JP7168825B2 - Estimation device, estimation method and estimation program - Google Patents

Description

The present invention relates to an estimating device, an estimating method, and an estimating program for estimating work quality when a worker performs a predetermined work.

In recent years, in promoting work style reform, work efficiency is desired. In particular, when a person performs a task, it is desired to be able to easily determine whether he/she is apt to perform the task or whether he/she can perform the task without any problems in his current physical condition. Patent Literature 1 describes a technique for determining drowsiness of a subject based on the power spectrum density analyzed from the heartbeat waveform of the subject and the total power of autonomic nerves. By applying the technique described in Patent Document 1 to a worker before performing the work, it is possible to determine whether the worker can properly perform the work.

Japanese Patent No. 6135054

By the way, drowsiness is only one of the causes of reduced work efficiency or deterioration of work quality. may occur. Therefore, with the technique described in Patent Literature 1, it was difficult to appropriately estimate the work quality.

Therefore, the present invention has been made in view of these points, and it is an object of the present invention to provide an estimation device, an estimation method, and an estimation program capable of appropriately estimating the work quality of a worker.

An estimating device according to a first aspect of the present invention includes an acquisition unit that acquires biometric information of a worker; and an output unit configured to output information on the work quality of the worker estimated by the estimation unit.

The estimating unit calculates the work quality of the worker based on the relationship between the biological information during standby acquired by the acquisition unit during a standby period in which the worker does not perform the predetermined work and the biological information during work. can be estimated.

The estimating device sets the start time of the work period to the end time of the waiting period, and sets the waiting period, which is a period between the end time and a time point a predetermined period before the end time, and the work period. The estimating unit includes the biological information during standby acquired by the acquiring unit during the standby period detected by the detecting unit and the biological information during the working period detected by the detecting unit. The work quality of the worker may be estimated based on the relationship with the biometric information during work acquired by the acquisition unit.

The estimating device further includes a specifying unit that specifies a stress index indicating a stress state of the worker based on the biological information acquired by the acquiring unit, and the estimating unit comprises: The work quality of the worker may be estimated based on the work stress index specified based on the biological information.

The estimating unit includes a standby stress index specified by the specifying unit based on the standby biological information acquired by the acquisition unit during a standby period in which the worker does not perform the predetermined work, and the work stress The work quality of the worker may be estimated based on the relationship with the index.

The estimating device further includes an identifying unit that identifies an activity index indicating an activity state of the worker based on the biometric information acquired by the acquiring unit, and the estimating unit includes: The work quality of the worker may be estimated based on the during-work activity index identified based on the biological information.

The specifying unit specifies a stress index indicating the stress state of the worker based on the biological information acquired by the acquiring unit, and the estimating unit specifies the specifying unit based on the biometric information at work. It may be estimated that the work quality of the worker is low when a numerical value indicated by the stress index during work exceeds a threshold value corresponding to the stress index during work.

The identifying unit identifies an activity index indicating the activity state of the worker based on the biological information acquired by the acquiring unit, and the estimating unit identifies the activity indicator based on the biometric information at work. It may be estimated that the work quality of the worker is low when the numerical value indicated by the activity index during work does not exceed the threshold value corresponding to the activity index during work.

The identifying unit identifies a stress index indicating the stress state of the worker and an activity index indicating the activity state of the worker based on the biological information acquired by the acquiring unit, and the estimating unit comprises: When the numerical value indicated by the work stress index specified by the specifying unit based on the work biomedical information does not exceed the threshold value corresponding to the work stress indicator, the specifying unit determines based on the work biomedical information It may be estimated that the work quality of the worker is high when a numerical value indicated by the identified activity indicator during work exceeds a threshold value corresponding to the activity indicator.

The specifying unit specifies a stress index indicating the stress state of the worker based on the biological information acquired by the acquiring unit, and the estimating unit specifies the specifying unit based on the biometric information at work. The standby stress index identified by the identification unit based on the standby biometric information acquired by the acquisition unit during a standby period in which the worker is not performing the predetermined work, from the numerical value indicated by the work stress index. If the stress difference value obtained by subtracting the indicated value does not exceed the threshold value corresponding to the stress difference value, it may be estimated that the work quality of the worker is low.

The identifying unit identifies an activity index indicating the activity state of the worker based on the biological information obtained by the obtaining unit, and the estimating unit determines whether the stress difference value corresponds to the stress difference value. When the threshold value is exceeded and the numerical value indicated by the activity indicator during work specified by the specifying unit based on the biometric information during work exceeds the threshold corresponding to the activity indicator during work, the work quality of the worker is improved. can be estimated to be high.

The estimation device may further include a threshold setting unit that sets the threshold.
The threshold setting unit determines the standby time specified based on the standby biological information acquired by the acquisition unit during a standby period in which the model worker whose work ability in the predetermined work is known does not perform the predetermined work. and an index during work specified based on the biological information during work of the model worker.

The threshold setting unit is specified based on the biological information of each of the plurality of workers included in the group having relatively high work quality in the predetermined work among the plurality of groups including the plurality of workers. The threshold may be set based on multiple indices.
The acquisition unit may acquire, as the biometric information, heartbeat data indicating temporal changes in the heartbeat of the worker.

An estimation method according to a second aspect of the present invention includes a step of acquiring biometric information of a worker, performed by a computer, and biometric information at work acquired during a work period in which the worker is performing a predetermined work. and outputting information about the estimated work quality.

An estimation program according to a third aspect of the present invention comprises a computer, an acquisition unit that acquires biometric information of a worker, based on biometric information during work acquired during a work period in which the worker is performing a predetermined work, function as an estimating unit for estimating the work quality of the worker and an output unit for outputting information on the work quality of the worker estimated by the estimating unit.

ADVANTAGE OF THE INVENTION According to this invention, it is effective in the ability to estimate a worker's work quality appropriately.

It is a figure for demonstrating the outline|summary of an estimation apparatus. It is a figure which shows the structure of the estimation apparatus which concerns on 1st Embodiment. It is a figure which represented the cardiac-beats waveform typically. 7 is a flow chart showing a flow of processing for estimating work quality of a worker by an estimation unit according to the first embodiment; 4 is a flow chart showing the flow of processing performed by an estimating device; FIG. 4 is a diagram schematically showing the work situation during working hours; It is a figure which shows the structure of the estimation apparatus which concerns on 2nd Embodiment. 9 is a flowchart showing a flow of processing for estimating work quality of a worker by an estimation unit according to the second embodiment;

<First Embodiment>
[Overview of estimation device 1]
The inventors of the present application have found that there is a relationship between the problematic behavior of the worker while performing the predetermined work and the state of the worker when performing the predetermined work. The predetermined work is a work that is performed repeatedly, such as a call center operator dealing with a customer or manufacturing a product in a factory. Problem behaviors are behaviors that lower work quality, behaviors that should not be performed in a given work, or the like. The worker's state is the worker's stress state, the worker's activity state (fatigue state), or the like. Therefore, in the first embodiment, the work quality of the worker is estimated using biometric information of the worker performing the predetermined work, which indicates the state of the worker.

FIG. 1 is a diagram for explaining an overview of the estimation device 1. As shown in FIG. The estimation device 1 is a device for estimating work quality when a worker performs a predetermined work, and is, for example, a computer. A measuring device (not shown) for measuring biological information is attached to the worker.

First, the estimation device 1 acquires the biological information of the worker from the measuring device attached to the body of the worker ((1) in FIG. 1). The estimating device 1, for example, in a production environment, which is an environment in which the worker is actually working, or a simulated environment corresponding to the production environment, the period during which the worker has performed a predetermined work several times (for example, three times). acquire the biological information measured by the measuring equipment.

The estimation device 1 estimates the work quality of the worker based on the acquired biological information, and outputs information about the estimated work quality of the worker ((2) and (3) in FIG. 1). In this way, the estimation device 1 can easily estimate the work quality of the worker by using the worker's biological information representing the worker's condition.
The configuration of the estimation device 1 will be described below.

[Configuration of estimation device 1 according to first embodiment]
FIG. 2 is a diagram showing the configuration of the estimation device 1 according to the first embodiment. The estimation device 1 has a communication unit 11 , a storage unit 12 and a control unit 13 .
The communication unit 11 is an interface for connecting to a network, and includes, for example, a LAN controller.

The storage unit 12 is a storage medium such as a ROM (Read Only Memory), a RAM (Random Access Memory), and a hard disk. The storage unit 12 stores programs executed by the control unit 13 .

The control unit 13 is, for example, a CPU (Central Processing Unit). The control unit 13 functions as an acquisition unit 131 , a specification unit 132 , a threshold value setting unit 133 , an estimation unit 134 and an output unit 135 by executing programs stored in the storage unit 12 .

The acquisition unit 131 acquires the biological information of the worker from a measuring device attached to the body of the worker. For example, the acquisition unit 131 acquires, as biological information, heartbeat data indicating changes in the heartbeat of the worker over time from the measuring device.

The heartbeat data is, for example, time-series data of R-wave intervals (hereinafter referred to as RR intervals) generated based on time-series data representing a heartbeat waveform (electrocardiographic waveform). FIG. 3 is a diagram schematically showing a heartbeat waveform. The heartbeat waveform includes a waveform representing R waves, and the interval between R waves included in one heartbeat can be specified based on the heartbeat waveform. As shown in FIG. 3, the RR interval is the interval from the R wave included in the nth heartbeat to the R wave included in the n+1th heartbeat. The acquiring unit 131 acquires heartbeat data generated based on a heartbeat waveform in the measuring device from the measuring device. The acquiring unit 131 acquires heartbeat data, for example, at predetermined intervals (for example, two seconds). Note that the acquiring unit 131 may acquire heartbeat data by acquiring time-series data representing a heartbeat waveform from a measuring device and analyzing the time-series data.

Returning to FIG. 2 , the specifying unit 132 specifies a stress index indicating the stress state of the worker based on the biological information acquired by the acquiring unit 131 . The stress index is, for example, the autonomic nervous system indicating the ratio of the low frequency component (hereinafter referred to as LF (Low Frequency)) and the high frequency component (hereinafter referred to as HF (Hi Frequency)) of the RR interval variation indicated by the heartbeat data. balance (hereinafter referred to as LF/HF ratio). LF is a frequency component from 0.04 Hz to 0.15 Hz among a plurality of frequency components included in heartbeat data. HF is a frequency component from 0.15 Hz to 0.4 Hz among a plurality of frequency components included in heartbeat data.

The specifying unit 132 extracts LF and HF based on the heartbeat data acquired by the acquiring unit 131, for example, at predetermined intervals (for example, two seconds). The identifying unit 132 calculates the LF/HF ratio based on the extracted LF and HF. Then, the identifying unit 132 identifies the stress index by aggregating (averaging) the LF/HF ratios calculated at predetermined intervals.

The identifying unit 132 also identifies an activity index indicating the activity state of the worker based on the biometric information acquired by the acquiring unit 131 . The activity index is, for example, total power (hereinafter referred to as TP (Total Power)) calculated by summing frequency components from 0 Hz to 0.4 Hz among multiple frequency components included in the heartbeat data. The identifying unit 132 identifies the TP from the LF and HF extracted at predetermined intervals, for example. Then, the identifying unit 132 identifies an activity index by aggregating (averaging) the identified TPs at predetermined intervals.

The identifying unit 132 according to the first embodiment calculates the stress index during work and the activity index during work based on the biological information during work acquired by the acquisition unit 131 during the work period in which the worker is performing a predetermined work. Identify.

The threshold setting unit 133 sets a threshold. Specifically, the threshold setting unit 133 sets a threshold corresponding to the type of index identified by the identifying unit 132 (stress index during work and activity index during work). The threshold setting unit 133 may set a predetermined threshold.

Further, the threshold setting unit 133 may set the threshold based on the model index specified based on the biological information during work of the model worker whose work efficiency in the predetermined work is known. The model index includes a stress index during work and an activity index during work corresponding to the model worker. For example, when the model worker performs a predetermined work, the threshold setting unit 133 sets the model index specified based on the biometric information acquired when the work efficiency is good and the biometric information acquired when the work efficiency is low. Thresholds may be set based on the model metrics identified based on the information. By doing so, the threshold setting unit 133 can appropriately set the threshold.

Further, the threshold value setting unit 133 sets the plurality of workers identified based on the biometric information of each of the plurality of workers included in the group in which the work quality in the predetermined work is relatively high among the plurality of groups including the plurality of workers. A threshold may be set based on the index of The groups in this case are, for example, groups clustered based on the K-means method. The threshold setting unit 133 may set the threshold based on, for example, a statistical value (for example, average value) calculated based on a plurality of indices. By doing so, the threshold setting unit 133 can set a more suitable threshold than when setting the threshold based on one model worker.

Also, the threshold setting unit 133 may set the threshold based on the type of predetermined work. In addition, the threshold setting unit 133 may set, as a threshold, a difference value between a numerical value indicated by the worker's biological information acquired during working hours and a numerical value indicated by the worker's biological information acquired during non-working hours.

The estimation unit 134 estimates the work quality of the worker based on the biological information during work. The work-time biometric information is biometric information acquired by the acquiring unit 131 during a work period in which the worker is performing a predetermined work.

Details of the process of estimating the work quality of the worker by the estimation unit 134 according to the first embodiment will be described with reference to FIG. 4 . FIG. 4 is a flowchart showing the flow of processing for estimating the work quality of the worker by the estimation unit 134 according to the first embodiment.

First, the estimating unit 134 calculates the worker Estimate the work quality of Specifically, the estimation unit 134 determines whether or not the numerical value indicated by the work stress index exceeds the first threshold set by the threshold setting unit 133 (S1). The first threshold according to the first embodiment is a threshold corresponding to the work stress index.

When determining that the numerical value indicated by the work stress index exceeds the first threshold (YES in S1), the estimation unit 134 estimates that the worker's work quality is low (S2). If the estimation unit 134 determines that the numerical value indicated by the stress index during work does not exceed the first threshold (NO in S1), the process proceeds to S3.

Subsequently, the estimating unit 134 determines whether the worker is performing the predetermined work based on the at-work activity index identified by the identifying unit 132 based on the at-work biometric information acquired by the acquiring unit 131 during the work period. Estimate the work quality of a person. Specifically, the estimation unit 134 determines whether or not the numerical value indicated by the activity index during work exceeds the second threshold (S3). The second threshold is a threshold corresponding to the at-work activity index.

When the estimation unit 134 determines that the numerical value indicated by the activity index during work does not exceed the second threshold value (NO in S3), the estimation unit 134 estimates that the worker's work quality is low (S2). On the other hand, when the numerical value indicated by the stress index during work does not exceed the first threshold (NO in S1), estimating unit 134 determines when the numerical value indicated by the activity index during work exceeds the second threshold (NO in S3). If YES), it is estimated that the work quality of the worker is high (S4). In this manner, the estimation unit 134 can appropriately estimate the work quality by estimating the work quality of the worker based on the worker's state while performing the predetermined work.

The output unit 135 outputs information about the work quality of the worker estimated by the estimation unit 134 . Specifically, the output unit 135 outputs information corresponding to the estimation result estimated by the estimation unit 134 . For example, when the estimation unit 134 estimates that the work quality is high, the output unit 135 may output to the display unit (not shown) that the worker is suitable for the predetermined work.

[Processing of estimation device 1]
Next, the flow of processing performed by the estimation device 1 will be described. FIG. 5 is a flow chart showing the flow of processing performed by the estimating device 1. As shown in FIG. This flowchart starts when the acquisition unit 131 acquires the biological information of the worker from the measuring device attached to the body of the worker (S11).

When the obtaining unit 131 obtains the biological information, the identifying unit 132 identifies the stress index and the activity index based on the obtained biological information (S12). When the identifying unit 132 identifies the stress index and the activity index, the threshold setting unit 133 sets a threshold (first threshold) corresponding to the stress index and a threshold (second threshold) corresponding to the activity index (S13). .

The estimating unit 134 estimates the work quality of the worker based on the stress index and the activity index specified by the specifying unit 132 and the threshold set by the threshold setting unit 133 (S14). Specifically, the estimation unit 134 estimates the work quality of the worker by performing the process of estimating the work quality of the worker by the estimation unit 134 shown in FIG. The output unit 135 outputs information about the work quality of the worker estimated by the estimation unit 134 (S15).

[Effects of the first embodiment]
As described above, the estimation device 1 estimates the work quality of the worker based on the biological information during work acquired during the work period, and outputs information about the estimated work quality of the worker. By doing so, the estimation device 1 can estimate the work quality of the worker based on the state of the worker when performing the predetermined work. As a result, the estimation device 1 can appropriately estimate the work quality of the worker.

In addition, the estimating apparatus 1 uses the heartbeat data as the biological information, so that the worker can perform a predetermined work without invading the worker or making the worker rest and close his/her eyes. work quality can be estimated. In addition, since the estimation device 1 can perform the process of estimating the work quality of the worker in a simulated environment such as a training environment, the process of estimating the work quality of the worker in the actual environment can be performed more efficiently than when performing the process of estimating the work quality of the worker. Cost can be reduced. In addition, the estimating device 1 estimates the work quality of the worker based on the biological information, so that the person who has experience of the predetermined work observes the worker performing the predetermined work and analyzes the presence or absence of problematic behavior. can save you the trouble of doing it. In addition, the person in charge of personnel affairs can analyze the aptitude of the worker by using the result of the estimation device 1 estimating the work quality of the worker for each type of predetermined work, and use it to determine the assignment.

<Second embodiment>
[Estimate work quality based on the relationship between biometric information during standby and biometric information during work]
Next, the estimation device 1 according to the second embodiment will be explained. The inventors of the present application have found that there is a relationship between the worker's state when the predetermined work is being performed and the worker's state when the predetermined work is not being performed, and the problem behavior. "When the prescribed work is not being performed" is, for example, when a call center operator at work is not responding to a customer, or when a factory worker at work is taking a break.

Therefore, in the second embodiment, the work quality of the worker is evaluated by using the biometric information when the worker is not performing the predetermined work and the biometric information when the worker is performing the predetermined work. presume. The parts different from the first embodiment will be described below.

FIG. 6 is a diagram schematically showing work situations during working periods. As shown in FIG. 6, the period during which the worker is working is continuous with a waiting period (first waiting period, second waiting period, etc.) during which the worker does not perform a predetermined work, and a waiting period. , a work period (a first work period, a second work period, etc.) during which the worker is performing a predetermined work.

The estimating device 1 according to the second embodiment determines the worker Estimate work quality. In the example illustrated in FIG. 6 , the estimating apparatus 1 acquires biometric information during standby acquired by the acquisition unit 131 during the first standby period, and The work quality of the worker is estimated based on the relationship with the biological information during work.

[Configuration of estimation device 1 according to second embodiment]
FIG. 7 is a diagram showing the configuration of the estimation device 1 according to the second embodiment. The control unit 13 according to the second embodiment further functions as a detection unit 136 by executing programs stored in the storage unit 12 .

The detection unit 136 detects the standby period and the work period. For example, when detecting a waiting period and a work period in a call center, the detection unit 136 first receives a work period from a CTI (Computer Telephony Integration) server managed by the call center via the communication unit 11 at predetermined intervals. Acquire call information indicating the call status of the operator whose quality is to be estimated. The call information may be information indicating whether or not there is a call, or voices of the operator and the customer. If the call information is the voices of the operator and the customer, the detection unit 136 may analyze the call status based on the unique voice patterns that occur when the call is received and disconnected in the voice of the customer. Call status may be analyzed based on volume or volume at the customer's end.

When the acquired call information indicates that a call is in progress and the previously acquired call information indicates that a call is not in progress, the detection unit 136 detects the time when the call information indicating that the call is in progress is acquired. It is detected as the end of the waiting period and the start of the work period. Further, when the acquired call information indicates that a call is not in progress, and the call information acquired immediately before indicates that a call is in progress, the detection unit 136 acquires the call information indicating that the call is not in progress. are detected as the end of the work period and the start of the waiting period.

Further, for example, when detecting a standby period and a work period in a factory, the detection unit 136 first detects a worker whose work quality is to be estimated in the factory via the communication unit 11 at predetermined intervals. acquires a captured image showing the work situation from a camera that captures an image of the work area where the worker works. For example, the detection unit 136 may analyze the work situation based on whether the worker is at a predetermined position in the acquired captured image, or may analyze the work situation based on whether the production line is in operation. may be analyzed.

When the captured image acquired indicates that work is being performed and the captured image acquired immediately before indicates that work is not being performed, the detection unit 136 determines the time at which the captured image indicating that work is being performed is acquired. It is detected as the end of the waiting period and the start of the work period. Further, when the captured image acquired indicates that work is not being performed and the captured image acquired immediately before indicates that work is being performed, the detection unit 136 obtains the captured image indicating that work is not being performed. are detected as the end of the work period and the start of the waiting period. In this way, the detection unit 136 detects the standby period and the work period by detecting the start time and the end time of each of the work period and the standby period.

Here, the inventors of the present application have found that the accuracy of estimating the work quality of the worker by the estimation unit 134 improves when the waiting period is short rather than when the waiting period is long. Therefore, the detection unit 136 sets the start time of the work period to the end time of the standby period, and the standby period that is the period between the end time and the time point before the end time by a predetermined period (for example, 1 minute), A work period may be detected. By doing so, the detection unit 136 can improve the accuracy of estimating the work quality of the worker.

The identifying unit 132 according to the second embodiment further identifies the standby stress index based on the standby biological information acquired by the acquisition unit 131 during the standby period in which the worker does not perform the predetermined work.

The threshold value setting unit 133 according to the second embodiment stores the index during standby specified based on the biometric information during standby of the model worker whose work ability in a predetermined work is known, and the biometric during work of the model worker. The thresholds may be set based on the information-based working indicators and/or. For example, standby biometric information is biometric information acquired by the acquiring unit 131 during a standby period in which the worker is not performing a predetermined work. The threshold setting unit 133 may set the threshold based on the difference value between the numerical value indicated by the indicator during standby and the numerical value indicated by the indicator during operation.

The estimation unit 134 estimates the work quality of the worker based on the relationship between the standby biometric information acquired by the acquisition unit 131 during the standby period and the work biometric information acquired by the acquisition unit 131 during the work period. Specifically, the estimating unit 134 obtains biometric information during standby acquired by the acquisition unit 131 during the standby period detected by the detection unit 136 and biometric information during work acquired by the acquisition unit 131 during the work period detected by the detection unit 136. Estimate the worker's work quality based on the relationship between

A flow of processing in which the estimation unit 134 according to the second embodiment estimates the work quality of the worker will be described with reference to FIG. FIG. 8 is a flow chart showing the flow of processing for estimating the worker's work quality by the estimation unit 134 according to the second embodiment.

First, the estimating unit 134 determines whether the waiting stress index specified by the specifying unit 132 based on the waiting biological information acquired by the acquiring unit 131 during the waiting period in which the worker is not performing a predetermined work, The work quality of the worker is estimated based on the relationship with the during-work stress index specified based on the during-work biological information acquired by the acquisition unit 131 during the work period during which the work is performed. Specifically, the estimation unit 134 determines whether or not a stress difference value obtained by subtracting the numerical value indicated by the stress index during standby from the numerical value indicated by the stress index during work exceeds a first threshold (S21). A first threshold according to the second embodiment is a threshold corresponding to the stress difference value.

When determining that the stress difference value does not exceed the first threshold value (NO in S21), the estimating unit 134 estimates that the worker's work quality is low (S22). When the estimation unit 134 determines that the stress difference value exceeds the first threshold (YES in S21), the process proceeds to S23.

Subsequently, the estimation unit 134 estimates the work quality of the worker based on the during-work activity index. Specifically, the estimation unit 134 determines whether or not the numerical value indicated by the activity index during work exceeds the second threshold (S23).

When determining that the numerical value indicated by the activity index during work does not exceed the second threshold (NO in S23), the estimation unit 134 estimates that the worker's work quality is low (S22). On the other hand, the estimation unit 134 estimates that the work quality of the worker is high when the stress difference value exceeds the threshold value corresponding to the stress difference value and the numerical value indicated by the activity index during work exceeds the second threshold value. (S24). In this manner, the estimation unit 134 estimates the work quality of the worker based on the biometric information during work.

[Effects of Second Embodiment]
As described above, the estimation device 1 estimates the work quality of the worker based on the relationship between the standby biometric information acquired during the standby period and the work biometric information acquired during the work period. Prints information about work quality. By doing so, the estimation device 1 can estimate the work quality of the worker in consideration of changes in the state of the worker during the standby period and the work period. As a result, the estimation device 1 can improve the estimation accuracy of the worker's work quality.

[Modification]
In the above description, an example in which the estimation device 1 estimates the work quality of the worker has been described, but the present invention is not limited to this. For example, the estimation device 1 may estimate work quality using a learning model that outputs quality information indicating work quality by inputting biometric information. The learning model is, for example, a learning model generated by SVM (Support Vector Machine) or DNN (Deep Neural Network).

For example, the estimating device 1 first performs machine learning based on teacher data that combines quality information indicating work quality in past quality inspections and information based on the biometric information of the worker when the quality inspection was performed. Generate a learning model by performing The information based on biometric information is, for example, a statistical value (eg, average value, standard deviation, or the like) of an index (stress index, activity index) calculated based on biometric information during standby and biometric information during work.

Then, in the quality inspection process, the estimating device 1 estimates the work quality using the quality information output by inputting the biometric information of the worker into the learning model. By doing so, the estimating device 1 accurately and easily performs the quality inspection of the worker based on the learning model in which the relationship between the information based on the biological information and the work quality is appropriately reflected by machine learning. It can be carried out.

Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments, and various modifications and changes are possible within the scope of the gist thereof. be. For example, in the process of estimating the work quality of the worker shown in FIG. A determination process (determination process of S1 shown in FIG. 4) may be performed. In this case, if the estimation unit 134 determines that the numerical value indicated by the work stress index exceeds the threshold value corresponding to the work stress index, the estimation unit 134 estimates that the worker's work quality is low, and does not exceed the threshold corresponding to the work stress index, the process may proceed to S21 shown in FIG.

Further, for example, the specific embodiment of distributing/integrating the device is not limited to the above-described embodiments, and all or part of it is functionally or physically distributed/integrated in arbitrary units. can do. In addition, new embodiments resulting from arbitrary combinations of multiple embodiments are also included in the embodiments of the present invention. The effect of the new embodiment caused by the combination has the effect of the original embodiment.

1 estimation device 11 communication unit 12 storage unit 13 control unit 131 acquisition unit 132 identification unit 133 threshold setting unit 134 estimation unit 135 output unit 136 detection unit

Claims (17)

The start time of the work period during which the worker is performing the predetermined work is defined as the end time of the waiting period during which the worker is not performing the predetermined work, and the end time and the time before the predetermined period from the end time. A detection unit that detects the standby period, which is the period between, and the work period;
Said an acquisition unit that acquires biometric information of a worker;
Wait-time biological information acquired by the acquisition unit during the standby period detected by the detection unit and biometric information detected by the detection unit Biometric information during work acquired by the acquisition unit during the work periodrelationship withan estimation unit that estimates the work quality of the worker based on
an output unit that outputs information about the work quality of the worker estimated by the estimation unit;
An estimating device having an acquisition unit that acquires biometric information of a worker;
Based on the work-time biological information acquired by the acquisition unit during a work period in which the worker is performing a predetermined work, a work-time stress index indicating the stress state of the worker and an activity state of the worker are indicated. an identifying unit that identifies an at-work activity indicator;
The work quality of the worker is estimated based on the work stress index, and if the value indicated by the work activity index does not exceed a threshold value corresponding to the work activity index, the work quality of the worker is low. an estimating unit that estimates that
an output unit that outputs information about the work quality of the worker estimated by the estimation unit;
An estimating device having an acquisition unit that acquires biometric information of a worker;
Based on the work-time biological information acquired by the acquisition unit during a work period in which the worker is performing a predetermined work, a work-time stress index indicating the stress state of the worker and an activity state of the worker are indicated. an identifying unit that identifies an at-work activity indicator;
When the numerical value indicated by the stress index during work does not exceed the threshold corresponding to the stress index during work, and the numerical value indicated by the activity index during work exceeds the threshold corresponding to the activity index during work, the work an estimation unit that estimates that the work quality of the person is high;
an output unit that outputs information about the work quality of the worker estimated by the estimation unit;
An estimating device having an acquisition unit that acquires biometric information of a worker;
A work stress index indicating a stress state of the worker during work is specified based on the work biological information acquired by the acquisition unit during a work period in which the worker is performing a predetermined work, an identifying unit that identifies a standby stress index indicating a stress state of the worker during standby based on the standby biological information acquired by the acquisition unit during a standby period in which the predetermined work is not performed;
If the stress difference value obtained by subtracting the value indicated by the stress index during standby from the value indicated by the stress index during work does not exceed a threshold value corresponding to the stress difference value, it is estimated that the work quality of the worker is low. an estimation unit;
an output unit that outputs information about the work quality of the worker estimated by the estimation unit;
An estimating device having The estimating unit includes a standby stress index specified by the specifying unit based on the standby biological information acquired by the acquisition unit during a standby period in which the worker does not perform the predetermined work, and the work stress estimating the work quality of the worker based on the relationship with the index;
The estimation device according to claim 2 or 3 . further comprising an identification unit that identifies an activity index indicating an activity state of the worker based on the biometric information acquired by the acquisition unit;
The estimating unit estimates the work quality of the worker based on the at-work activity index identified by the identifying unit based on the at-work biological information.
The estimating device according to claim 1. The specifying unit specifies a stress index indicating a stress state of the worker based on the biological information acquired by the acquiring unit,
The estimating unit determines that the work quality of the worker is low when the numerical value indicated by the stress index during work identified by the identifying unit based on the biological information during work exceeds a threshold value corresponding to the stress index during work. presume that
The estimating device according to any one of claims 2 to 5 . The identifying unit identifies an activity index indicating an activity state of the worker based on the biometric information acquired by the acquiring unit,
When the stress difference value exceeds a threshold value corresponding to the stress difference value, the estimation unit determines that the numerical value indicated by the at-work activity index identified by the identification unit based on the at-work biological information is estimating that the worker's work quality is high if the threshold corresponding to the activity index is exceeded;
The estimation device according to claim 4 . further comprising a threshold setting unit that sets the threshold;
An estimating device according to any one of claims 2 to 5, 7 and 8 . The threshold setting unit determines the standby time specified based on the standby biological information acquired by the acquisition unit during a standby period in which the model worker whose work ability in the predetermined work is known does not perform the predetermined work. setting the threshold value based on at least one of the indicator of and the indicator during work specified based on the biometric information during work of the model worker;
The estimation device according to claim 9 . The threshold setting unit is specified based on the biological information of each of the plurality of workers included in the group having relatively high work quality in the predetermined work among the plurality of groups including the plurality of workers. setting the threshold based on a plurality of indicators;
The estimation device according to claim 9 . The acquisition unit acquires, as the biometric information, heartbeat data indicating changes in the heartbeat of the worker over time.
An estimating device according to any one of claims 1 to 11 . the computer runs
The start time of the work period during which the worker is performing the predetermined work is defined as the end time of the waiting period during which the worker is not performing the predetermined work, and the end time and the predetermined time before the end time. detecting the waiting period and the working period, which is the period between
Said a step of obtaining biometric information of a worker;
The biometric information during standby acquired during the detected standby period, and the detected biometric information Work-time biometric information acquired during the work periodrelationship withestimating the worker's work quality based on
outputting information about the estimated work quality;
An estimation method with the computer,
The start time of the work period during which the worker is performing the predetermined work is defined as the end time of the waiting period during which the worker is not performing the predetermined work, and the end time and the time before the predetermined period from the end time. A detection unit that detects the standby period, which is the period between
an acquisition unit that acquires the biometric information of the worker;
The biometric information during standby acquired during the standby period detected by the detection unit and the biometric information detected by the detection unit Work-time biometric information acquired during the work periodrelationship withan estimation unit that estimates the work quality of the worker based on
an output unit that outputs information about the work quality of the worker estimated by the estimation unit;
An estimation program that acts as a the computer,
an acquisition unit that acquires the biometric information of the worker;
Based on the work-time biological information acquired by the acquisition unit during a work period in which the worker is performing a predetermined work, a work-time stress index indicating the stress state of the worker and an activity state of the worker are indicated. an identification unit that identifies an activity index during work;
The work quality of the worker is estimated based on the work stress index, and if the value indicated by the work activity index does not exceed a threshold value corresponding to the work activity index, the work quality of the worker is low. and an estimator that estimates
an output unit that outputs information about the work quality of the worker estimated by the estimation unit;
An estimation program that acts as a the computer,
an acquisition unit that acquires the biometric information of the worker;
Based on the work-time biological information acquired by the acquisition unit during a work period in which the worker is performing a predetermined work, a work-time stress index indicating the stress state of the worker and an activity state of the worker are indicated. an identification unit that identifies the at-work activity indicator;
When the numerical value indicated by the stress index during work does not exceed the threshold corresponding to the stress index during work and the numerical value indicated by the activity index during work exceeds the threshold corresponding to the activity index during work, the work an estimation unit that estimates that the work quality of the person is high, and
an output unit that outputs information about the work quality of the worker estimated by the estimation unit;
An estimation program that acts as a the computer,
an acquisition unit that acquires the biometric information of the worker;
A work stress index indicating a stress state of the worker during work is specified based on the work biological information acquired by the acquisition unit during a work period in which the worker is performing a predetermined work, an identifying unit that identifies a standby stress index indicating a stress state of the worker during standby based on the standby biological information acquired by the acquisition unit during a standby period in which the predetermined work is not performed;
If a stress difference value obtained by subtracting the value indicated by the stress index during standby from the value indicated by the stress index during work does not exceed a threshold value corresponding to the stress difference value, it is estimated that the work quality of the worker is low. an estimator, and
an output unit that outputs information about the work quality of the worker estimated by the estimation unit;
An estimation program that acts as a

Images