Work support device, work support method and work support program

The work support system addresses the challenge of providing a tailored work environment by using biometric data to analyze and adjust operations, enhancing safety and efficiency.

JP2024158263APending Publication Date: 2024-11-08YOKOGAWA ELECTRIC CORP
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
JP2023073319
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-04-27
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

Conventional technologies fail to provide an appropriate work environment tailored to the physical and mental condition of workers, particularly in hazardous or concentration-requiring operations, leading to potential accidents and inefficiencies.

Method used

A work support system that includes a work support device, method, and program to acquire biometric data, analyze worker states, and intervene when necessary by adjusting the work environment or equipment operations based on the analysis results.

Benefits of technology

The system effectively presents a tailored work environment, reducing the risk of accidents and improving worker safety and efficiency by adapting to the physical and mental states of workers.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024158263000001_ABST
    Figure 2024158263000001_ABST
Patent Text Reader

Abstract

To present appropriate work environment according to states of workers.SOLUTION: A work support server 10 is a work support device that acquires biological data of a plurality of workers who perform common work about plant operation, estimates respective states of the plurality of workers on the basis of the biological data of the plurality of workers, analyzes the respective states of the plurality of workers, and determines whether or not to intervene in the common work by the work support device on the basis of analysis results.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to a work assistance device, a work assistance method, and a work assistance program. [Background technology]

[0002] 2. Description of the Related Art Conventionally, there are techniques for providing feedback to workers in plants based on the workers' biometric data, and providing feedback to devices and equipment installed in the plant (referred to as "plant equipment") based on the plant's operational data. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6192885 [Patent Document 2] JP 2020-161187 A [Patent Document 3] JP 2020-099019 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the conventional technology, it is difficult to present a more appropriate working environment according to the physical and mental state of the worker. For example, in the conventional technology, the operation target of the worker is constant over time, even though the operation of some plant equipment may be dangerous or require sufficient concentration. In other words, in the conventional technology, the operating environment is not changed to be suitable for the worker according to the worker's state.

[0005] The present invention has been made in consideration of the above, and has an object to be able to present an appropriate work environment according to the state of a worker. [Means for solving the problem]

[0006] The present invention provides a work support device including an acquisition unit that acquires biometric data of a plurality of workers performing a common task related to plant operation, an analysis unit that estimates a condition of each of the plurality of workers based on the biometric data of the plurality of workers and analyzes the condition of each of the plurality of workers, and a decision unit that decides whether or not to intervene in the common task by the work support device based on an analysis result by the analysis unit.

[0007] The present invention also provides a work support method executed by a work support device, the work support method including: an acquisition step of acquiring biometric data of a plurality of workers performing a common task related to plant operation; an analysis step of estimating a condition of each of the plurality of workers based on the biometric data of the plurality of workers and analyzing the condition of each of the plurality of workers; and a decision step of deciding whether or not to intervene in the common task by the work support device based on an analysis result of the analysis step.

[0008] The present invention also provides a work assistance program that causes a work assistance device to execute processing, the work assistance program executing an acquisition procedure for acquiring biometric data of a plurality of workers performing common work related to plant operation, an analysis procedure for estimating a condition of each of the plurality of workers based on the biometric data of the plurality of workers and analyzing the condition of each of the plurality of workers, and a decision procedure for deciding whether or not to intervene in the common work by the work assistance device based on an analysis result of the analysis procedure. Effect of the Invention

[0009] According to the present invention, it is possible to provide an appropriate working environment according to the condition of a worker. [Brief description of the drawings]

[0010] [Figure 1] 1 is a diagram illustrating an example of the configuration of a work support system according to an embodiment. [Diagram 2] FIG. 2 is a block diagram showing an example of the configuration of each device according to the embodiment. [Diagram 3] FIG. 4 is a diagram illustrating an example of a work environment data storage unit of the work support server according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of a work content data storage unit of the work support server according to the embodiment. [Diagram 5] FIG. 4 is a diagram illustrating an example of a biometric data storage unit of the work support server according to the embodiment. [Figure 6] FIG. 4 is a diagram illustrating an example of an operation data storage unit of the work support server according to the embodiment. [Figure 7] FIG. 4 is a diagram illustrating an example of a group data storage unit of the work support server according to the embodiment. [Figure 8] FIG. 4 is a diagram illustrating an example of a correspondence relationship data storage unit of the work support server according to the embodiment. [Figure 9] FIG. 4 is a diagram illustrating an example of an intervention data storage unit of the work support server according to the embodiment. [Figure 10] FIG. 4 is a diagram illustrating an example of an intervention data storage unit of the work support server according to the embodiment. [Figure 11] FIG. 4 is a diagram illustrating a specific example 1 of a state estimation process according to the embodiment. [Figure 12] FIG. 11 is a diagram illustrating a specific example 2 of the state estimation process according to the embodiment. [Figure 13] FIG. 4 is a diagram showing a specific example of a display screen according to the embodiment. [Figure 14] 10 is a flowchart showing an example of the overall flow of a work support process according to the embodiment. [Figure 15] 10 is a flowchart showing an example of the flow of a data acquisition process according to the embodiment. [Figure 16] 10 is a flowchart illustrating an example of the flow of a worker classification process according to the embodiment. [Figure 17] 10 is a flowchart illustrating an example of the flow of a data analysis process according to the embodiment. [Figure 18] 13 is a flowchart showing an example of the flow of an intervention decision process according to the embodiment. [Figure 19] 13 is a flowchart showing an example of a flow of an intervention execution process according to the embodiment. [Figure 20] FIG. 2 is a diagram illustrating an example of a hardware configuration. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, a work support device, a work support method, and a work support program according to an embodiment of the present invention will be described in detail with reference to the drawings. Note that the present invention is not limited to the embodiment described below.

[0012] [Embodiment] The configuration of the work support system according to the embodiment, the configuration of each device, and the process flow will be described below in order, and finally, the effects of the embodiment will be described.

[0013] 1. Configuration of the work support system 100 The configuration of the work support system 100 according to the embodiment will be described in detail with reference to Fig. 1. Fig. 1 is a diagram showing an example of the configuration of the work support system 100 according to the embodiment. Below, an example of the overall configuration of the work support system 100, the processing of the work support system 100, and problems with the reference technology will be described in this order, and finally, the effects of the work support system 100 will be described. Note that in the embodiment, the work support processing in a plant will be described as an example, but the equipment and the field of use are not limited thereto.

[0014] (1-1. Example of the overall configuration of the work support system 100) The work support system 100 includes a work support server 10, which is a work support device, a measuring device 20, a management device 30, wearable devices 40 (40A, 40B, 40C, 40D) worn by plant workers W (WA, WB, WC, WD), and plant devices 50 (50A, 50B, 50C). Here, the work support server 10, the measuring device 20, the management device 30, the wearable device 40, and the plant devices 50 are connected to each other via a predetermined communication network (not shown) so as to be able to communicate with each other by wire or wirelessly. The measuring device 20, the management device 30, the wearable device 40, and the plant devices 50 are installed in the plant.

[0015] 1 may include a plurality of work support servers 10, a plurality of measuring devices 20, or a plurality of management devices 30. In addition, one or more of the measuring devices 20, the management devices 30, the wearable devices 40, and the plant devices 50 may be integrated into one configuration.

[0016] (1-2. Overall processing of the work support system 100) The following describes the overall processing of the task support system 100. Note that the following steps S1 to S8 may be executed in a different order. Also, among the following steps S1 to S8, some processing may be omitted.

[0017] (1-2-1. Work environment data acquisition process) The work support server 10 acquires work environment data from measuring devices 20 installed in the plant (step S1). For example, the work support server 10 acquires work environment data such as temperature, humidity, sound, brightness, odor, etc. for each area in the plant from measuring devices 20 such as thermometers and hygrometers.

[0018] (1-2-2. Work content data acquisition process) The work support server 10 acquires work content data from the management device 30 (step S2). For example, the work support server 10 acquires work content data such as a work schedule for each worker W, a worker ID, a work location, an operating device, and an image of a line-of-sight camera of the worker W from the management device 30 such as a PC or a camera.

[0019] (1-2-3. Biometric data acquisition processing) The work support server 10 acquires biometric data from the wearable device 40 worn by the worker W (step S3). For example, the work support server 10 acquires biometric data such as pulse, heart rate, skin potential, muscle potential, eye potential, brain wave, cerebral blood flow, facial expression, tone of voice, blood sugar level, etc., for each worker W from the wearable device 40 such as a smart watch.

[0020] (1-2-4. Operation data acquisition processing) The work support server 10 acquires operation data from the plant equipment 50 installed in the plant (step S4). For example, the work support server 10 acquires physical operation data used for controlling the plant, such as pressure, flow rate, temperature, and liquid level of fluids and solids, from the plant equipment 50 such as tanks, pipes, and furnaces.

[0021] (1-2-5. Worker classification processing) The work support server 10 classifies the workers W who perform common work (step S5). For example, the work support server 10 identifies a work process for each worker W from the work environment data and the work content data, and classifies the workers W for each common work process. In the example of FIG. 1, the work support server 10 classifies workers WA, WC, and WD into work process 1, and classifies worker WB into work process 2.

[0022] (1-2-6. Data analysis processing) The work support server 10 analyzes the acquired data (step S6). For example, the work support server 10 estimates the state of each worker W from the biometric data and detects an abnormality in the worker W for each common work process. In the example of FIG. 1, the work support server 10 detects an abnormality in the worker W in work process 1 when the workers WA, WC, and WD classified in work process 1 are all in the "impatient" state.

[0023] (1-2-7. Intervention decision processing) The work support server 10 decides to intervene in the plant (step S7). For example, when the work support server 10 detects an abnormality in the worker W, it decides to intervene by notifying the worker W to provide a work instruction or to restrict the work. At this time, the work support server 10 can predict the time evolution of evaluation indexes such as process values ​​when the intervention is performed, and can determine whether or not to intervene and the means of intervention.

[0024] (1-2-8. Intervention execution process) The work support server 10 executes intervention in the plant (step S8). For example, the work support server 10 executes a notification to the wearable device 40 of the worker W, and executes control to change the process value of the plant equipment 50 to the safe side. In the example of Fig. 1, the work support server 10 decides to intervene by notifying the workers WA and WC who have a low level of "impatience" of a work instruction and by notifying the worker WD who has a high level of "impatience" of a work restriction, and executes control over the plant equipment 50A operated by the worker WD.

[0025] (1-3. Problems with the work support process of the reference technology) The problems with the work support processes described in the reference techniques disclosed in Patent Documents 1 to 3 will be described.

[0026] (1-3-1. Problems with the work support process in Patent Document 1) The work support process described in Patent Document 1 proposes a technology that links behavioral information and biological information to grasp the magnitude of the worker's workload and issue a warning. However, the above work support process has a problem in that the measured biological information is only used to detect abnormalities and display warnings, and the operating environment of the worker cannot be changed in an appropriate direction based on the measured biological information.

[0027] (1-3-2. Problems with the work support process in Patent Document 2) The work support process described in Patent Document 2 proposes a technology for using biological information to perform "preventive intervention actions that may contribute to maintaining or improving health. However, the above work support process has a problem in that the feedback using biological information is provided to humans, and feedback cannot be provided to devices or equipment.

[0028] (1-3-3. Problems with the work support process in Patent Document 3) The work support process described in Patent Document 3 proposes an equipment control device equipped with a control mode change unit that changes the control mode based on the biometric information of the worker, the work environment, and operation data of a facility such as a thermal power plant. However, in the above work support process, the biometric data is targeted at humans with a huge number of explanatory variables, so it fluctuates more than measurements of clearly characterized physical quantities, and the measurement accuracy is inferior. Therefore, in the above work support process, there is a problem in practical operation that people are hesitant to use biometric data as a basis for judgment in situations where a large loss may occur if feedback based on biometric data is incorrect.

[0029] (1-4. Effects of the work support system 100) In the work support process of the above-mentioned reference technology, the operation target of the worker is invariant over time, and the operation environment is not changed to suit the worker according to the worker's condition. Therefore, the work support process of the reference technology has not provided a mechanism for presenting a more suitable operation environment (work environment) according to the physical or mental condition of the worker. However, some devices and equipment may be dangerous to operate or require sufficient concentration to use. Therefore, it is considered that safe and comfortable use of the devices and equipment can be achieved by changing the operability of the devices and equipment according to the user's level of concentration or attention. For example, when the user lacks attention, irreversible operations may be restricted, or the operating speed of the equipment may be slowed down to prevent dangerous situations such as accidents.

[0030] The work support system 100 proposes to estimate the physical and mental state of the worker W from biometric data measured using various wearable devices 40, and to provide immediate feedback to the person or the device.

[0031] In the work assistance system 100, the objects to be measured by the wearable device 40 include pulse rate, heart rate, skin potential, muscle potential, eye potential, brain waves, cerebral blood flow, facial expression, tone of voice, blood sugar level, etc., but are not limited to these and include any biological data for estimating physical or mental state.

[0032] In the work support system 100, examples of changes in the operating environment include the following, but these are only examples and the changes in the working environment are not limited to the following examples. For example, the speed of an operation that requires attention to adjust the operation of a robot arm, etc. is slowed down, an operation that causes a large loss due to an incorrect decision is limited or changed to a specification that requires multiple authentication, and the load of a worker performing line work, etc. is temporarily reduced and the task volume is changed to a level that the worker can handle at that time. Alternatively, for example, when a worker W is concentrating, a normal operation screen is displayed, and when the worker is distracted, irreversible operations are limited or the operation screen is changed to a simpler one. Alternatively, in the work support system 100, it is expected that these changes can guide correct operations and reduce incorrect operations.

[0033] The above-described work assistance system 100 can be implemented in any equipment or device that requires human operation. In particular, the work assistance system 100 can be introduced in a plant or the like where a single mistake by a worker W can lead to a large loss.

[0034] Proposals similar to the above-mentioned work support system 100 have been proposed, that is, feedback to humans (work support, alerts, etc.) using operational data and biometric data, or feedback to devices and systems to implement optimal control. However, compared to physical measurements, biometric data is ambiguous, and so it is not currently used in situations where incorrect decisions could bring about significant losses. In other words, improving the accuracy of decisions made using biometric data is necessary for utilizing biometric data in the above-mentioned situations.

[0035] Therefore, the work support system 100 proposes the following method to improve the accuracy of judgments using operation data and biometric data. First, the work support system 100 estimates the inner state of the worker W and the environment that the worker W faces with high accuracy by consulting the operation data and the biometric data of multiple workers W who perform similar work, and if it is determined that an abnormal state exists, it provides appropriate feedback to the person or to the equipment or system. Second, the work support system 100 performs a simulation (digital twin, or predicts the time development from the above state from past history) for the judgment result using the state determined by the operation data and biometric data, and adopts only the judgment that transitions the operation state in a good direction. Third, the work support system 100 combines multiple biometric data to improve the accuracy of predictions. As described above, the work support system 100 makes it possible to present a more appropriate work environment according to the physical and mental state of the worker W.

[0036] 2. Configuration of each device in the work support system 100 The functional configuration of each device included in the work support system 100 shown in Fig. 1 will be described with reference to Fig. 2. Fig. 2 is a block diagram showing an example of the configuration of each device according to the embodiment. In the following, an example of the overall configuration of the work support system 100 according to the embodiment will be described, and then an example of the configuration of the work support server 10, the measuring device 20, the management device 30, the wearable device 40, and the plant device 50 according to the embodiment will be described in detail.

[0037] (2-1. Example of the overall configuration of the work support system 100) 2, the work support system 100 includes a work support server 10, a measuring device 20, a management device 30, a wearable device 40, and a plant device 50. The work support server 10 is communicatively connected to the measuring device 20, the management device 30, the wearable device 40, and the plant device 50 via a predetermined communication network.

[0038] (2-2. Example of the configuration of the work support server 10) First, a configuration example of a work support server 10, which is a work support device, will be described with reference to Fig. 2. The work support server 10 has an input unit 11, an output unit 12, a communication unit 13, a storage unit 14, and a control unit 15.

[0039] (2-2-1. Input section 11) The input unit 11 is responsible for inputting various types of information to the work support server 10. For example, the input unit 11 is realized by a mouse, a keyboard, etc., and accepts input of setting information and the like to the work support server 10.

[0040] (2-2-2. Output section 12) The output unit 12 is responsible for displaying various information from the work support server 10. For example, the output unit 12 is realized by a display or the like, and displays setting information stored in the work support server 10, etc.

[0041] (2-2-3. Communications Department 13) The communication unit 13 manages data communication with other devices. For example, the communication unit 13 performs data communication with each communication device via a router, etc. The communication unit 13 can also perform data communication with an operator's terminal (not shown).

[0042] (2-2-4. Storage section 14) The storage unit 14 stores various information referenced when the control unit 15 operates and various information acquired when the control unit 15 operates. The storage unit 14 has a work environment data storage unit 14a, a work content data storage unit 14b, a biological data storage unit 14c, an operation data storage unit 14d, a set data storage unit 14e, a correspondence data storage unit 14f, an intervention data storage unit 14g, and a prediction model 14h. Here, the storage unit 14 can be realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. In the example of FIG. 2, the storage unit 14 is installed inside the work support server 10, but may be installed outside the work support server 10, or multiple storage units may be installed.

[0043] (2-2-4-1. Working environment data storage unit 14a) The work environment data storage unit 14a stores the work environment data transmitted from the measuring device 20. An example of data stored in the work environment data storage unit 14a will now be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the work environment data storage unit 14a of the work support server 10 according to the embodiment. In the example of Fig. 3, the work environment data storage unit 14a has items such as "area", "temperature", "humidity", "sound", "brightness", and "odor".

[0044] "Area" indicates identification information for identifying the location within the plant where work is performed, such as a plant section number or a work process identification number. "Temperature" indicates the temperature for each plant area, for example, expressed in Celsius degrees Celsius. "Humidity" indicates the humidity for each plant area, for example, expressed in percentage %. "Sound" indicates the sound volume for each plant area, for example, expressed in decibels dB. "Brightness" indicates the brightness for each plant area, for example, expressed in lux lx. "Odor" indicates the odor intensity for each plant area, for example, expressed in odor concentration ppm.

[0045] That is, Figure 3 shows an example in which the temperature for the plant area identified by "Area #1" is "Temperature #1", the humidity is "Humidity #1", the sound is "Sound #1", the brightness is "Brightness #1", and the odor is "Odor #1", while the temperature for the plant area identified by "Area #2" is "Temperature #2", the humidity is "Humidity #2", the sound is "Sound #2", the brightness is "Brightness #2", and the odor is "Odor #2", while the temperature for the plant area identified by "Area #3" is "Temperature #3", the humidity is "Humidity #3", the sound is "Sound #3", the brightness is "Brightness #3", and the odor is "Odor #3".

[0046] (2-2-4-2. Work content data storage unit 14b) The work content data storage unit 14b stores the work content data transmitted from the management device 30. An example of data stored in the work content data storage unit 14b will now be described with reference to Fig. 4. Fig. 4 is a diagram showing an example of the work content data storage unit 14b of the work support server 10 according to the embodiment. In the example of Fig. 4, the work content data storage unit 14b has items such as "worker," "working hours," "work location," "operation device," and "video data."

[0047] "Worker" refers to identification information for identifying a worker W performing work within a plant, such as the identification number of the worker W. "Working hours" refers to the time that the worker W is engaged in work, such as the start time, break start time, break end time, and work finish time. "Work location" refers to the work process in which the worker W is engaged in work, such as the identification number of the work process. "Operating equipment" refers to the equipment that the worker W operates when engaged in work, such as the identification number of plant equipment 50. "Video data" refers to video data capturing the working status of the worker W, such as video data captured by a camera worn by the worker W or a camera installed within the plant.

[0048] That is, Figure 4 shows an example in which, for worker WA identified by "Worker A," the working hours are "Working Hours 1," the work location is "Working Location 1," the operating device is "Operating Device 1," and the video data is "Video Data A," while for worker WB identified by "Worker B," the working hours are "Working Hours 2," the work location is "Working Location 2," the operating device is "Operating Device 2," and the video data is "Video Data B," while for worker WC identified by "Worker C," the working hours are "Working Hours 1," the work location is "Working Location 1," the operating device is "Operating Device 1," and the video data is "Video Data C," and for worker WD identified by "Worker D," the working hours are "Working Hours 1," the work location is "Working Location 1," the operating device is "Operating Device 1," and the video data is "Video Data D."

[0049] (2-2-4-3. Biometric data storage unit 14c) The biometric data storage unit 14c stores the biometric data transmitted from the wearable device 40. An example of data stored in the biometric data storage unit 14c will now be described with reference to FIG. 5. FIG. 5 is a diagram showing an example of the biometric data storage unit 14c of the work support server 10 according to the embodiment. In the example of FIG. 5, the biometric data storage unit 14c has items such as "worker", "pulse rate", "heart rate", "skin potential", "muscle potential", "oculogram potential", "electroencephalogram", "cerebral blood flow", "facial expression", "tone of voice", and "blood glucose level".

[0050] "Worker" indicates identification information for identifying a worker W who works in a plant, for example, the identification number of the worker W. "Pulse" indicates the pulse of the worker W when he works, for example, the number of pulse beats per minute. "Heart rate" indicates the heart rate of the worker W when he works, for example, the number of heart beats per minute. "Skin potential" indicates the skin potential of the worker W when he works, for example, the skin potential data during work. "Myoelectric potential" indicates the myoelectric potential of the worker W when he works, for example, the electromyogram data during work. "Oculography" indicates the eye potential of the worker W when he works, for example, the electrooculogram data during work. "Electroencephalogram" indicates the brain waves of the worker W when he works, for example, the electroencephalogram data during work. "Cerebral blood flow" indicates the cerebral blood flow of the worker W when he works, for example, the amount of cerebral blood flow per minute. "Facial expression" indicates the facial expression of worker W when working, and is, for example, image data of worker W's face. "Tone of voice" indicates the tone of voice of worker W when working, and is, for example, audio data of worker W's voice. "Blood glucose level" indicates the blood glucose level of worker W when working, and is, for example, the glucose concentration in worker W's blood.

[0051] That is, in FIG. 5, for worker WA identified by "worker A," the pulse is "pulse A," the heart rate is "heart rate A," the skin potential is "skin potential A," the myoelectric potential is "myoelectric potential A," the eye potential is "eye potential A," the brain wave is "brain wave A," the cerebral blood flow is "cerebral blood flow A," the facial expression is "facial expression A," the tone of voice is "tone of voice A," and the blood glucose level is "blood glucose level A." For worker WB identified by "worker B," the pulse is "pulse B," the heart rate is "heart rate B," the skin potential is "skin potential B," the myoelectric potential is "myoelectric potential B," the eye potential is "eye potential B," the brain wave is "brain wave B," the cerebral blood flow is "cerebral blood flow B," the facial expression is "facial expression B," the tone of voice is "tone of voice B," and the blood glucose level is "blood glucose level B." An example is shown in which, for worker WC identified by "worker C," the pulse is "pulse rate C," the heart rate is "heart rate C," the skin potential is "skin potential C," the myoelectric potential is "myoelectric potential C," the eye potential is "electrooculography C," the brain wave is "brain wave C," the cerebral blood flow is "cerebral blood flow C," the facial expression is "facial expression C," the tone of voice is "tone of voice C," and the blood glucose level is "blood glucose level C," and for worker WD identified by "worker D," the pulse is "pulse rate D," the heart rate is "heart rate D," the skin potential is "skin potential D," the myoelectric potential is "electromyoelectric potential D," the eye potential is "electrooculography D," the brain wave is "brain wave D," the cerebral blood flow is "cerebral blood flow D," the facial expression is "facial expression D," the tone of voice is "tone of voice D," and the blood glucose level is "blood glucose level D."

[0052] (2-2-4-4. Operation data storage unit 14d) The operation data storage unit 14d stores operation data transmitted from the plant equipment 50. An example of data stored in the operation data storage unit 14d will now be described with reference to Fig. 6. Fig. 6 is a diagram showing an example of the operation data storage unit 14d of the work support server 10 according to the embodiment. In the example of Fig. 6, the operation data storage unit 14d has items such as "plant equipment", "pressure", "flow rate", "temperature", and "liquid level".

[0053] "Plant equipment" indicates identification information for identifying plant equipment 50 installed in the plant, for example, the identification number of the plant equipment 50. "Pressure" indicates pressure data of liquid or gas transmitted from plant equipment 50 such as a pressure gauge, and is expressed, for example, in pascals (Pa). "Flow velocity" indicates flow velocity data of liquid or gas transmitted from plant equipment 50 such as a flow meter, and is expressed, for example, in meters per second (m / s). "Temperature" indicates temperature data of liquid or gas transmitted from plant equipment 50 such as a thermometer, and is expressed, for example, in degrees Celsius (°C). "Liquid level" indicates data on the height of the interface surface of the liquid transmitted from plant equipment 50 such as a liquid level gauge, and is expressed, for example, in meters (m).

[0054] That is, Figure 6 shows an example in which, for the plant equipment 50 identified by "Plant Equipment #1", the pressure is "Pressure #1", the flow velocity is "Flow Velocity #1", the temperature is "Temperature #1", and the liquid level is "Liquid Level #1", while for the plant equipment 50 identified by "Plant Equipment #2", the pressure is "Pressure #2", the flow velocity is "Flow Velocity #2", the temperature is "Temperature #2", and the liquid level is "Liquid Level #2", and for the plant equipment 50 identified by "Plant Equipment #3", the pressure is "Pressure #3", the flow velocity is "Flow Velocity #3", the temperature is "Temperature #3", and the liquid level is "Liquid Level #3".

[0055] (2-2-4-5. Collective data storage unit 14e) The group data storage unit 14e stores the group data generated by the classification unit 15b. An example of data stored in the group data storage unit 14e will now be described with reference to Fig. 7. Fig. 7 is a diagram showing an example of the group data storage unit 14e of the work support server 10 according to the embodiment. In the example of Fig. 7, the group data storage unit 14e has items such as "time", "process", "worker", and "video data".

[0056] "Time" indicates the time that a worker W classified as a group is engaged in work, and is expressed, for example, in hours and minutes. "Process" indicates the work process in which a worker W classified as a group is engaged, and is, for example, the identification number of the work process. "Worker" indicates identification information for identifying a worker W classified as a group, and is, for example, the identification number of the worker W. "Video data" indicates video data capturing the working status of a worker W classified as a group, and is, for example, video data captured by a camera worn by the worker W or a camera installed in the plant.

[0057] That is, FIG. 7 shows an example of data classified as "Worker A" and "Video Data A," "Worker C" and "Video Data C," and "Worker D" and "Video Data D" for a work process identified by "Process 2" at "Time T," and "Worker B" and "Video Data B" for a work process identified by "Process 2."

[0058] (2-2-4-6. Correspondence data storage unit 14f) The correspondence data storage unit 14f stores the correspondence data referred to by the determination unit 15d. An example of data stored in the correspondence data storage unit 14f will be described with reference to Fig. 8. Fig. 8 is a diagram showing an example of the correspondence data storage unit 14f of the work support server 10 according to the embodiment. In the example of Fig. 8, the correspondence data storage unit 14f has items such as "step", "biometric data interpretation value", "involved party intervention", "related party intervention", and "equipment intervention".

[0059] "Process" indicates the work process in which the worker W is engaged, and is, for example, the identification number of the work process. "Biometric data interpretation value" indicates the physical and mental state of the worker W, and is expressed, for example, by the characteristics of the state, the numerical value of the state, etc. "Party involved intervention" indicates a means of intervention for the worker W1 who is the party involved in the detection of the abnormality, and is, for example, a notification sent to the party involved worker W1. "Party involved intervention" indicates a means of intervention for a worker W2 other than the party involved in the detection of the abnormality, and is, for example, a notification sent to the manager of the party involved worker W1 or a worker W2 who is engaged in a common work process with the party involved worker W1. "Equipment intervention" indicates a means of intervention for the plant equipment 50 in which the party involved worker W1 who is the party involved in the detection of the abnormality is involved, and is, for example, a control means for the plant equipment 50 operated by the party involved worker W1.

[0060] That is, FIG. 8 shows an example of data in which, for a work process identified by "Process 1," when the biometric data interpretation value is "anxiety 1-3," the intervention means selected are the party intervention "presentation of work instructions," the party intervention "contact manager," and the equipment intervention "operation to change the process value to the safe side," when the biometric data interpretation value is "anxiety 4-6," the intervention means selected are the party intervention "restriction of work," the party intervention "contact manager," and the equipment intervention "operation to change the process value to the safe side," when the biometric data interpretation value is "drowsiness 1-3," the intervention means selected are the party intervention "alarm notification" and the party intervention "contact manager," and when the biometric data interpretation value is "drowsiness 4-6," the intervention means selected are the party intervention "restriction of work" and the party intervention "contact manager."

[0061] (2-2-4-7. Intervention data storage unit 14g) The intervention data storage unit 14g stores the intervention data generated by the determination unit 15d. An example of data stored in the intervention data storage unit 14g will be described with reference to Figs. 9 and 10. Figs. 9 and 10 are diagrams showing an example of the intervention data storage unit 14g of the work support server 10 according to the embodiment. In Figs. 9 and 10, the intervention data storage unit 14g has items such as "worker", "process", "time", "operation data", "biometric data interpretation value", "participant intervention", "related party intervention", and "equipment intervention".

[0062] "Worker" indicates identification information for identifying the intervening worker W, for example, the identification number of the worker W. "Process" indicates the work process in which the intervening worker W is engaged, for example, the identification number of the work process. "Time" indicates the time during which the intervening worker W is engaged in the work, for example, expressed in hours and minutes. "Operation data" indicates operation data related to the work of the intervening worker W, for example, the measurement value of the plant equipment 50 operated by the worker W. "Biometric data interpretation value" indicates the estimated physical and mental state of the worker W, for example, expressed by the characteristics of the state, the numerical value of the state, etc. "Party intervention" indicates a means of intervention for the worker W1 who is the party in which the abnormality is detected, for example, a notification sent to the party W1. "Party intervention" indicates a means of intervention for a worker W2 other than the party in which the abnormality is detected, for example, a notification sent to the manager of the party W1 who is the party, or a notification sent to the party W2 who is engaged in a work process common to the party W1. "Equipment intervention" refers to an intervention means for the plant equipment 50 involving the worker W1 who is the party involved in the detection of the abnormality, for example, a control means for the plant equipment 50 operated by the worker W1 who is the party.

[0063] That is, in FIG. 9, for worker WA (process "Process 1", time "Time T", operation data "Operation Data 1") identified by "Worker A", the biometric data interpretation value is "Impatience 2", so the following interventions are decided: First Party Intervention "Present Work Instructions", Second Party Intervention "Contact Manager", and Equipment Intervention "Operation to Change Process Value to Safety Side". For worker WB (process "Process 2", time "Time T", operation data "Operation Data 2") identified by "Worker B", the biometric data interpretation value is "Drowsiness 3", so the following interventions are decided: First Party Intervention "Notify Alarm" and Second Party Intervention "Contact Manager". For worker C, For worker WC identified by this (process "Process 1", time "Time T", operation data "Operation Data 1"), the biometric data interpretation value is "Impatience 1", so the following interventions are decided: party intervention "Present work instructions", party intervention "Contact manager", and equipment intervention "Operation to change process value to safe side", and for worker WD identified by "Worker D" (process "Process 1", time "Time T", operation data "Operation Data 1"), the biometric data interpretation value is "Impatience 4", party intervention "Work restriction", party intervention "Contact manager", and equipment intervention "Operation to change process value to safe side", are decided:

[0064] FIG. 10 shows an example of data in which intervention is not determined for Worker WA (process "Process 1", time "Time T", operation data "Operation Data 1") identified by "Worker A" because the biometric data interpretation value is "normal", intervention is not determined for Worker WB (process "Process 2", time "Time T", operation data "Operation Data 2") identified by "Worker B" because the biometric data interpretation value is "normal", intervention is not determined for Worker WC (process "Process 1", time "Time T", operation data "Operation Data 1") identified by "Worker C" because the biometric data interpretation value is "normal", and intervention is not determined for Worker WD (process "Process 1", time "Time T", operation data "Operation Data 1") identified by "Worker D" because the biometric data interpretation value is "impatient 4", intervention is determined as the party involved intervention "alarm notification" and the related party intervention "contact Workers A and B and request for assistance".

[0065] (2-2-4-8. Prediction model 14h) The prediction model 14h is a machine learning model that outputs a plant evaluation index in response to input of time-series data including biological data, operation data, work environment data, or work content data. For example, the prediction model 14h is a deterministic model such as a physical model, a statistical model that executes deep learning, or the like.

[0066] (2-2-5. Control unit 15) The control unit 15 controls the entire work support server 10. The control unit 15 has an acquisition unit 15a, a classification unit 15b, an analysis unit 15c, a determination unit 15d, an execution unit 15e, a training unit 15f, a prediction unit 15g, and a display unit 15h. Here, the control unit 15 can be realized by, for example, an electronic circuit such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit), or an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0067] (2-2-5-1. Acquisition part 15a) The acquiring unit 15a acquires biometric data of multiple workers W who perform common tasks related to the operation of the plant. For example, the acquiring unit 15a acquires biometric data such as pulse, heart rate, skin potential, muscle potential, eye potential, electroencephalogram, cerebral blood flow, facial expression, tone of voice, blood sugar level, etc., transmitted from wearable devices 40 (40A, 40B, 40C, 40D) worn by multiple workers W (WA, WB, WC, WD). The acquiring unit 15a stores the acquired biometric data in the biometric data storage unit 14c.

[0068] In the above biometric data acquisition process, one or more wearable devices 40 are used to acquire biometric data of the worker W, thereby making it possible to acquire the condition of the worker W in real time. At this time, the acquired biometric data is processed into an expression that is easily interpreted by humans, and becomes information for providing feedback to a person or a device.

[0069] The acquiring unit 15a also acquires operation data collected from plant equipment 50 installed in the plant. For example, the acquiring unit 15a acquires operation data such as pressure, flow rate, temperature, and liquid level of fluids and solids transmitted from a plurality of plant equipment 50 (50A, 50B, 50C) installed in tanks, pipes, furnaces, etc. The acquiring unit 15a stores the acquired operation data in the operation data storage unit 14d.

[0070] The acquisition unit 15a also acquires work environment data related to the environment of the plant where each of the multiple workers works. For example, the acquisition unit 15a acquires work environment data such as temperature, humidity, sound, brightness, and odor in the plant transmitted from a measuring device 20 installed in the plant. The acquisition unit 15a may also acquire weather information as work environment data outside the plant. The acquisition unit 15a stores the acquired work environment data in the work environment data storage unit 14a.

[0071] The acquisition unit 15a also acquires work content data related to the work performed by each of the multiple workers. For example, the acquisition unit 15a acquires work content data such as the working hours, work location, operation device, and video data of the worker W transmitted from the management device 30 installed in the plant. To explain a specific example, the acquisition unit 15a acquires work content data such as the working hours, work location, operation device, and the like of the worker W from a PC in which the roster data is saved, and acquires work content data such as video data from a camera installed in the plant or a camera worn by the worker W. The acquisition unit 15a stores the acquired work content data in the work content data storage unit 14b.

[0072] (2-2-5-2.Classification section 15b) The classification unit 15b uses the work environment data and the work content data to identify the work process of each of the multiple workers W, and classifies the multiple workers by common work process. For example, the classification unit 15b identifies the work process in which the multiple workers W (WA, WB, WC, WD) are engaged at each time, classifies the multiple workers W (WA, WB, WC, WD) by common work process, and generates aggregate data.

[0073] To explain a specific example, the classification unit 15b uses the plant area, working hours, work location, operating equipment, video data, etc. to identify that at time T, workers WA, WC, and WD are engaged in a work process of process 1, and worker WB is engaged in a work process of process 2, and generates group data classified into {Process 1: worker WA, worker WC, worker WD} and {Process 2: worker WB}. The classification unit 15b stores the generated group data in the group data storage unit 14e.

[0074] In the above worker classification process, the classification unit 15b identifies the work process of the worker W based on the work environment data and work content data of the worker W among the data acquired by the acquisition unit 15a. At this time, the classification unit 15b can update the work process identification process every time (in units of time of about several seconds to several minutes). Therefore, in the above worker classification process, it is possible to identify the work content more in line with reality not only based on data based on a work schedule or the like that describes a predetermined worker schedule, but also based on images from the line-of-sight camera of the worker W acquired in real time and information on the operation target of the worker W, etc.

[0075] (2-2-5-3. Analysis Department 15c) The analysis unit 15c estimates the state of each of the multiple workers W based on the biometric data of the multiple workers W, and analyzes the state of each of the multiple workers W. For example, the analysis unit 15c estimates a physical state or mental state as the state of each of the multiple workers W based on the biometric data collected from the device worn by each of the multiple workers W, and detects an abnormality in the worker W performing the work when the ratio of the workers W showing a predetermined state among the multiple workers W performing a common task exceeds a threshold. In addition, the analysis unit 15c analyzes the state of each of the multiple workers W performing the common task based on the classification result by the classification unit 15b.

[0076] To explain a specific example of the estimated state, the analysis unit 15c analyzes the biodata acquired by the acquisition unit 15a using an analysis method of machine learning such as event-related potential analysis, frequency analysis, waveform analysis, and deep learning, and characterizes and classifies the state of the worker W. At this time, the analysis unit 15c estimates characteristics such as "normal," "impatient," and "drowsy" as the physical or mental state of the worker W, and estimates a numerical value indicating the degree of the state.

[0077] In the above data analysis process, the analysis unit 15c processes the acquired raw biometric data into a form that can be interpreted by humans, thereby making the data available for use as information for making decisions.

[0078] To explain a specific example of an abnormality that is detected, when, for example, 80% or more of workers WA, WC, and WD engaged in the work of process 1, which is a work process, are estimated to be in an "impatient" state, the analysis unit 15c detects an abnormality in worker W engaged in process 1. In this case, when all workers W are estimated to be in an "impatient" state (AND condition met), the analysis unit 15c may detect an abnormality in worker W engaged in process 1 and immediately start intervention for the abnormality. On the other hand, when only some of the workers W are estimated to be in an "impatient" state (AND condition not met), the analysis unit 15c may not detect an abnormality in worker W engaged in process 1 and may intervene after checking the situation.

[0079] (Example 1) Here, specific example 1 of the state estimation process executed by the analysis unit 15c will be described with reference to Fig. 11. Fig. 11 is a diagram showing specific example 1 of the state estimation process according to the embodiment. Note that the process shown in specific example 1 is merely one example of the state estimation process, and is not particularly limited.

[0080] As shown in the example of FIG. 11, in a specific example 1 of the state estimation process, the analysis unit 15c uses biometric data such as "pulse, heart rate (autonomic nerves)," "skin potential (sweating)," "muscle potential," "oculogram potential (blink frequency)," "electroencephalogram," "cerebral blood flow," "facial expression," "tone of voice," and "blood sugar level," and performs a two-level evaluation of whether each piece of biometric data is applicable or not (checked: applicable, unchecked: not applicable) to estimate characteristics such as "impatience," "drowsiness," "tension," "concentration," and "relaxed (normal)" as the physical or mental state of the worker W.

[0081] As shown in the example of FIG. 11, when the biometric data of the worker W, "skin potential (sweating)", "electroencephalogram", "cerebral blood flow", "facial expression", and "tone of voice", exceed the predetermined thresholds, the analysis unit 15c estimates that the state of the worker W is "impatient". When the biometric data of the worker W, "pulse, heart rate (autonomic nerves)", "oculogram (blink frequency)", "electroencephalogram", "cerebral blood flow", "facial expression", and "tone of voice", exceed the predetermined thresholds, the analysis unit 15c estimates that the state of the worker W is "drowsy". When the biometric data of the worker W, "pulse, heart rate (autonomic nerves)", "skin potential (sweating)", "electroencephalogram", "cerebral blood flow", "facial expression", and "tone of voice", exceed the predetermined thresholds, the analysis unit 15c estimates that the state of the worker W is "tension". Furthermore, when each of the biometric data of worker W, "pulse, heart rate (autonomic nerves)," "skin potential (sweating)," "oculogram (blinking frequency)," "brain waves," "cerebral blood flow," and "facial expression," exceeds a predetermined threshold, the analysis unit 15c estimates that the state of worker W is "concentration." Furthermore, when each of the biometric data of worker W, "pulse, heart rate (autonomic nerves)," "brain waves," "cerebral blood flow," and "facial expression," exceeds a predetermined threshold, the analysis unit 15c estimates that the state of worker W is "relaxed."

[0082] At this time, the analysis unit 15c may estimate a value indicating the degree of the condition based on the value exceeding the threshold value of each piece of biometric data. For example, when the biometric data of the worker W, "skin potential (sweating)", "brain wave", "cerebral blood flow", "facial expression", and "tone of voice", exceed the predetermined threshold value and all the values ​​exceeding the threshold value of each piece of biometric data are equal to or greater than the set value set for each piece of biometric data, the analysis unit 15c estimates that the condition and degree of the worker W is "impatience 4".

[0083] (Example 2) Specific example 2 of the state estimation process executed by the analysis unit 15c will be described with reference to Fig. 12. Fig. 12 is a diagram showing specific example 2 of the state estimation process according to the embodiment. Note that the process shown in specific example 2 is merely one example of the state estimation process and is not particularly limited.

[0084] As shown in the example of FIG. 12, in specific example 2 of the state estimation process, the analysis unit 15c uses biometric data such as "pulse, heart rate (autonomic nerves)," "skin potential (sweating)," "muscle potential," "oculogram potential (blink frequency)," "electroencephalogram," "cerebral blood flow," "facial expression," "tone of voice," and "blood sugar level," and performs a three-level evaluation of each biometric data, with two levels of appropriateness and three levels of inappropriateness (double circle: significantly appropriate, circle: appropriate, no mark: inappropriate), to estimate characteristics such as "impatience," "drowsiness," "tension," "concentration," and "relaxed (normal)," as the physical or mental state of the worker W.

[0085] 12, when the biometric data of the worker W, such as "skin potential (sweating)" (double circle), "electroencephalogram" (circle), "cerebral blood flow" (circle), "facial expression" (circle), and "tone of voice" (circle), exceed a predetermined threshold, the analysis unit 15c estimates that the state of the worker W is "impatient." In addition, when the biometric data of the worker W, such as "skin potential (sweating)" (circle), "electrooculogram (blink frequency)" (circle), "electroencephalogram" (double circle), "cerebral blood flow" (circle), "facial expression" (circle), and "tone of voice" (circle), exceed a predetermined threshold, the analysis unit 15c estimates that the state of the worker W is "drowsy." Furthermore, when the biometric data of the worker W, "pulse, heart rate (autonomic nerves)" (double circle), "skin potential (sweating)" (double circle), "muscle potential" (circle), "electroencephalogram" (circle), "cerebral blood flow" (circle), "facial expression" (circle), and "tone of voice" (circle), exceed a predetermined threshold, the analysis unit 15c estimates that the state of the worker W is "tension." Furthermore, when the biometric data of the worker W, "pulse, heart rate (autonomic nerves)" (circle), "skin potential (sweating)" (circle), "electroencephalogram (blink frequency)" (double circle), "electroencephalogram" (circle), "cerebral blood flow" (circle), and "facial expression" (circle), exceed a predetermined threshold, the analysis unit 15c estimates that the state of the worker W is "concentration." In addition, if the biometric data of worker W, including "pulse, heart rate (autonomic nerves)" (circle), "brain waves" (circle), "cerebral blood flow" (circle), and "facial expression" (circle), each exceed a predetermined threshold, the analysis unit 15c estimates that worker W's state is "relaxed."

[0086] At this time, the analysis unit 15c may determine "significantly applicable (double circle)" or "approved (circle)" based on the value exceeding the threshold value of each piece of biometric data, and may further estimate a value indicating the degree of the state based on the number of double circles. For example, when the biometric data of worker W includes "pulse, heart rate (autonomic nerves)", "electrooculography (blink frequency)", "electroencephalogram", "cerebral blood flow", "facial expression", and "tone of voice" that exceed a predetermined threshold value and there is one piece of biometric data that is determined to be "significantly applicable (double circle)", the analysis unit 15c estimates that the state and degree of worker W is "drowsiness 2".

[0087] (2-2-5-4.Decision section 15d) The decision unit 15d decides whether or not to intervene in the common work by the work support server 10, which is a work support device, based on the analysis result by the analysis unit 15c. For example, when the analysis unit 15c detects an abnormality in a worker W performing a work, the decision unit 15d decides an intervention means for the plant. In addition, the decision unit 15d decides the intervention means by referring to the correspondence data indicating the history of interventions in the plant, using the status, operation data, work environment data, and work content data of each of the multiple workers W. The decision unit 15d stores the intervention data, which is the decided intervention means, in the intervention data storage unit 14g.

[0088] The correspondence data referred to in the above intervention decision process is data stored in a table format or the like, which is an intervention measure expected to avoid deterioration of the plant operation state or to transition the state in an optimal direction in response to the state determined by the biometric data interpretation result (state of the worker W), work environment data, work content data, and plant operation data of each set generated by the classification unit 15b. The above correspondence may be stored in advance, or may be input or set by a manager or the like each time based on data previously acquired by the acquisition unit 15a and past intervention results. In other words, in the intervention decision process using the above correspondence data, an intervention plan that is determined to be appropriate based on experience and track record can be selected according to the biometric data interpretation result and operation data.

[0089] (Example 1) Regarding specific example 1, the decision unit 15d refers to the correspondence data shown in FIG. 8 and decides on the intervention means for a worker WA who is estimated to be “anxious 2”, namely, the party intervention “presentation of work instructions”, the party intervention “contact the manager”, and the equipment intervention “operation to change the process value to the safe side”, and decides on the intervention means for a worker WB who is estimated to be “drowsy 3”, namely, the party intervention “alarm notification” and the party intervention “contact the manager”, and the equipment intervention “operation to change the process value to the safe side”, and decides on the intervention means for a worker WC who is estimated to be “anxious 1”, namely, the party intervention “presentation of work instructions”, the party intervention “contact the manager”, and the equipment intervention “operation to change the process value to the safe side”, and decides on the intervention means for a worker WD who is estimated to be “anxious 4”, namely, the party intervention “restriction of work”, the party intervention “contact the manager”, and the equipment intervention “operation to change the process value to the safe side”, and generates the intervention data shown in FIG. 9.

[0090] In the above specific example 1, because workers WA, WC, and WD engaged in process 1, which is a common work process, are all in a state of panic, the decision unit 15d determines that there is a high probability that worker W is in a state of panic due to some kind of abnormality, and decides on an intervention measure to be taken for the person in question, related parties, and equipment. Here, the related parties include the manager of the work of worker W1, whose condition has been estimated, and worker W2, who is involved in the work of worker W1.

[0091] (Example 2) Regarding the specific example 2, the decision unit 15d refers to the correspondence data, and even if the state of the worker WD is estimated to be “impatient 4”, if the states of the workers WA and WC in the process 1, which is a common work process, are “normal”, the decision unit 15d decides on the party involved intervention “alarm notification” and the related party intervention “contact workers A and B and request for assistance” as the intervention means for the worker WD, and generates the intervention data shown in FIG. 10.

[0092] In the above specific example 2, the decision unit 15d determines an intervention means to request support from the workers WA and WC performing the common process 1, such as checking the work content and state of the worker WD, since among the workers WA, WC, and WD engaged in the common work process 1, only the worker WD is in a state of panic, and therefore there is a possibility that an abnormality has occurred only in the work of the worker WD, or that a false positive has been detected in the worker WD being in a state of panic.

[0093] In the intervention decision process of the above-mentioned concrete example 1 and concrete example 2, the decision unit 15d compares the biometric data interpretation result of the worker group, the work content, the plant operation data, and the work environment with the correspondence data according to each group generated by the classification unit 15b, and determines an intervention means expected to transition the situation to an optimal direction in order to prevent the situation from worsening for each worker W included in the group, all workers W included in the group, one or more workers W related to the work content, the manager of the work, the equipment and devices controlled in the work, and other devices. Note that the decision unit 15d changes the degree of intervention for the workers W, managers, and devices and devices according to the degree of agreement of the biometric data interpretation results of multiple workers W performing the same work.

[0094] That is, in the intervention decision process of the above specific example 1, when the agreement of the biometric data interpretation results of the worker group is high, it is determined that the worker W who is included in the above group and performs the same process is likely to be in a state based on the biometric data interpretation result, and more effective intervention can be expected to be performed based on the information on the state of the worker W with high accuracy. For example, if it is found that multiple workers W performing a specific task are equally in a state that deviates from normal, it can be assumed that an abnormality occurs in the above task and the worker W is having difficulty dealing with it. In this case, the situation is considered to be more urgent and important, and it is desirable to prioritize contact with a higher-level manager or, depending on the operating state at that time, to intervene by shifting the device or equipment to be worked on to a safe side without waiting for the manager's judgment.

[0095] On the other hand, in the intervention decision process of the above specific example 2, if the degree of agreement of the biometric data interpretation results of the group of workers is low, it is possible that an abnormality has occurred only in the work of a specific worker W1 in the above process, or that the condition of the specific worker W1 has been erroneously determined (false positive). In such a case, it is possible to perform preventive intervention at low cost with little possibility of causing an irreversible situation, such as providing feedback to the worker W1 by voice to alleviate the abnormal state, or requesting confirmation and support of the work content of another worker W2 in the same process as the worker W1.

[0096] That is, although intervention is expected to entail some cost (for example, if an intervention is made to stop part of the factory / plant functions to prevent an accident, an opportunity loss occurs in that what could have been produced cannot be produced), the above-mentioned intervention decision process makes it possible to carry out low-cost intervention rather than high-cost intervention. On the other hand, the above-mentioned intervention decision process can also improve the accuracy of high-cost intervention decisions.

[0097] (Intervention decision process 1) The determination unit 15d determines an intervention measure from among the multiple intervention measures selected by referring to the correspondence data, using the time evolution of the evaluation index of the plant predicted by the prediction unit 15g. For example, when the state of the worker W is estimated to be "impatient," the determination unit 15d selects multiple intervention measures by referring to the correspondence data, predicts the time evolution of the evaluation index of the plant when the selected intervention measures are executed, and determines "presentation of work instructions," which provides the most favorable prediction result, as the intervention measure for the worker W. To explain this by taking a specific example, the determination unit 15d determines, from among the multiple selected intervention measures, the intervention measure that maximizes the process value after a predetermined period has elapsed, or the intervention measure that minimizes the amount of decrease in the process value after a predetermined period has elapsed.

[0098] (Intervention decision process 2) The determination unit 15d determines an intervention measure from a history of interventions based on the time evolution of the evaluation index predicted by the prediction unit 15g among a plurality of intervention histories included in the correspondence data. For example, the determination unit 15d predicts the time evolution of the evaluation index of the plant when all intervention measures stored in the correspondence data are executed, extracts correspondence data including a plurality of intervention measures that can obtain a favorable prediction result of a predetermined value or more, and determines an intervention measure for the worker W from the extracted correspondence data. To explain this by taking a specific example, the determination unit 15d predicts a process value after a predetermined period has elapsed when all intervention measures stored in the correspondence data are executed, extracts correspondence data including a plurality of intervention measures that can obtain a process value of a predetermined value or more, and determines an intervention measure for the worker W from the extracted correspondence data.

[0099] The above-mentioned intervention decision process 1 and intervention decision process 2 are processes that perform only feedback that obtains a desired progress using a simulation model / digital twin. That is, the above-mentioned intervention decision process 1 and intervention decision process 2 simulate what changes the intervention in the device or equipment presented by the decision unit 15d will bring about over time in the operating state of the plant, and if the intervention does not lead to a desired result, the intervention is not executed, thereby making it possible to select an effective intervention.

[0100] (Intervention decision process 3) The determination unit 15d determines the intervention means designated by the selection unit 15d from among the intervention means selected by referring to the correspondence data. For example, when a plurality of intervention means are presented as selectable by referring to the correspondence data, the determination unit 15d selects one of the presented intervention means as the intervention means for the worker W by accepting the selection by the plant manager.

[0101] The above-mentioned intervention decision process 3 is a process that receives as input the judgment of the plant manager or the like with respect to the decision made by the decision unit 15d, and provides feedback via the judgment. In the above-mentioned intervention decision process 3, an evaluator judges the pros and cons of the intervention presented by the decision unit 15d, so that only effective interventions can be executed without executing interventions that do not lead to desirable results. The above-mentioned intervention decision process 3 can be used in cases where it is desirable to closely monitor the operating state, such as in a plant with a short operating history or when there are workers with a short work history, or when there is not enough data accumulated to create a simulation, a digital twin, or correspondence data.

[0102] (2-2-5-5. Executive Unit 15e) The execution unit 15e executes an intervention in the plant where the common work is executed. For example, the execution unit 15e executes an intervention in the plant based on the intervention means determined by the determination unit 15d. In addition, the execution unit 15e executes a notification to a predetermined worker or a person related to the predetermined worker, or controls a plant device according to the determined intervention means.

[0103] To explain a specific example, when the decision unit 15d decides on the party involved intervention "present work instruction" for the worker W1, the execution unit 15e notifies the wearable device 40 of the worker W1 of an operation instruction based on the manual for the abnormality, such as "perform XX operation." In addition, when the decision unit 15d decides on the party involved intervention "contact manager" for the work related party of the worker W1, the execution unit 15e notifies the terminal device of the manager of the worker W1 of the occurrence of the abnormality, such as "an abnormality has been detected in process 1."

[0104] (2-2-5-6.Training Department 15f) The training unit 15f trains a machine learning model that outputs an evaluation index of a plant in response to input of time-series data including biometric data, operation data, work environment data, or work content data. For example, the training unit 15f constructs a prediction model 14h by using time-series data that holds a time-series relationship for the biometric data, operation data, work environment data, and work content data of a plurality of workers W in the plant. To explain a specific example, the training unit 15f constructs a prediction model 14h of a digital twin by using the above-mentioned time-series data as training data for the time evolution equation or parameter selection of a deterministic model (such as a physical model), or for creating a statistical model (such as deep learning).

[0105] (2-2-5-7. Prediction section 15g) The prediction unit 15g predicts the time evolution of an evaluation index from the time of intervention based on a result obtained by inputting the biometric data, operation data, work environment data, or work content data changed by the intervention into a trained machine learning model. For example, the prediction unit 15g predicts the time evolution of a KPI from the time of perturbation (intervention) to a predetermined initial state by inputting the biometric data, operation data, work environment data, or work content data changed by the intervention into a prediction model 14h that outputs KPIs (Key Performance Indicators) such as process values ​​related to plant operation.

[0106] (2-2-5-8. Display section 15h) The display unit 15h displays the aggregate data generated by the classification unit 15b. For example, the display unit 15h displays the work status, such as the video data of the worker W, for each work process classified by the classification unit 15b on a terminal device of a plant manager.

[0107] (Example of display screen) A specific example of a display screen output by the display unit 15h will be described with reference to Fig. 13. Fig. 13 is a diagram showing a specific example of a display screen according to the embodiment. As shown in Fig. 13, the display unit 15h refers to the aggregate data generated by the classification unit 15b, and displays the operation status of the plant according to the selected display condition. For example, the display unit 15h can display radio buttons or the like that allow the selection of "display by process," "display by worker," "display by operating device," or the like as the display condition.

[0108] In the example of FIG. 13, the display unit 15h displays, as the “plant operation status,” video data of “Worker A,” “Worker C,” and “Worker D” engaged in the work process of “Process 1,” and video data of “Worker B” engaged in the work process of “Process 2.”

[0109] The above-mentioned collective data display process can clarify the work of each work in real time by dividing the workers W who perform the same work (including work that uses different operating equipment but has the same purpose at a higher level) for all the workers in the plant. In addition, by making it possible to display the above-mentioned work, the work manager and the worker W2 who performs related work can immediately visually confirm the worker W1 currently involved in the specific work, and it is expected that the recognition of the situation of the plant operation will be facilitated. In addition, by displaying the status of the worker W involved in each work, it is expected that the status of the worker W involved in the plant operation can be easily grasped. For example, it is expected that another worker W2 can easily recognize that the status of a specific worker W1 performing a specific work is not desirable for the work execution, and that the action of checking the current situation and supporting the worker W2 will be promoted.

[0110] (2-3. Configuration example of measuring device 20) An example of the configuration of the measuring device 20 will be described with reference to Fig. 2. For example, the measuring device 20 is a device such as a thermometer, a hygrometer, a sound level meter, a photometer, an odor meter, etc. that is installed in a plant, and collects work environment data such as temperature, humidity, sound, brightness, odor, etc. within the plant. The measuring device 20 can also collect weather information, etc. as work environment data outside the plant.

[0111] (2-4. Configuration example of management device 30) An example of the configuration of the management device 30 will be described with reference to Fig. 2. For example, the management device 30 is a PC or a camera installed in a plant, and collects work content data such as the working hours, work location, operation devices, and video data of the worker W.

[0112] (2-5. Configuration Example of Wearable Device 40) A configuration example of the wearable device 40 will be described with reference to Fig. 2. For example, the wearable device 40 is an earphone-type wearable electroencephalograph, a heart rate monitor using electrodes such as disposable electrodes, wearable electrodes, and belt electrodes, a smart watch, smart glasses, etc., which is worn by the worker W, and collects biological data such as the pulse, heart rate, skin potential, muscle potential, eye potential, brain wave, cerebral blood flow, facial expression, tone of voice, blood sugar level, etc. of the worker W.

[0113] (2-6. Configuration Example of Plant Device 50) A configuration example of the plant equipment 50 will be described with reference to Fig. 2. For example, the plant equipment 50 is a sensor device or the like that is a measuring device installed in a tank, a pipe, a furnace, or the like of a plant, and collects operational data such as pressure, flow rate, temperature, and liquid level of a fluid or solid.

[0114] 3. Processing flow of the work support system 100 14 to 19, the process flow of the work support system 100 according to the embodiment will be described. Below, the overall process flow of the work support system 100 will be described, and then the process flow of each step will be described.

[0115] (3-1. Overall processing flow of the work support system 100) The overall process flow of the task support system 100 will be described with reference to Fig. 14. Fig. 14 is a flowchart showing an example of the overall process flow according to the embodiment. Note that the following steps S101 to S105 may be executed in a different order. Also, some of the following steps S101 to S105 may be omitted.

[0116] First, the acquisition unit 15a of the work support server 10 executes a data acquisition process (step S101). Second, the classification unit 15b of the work support server 10 executes a worker classification process (step S102). Third, the analysis unit 15c of the work support server 10 executes a data analysis process (step S103). Fourth, the decision unit 15d of the work support server 10 executes an intervention decision process (step S104). Fifth, the execution unit 15e of the work support server 10 executes an intervention execution process (step S105) and ends the process.

[0117] (3-2. Data acquisition process flow) The flow of the data acquisition process by the acquisition unit 15a will be described with reference to Fig. 15. Fig. 15 is a flowchart showing an example of the flow of the data acquisition process according to the embodiment. Note that the following steps S201 to S204 may be executed in a different order. Also, some of the following steps S201 to S204 may be omitted.

[0118] (3-2-1. Work environment data acquisition process) The acquiring unit 15a executes a work environment data acquiring process (step S201). For example, the acquiring unit 15a acquires biometric data such as pulse, heart rate, skin potential, muscle potential, eye potential, electroencephalogram, cerebral blood flow, facial expression, tone of voice, blood sugar level, etc., transmitted from the wearable devices 40 (40A, 40B, 40C, 40D) worn by the multiple workers W (WA, WB, WC, WD).

[0119] (3-2-2. Work environment data acquisition process) The acquiring unit 15a executes a work content data acquiring process (step S202). For example, the acquiring unit 15a acquires operation data such as pressure, flow rate, temperature, and liquid level of fluids and solids transmitted from a plurality of plant devices 50 (50A, 50B, 50C) installed in tanks, pipes, furnaces, etc.

[0120] (3-2-3. Biometric data acquisition processing) The acquiring unit 15a executes a biological data acquiring process (step S203). For example, the acquiring unit 15a acquires work environment data such as temperature, humidity, sound, brightness, and odor in the plant transmitted from a measuring device 20 installed in the plant.

[0121] (3-2-4. Operation data acquisition processing) The acquiring unit 15a executes an operation data acquiring process (step S204). For example, the acquiring unit 15a acquires work content data such as the working hours, work location, operation device, and video data of the worker W transmitted from the management device 30 installed in the plant.

[0122] (3-3. Worker classification process flow) The flow of the worker classification process by the classification unit 15b will be described with reference to Fig. 16. Fig. 16 is a flowchart showing an example of the flow of the worker classification process according to the embodiment. Note that the following steps S301 to S304 may be executed in a different order. Also, some of the following steps S301 to S304 may be omitted.

[0123] (3-3-1. Working environment specific processing) The classification unit 15b executes a work environment identification process (step S301). For example, the classification unit 15b identifies a work environment for each worker W by using the work environment data.

[0124] (3-3-2. Work content identification process) The classification unit 15b executes a task content identification process (step S302). For example, the classification unit 15b identifies the task content for each worker W by using the task content data.

[0125] (3-3-3. Set generation process) The classification unit 15b executes a set generation process (step S303). For example, the classification unit 15b generates set data by classifying the workers W for each common work process based on the work environment and work content identified for each worker W.

[0126] (3-3-4. Collective data display processing) The display unit 15h executes a collective data display process (step S304). For example, the classification unit 15b displays the generated collective data on a terminal device of a plant manager.

[0127] (3-4. Data analysis process flow) The flow of the data analysis process by the analysis unit 15c will be described with reference to Fig. 17. Fig. 17 is a flowchart showing an example of the flow of the data analysis process according to the embodiment. Note that the following steps S401 to S403 may be executed in a different order. Also, some of the following steps S401 to S403 may be omitted.

[0128] (3-4-1. State feature estimation process) The analysis unit 15c executes a state characteristic estimation process (step S401). For example, the analysis unit 15c estimates state characteristics such as "normal", "impatience", "drowsiness", etc.

[0129] (3-4-2. State Numerical Value Estimation Processing) The analysis unit 15c executes a state numerical value estimation process (step S402). For example, the analysis unit 15c estimates a numerical value indicating the degree of a state characteristic such as "impatience 2" or "sleepiness 4".

[0130] (3-4-3. Abnormality detection processing) The analysis unit 15c executes an abnormality detection process (step S403). For example, when the analysis unit 15c estimates that all of the workers W engaged in a common work process are in the “impatient” state, the analysis unit 15c detects an abnormality in the work process.

[0131] (3-5. Intervention decision process flow) The flow of the data analysis process by the analysis unit 15c will be described with reference to Fig. 18. Fig. 18 is a flowchart showing an example of the flow of the intervention decision process according to the embodiment. Note that the following steps S501 to S511 may be executed in a different order. Also, some of the following steps S501 to S511 may be omitted.

[0132] (3-5-1. Prediction model training process) The training unit 15f executes a prediction model training process (step S501). For example, the training unit 15f trains the prediction model 14h that outputs an evaluation index of a plant in response to input of time-series data including biological data, operation data, work environment data, or work content data.

[0133] (3-5-2. Intervention decision process 1) The decision unit 15d executes the intervention decision process 1 in the following manner: The intervention decision process 1 is a process that uses the prediction model 14h and generates intervention data after a simulation.

[0134] (3-5-2-1. Time evolution prediction processing) The determination unit 15d uses the prediction model 14h (step S502: Yes) and, when a simulation is performed before data generation (step S503: before data generation), executes a time evolution prediction process (step S504). For example, the determination unit 15d predicts a process value when all intervention measures of the correspondence data are executed, and extracts intervention measures whose process value is equal to or greater than a predetermined value.

[0135] (3-5-2-2. Intervention data generation process) The determining unit 15d executes an intervention data generating process (step S505). For example, the determining unit 15d generates intervention data from the intervention means whose process value extracted in the process of step S504 is equal to or greater than a predetermined value.

[0136] (3-5-3. Intervention decision process 2) The decision unit 15d executes the intervention decision process 2 in the following manner: The intervention decision process 2 is a process that uses the prediction model 14h and performs a simulation after generating intervention data.

[0137] (3-5-3-1. Intervention data generation process) When the determination unit 15d uses the prediction model 14h (step S502: Yes) and executes a simulation after data generation (step S503: after data generation), the determination unit 15d executes an intervention data generation process (step S506). For example, the determination unit 15d refers to the correspondence data and generates intervention data including a plurality of intervention means.

[0138] (3-5-3-2. Time evolution prediction processing) The determination unit 15d executes a time evolution prediction process (step S507). For example, the determination unit 15d predicts a process value when the intervention means of the intervention data generated in the process of step S506 is executed, and selects an optimal intervention means that maximizes the process value.

[0139] (3-5-4. Intervention decision processing 3) The decision unit 15d executes the intervention decision process 3 in the following manner: The intervention decision process 3 is a process that does not use the prediction model 14h and that accepts the decision of the manager.

[0140] (3-5-4-1. Intervention data generation process) When the prediction model 14h is not used (step S502: No), the determination unit 15d executes an intervention data generation process (step S508). For example, the determination unit 15d refers to the correspondence data and generates intervention data including a plurality of intervention measures.

[0141] (3-5-4-2. Judgment acceptance process) When there is a decision of the plant manager (step S509: Yes), the decision unit 15d executes a decision receiving process (step S510). For example, the decision unit 15d refers to the correspondence data and receives the intervention means designated by the plant manager from the intervention data including a plurality of intervention means.

[0142] (3-5-5. Intervention decision processing 4) The decision unit 15d executes the intervention decision process 4 in the following manner: The intervention decision process 4 is a process that does not use the prediction model 14h and does not accept the decision of the manager.

[0143] (3-5-5-1. Intervention data generation process) When the prediction model 14h is not used (step S502: No), the decision unit 15d executes an intervention data generation process (step S508). For example, the decision unit 15d refers to the correspondence data and generates intervention data including a plurality of intervention means. When there is no decision of the plant manager (step S509: No), the decision unit 15d proceeds to the process of step S511.

[0144] (3-5-6. Intervention Data Decision Processing) After the process of step S505, S507, S509, or S510 is completed, the determination unit 15d executes an intervention data determination process (step S511). For example, the determination unit 15d determines intervention data that satisfies a condition from among the generated intervention data.

[0145] (3-5-7.Others) The decision unit 15d can also execute the intervention decision process 3 after executing the intervention decision process 1 or the intervention decision process 2. That is, the decision unit 15d can also execute only the intervention means approved by accepting the judgment of the administrator for the intervention data generated through the process using the prediction model 14h.

[0146] (3-6. Intervention execution process flow) The flow of the data analysis process by the analysis unit 15c will be described with reference to Fig. 19. Fig. 19 is a flowchart showing an example of the flow of the intervention execution process according to the embodiment. Note that the following steps S601 to S605 may be executed in a different order. Also, among the following steps S601 to S605, some processes may be omitted.

[0147] (3-6-1. Intervention execution process 1) The execution unit 15e executes the intervention execution process 1 in the following manner: The intervention decision process 1 is a process for determining whether or not a related person in the work is to be an intervention target.

[0148] (3-6-1-1. Notification to the parties involved) When the intervention target is a related person in the work (step S601: Intervene with a related person in the work), the execution unit 15e executes a party notification process. For example, the execution unit 15e transmits an alarm notification to the worker W1 in which the abnormality has been detected.

[0149] (3-6-1-2. Notification process for related workers) The execution unit 15e executes a related worker notification process. For example, the execution unit 15e transmits a support request notification for the worker W1 to the worker W2 who is engaged in a common operation process with the worker W1 in whom the abnormality has been detected.

[0150] (3-6-1-3. Administrator notification process) The execution unit 15e executes a manager notification process, for example, by sending an abnormality detection notification to the manager of the worker W1 in whom the abnormality has been detected.

[0151] (3-6-2. Intervention execution process 2) The execution unit 15e executes the intervention execution process 2 in the following manner: The intervention decision process 2 is a process for determining an appliance as an intervention target.

[0152] (3-6-2-1. Equipment control processing) When the intervention target is an equipment (Step S601: Intervene in Equipment), the execution unit 15e executes an equipment control process. For example, the execution unit 15e executes control to change the process value of the operation equipment of the operator W1 in which an abnormality has been detected to the safe side.

[0153] (3-6-3.Others) The execution unit 15e can also execute an intervention execution process 1 in which a worker involved in the work is the intervention target, and an intervention execution process 2 in which a machine is the intervention target.

[0154] 4. Effects of the embodiment Finally, effects of the embodiment will be described below: Effects 1 to 6 corresponding to the processing according to the embodiment will be described below.

[0155] (4-1. Effect 1) First, in the process according to the embodiment described above, biometric data of multiple workers who perform common tasks related to plant operation is acquired, the condition of each of the multiple workers W is estimated based on the biometric data of the multiple workers W, the condition of each of the multiple workers W is analyzed, and based on the analysis result, it is determined whether or not to intervene in the common task. Therefore, in this process, an appropriate work environment can be presented according to the condition of the worker W.

[0156] (4-2. Effect 2) Secondly, in the process according to the embodiment described above, when an abnormality is detected in the worker W performing the work, an intervention measure for the plant is determined, and intervention is performed for the plant where the common work is performed based on the intervention measure. Therefore, in this process, an abnormality can be accurately detected according to the condition of the worker W, and an appropriate work environment can be presented.

[0157] (4-3. Effect 3) Thirdly, in the process according to the embodiment described above, operation data collected from the plant equipment 50 installed in the plant, work environment data related to the environment of the plant where each of the multiple workers W works, and work content data related to the work performed by each of the multiple workers W are further acquired, and the physical or mental state of each of the multiple workers W is estimated based on the biometric data collected from the equipment worn by each of the multiple workers W, and when the ratio of the multiple workers W who show a predetermined state among the multiple workers W who perform a common work exceeds a threshold, an abnormality of the worker W is detected, and an intervention means is determined by referring to the correspondence data showing the history of intervention in the plant using the state, operation data, work environment data, and work content data of each of the multiple workers W, and a notification is given to a specific worker W1 or a person related to the specific worker W1, or control is performed on the plant equipment. Therefore, in this process, an abnormality can be accurately detected according to the state of the worker W, and an appropriate work environment can be effectively presented.

[0158] (4-4. Effect 4) Fourth, in the process according to the embodiment described above, the work process of each of the workers W is identified using the work environment data and the work content data, and the workers W are classified according to the common work process. Therefore, in this process, by identifying the workers W engaged in the common work process, it is possible to more effectively present an appropriate work environment according to the condition of the workers W.

[0159] (4-5. Effect 5) Fifth, in the process according to the embodiment described above, a machine learning model is trained to output a plant evaluation index in response to input of time-series data including biometric data, operation data, work environment data, or work content data, and the biometric data, operation data, work environment data, or work content data changed by the intervention is input to the trained machine learning model, and based on the results obtained, the time evolution of the evaluation index from the time of the intervention is predicted. Therefore, in this process, the plant situation after the intervention is simulated, making it possible to more effectively present an appropriate work environment in response to the state of the worker W.

[0160] (4-6. Effect 6) Sixth, in the process according to the embodiment described above, an intervention measure is determined from a plurality of intervention measures selected by referring to the correspondence data, using the predicted time evolution of the evaluation index. Therefore, in this process, by simulating the plant situation after generating the intervention data, it is possible to more effectively present an appropriate working environment according to the state of the worker W.

[0161] (4-7. Effect 7) Seventh, in the process according to the embodiment described above, the intervention means is determined by referring to the correspondence data selected using the predicted time evolution of the evaluation index. Therefore, in this process, the intervention data is generated after simulating the plant situation, so that an appropriate working environment can be presented according to the state of the worker W more effectively.

[0162] (4-8. Effect 8) Eighth, in the process according to the embodiment described above, the intervention means designated is determined from among a plurality of intervention means selected by referring to the correspondence data. Therefore, in this process, even if the correspondence data is not sufficiently accumulated, by accepting the manager's decision, it is possible to more effectively present an appropriate working environment according to the state of the worker W.

[0163] 〔system〕 The information including the processing procedures, control procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified.

[0164] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure. In other words, all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.

[0165] Furthermore, each processing function performed by each device may be realized, in whole or in part, by a CPU and a program analyzed and executed by the CPU, or may be realized as hardware using wired logic.

[0166] [Hardware] Next, a hardware configuration example of the work support server 10, which is an information processing device, will be described. Note that other devices can also have a similar hardware configuration. FIG. 20 is a diagram for explaining a hardware configuration example. As shown in FIG. 20, the work support server 10 has a communication device 10a, a HDD (Hard Disk Drive) 10b, a memory 10c, and a processor 10d. Furthermore, each unit shown in FIG. 20 is connected to each other via a bus or the like.

[0167] The communication device 10a is a network interface card or the like, and communicates with other servers. The HDD 10b stores programs and DBs that operate the functions shown in FIG.

[0168] The processor 10d reads out a program that executes the same processes as the respective processing units shown in FIG. 2 from the HDD 10b or the like and expands it in the memory 10c, thereby operating a process that executes each function described in FIG. 2 or the like. For example, this process executes the same functions as the respective processing units of the work support server 10. Specifically, the processor 10d reads out a program having the same functions as the acquisition unit 15a, the classification unit 15b, the analysis unit 15c, the determination unit 15d, the execution unit 15e, the training unit 15f, the prediction unit 15g, the display unit 15h, or the like from the HDD 10b or the like. Then, the processor 10d executes a process that executes the same processes as the acquisition unit 15a, the classification unit 15b, the analysis unit 15c, the determination unit 15d, the execution unit 15e, the training unit 15f, the prediction unit 15g, the display unit 15h, or the like.

[0169] In this way, the work support server 10 operates as a device that executes various processing methods by reading and executing a program. The work support server 10 can also realize functions similar to those of the above-mentioned embodiment by reading the program from a recording medium using a media reading device and executing the read program. Note that the program in these other embodiments is not limited to being executed by the work support server 10. For example, the present invention can be similarly applied to cases where another computer or server executes a program, or where these execute a program in cooperation with each other.

[0170] This program can be distributed via a network such as the Internet. This program can also be recorded on a computer-readable recording medium such as a hard disk, a flexible disk (FD), a CD-ROM, a magneto-optical disk (MO), or a digital versatile disk (DVD), and can be executed by being read out from the recording medium by a computer.

[0171] 〔others〕 Some examples of combinations of the disclosed technical features are set out below.

[0172] (1) A work support device comprising: an acquisition unit that acquires biometric data of a plurality of workers performing a common task related to plant operation; an analysis unit that estimates a condition of each of the plurality of workers based on the biometric data of the plurality of workers and analyzes the condition of each of the plurality of workers; and a decision unit that decides whether or not to intervene in the common task by the work support device based on an analysis result by the analysis unit.

[0173] (2) The work support device according to (1), further comprising an execution unit that executes an intervention in the plant where the common work is performed, wherein the decision unit determines an intervention means for the plant when the analysis unit detects an abnormality in a worker performing the work, and the execution unit executes the intervention in the plant based on the intervention means.

[0174] (3) The work support device described in (2), wherein the acquisition unit further acquires operation data collected from plant equipment installed in the plant, work environment data related to an environment of the plant where each of the plurality of workers works, and work content data related to the work performed by each of the plurality of workers, the analysis unit estimates a physical or mental state as a state of each of the plurality of workers based on the biometric data collected from equipment worn by each of the plurality of workers, and detects the abnormality when a ratio of workers exhibiting a predetermined state among the plurality of workers performing a common task exceeds a threshold, the determination unit determines the intervention means by referring to correspondence data indicating a history of intervention in the plant using the states of each of the plurality of workers, the operation data, the work environment data, and the work content data, and the execution unit executes notification to a predetermined worker or a person related to the predetermined worker, or control of the plant equipment in accordance with the determined intervention means.

[0175] (4) The work support device described in (3), further comprising a classification unit that identifies a work process for each of the multiple workers using the work environment data and the work content data, and classifies the multiple workers according to the common work process, and the analysis unit analyzes the status of each of the multiple workers performing the common work based on a classification result by the classification unit.

[0176] (5) The work support device according to (3) or (4), further comprising: a training unit that trains a machine learning model that outputs an evaluation index of the plant in response to input of time series data including the biometric data, the operational data, the work environment data, or the work content data; and a prediction unit that predicts the time evolution of the evaluation index from the time when the intervention is performed based on a result obtained by inputting the biometric data, the operational data, the work environment data, or the work content data that has been changed by the execution of the intervention into the trained machine learning model.

[0177] (6) The work support device according to (5), wherein the determination unit determines the intervention means from a plurality of intervention means selected by referring to the correspondence data, using the time evolution predicted by the prediction unit.

[0178] (7) The work support device according to (5), wherein the determination unit determines the intervention means from a history of interventions based on a time evolution of the evaluation index predicted by the prediction unit, among a plurality of intervention histories included in the correspondence data.

[0179] (8) The work support device according to any one of (3) to (7), wherein the determination unit determines the intervention means, the designation of which has been accepted, from among a plurality of intervention means selected by referring to the correspondence data.

[0180] (9) A work support method executed by a work support device, the work support method including: an acquisition step of acquiring biometric data of a plurality of workers performing a common task related to plant operation; an analysis step of estimating a condition of each of the plurality of workers based on the biometric data of the plurality of workers and analyzing the condition of each of the plurality of workers; and a determination step of determining whether or not to intervene in the common task by the work support device based on an analysis result by the analysis step.

[0181] (10) A work assistance program that causes a work assistance device to execute processing, the work assistance program executing: an acquisition procedure for acquiring biometric data of a plurality of workers performing common work related to plant operation; an analysis procedure for estimating a condition of each of the plurality of workers based on the biometric data of the plurality of workers and analyzing the condition of each of the plurality of workers; and a decision procedure for deciding whether or not to intervene in the common work by the work assistance device based on an analysis result by the analysis procedure. [Explanation of symbols]

[0182] 10 Work support server 11 Input section 12 Output section 13. Communications Department 14 Storage section 14a Working environment data storage section 14b Work content data storage unit 14c Biometric data storage unit 14d Operation data storage section 14e Collective data storage unit 14f Correspondence data storage unit 14g Intervention data storage section 14h forecast model 15 Control section 15a Acquisition part 15b Classification section 15c Analysis Department 15d Decision section 15e Executive Department 15f Training Department 15g Prediction section 15h Display 20 Measuring equipment 30 Management equipment 40 Wearable Devices 50 Plant Equipment 100 Work Support System

Claims

1. A work support device, An acquisition unit that acquires biometric data of a plurality of workers who perform common tasks related to the operation of the plant; an analysis unit that estimates a state of each of the plurality of workers based on biometric data of the plurality of workers and analyzes the state of each of the plurality of workers; a decision unit that decides whether or not the task assistance device should intervene in the common task based on an analysis result by the analysis unit; and A work support device comprising:

2. an execution unit that executes an intervention on the plant in which the common task is executed; Further equipped with The determination unit is determining an intervention measure for the plant when an abnormality in a worker performing the work is detected by the analysis unit; The execution unit is executing an intervention on the plant based on the intervention means; The work support device according to claim 1 .

3. The acquisition unit is Further acquiring operation data collected from plant equipment installed in the plant, work environment data relating to an environment of the plant in which each of the plurality of workers performs work, and work content data relating to work performed by each of the plurality of workers; The analysis unit includes: estimating a physical or mental state as a state of each of the plurality of workers based on the biometric data collected from devices worn by each of the plurality of workers, and detecting the abnormality when a ratio of workers exhibiting a predetermined state among the plurality of workers performing a common task exceeds a threshold value; The determination unit is determining the intervention means by referring to correspondence data indicating a history of interventions in the plant using the statuses of the respective workers, the operation data, the work environment data, and the work content data; The execution unit is In accordance with the determined intervention means, a notification is given to a predetermined worker or a person related to the predetermined worker, or control is performed on the plant equipment. The work support device according to claim 2.

4. a classification unit that identifies a work process for each of the plurality of workers by using the work environment data and the work content data, and classifies the plurality of workers according to the common work process; Further equipped with The analysis unit includes: analyzing a state of each of the plurality of workers performing a common task based on a classification result by the classification unit; The work support device according to claim 3.

5. A training unit that trains a machine learning model that outputs an evaluation index of the plant in response to input of time-series data including the biometric data, the operation data, the work environment data, or the work content data; a prediction unit that predicts the time evolution of the evaluation index from the time point when the intervention is performed based on a result obtained by inputting the biodata, the operation data, the work environment data, or the work content data changed by the execution of the intervention into the trained machine learning model; and The work support device according to claim 3 or 4, further comprising:

6. The determination unit is determining the intervention means from a plurality of intervention means selected by referring to the correspondence data, using the time evolution predicted by the prediction unit; The work support device according to claim 5.

7. The determination unit is determining the intervention means from a history of interventions based on the time evolution of the evaluation index predicted by the prediction unit, among a plurality of intervention histories included in the correspondence data; The work support device according to claim 5.

8. The determination unit is determining the intervention means whose designation has been accepted from among the plurality of intervention means selected by referring to the correspondence data; The work support device according to claim 3 or 4.

9. A work assistance method executed by a work assistance device, comprising: An acquisition step of acquiring biometric data of a plurality of workers who perform common tasks related to the operation of the plant; an analysis step of estimating a condition of each of the plurality of workers based on the biometric data of the plurality of workers and analyzing the condition of each of the plurality of workers; a determination step of determining whether or not the task support device should intervene in the common task based on the analysis result of the analysis step; A work support method comprising:

10. A work assistance program for causing a work assistance device to execute a process, An acquisition procedure for acquiring biometric data of a plurality of workers who perform a common task related to the operation of the plant; an analysis step of estimating a state of each of the plurality of workers based on biometric data of the plurality of workers and analyzing the state of each of the plurality of workers; a determination step for determining whether or not the task assistance device needs to intervene in the common task based on an analysis result of the analysis step; A work support program that executes the above.

Citation Information

Patent Citations

  • Apparatus control device and apparatus control system

    JP2020099019A

  • Group environmental assessment method and group environmental assessment system

    JP2020113117A

  • Ink jet recording method

    JP1986092885A

  • Method, device, and program for evaluating relevance between health degree of interest health region and each preventive intervention action

    JP2020161187A