly and foreign workers, is increasing to secure a labor force. There are many manual tasks in manufacturing that require skilled techniques, and at these sites, it is becoming an important issue to pass on the skills of aging workers to the next generation.

When it comes to training skilled workers, there are issues such as the inability to teach effectively because the skilled workers themselves do not understand the tricks of their own skills or the actions required to maintain high quality, and the difficulty of conveying the skills in a way that is understandable to those acquiring the skills due to communication gaps between generations. One solution that has been proposed to solve these issues is to digitize and visualize human work using sensors and video, etc., to provide training.

For example, the following Patent Document 1 discloses an information processing device capable of promoting the training of workers. This information processing device includes a first acquisition means, a second acquisition means, a determination means, and a presentation means. The first acquisition means acquires first motion data indicating the motion of a first worker. The second acquisition means acquires second motion data indicating the motion of a second worker. The determination means compares the first motion data and the second motion data to determine similarity. The presentation means presents instruction data indicating areas for improvement regarding the motion when performing a specified task to the first worker according to the result of the determination by the determination means.

Furthermore, the following Patent Document 2 discloses a cell culture education system that applies virtual reality technology to acquire and master techniques related to stem cell culture. This cell culture education system includes a measurement device that measures the position, posture, and movement of the subject, and a control device, and the control device has the functions of calculating and creating the position, posture, and movement of the subject from information from the measurement device and displaying it in virtual reality, correcting data (position, posture, movement, etc.) based on the protocol of the cell culture technology in accordance with the subject (height, etc.), calculating the position, posture, and movement when the subject follows the protocol, and creating data (position, posture, movement, etc.), and comparing the subject's position, posture, and movement with the data according to the protocol.

JP 2019-20913 A JP 2020-166264 A

In general, when learning a task, it is often the case that one must master not just one type of technique, but several different skills before one can complete the task. In addition, when it comes to multiple types of skills, it is often effective to divide the skills according to their learning stages and order the items to be learned.

Even if the above-mentioned conventional technology can adequately visualize each of the skills to be transferred, it does not address cases where the mastery period varies depending on the order in which the multiple skills to be transferred are acquired.

The present invention aims to provide appropriate information regarding the training sequence of multiple skills.

A skill learning support device 100 which is one aspect of the invention disclosed in the present application is a skill learning support device 100 having a processor which executes a program and a storage device which stores the program, and the processor is characterized in that it executes an acquisition process which acquires data regarding the movements of a worker during work, a calculation process which calculates a score for each of a plurality of skills required for the work based on the data acquired by the acquisition process, a generation process which generates a skill training sequence which indicates the training sequence of the plurality of skills based on the calculation results of the plurality of skills calculated by the calculation process for each of the work, and an output process which outputs the skill training sequence generated by the generation process .

According to a representative embodiment of the present invention, it is possible to provide appropriate information regarding the training sequence of multiple skills. Problems, configurations, and effects other than those described above will become clear from the explanation of the following examples.

FIG. 1 is an explanatory diagram showing an example of providing a skill training sequence. FIG. 2 is a block diagram showing an example of a hardware configuration of the skill learning assistance device. FIG. 3 is a block diagram showing an example of a functional configuration of the skill learning assistance device. FIG. 4 is a flowchart showing an example of a procedure for a work sequence generation process performed by the skill learning assistance device. FIG. 5 is an explanatory diagram illustrating an example of the contents stored in the DB. FIG. 6 is an explanatory diagram showing a first example of skill training sequence generation. FIG. 7 is an explanatory diagram showing a second example of skill mastery sequence generation. FIG. 8 is an explanatory diagram showing a third example of skill training sequence generation. FIG. 9 is an explanatory diagram showing an example of a skill training sequence list in the fourth example of skill training sequence generation.

<Example of skill training sequence>
1 is an explanatory diagram showing an example of providing a skill training sequence. The skill training sequence is a sequence in which a plurality of skills are trained. A worker W wears gloves 102 with wearable sensors 101 on his/her hands and a camera 103 on his/her head. A camera 104 is also installed in the work environment. The worker W also holds an electric tool 105 such as an electric screwdriver or a spray gun. The wearable sensor 101 is a sensor that detects data related to the movements of the worker W during work, and includes, for example, an acceleration sensor, a gyro sensor, a geomagnetic sensor, a microphone, a pressure sensor (which also serves as a slip sensor), and a transmitter.

The acceleration sensor detects the acceleration related to the movement of the worker W's hand. The gyro sensor detects the angular velocity related to the movement of the worker W's hand. The gyro sensor detects the direction of the movement of the worker W's hand. The microphone collects sound around the worker W's hand. The pressure sensor detects the pressure applied by the worker W's fingers.

The transmission unit transmits the various acquired data 112 acquired by the wearable sensor 101 to the skill learning assistance device 100 via a wired or wireless connection together with the worker ID. The wearable sensor 101 may be worn directly on the hand without using the glove 102. The wearable sensor 101 may also be in the form of a shoe or workwear. The wearable sensor 101 may be an inertial sensor that detects body movements, or a bending sensor or strain sensor that detects bending and straightening of the body.

The camera 103 acquires imaging data relating to the movements of the worker W during work and transmits the imaging data to the skill learning support device 100 by wired or wireless connection, directly or via a network. The camera 104 acquires imaging data relating to the movements of the worker W and transmits the imaging data to the skill learning support device 100 by wired or wireless connection, directly or via a network. The power tool 105 transmits operation data resulting from the operation of the worker W to the skill learning support device 100 by wired or wireless connection, directly or via a network. The operation data is, for example, the rotation direction and rotation speed of the driver in the case of an electric screwdriver, or the amount of liquid sprayed and spray time in the case of a spray gun.

The skill learning assistance device 100 receives acquired data 112 from the wearable sensor 101 and the camera 103, and generates a skill training sequence for each task 111. A task 111 is an action performed by a worker W. For example, in a certain processing process, there are three tasks 111: task X, task Y, and task Z.

The skill proficiency assistance device 100 also calculates a score for the skill 113 required for the task 111 based on the acquired data 112 required for each task 111. For example, to calculate the score for the skill 113 of task X, acceleration, pressure, and sound are required as the acquired data 112. The higher the score for the skill 113, the higher the proficiency of that skill 113.

The skill learning assistance device 100 also calculates a score for each skill 113. Skill 113 is an ability that the worker W has acquired through education and training. For example, A1 to A3 are skills for mastering task X. The score for skill 113 is calculated using the corresponding detection data. For example, the scores for skills A1 and A2 are calculated using acceleration as the acquired data 112, and the score for skill A3 is calculated using pressure and sound as the acquired data 112. The units of the detection data differ for each data, but are normalized by converting them into scores.

Worker W performs task 111 multiple times. As worker W performs task 111 more times, his/her skill 113 for task 111 improves, and the score for skill 113 also increases. The skill learning support device 100 generates a skill training sequence using the score for skill 113. For example, the skill training sequence for task X is A2 ⇒ A1 ⇒ A3. This makes it possible to identify which skills 113 worker W has mastered and in which order. Therefore, when another worker W masters task 111, the other worker W can master task 111 early by working according to the skill training sequence 114.

<Example of hardware configuration of skill learning assistance device 100>
2 is a block diagram showing an example of a hardware configuration of the skill learning assistance device 100. The skill learning assistance device 100 has a processor 201, a storage device 202, an input device 203, an output device 204, and a communication interface (communication IF) 205. The processor 201, the storage device 202, the input device 203, the output device 204, and the communication IF 205 are connected by a bus 206. The processor 201 controls the skill learning assistance device 100. The storage device 202 is a working area for the processor 201. The storage device 202 is a non-temporary or temporary recording medium that stores various programs and data. Examples of the storage device 202 include a ROM (Read Only Memory), a RAM (Random Access Memory), a HDD (Hard Disk Drive), and a flash memory. The input device 203 inputs data. Examples of the input device 203 include a keyboard, a mouse, a touch panel, a numeric keypad, a scanner, a microphone, and a sensor. The output device 204 outputs data. Examples of the output device 204 include a display, a printer, and a speaker. The communication IF 205 connects to a network and transmits and receives data.

<Example of functional configuration of skill learning assistance device 100>
Fig. 3 is a block diagram showing an example of a functional configuration of the skill learning support device 100. Fig. 4 is a flowchart showing an example of a task sequence generation process procedure by the skill learning support device 100. The skill learning support device 100 has a DB 300 (database) 300, a setting unit 301, an acquisition unit 302, a calculation unit 303, a generation unit 304, and an output unit 305. Specifically, the DB 300 is realized by, for example, the storage device 202 shown in Fig. 2 or the storage device 202 of another computer that can communicate with the skill learning support device 100.

The setting unit 301 sets the task 111 (hereinafter, the target task 111) for which a skill training sequence is to be generated based on input from the worker W (step S401).

The acquisition unit 302 acquires data on the movements of the worker W during work from the wearable sensor 101 and the camera 103, and stores the data in the DB 300 as acquired data 112 (step S402). In the case of image data, for example, the acquisition unit 302 extracts data on bending and straightening the joints of the worker W from the image data.

The calculation unit 303 calculates the score for the skill 113 required for the target task 111 set by the setting unit 301 for each worker W using the acquired data 112, and stores the calculation result in the DB 300 (step S403). The score is calculated for each task. The calculation unit 303 may calculate a total score for each worker W by adding up the scores for the skill 113.

The generation unit 304 generates a skill training sequence based on the calculation results for each skill 113 by the calculation unit 303, and stores the sequence in the DB 300 (step S404). Specifically, for example, the generation unit 304 generates a skill training sequence for the target task 111 by arranging the multiple skills 113 of the target task 111 in order of mastery (in order of the least number of mastery tasks).

The generation unit 304 may determine whether the score for each skill 113 is equal to or higher than the proficiency certification level. If the score for a skill 113 is equal to or higher than the proficiency certification level, the generation unit 304 determines that the worker W has mastered that skill 113. The generation unit 304 may also determine whether the score for a skill 113 is equal to or higher than the proficiency certification level multiple times in a row. If the score for a skill 113 is equal to or higher than the proficiency certification level multiple times in a row, the generation unit 304 determines that the worker W has mastered that skill 113.

The proficiency certification level may be an arbitrarily set value, or may be a statistical value (average value, maximum value, minimum value, or mode value) of the scores of workers W who have actually mastered skill 113. The generation unit 304 also stores in DB 300 the number of tasks performed when it is determined that skill 113 has been mastered (hereinafter, the number of tasks performed to master the skill) as the determination result.

The output unit 305 outputs the skill training sequence for the target task 111 stored in the DB 300 (step S406). Specifically, for example, the output unit 305 may display the skill training sequence on a display device, which is an example of an output device, print it out on a printer, which is an example of an output device, or transmit it to another computer that can communicate with the skill learning assistance device 100 via a network.

<Storage contents of DB300>
Fig. 5 is an explanatory diagram showing an example of the contents stored in the DB 300. In Fig. 5, the DB 300 stores a worker ID 501, a task count 502, time-series acquired data 503, and a score 504 of each worker W for each task 111.

The worker ID 501 is identification information that uniquely identifies the worker W. The number of tasks 502 is the number of times that the worker W identified by the worker ID 501 has performed the task 111. The time-series acquired data 503 is the time-series acquired data 112 for each task in the task 111. The score 504 is a score related to the skill 113 for each task in the task 111.

<Example of Skill Training Sequence Generation by Generation Unit 304>
Next, an example of the judgment process by the judging unit will be described with reference to FIGS. 6 to 11, taking the skill 113 in the task X as an example.

[Example 1 of skill training sequence generation]
FIG. 6 is an explanatory diagram showing a skill training sequence generation example 1. FIG. 6 is an example of generating a skill training sequence using a correlation coefficient. The vertical and horizontal axes of each graph in FIG. Specifically, for example, the generation unit 304 calculates a correlation coefficient R11 between the scores for skills A1 and A1, a correlation coefficient R12 between the scores for skills A1 and A2, and a correlation coefficient R13 between the scores for skills A1 and A3. A correlation coefficient R13, a correlation coefficient R22 between the scores relating to skills A2 and A2, a correlation coefficient R23 between the scores relating to skills A2 and A3, and a correlation coefficient R33 between the scores relating to skills A3 and A3 are calculated.

In the case of FIG. 6, the correlation coefficient R12 is higher than the other correlation coefficients. Therefore, the generation unit 304 determines that skills A1 and A2 should be acquired in preference to skill A3. Furthermore, the correlation coefficient R13 is higher than the correlation coefficient R23. Therefore, the generation unit 304 determines that skills A1, A2, and A3 should be mastered in that order. The generation unit 304 then generates a skill training sequence (A1 ⇒ A2 ⇒ A3).

[Skill mastery sequence generation example 2]
Fig. 7 is an explanatory diagram showing a second example of skill mastery order generation. Fig. 7 shows an example of generating a skill mastery order in order of the degree of difficulty of mastering each skill. The degree of difficulty of mastering is an index showing how quickly the skill 113 has been mastered. The generation unit 304 determines the degree of mastery based on the score, gradient, and number of tasks related to the skill 113 in the graph.

Graph 700 shows the relationship between the total score of the four skills A1 to A4 required for task X and the number of tasks for one or more target workers W.

The points plotted on the graph 700 indicate the total scores of the four skills A1 to A4 for one worker W for the number of times the worker performs task 111. The curve 710 is a regression curve based on the points. Furthermore, L0 is the proficiency certification level for task 111. L0 may be the total value of L1 to L4, which will be described later.

Graph 701 shows the relationship between the score for skill A1 and the number of tasks for one or more target workers W. The points plotted on graph 701 show the score for skill A1 for the number of tasks for task 111 for one worker W. Curve 711 is a regression curve based on the points. Furthermore, L1 is the proficiency certification level for skill A1.

Graph 702 shows the relationship between the score for skill A2 and the number of tasks for one or more target workers W. The points plotted on graph 702 show the score for skill A2 for the number of tasks for task 111 for one worker W. Curve 712 is a regression curve based on the points. Furthermore, L2 is the proficiency certification level for skill A2.

Graph 703 shows the relationship between the score for skill A3 and the number of tasks for one or more target workers W. The points plotted on graph 703 show the score for skill A3 for the number of tasks for task 111 for one worker W. Curve 713 is a regression curve based on the points. Furthermore, L3 is the proficiency certification level for skill A3.

Graph 704 shows the relationship between the score for skill A4 and the number of tasks for one or more target workers W. The points plotted on graph 704 show the score for skill A4 for the number of tasks for task 111 for one worker W. Curve 714 is a regression curve based on the points. Additionally, L4 is the proficiency certification level for skill A4.

The generation unit 304 decomposes the regression curve 710 into regression curves 711 to 714. The regression curves 711 to 714 are added together to obtain the regression curve 710.

The skill 113 whose score increased the earliest in graphs 701 to 704 is skill A1. The score for skill A2 increases after the increase in skill A1, and the score for skill A3 increases after the increase in skill A2. The score for skill A4 increases monotonically regardless of the increase in the scores for the other skills A1 to A3.

In such a case, the generation unit 304 sets the skill A1, which is the fastest to master, to the first in the skill training order, the skill A2, which is the second fastest to master after skill A1, to the second in the skill training order, the skill A3, which is the second fastest to master after skill A2, to the second in the skill training order, and the skill A4, which increases monotonically regardless of the increase in the scores for the other skills A1 to A3, to the second in the skill training order. As a result, in the future, a worker W who is in the process of mastering skills will be able to quickly master skills A1 to A4 by receiving training in the order of skills A1 ⇒ A2 ⇒ A3 ⇒ A4.

[Example 3 of skill training sequence generation]
8 is an explanatory diagram showing a skill training sequence generation example 3. In FIG. 8, a group of workers who have been trained for a certain period of time in a plurality of skill training sequences for skills A1 to A4 perform an operation 111. In this case, the skill learning assistance device 100 acquires the number of tasks and the total score for each worker group by the acquisition unit 302, the calculation unit 303, and the generation unit 304, and determines in which skill training order the worker group has been trained. reaches the proficiency certification level L0. The skill training sequence for each of the multiple worker groups is stored in the DB 300 in association with the worker group.

Curve 801 is a regression curve showing the relationship between the total score for skills A1 to A4 and the number of tasks for a group of workers trained in the skill training sequence (A1 ⇒ A4 ⇒ A2 ⇒ A3). Curve 802 is a regression curve showing the relationship between the total score for skills A1 to A4 and the number of tasks for a group of workers trained in the skill training sequence (A2 ⇒ A3 ⇒ A1 ⇒ A4). Curve 803 is a regression curve showing the relationship between the total score for skills A1 to A4 and the number of tasks for a group of workers trained in the skill training sequence (A3 ⇒ A2 ⇒ A4 ⇒ A1).

In the example of FIG. 8, curve 802 reaches proficiency certification level L0 the earliest. Therefore, the generation unit 304 reads out the skill training sequence (A2 ⇒ A3 ⇒ A1 ⇒ A4) from DB 300 and determines it as the optimal skill training sequence. As a result, other worker groups who have not received training in the skill training sequence (A2 ⇒ A3 ⇒ A1 ⇒ A4) switch to the skill training sequence (A2 ⇒ A3 ⇒ A1 ⇒ A4) and receive training. This allows the other worker groups to acquire skills proficiency earlier.

[Example 4 of skill training sequence generation]
9 is an explanatory diagram showing an example of a skill training sequence list in skill training sequence generation example 4. The skill training sequence list 900 has an item number 901 and a skill training sequence 902. The skill training sequence list 900 includes: The training order 902 is stored in the DB 300. The output unit 305 outputs the skill training order 902 in ascending order of the item number 901, for example. Receive training. The trained group of workers performs the task 111.

The skill proficiency support device 100 acquires the number of tasks and the overall score for this worker group using the acquisition unit 302 and the calculation unit 303. The generation unit 304 determines whether the overall score reaches proficiency certification level L0 within the specified number of tasks. If it has not been reached, the output unit 305 outputs the skill training sequence 902 of the next item number 901. The worker group then undergoes training according to the output skill training sequence 902. This procedure is repeated until the overall score reaches proficiency certification level L0 within the specified number of tasks. This allows the worker group to quickly acquire skills A1 to A4.

Although the skill learning assistance device 100 selected the skill training sequence 902 in ascending order of item number 901, the skill training sequence 902 may be selected randomly.

In the above-mentioned skill training sequence generation examples 1 to 4, when a group of workers undergoes training, in addition to a method of training the next skill 113 once one skill 113 has been mastered, training may also be performed according to the skill training sequence over a short period of time (for example, one day).

In the above-described skill learning support device 100, the output unit 305 outputs the skill training sequence, but it may also output the score for skill 113 in the number of tasks for each skill 113, as shown in FIG. 7. This allows the user of the skill learning support device 100 to determine in what order worker W should train the skills 113.

The present invention is not limited to the above-described embodiments, but includes various modified examples and equivalent configurations within the spirit of the appended claims. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to having all of the configurations described. Furthermore, a portion of the configuration of one embodiment may be replaced with the configuration of another embodiment. Furthermore, the configuration of another embodiment may be added to the configuration of one embodiment. Furthermore, other configurations may be added, deleted, or replaced with part of the configuration of each embodiment.

Furthermore, each of the configurations, functions, processing units, processing means, etc. described above may be realized in part or in whole in hardware, for example by designing them as integrated circuits, or may be realized in software by a processor interpreting and executing a program that realizes each function.

Information such as programs, tables, and files that realize each function can be stored in a storage device such as a memory, a hard disk, or an SSD (Solid State Drive), or in a recording medium such as an IC (Integrated Circuit) card, an SD card, or a DVD (Digital Versatile Disc).

In addition, the control lines and information lines shown are those considered necessary for explanation, and do not necessarily represent all control lines and information lines necessary for implementation. In reality, it is safe to assume that almost all components are interconnected.

100 Skill learning support device 101 Wearable sensor 103 Camera 111 Work 112 Acquired data 113 Skill 114 Skill training sequence 201 Processor 202 Storage device 300 DB
301 Setting section 302 Acquisition section
303 Calculation unit 304 Generation unit 305 Output unit

Claims (7)

A skill learning assistance device having a processor that executes a program and a storage device that stores the program,
The processor,
An acquisition process for acquiring data on the worker's movements during work;
A calculation process for calculating a score for each of a plurality of skills required for the work based on the data acquired by the acquisition process;
a generation process for generating a skill training sequence indicating a training sequence of the plurality of skills based on the calculation results of the plurality of skills calculated by the calculation process for each of the tasks;
an output process for outputting the skill training sequence generated by the generation process ;
A skill learning assistance device that executes the above. The skill learning assistance device according to claim 1,
In the generation process, the processor generates the skill training sequence based on the correlation between the skills.
A skill learning assistance device characterized by: The skill learning assistance device according to claim 1,
In the generation process, the processor generates the skill training sequence based on the score for the skill and the number of tasks up to the time when the score was calculated.
A skill learning assistance device characterized by: The skill learning assistance device according to claim 1,
The system is capable of accessing data associating a plurality of skill training sequences, each of which indicates a training sequence for a plurality of skills, with a plurality of workers;
In the acquisition process, the processor acquires data on movements of the plurality of workers in the work,
In the calculation process, the processor calculates a skill score for each of the plurality of skills for each of the plurality of workers, and calculates a total score by adding up the skill scores for the plurality of skills;
In the generation process, the processor selects a specific skill training sequence from the plurality of skill training sequences based on the total scores of the plurality of workers;
In the output process, the processor outputs the specific skill training sequence.
A skill learning assistance device characterized by: The skill learning assistance device according to claim 1,
In the calculation process, the processor calculates a total score by summing the scores related to the plurality of skills,
In the generation process, the processor determines whether or not the overall score becomes equal to or greater than a predetermined threshold value within a predetermined number of operations;
In the output process, the processor outputs a determination result.
A skill learning assistance device characterized by: The skill learning assistance device according to claim 5,
In the output process, when the total score does not reach or exceed a predetermined threshold value within the predetermined number of tasks, the processor outputs another skill training sequence.
A skill learning assistance device characterized by: A skill learning support method executed by a skill learning support device having a processor that executes a program and a storage device that stores the program,
The processor,
An acquisition process for acquiring data on the movements of a worker during work;
A calculation process for calculating a score for each of a plurality of skills required for the work based on the data acquired by the acquisition process;
a generation process for generating a skill training sequence indicating a training sequence of the plurality of skills based on the calculation results of the plurality of skills calculated by the calculation process for each of the tasks;
an output process for outputting the skill training sequence generated by the generation process;
A skill mastery support method comprising the steps of:

Images