JP7567707B2 - Information processing device, worker evaluation method, and worker evaluation program - Google Patents

Description

The present invention relates to an information processing device, a worker evaluation method, and a worker evaluation program.

A variety of efforts are being made to improve worker capabilities, regardless of industry or field. For example, there is known technology that evaluates workers by comparing sensor data measured from workers using sensors while they are working with evaluation criteria such as thresholds.

JP 2020-149452 A JP 2007-206386 A JP 2020-106574 A JP 2020-35331 A

However, the above evaluation criteria are subjective to the judgment of the person who sets them, and therefore lack objectivity. If workers are evaluated according to such criteria, it is difficult to obtain fair evaluation results.

Therefore, in one aspect, the objective is to provide an information processing device, a worker evaluation method, and a worker evaluation program that can realize a fair evaluation of plant workers.

The information processing device according to one aspect has an acquisition unit that acquires electroencephalogram data of a first worker to be evaluated for each task related to plant operation and electroencephalogram data of a second worker to be used as an evaluation criterion for the first worker, and an evaluation unit that evaluates the first worker based on a comparison result between the electroencephalogram data of the first worker and the electroencephalogram data of the second worker.

In one aspect of the worker evaluation method, a computer executes a process of acquiring EEG data of a first worker to be evaluated for each task related to plant operation and EEG data of a second worker to be used as the evaluation criterion for the first worker, and evaluating the first worker based on a comparison result between the EEG data of the first worker and the EEG data of the second worker.

In one aspect, the worker evaluation program causes a computer to execute a process of acquiring EEG data of a first worker to be evaluated for each task related to plant operation and EEG data of a second worker to be used as the evaluation criterion for the first worker, and evaluating the first worker based on a comparison result between the EEG data of the first worker and the EEG data of the second worker.

According to one embodiment, a fair evaluation of plant workers can be achieved.

FIG. 1 is a diagram illustrating an example of a usage scene of an information processing device. 2 is a block diagram showing an example of a functional configuration of an information processing device; FIG. 11 is a diagram showing an example of first electroencephalogram data. FIG. 11 is a diagram showing an example of second electroencephalogram data. FIG. 11 is a diagram illustrating an example of a first time difference and a second time difference. 13 is a flowchart showing a procedure for worker evaluation processing. FIG. 11 is a diagram illustrating another example of the first time difference and the second time difference. FIG. 1 is a diagram showing an example of a pattern of cognitive change. FIG. 2 is a diagram illustrating an example of a hardware configuration.

Embodiments of the information processing device, task evaluation method, and task evaluation program according to the present application will be described below with reference to the attached drawings. Each embodiment merely shows one example or aspect, and such examples do not limit the range of values, functions, or usage scenarios. Moreover, each embodiment can be appropriately combined within a range that does not cause inconsistencies.

(Usage scenario)
Fig. 1 is a diagram showing an example of a usage scene of an information processing device 10. The information processing device 10 shown in Fig. 1 provides a worker evaluation function for evaluating a worker 3 in a plant 1 from the viewpoint of supporting education and training that contributes to improving the capabilities of the worker 3.

Plant 1 is an example of various plants that use petroleum, petrochemicals, chemicals, gas, etc., and includes factories equipped with various facilities for obtaining products. Examples of products are LNG (liquefied natural gas), resins (plastics, nylon, etc.), chemical products, etc. Examples of facilities are factory facilities, machine facilities, production facilities, power generation facilities, storage facilities, facilities at wellheads for extracting petroleum, natural gas, etc., etc.

In plant 1, a process control system may be constructed to control the production process, or so-called process, in the plant. Examples of such process control systems include distributed control systems (DCS) and programmable logic controllers (PLC). Taking a DCS as an example, measuring devices such as sensors and operating devices such as actuators are installed as field devices (not shown) in the field of plant 1. Controllers that control these field devices are distributed and arranged for each control loop, which is the control unit of the process, such as loops for measurement, control calculation, and operation.

For example, the operation of plant 1 may be carried out through workers 3 called operators. For example, in outdoor work such as regular inspections of field devices, fault detection, and fault location identification, workers 3 grasp the operating trends of plant 1 based on actual measurements of temperature, pressure, etc. obtained from measuring devices such as temperature sensors and flow meters installed in plant 1. Depending on the operating trends of plant 1 thus grasped, workers 3 operate operating devices such as valves and heaters installed in plant 1. In this manner, operation of plant 1 is carried out.

In addition, the worker 3 performs monitoring work to monitor the operating status of the plant 1 in the monitoring room 2 or the like. For example, a computer device equipped with an alarm function that functions as an HMI (Human Machine Interface) between the process control system and the worker 3 is used for the monitoring work. The monitoring room 2 may be installed near the plant 1 or in a completely different location.

The alarm function may include a function for monitoring process data in real time and notifying the operator 3 when an abnormal state or failure is detected. The "process data" referred to here may include measured values (Process Variables: PV), setting values (Setting Variables: SV), manipulated variables (Manipulated variables: MV), etc. "Process data" may also include information on the type of measured value to be output (e.g., pressure, temperature, flow rate, etc.).

When such an alarm is notified, worker 3 performs various actions depending on the type of alarm, such as investigating the cause or checking actions performed when canceling the alarm.

Here, the worker 3 may be fitted with a sensor device (not shown) that measures brainwave data. For example, the sensor device may be realized by a headset-type or earphone-type brainwave measuring device. Such a sensor device measures brainwave data of the worker 3 during operations such as driving operations and monitoring operations. For example, during monitoring operations, brainwave data including changes in brainwave waveforms corresponding to perception and recognition of stimuli such as an alarm display or sound is measured. Furthermore, during operation of the plant 1, brainwave data including changes in brainwave waveforms corresponding to perception and recognition of an event, that is, an operation performed on an operating device, is measured. Furthermore, the sensor device may also be equipped with a communication function that transmits the brainwave data measured by the sensor device to another device, such as the information processing device 10. In this case, the sensor device may also function as an IoT (Internet of Things) device.

Through such sensor devices, the information processing device 10 collects the brainwave data of the worker 3. For example, as an example of brainwave data of a first worker to be evaluated, the information processing device 10 can acquire the brainwave data of new worker 3A from a sensor device worn by new worker 3A. On the other hand, as an example of brainwave data of a second worker to be used as a reference, the information processing device 10 can acquire the brainwave data of experienced worker 3B from a sensor device worn by experienced worker 3B.

By comparing the electroencephalogram data of the new worker 3A and the electroencephalogram data of the experienced worker 3B, the information processing device 10 evaluates the new worker 3A. The information processing device 10 can then output the evaluation results of the new worker 3A to any output destination. As merely one example of such an output destination, a user terminal 50 that receives the worker evaluation function according to this embodiment is given as an example. For example, the user terminal 50 can be used by all those involved in the plant 1, such as the person being evaluated, his/her instructor or evaluator, and even the manager of the plant 1. The user terminal 50 may also be installed near the plant 1, or in a completely different location.

As described above, the information processing device 10 evaluates the brainwave data of the new worker 3A using the brainwave data of the veteran worker 3B as the evaluation criterion. Therefore, unlike in the case where a threshold value or the like is used as the evaluation criterion, the evaluation is not left to the subjectivity of the person who sets the evaluation criterion, and therefore loss of objectivity can be suppressed. Therefore, the information processing device 10 can realize a fair evaluation of the workers 3 of the plant 1.

(Functional configuration of information processing device 10)
Fig. 2 is a block diagram showing an example of the functional configuration of the information processing device 10. Fig. 2 shows a schematic diagram of blocks corresponding to functions of the information processing device 10. As shown in Fig. 2, the information processing device 10 has a communication interface unit 11, a storage unit 13, and a control unit 15. Note that Fig. 2 merely shows an excerpt of functional units related to the above-mentioned worker evaluation function, and the information processing device 10 may also be provided with functional units that existing computers are equipped with as default or options other than those shown in the figure.

The communication interface unit 11 corresponds to an example of a communication control unit that controls communication between the information processing device 10 and other devices, such as the sensor device 30 worn by the worker 3 and the user terminal 50. As just one example, the communication interface unit 11 can be realized by a network interface card such as a LAN (Local Area Network) card. For example, the communication interface unit 11 receives brainwave data of the worker 3 from the sensor device 30, and also receives an evaluation request for the worker 3 from the user terminal 50. The communication interface unit 11 also outputs the evaluation result of the worker 3 to the user terminal 50.

The memory unit 13 is a functional unit that stores various types of data. As just one example, the memory unit 13 is realized by internal, external, or auxiliary storage of the information processing device 10. For example, the memory unit 13 stores first brainwave data 13A and second brainwave data 13B. In addition to the first brainwave data 13A and second brainwave data 13B, the memory unit 13 does not prevent other data from being stored, such as operation history for field devices and history related to alarms notified by an alarm function.

The first brainwave data 13A and the second brainwave data 13B are both brainwave data of the worker 3. Here, "brainwave data" refers to the waveform of an electrical signal corresponding to an brainwave, for example, time series data of signal strength.

The following is merely one example of electroencephalogram data, and an example will be given in which the original waveform of the electroencephalogram measured by the sensor device 30 is used; however, analysis results obtained by frequency analysis or independent component analysis, such as power spectrum or time waveforms for each frequency band, may also be used.

The first EEG data 13A is the EEG data of the worker 3 to be evaluated. Meanwhile, the second EEG data 13B is the EEG data of the worker 3 to be used as a reference. For example, when evaluating the proficiency of a new worker 3A, the EEG data of the new worker 3A can be set as the evaluation target, while the EEG data of the experienced worker 3B can be set as the reference.

Figure 3 is a diagram showing an example of the first electroencephalogram data 13A. Figure 4 is a diagram showing an example of the second electroencephalogram data 13B. Figures 3 and 4 show an example in which the electroencephalogram data of a new worker 3A is the evaluation target, while the electroencephalogram data of a veteran worker 3B is used as a reference. As shown in Figures 3 and 4, the first electroencephalogram data 13A and the second electroencephalogram data 13B can be data in which a worker ID (identification), an operation code, and electroencephalogram data are associated with each other.

Here, the "worker ID" corresponds to an example of identification information for identifying the worker 3. For example, as shown in FIG. 3, the new worker 3A is given a worker ID with a leading digit of "2", while the veteran worker 3B is given a worker ID with a leading digit of "1", as shown in FIG. 4. For example, the new worker 3A and the veteran worker 3B may be classified based on the length of service or years of experience of the worker 3, or on the presence or absence of qualifications related to the plant 1 or operators. In addition, the worker 3 may be manually classified as a new worker 3A or a veteran worker 3B by a decision-maker such as an instructor, evaluator, or manager of the plant 1.

The "activity code" corresponds to an example of identification information that identifies the activity performed by the worker 3. Examples of such activities include various activities such as operating and monitoring the plant 1, and these activities are identified by the activity code.

Furthermore, "brainwave data" refers to data on the brainwave waveform of new worker 3A or experienced worker 3B. As an example only, the brainwave data of new worker 3A and the brainwave data of experienced worker 3B may be stored as a binary file.

The first brainwave data 13A and the second brainwave data 13B are not limited to the examples shown in Figures 3 and 4, and may include other items, such as the date and time of measurement or acquisition of the brainwaves and identification information of the sensor device 30.

Although Figs. 3 and 4 show an example in which each data is stored in a table format, this is merely one example, and the data structure is not limited to a relational database. For example, the data may be described in tag format using a markup language such as XML (Extensible Markup Language), or data described using commas and line breaks such as CSV (Comma-Separated Values).

The control unit 15 is a processing unit that performs overall control of the information processing device 10. For example, the control unit 15 can be realized by a process executed by a hardware processor. As shown in FIG. 2, the control unit 15 has an acquisition unit 15A, an evaluation unit 15B, and an output unit 15C.

The acquisition unit 15A is a processing unit that acquires the brainwave data of the worker 3. In one aspect, when the brainwave data acquired from the sensor device 30 is the brainwave data of the new worker 3A, the acquisition unit 15A adds the brainwave data acquired from the sensor device 30 to the first brainwave data 13A stored in the memory unit 13. In another aspect, when the brainwave data acquired from the sensor device 30 is the brainwave data of the experienced worker 3B, the acquisition unit 15A adds the brainwave data acquired from the sensor device 30 to the second brainwave data 13B stored in the memory unit 13. The acquisition unit 15A may acquire the brainwave data in real time or by batch processing.

The evaluation unit 15B is a processing unit that evaluates the worker 3 to be evaluated. As an example, the evaluation unit 15B calculates a first time difference from when a change corresponding to perception is observed in the electroencephalogram data of the new worker 3A until a change corresponding to cognition is observed. The term "perception" here refers to being aware of an object or an event based on each sensory information, such as vision, hearing, smell, taste, somatosensation, and balance. In one aspect, perception can be measured as a first electroencephalogram change that appears after a stimulus. In addition, "cognition" refers to judging, understanding, and interpreting a situation after perception. In one aspect, cognition can be measured as a second electroencephalogram change that occurs following the first electroencephalogram change. Hereinafter, a change in the waveform observed on the electroencephalogram waveform that corresponds to perception will be referred to as a "perceptual change," while a change that corresponds to cognition will be referred to as a "cognitive change." Furthermore, the evaluation unit 15B calculates a second time lag from when a perceptual change is observed in the electroencephalogram data of the experienced worker 3B until a cognitive change is observed. Then, the evaluation unit 15B evaluates the new worker 3A based on the comparison result between the first time lag and the second time lag.

More specifically, the evaluation unit 15B can receive an evaluation request for the worker 3 from the user terminal 50. For example, when receiving an evaluation request, it can receive the specification of the new worker 3A to be evaluated, such as the worker ID, as well as the specification of the type of work, such as the work code. This makes it possible to specify which worker is to be evaluated, and further, what type of work is to be evaluated.

Then, the evaluation unit 15B acquires the electroencephalogram data of the new worker 3A corresponding to the worker ID specified in the evaluation request from the first electroencephalogram data 13A stored in the memory unit 13. Next, the evaluation unit 15B calculates, from the electroencephalogram data of the new worker 3A, the time difference between the timing at which the perceptual change begins and the timing at which the cognitive change begins as a first time difference.

In this way, either before or after the process of calculating the first time difference, or in parallel with the process of calculating the first time difference, the evaluation unit 15B calculates a representative value of the second time difference that represents the second time differences of M (natural number) experienced workers 3B.

For example, the evaluation unit 15B calculates the second time difference for each of the M experienced workers 3B as follows. That is, the evaluation unit 15B acquires the electroencephalogram data of the experienced worker 3B selected from the M experienced workers 3B from the second electroencephalogram data 13B stored in the storage unit 13. Next, the evaluation unit 15B calculates the time difference between the timing at which the perceptual change begins and the timing at which the cognitive change begins as the second time difference from the electroencephalogram data of the experienced worker 3B. Then, when the second time difference is calculated for each of the M experienced workers 3B, the evaluation unit 15B performs any statistical processing on the second time differences of the M experienced workers 3B to calculate a representative value that represents the second time differences of the M experienced workers 3B. At this time, the evaluation unit 15B can perform a process of calculating the average value, median value, or mode value as an example of the statistical processing.

Here, any known algorithm can be used to detect perceptual and cognitive changes, but as just one example, the timing at which a perceptual change begins and the timing at which a cognitive change begins can be detected based on event-related potentials.

For example, if monitoring work is taken as an example of the work to be evaluated, when alarm notifications are realized by display, visual evoked potentials evoked by visual stimuli can be used to detect perceptual changes. When alarm notifications are realized by voice or sound, auditory evoked potentials evoked by auditory stimuli can be used to detect perceptual changes. Furthermore, positive potential changes 300 ms after stimulation, known as P300, can be used to detect cognitive changes. Note that while monitoring work has been taken as an example here, when operations are external stimuli, such as in the case of operating plant 1, somatosensory evoked potentials can be used to detect perceptual and cognitive changes.

When detecting perceptual changes and cognitive changes based on event-related potentials in this way, the evaluation unit 15B can use the timing at which a stimulus is given to the worker 3 as auxiliary information. Hereinafter, the timing at which a stimulus is given to the worker 3 may be referred to as the "stimulus occurrence timing." For example, in the case of monitoring work, the timing at which an alarm is notified by the alarm function may be obtained.

As merely an example, the timing at which a perceptual change begins and the timing at which a cognitive change begins can be realized by generating a machine learning model such as the following. Hereinafter, the timing at which a perceptual change begins and the timing at which a cognitive change begins may be referred to as the "perceptual change begin timing" and the "cognitive change begin timing", respectively. As merely an example, these perceptual change begin timings and cognitive change begin timings can be expressed as the elapsed time from the occurrence of a stimulus.

For example, a machine learning model that receives the EEG data and the stimulus occurrence timing of the worker 3 as input and outputs the start timing of a perception change can be generated. In this case, a data set including training data in which the EEG data and the stimulus occurrence timing of the worker 3 correspond to the start timing of a perception change of the correct label can be used for training the machine learning model. Under such a data set, in the learning phase, the EEG data and the stimulus occurrence timing of the worker 3 are set as explanatory variables of the machine learning model, and the label is set as the objective variable of the machine learning model, and the machine learning model can be trained according to any machine learning algorithm, such as deep learning. This results in a trained machine learning model. According to such a trained machine learning model, when the EEG data and the stimulus occurrence timing of the worker 3 are input, the start timing of a perception change can be output. Note that a machine learning model that receives the EEG data and the stimulus occurrence timing of the worker 3 as input and outputs the start timing of a cognitive change can also be generated in the same manner as the above training method.

Furthermore, the evaluation unit 15B does not necessarily have to use the original waveform of the electroencephalogram to detect perceptual and cognitive changes. For example, the evaluation unit 15B can use the time waveform of a frequency band in which perceptual and cognitive changes are predominant, such as beta waves corresponding to 13 to 32 Hz or gamma waves corresponding to 25 to 140 Hz, to detect perceptual and cognitive changes.

Fig. 5 is a diagram showing an example of the first time difference and the second time difference. Fig. 5 shows a waveform WA1 of a portion corresponding to a perceptual change and a waveform WA2 of a portion corresponding to a cognitive change in the electroencephalogram data of the new worker 3A. Furthermore, the waveform WA1 shows a perceptual change start timing _T3A1 , and the waveform WA2 shows a cognitive change start timing _T3A2 . According to this example, the first time difference TL1 can be calculated by calculating the difference between the perceptual change start timing _T3A1 and the cognitive change start timing _T3A2 , for example, _T3A2 - _T3A1 .

5 shows a waveform WB1 of a portion of the electroencephalogram data of the experienced worker 3B corresponding to a perceptual change and a waveform WB2 of a portion of the electroencephalogram data of the experienced worker 3B corresponding to a cognitive change. The waveform WB1 shows a perceptual change start timing _T3B1 , and the waveform WB2 shows a cognitive change start timing _T3B2 . According to this example, the second time difference TL2 can be calculated by calculating the difference between the perceptual change start timing _T3B1 and the cognitive change start timing _T3B2 , for example, _T3B2 - _T3B1 .

Then, the evaluation unit 15B evaluates the new worker 3A based on the gap G between the representative values of the first time difference TL1 and the second time difference TL2. The reason why such a gap G is used to evaluate the new worker 3A is that there are the following aspects. For example, in the case of monitoring work, a difference appears between the new worker 3A and the experienced worker 3B in the time from when an alarm notification is perceived to when a response such as an action to investigate the cause is recognized. In other words, partly because the experienced worker 3B is more skilled at monitoring work than the new worker 3A, it is clear that the second time difference, which is the time difference between perception and cognition of the experienced worker 3B, tends to be shorter than the first time difference, which is the time difference between perception and cognition of the new worker 3A.

As a result, the evaluation unit 15B can evaluate the proficiency of the new worker 3A to be high as the gap G becomes smaller, and can evaluate the proficiency of the new worker 3A to be low as the gap G becomes larger. For example, the evaluation unit 15B can calculate the proficiency normalized to any numerical range, such as 0 to 10 or 0 to 100, as an example of the evaluation of the new worker 3A.

The output unit 15C is a processing unit that outputs the evaluation result of the worker 3. As an example, the output unit 15C outputs the proficiency of the new worker 3A evaluated by the evaluation unit 15B to the user terminal 50. Here, the user terminal 50 is given as an example of the output destination of the evaluation result, but this is not limited to this. For example, the output unit 15C may store the proficiency of the new worker 3A in the storage unit 13, or may output it to a database server outside the information processing device 10. In addition, the output unit 15C may output an application or service that uses the evaluation result of the worker 3 as an input and executes various processes, such as personnel evaluation and ability-based pay calculation. These applications and services do not necessarily have to be executed by the information processing device 10, and may be executed by an external server device, etc.

(Processing flow)
Fig. 6 is a flowchart showing the procedure of the worker evaluation process. Fig. 6 shows, as an example only, an example in which the process is started when an evaluation request for the worker 3 is received, but is not limited to this. For example, the process may be automatically started when the electroencephalogram data of the new worker 3A is acquired from the sensor device 30, or batch processing may be performed for each piece of electroencephalogram data of the new worker 3A acquired up to that point at a regular time, for example, at 6:00 p.m. or 12:00 a.m.

As shown in FIG. 6, when an evaluation request for worker 3 is received (step S101), the evaluation unit 15B executes the following process. That is, the evaluation unit 15B acquires the brainwave data of new worker 3A corresponding to the worker ID specified in the evaluation request received in step S101 from the first brainwave data 13A stored in the memory unit 13 (step S102).

Next, the evaluation unit 15B calculates the time difference between the timing at which the perceptual change begins and the timing at which the cognitive change begins as a first time difference from the electroencephalogram data of the new worker 3A acquired in step S102 (step S103).

The evaluation unit 15B also executes the processes of steps S104 and S105 a number of times corresponding to the M experienced workers 3B. That is, the evaluation unit 15B acquires the brainwave data of the experienced worker 3B being selected from the M experienced workers 3B from the second brainwave data 13B stored in the storage unit 13 (step S104).

Next, the evaluation unit 15B calculates the time difference between the timing at which the perceptual change begins and the timing at which the cognitive change begins as a second time difference from the electroencephalogram data of the experienced worker 3B acquired in step S104 (step S105).

Then, when the second time difference is calculated for each of the M experienced workers 3B, the evaluation unit 15B performs statistical processing on the second time differences of the M experienced workers 3B to calculate a representative value that represents the second time differences of the M experienced workers 3B (step S106).

Then, the evaluation unit 15B evaluates the new worker 3A based on the gap G between the representative values of the first time difference TL1 and the second time difference TL2 (step S107). After that, the output unit 15C outputs the proficiency of the new worker 3A evaluated in step S107 to the user terminal 50 (step S108), and the process ends.

(effect)
As described above, the information processing device 10 acquires the electroencephalogram data of the first worker to be evaluated for each task related to the operation of the plant 1 and the electroencephalogram data of the second worker to be used as the evaluation criterion for the first worker. The information processing device 10 then evaluates the first worker based on the comparison result between the electroencephalogram data of the first worker and the electroencephalogram data of the second worker. This allows for relative evaluation, such as evaluating the electroencephalogram data of the new worker 3A using the electroencephalogram data of the veteran worker 3B as the evaluation criterion. This prevents the evaluation criterion from being left to the subjectivity of the person who sets it, as in the case where a threshold value or the like is used as the evaluation criterion, and thus prevents objectivity from being impaired. Therefore, the information processing device 10 can achieve a fair evaluation of the workers 3 of the plant 1.

The information processing device 10 also evaluates the first worker based on a comparison between a first time difference between when a first change is observed in the electroencephalogram data of the first worker and when a second change is observed, and a second time difference between when a first change is observed in the electroencephalogram data of the second worker and when a second change is observed. Therefore, the information processing device 10 can use the time difference in perception and cognition between the new worker 3A and the experienced worker 3B as an evaluation axis, making it possible to evaluate, by way of example only, the proficiency of the new worker 3A and the concentration level of the experienced worker 3B.

Furthermore, the information processing device 10 evaluates the proficiency of new worker 3A lower as the gap between the first time difference observed in the electroencephalogram data of new worker 3A and the second time difference observed in the electroencephalogram data of experienced worker 3B becomes larger, and evaluates the proficiency of new worker 3A higher as the gap becomes smaller. Therefore, the information processing device 10 can qualitatively evaluate the proficiency of new worker 3A.

(Application example)
The above embodiment is merely an example, and various applications are possible.

(1) Evaluation of the Concentration Level of the Veteran Worker 3B In the above embodiment, an example has been given in which the new worker 3A is the evaluation target while the veteran worker 3B is the reference from the viewpoint of evaluating the proficiency level of the new worker 3A, but this is not limiting. For example, from the viewpoint of evaluating the concentration level of the veteran worker 3B, the veteran worker 3B can be the evaluation target while the new worker 3A can be the reference.

Fig. 7 is a diagram showing another example of the first time difference and the second time difference. Fig. 7 shows a waveform WB3 of a portion corresponding to a perceptual change and a waveform WB4 of a portion corresponding to a cognitive change in the electroencephalogram data of the experienced worker 3B. Furthermore, the waveform WB3 shows a perceptual change start timing _T3B3 , and the waveform WB4 shows a cognitive change start timing _T3B4 . According to this example, the first time difference TL3 can be calculated by calculating the difference between the perceptual change start timing _T3B3 and the cognitive change start timing _T3B4 , for example, _T3B4 - _T3B3 .

7 shows a waveform WA3 of a portion of the electroencephalogram data of new worker 3A corresponding to a perceptual change and a waveform WA4 of a portion of the electroencephalogram data of new worker 3A corresponding to a cognitive change. The waveform WA3 shows a perceptual change start timing _T3A3 , and the waveform WA4 shows a cognitive change start timing _T3A4 . According to this example, the second time difference TL4 can be calculated by calculating the difference between the perceptual change start timing _T3A3 and the cognitive change start timing _T3A4 , for example, _T3A4 - _T3A3 .

Then, the evaluation unit 15B evaluates the concentration level of the experienced worker 3B based on the gap G2 between the representative values of the first time difference TL3 and the second time difference TL4.

Here, because new worker 3A approaches the work with a greater sense of tension than experienced worker 3B, the second time difference, which is the time difference between the perception and cognition of new worker 3A, may tend to be shorter than the first time difference, which is the time difference between the perception and cognition of experienced worker 3B.

As a result, the evaluation unit 15B can evaluate the concentration level of the experienced worker 3B lower as the gap G2 between the first time difference observed in the electroencephalogram data of the experienced worker 3B and the second time difference observed in the electroencephalogram data of the new worker 3A becomes larger, and can evaluate the concentration level of the experienced worker 3B higher as the gap G2 becomes smaller. For example, the evaluation unit 15B can calculate a concentration level normalized to any numerical range, such as 0 to 10 or 0 to 100, as an example of the evaluation of the experienced worker 3B.

In this way, according to the application example of the above embodiment, the concentration level of experienced worker 3B can be qualitatively evaluated.

(2) Evaluation of concentration level based on beta waves In addition to the above (1), the evaluation unit 15B can use the intensity of beta waves to evaluate the concentration level of the worker 3. For example, beta waves corresponding to a frequency band of 13 to 32 Hz in the electroencephalogram data of the worker 3 tend to be more easily observed as the worker's concentration level increases. For this reason, the concentration level of the worker 3 can be evaluated as higher as the intensity of beta waves observed in the electroencephalogram data of the worker 3 increases, and the concentration level of the worker 3 can be evaluated as lower as the intensity of beta waves observed in the electroencephalogram data of the worker 3 decreases.

Such an evaluation of the concentration level based on the intensity of beta waves can also be implemented in combination with the above (1). For example, when evaluating the concentration level of experienced worker 3B, if the intensity of beta waves observed in the electroencephalogram data of experienced worker 3B is not equal to or greater than a threshold, the concentration level is calculated based on the above (1), whereas if the intensity of beta waves is equal to or greater than a threshold, the concentration level is calculated from the intensity of beta waves. In this way, if there is a high possibility that experienced worker 3B's concentration has decreased due to familiarity, the concentration level of experienced worker 3B can be calculated using the electroencephalogram data of new worker 3A as a reference. On the other hand, if there is a high possibility that experienced worker 3B's concentration has not decreased due to familiarity, the concentration level can be calculated from the intensity of beta waves. This makes it possible to apply the above (1) to situations where experienced worker 3B's concentration has decreased due to familiarity.

(3) Evaluation due to Perception Leakage For example, the evaluation unit 15B can evaluate the new worker 3A based on whether or not the perceptual change observed in the electroencephalogram data of the veteran worker 3B is observed in the electroencephalogram data of the new worker 3A. In this case, if the perceptual change observed in the electroencephalogram data of the veteran worker 3B is observed in the electroencephalogram data of the new worker 3A, it is highly likely that the new worker 3A has acquired tacit knowledge that only the veteran worker 3B can notice. In this case, the evaluation unit 15B can evaluate the proficiency of the new worker 3A as high. On the other hand, if the perceptual change observed in the electroencephalogram data of the veteran worker 3B is not observed in the electroencephalogram data of the new worker 3A, it is highly likely that the new worker 3A has not acquired tacit knowledge that only the veteran worker 3B can notice. In this case, the evaluation unit 15B can evaluate the proficiency of the new worker 3A as low.

(4) Evaluation of habituation based on the pattern of cognitive change When the evaluation unit 15B regards an initial response to a stimulus, i.e., a change from calmness, as a perceptual change, it can also evaluate the habituation of the worker 3 based on the pattern of cognitive change after the above-mentioned initial response.

Figure 8 is a diagram showing an example of a pattern of cognitive change. Figure 8 shows three cognitive change patterns P1 to P3 that branch out after an initial response to a stimulus. Cognitive change pattern P1 shown in Figure 8 is "homeostatic activity" that is fixed in the state after the initial response. Cognitive change pattern P2 is "oscillation" that recovers with inertia to the state before the stimulus. Cognitive change pattern P3 is "adaptation" that returns to the state before the stimulus.

Under these classifications of three cognitive change patterns P1 to P3, familiarity can be evaluated based on which pattern the EEG data of worker 3 corresponds to. For example, evaluation unit 15B calculates the waveform similarity between the EEG data of worker 3 and the three cognitive change patterns P1 to P3. If the similarity of cognitive change pattern P1 is highest, evaluation unit 15B evaluates the degree of familiarity as "low." If the similarity of cognitive change pattern P2 is highest, evaluation unit 15B evaluates the degree of familiarity as "medium." If the similarity of cognitive change pattern P3 is highest, evaluation unit 15B evaluates the degree of familiarity as "high."

(5) Evaluation Axis Other Than Time Difference In the above embodiment, an example was given in which the time difference between perception and cognition was used as an evaluation axis to evaluate the worker 3, but it is also possible to evaluate the worker 3 using other evaluation axes. For example, one factor is that the veteran worker 3B is more skilled at monitoring work than the new worker 3A, and the electroencephalogram data of the veteran worker 3B tends to show waveforms corresponding to cognitive changes more clearly than the electroencephalogram data of the new worker 3A. Taking monitoring work as an example, the veteran worker 3A is more likely to be able to clearly recognize the type of alarm and the measures to be taken to respond to the type of alarm, such as cause investigation actions and check actions, after perceiving the alarm, from the type of the alarm, than the new worker 3A. For this reason, when evaluating the proficiency of the new worker 3A as the evaluation subject, the evaluation unit 15B can evaluate the proficiency of the new worker 3A lower as the gap between the amplitude observed in the cognitive change of the electroencephalogram data of the new worker 3A, for example the difference between the minimum and maximum displacements, and the amplitude observed in the cognitive change of the electroencephalogram data of the experienced worker 3B becomes larger, and can evaluate the proficiency of the new worker 3A higher as the gap becomes smaller. Note that, although an example in which the amplitude in the cognitive change is used as the evaluation axis has been given here, the amplitude in the perceptual change can also be used as the evaluation axis.

(6) Electroencephalogram Data In the above embodiment and application example, the electroencephalogram data of different workers are compared, but the electroencephalogram data of the same worker can also be compared. For example, the electroencephalogram data measured in the first year of operator work for the same worker 3 can be compared with the electroencephalogram data measured in the Nth year of operator work to evaluate the growth of the worker 3. In this case, the electroencephalogram data measured in the Nth year of operator work is used as the evaluation target, while the electroencephalogram data measured in the first year of operator work is used as the reference. Then, the evaluation unit 15B subtracts the time difference between perception and cognition in the electroencephalogram data in the Nth year from the time difference between perception and cognition in the electroencephalogram data in the first year. At this time, the greater the subtraction value, the higher the evaluation of the growth of the worker 3, while the smaller the subtraction value, the lower the evaluation of the growth of the worker 3.

<Application Examples>
The above embodiment is merely an example, and various applications are possible.

(1) System Information including processing procedures, control procedures, specific names, various data and parameters shown in the above documents and drawings may be changed as desired unless otherwise specified.

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 depending on various loads, usage conditions, etc.

Furthermore, each processing function performed by each device can be realized, in whole or in part, by a CPU (Central Processing Unit) and a program analyzed and executed by the CPU, or can be realized as hardware using wired logic.

(2) Hardware Next, a hardware configuration example of the information processing device 10 will be described. Fig. 9 is a diagram for explaining a hardware configuration example. As shown in Fig. 9, the information processing device 10 has a communication device 10a, a HDD (Hard Disk Drive) 10b, a memory 10c, and a processor 10d. In addition, each unit shown in Fig. 8 is connected to each other by a bus or the like.

The communication device 10a is a network interface card or the like, and communicates with other servers. The HDD 10b stores the programs and DBs that operate the functions shown in FIG. 2.

The processor 10d reads out a program that executes the same processes as the processing units shown in FIG. 2 from the HDD 10b etc. and expands it in the memory 10c, thereby operating a process that executes the functions described in FIG. 2 etc. For example, this process executes the same functions as the processing units of the information processing device 10. Specifically, the processor 10d reads out a program that has the same functions as the acquisition unit 15A, the evaluation unit 15B, the output unit 15C etc. from the HDD 10b etc. Then, the processor 10d executes a process that executes the same processes as the acquisition unit 15A, the evaluation unit 15B, the output unit 15C etc.

In this way, the information processing device 10 operates as a computer that executes a parameter calculation method by reading and executing a program. The information processing device 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 information processing device 10. For example, the present invention can be similarly applied to cases where another computer or server executes a program, or where these cooperate to execute a program.

This program can be distributed via a network such as the Internet. In addition, this program can be recorded on a computer-readable recording medium such as a hard disk, a flexible disk (FD), a CD-ROM, an MO (Magneto-Optical disk), or a DVD (Digital Versatile Disc), and can be executed by being read from the recording medium by a computer.

REFERENCE SIGNS LIST 10 Information processing device 11 Communication interface unit 13 Storage unit 13A First electroencephalogram data 13B Second electroencephalogram data 15 Control unit 15A Acquisition unit 15B Evaluation unit 15C Output unit

Claims (9)

an acquisition unit that acquires electroencephalogram data of a first worker to be evaluated for each task related to the operation of the plant and electroencephalogram data of a second worker to be used as an evaluation criterion for the first worker;
an evaluation unit that evaluates the first worker based on a comparison result between the electroencephalogram data of the first worker and the electroencephalogram data of the second worker;
having
The evaluation unit evaluates the first worker based on a comparison result between a first time difference from when a first change is observed in the electroencephalogram data of the first worker to when a second change is observed, and a second time difference from when the first change is observed in the electroencephalogram data of the second worker to when the second change is observed. 2. The information processing device according to claim 1, wherein the evaluation unit lowers the evaluation of the first worker as a gap between the first time difference observed in the electroencephalogram data of the first worker and the second time difference observed in the electroencephalogram data of the second worker increases, and raises the evaluation of the first worker as the gap decreases. the acquiring unit acquires electroencephalogram data of the new worker to be evaluated and electroencephalogram data of the experienced worker to be used as the evaluation standard,
3. The information processing device according to claim 2, wherein the evaluation unit evaluates the proficiency of the new worker lower as a gap between the first time difference observed in the electroencephalogram data of the new worker and the second time difference observed in the electroencephalogram data of the experienced worker becomes larger, and evaluates the proficiency of the new worker higher as the gap becomes smaller. the acquiring unit acquires electroencephalogram data of the experienced worker to be evaluated and electroencephalogram data of the new worker to be used as the evaluation criterion,
3. The information processing device according to claim 2, wherein the evaluation unit evaluates the level of concentration of the experienced worker lower as a gap between the first time difference observed in the electroencephalogram data of the experienced worker and the second time difference observed in the electroencephalogram data of the rookie worker increases, and evaluates the level of concentration of the experienced worker higher as the gap decreases. an acquisition unit that acquires electroencephalogram data of a first worker to be evaluated for each task related to the operation of the plant and electroencephalogram data of a second worker to be used as an evaluation criterion for the first worker;
an evaluation unit that evaluates the first worker based on a comparison result between the electroencephalogram data of the first worker and the electroencephalogram data of the second worker;
having
The evaluation unit evaluates the first worker based on whether a first change observed in the electroencephalogram data of the second worker is observed in the electroencephalogram data of the first worker. an acquisition unit that acquires electroencephalogram data of a first worker to be evaluated for each task related to plant operation and electroencephalogram data of a second worker to be used as an evaluation criterion for the first worker;
an evaluation unit that evaluates the first worker based on a comparison result between the electroencephalogram data of the first worker and the electroencephalogram data of the second worker;
having
The evaluation unit evaluates the habituation of the first worker or the second worker based on a pattern of a second change that appears following a first change observed in the electroencephalogram data of the first worker or the electroencephalogram data of the second worker after stimulation. 7. The information processing device according to claim 6, wherein the evaluation unit evaluates a degree of habituation of the first worker or the second worker based on whether a second change observed in the electroencephalogram data of the first worker or the electroencephalogram data of the second worker corresponds to a first pattern in which the second change is fixed to a state after the first change, a second pattern in which the second change is restored with inertia to a state before the stimulation, or a third pattern in which the second change returns to a state before the stimulation. acquiring electroencephalogram data of a first worker to be evaluated for each task related to plant operation and electroencephalogram data of a second worker to be used as an evaluation criterion for the first worker;
evaluating the first worker based on a comparison result between the electroencephalogram data of the first worker and the electroencephalogram data of the second worker;
The computer executes the process ,
The evaluation process includes a method for evaluating the first worker based on a comparison result between a first time difference from when a first change is observed in the electroencephalogram data of the first worker to when a second change is observed, and a second time difference from when the first change is observed in the electroencephalogram data of the second worker to when the second change is observed . acquiring electroencephalogram data of a first worker to be evaluated for each task related to plant operation and electroencephalogram data of a second worker to be used as an evaluation criterion for the first worker;
evaluating the first worker based on a comparison result between the electroencephalogram data of the first worker and the electroencephalogram data of the second worker;
The process is executed by a computer ,
The evaluation process evaluates the first worker based on a comparison result between a first time difference from when a first change is observed in the electroencephalogram data of the first worker to when a second change is observed, and a second time difference from when the first change is observed in the electroencephalogram data of the second worker to when the second change is observed .

Images