Evaluation device, learning device, evaluation system, evaluation method, learning method, and computer program

Abstract

This technology makes it easy to evaluate the skill level of workers. [Solution] The evaluation device includes a control unit. The control unit acquires feature quantities indicating eye movements based on information detected by a sensor that acquires information on the eye movements of a person to be evaluated while performing a predetermined task, and evaluates the quality of the person's predetermined task based on the acquired feature quantities. The feature quantities include at least one of the following: drift, microsaccades, saccades, smooth tracking eye movements, convergence / divergence eye movements, and blinking.

Description

Technical Field

[0001] The present invention relates to an evaluation device, a learning device, an evaluation system, an evaluation method, a learning method, and a computer program.

Background Art

[0002] There is a system that can quantitatively evaluate the performance of plant operators (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the above-described conventional system, various types of performance data of the operator are acquired and used for evaluation. Therefore, various sensors and devices for acquiring those performance data had to be prepared. In addition, it was necessary to select in advance words and parameters for use in evaluation from procedure manual data and the like. Thus, in the prior art, the preparation for evaluating an operator who performs a predetermined task such as a plant operator was complicated.

[0005] In view of the above circumstances, the present invention provides a technique that enables easy evaluation of work performed by an operator.

Means for Solving the Problems

[0006] One aspect of the present invention is an evaluation device comprising a control unit that acquires feature quantities indicating eye movements based on information detected by a sensor that acquires information regarding the eye movements of a person to be evaluated while the person is performing a predetermined task, and that evaluates the quality of the predetermined task performed by the person based on the acquired feature quantities, wherein the feature quantities include at least one of the following: drift, microsaccades, saccades, smooth tracking eye movements, convergence and divergence eye movements, and blinking.

[0007] One aspect of the present invention is a learning device comprising: a learning unit that learns a trained model which outputs an evaluation of the quality of the predetermined work of a person to be judged, by performing a learning process using a combination of feature quantities indicating the movement of the eyeballs of a person when they are performing a predetermined task and the quality of the predetermined task performed by the person as training data, and newly inputting feature quantities indicating the movement of the eyeballs obtained based on information detected by a sensor that acquires information on the movement of the eyeballs of a person to be judged when they are performing a predetermined task, wherein the feature quantities include at least one feature quantity from among drift, microsaccades, saccades, smooth tracking eye movements, convergence and divergence eye movements, and blinking.

[0008] One aspect of the present invention is an evaluation system comprising: a learning unit that learns a trained model by performing a learning process using a combination of feature quantities indicating the movement of the eyeballs of a person when performing a predetermined task and the quality of the person's predetermined task as training data, thereby taking the feature quantities indicating the movement of the eyeballs of a person when performing a predetermined task as new input and outputting an evaluation of the quality of the person's predetermined task based on the input feature quantities; and a control unit that acquires feature quantities indicating the movement of the eyeballs of a person to be judged based on information detected by a sensor that acquires information regarding the movement of the eyeballs of a person to be judged when performing a predetermined task, and uses the acquired feature quantities and the trained model to evaluate the quality of the person's predetermined task, wherein the feature quantities include at least one of the following: drift, microsaccades, saccades, smooth tracking eye movements, convergence / divergence eye movements, and blinking.

[0009] One aspect of the present invention is an evaluation method comprising a control step of acquiring feature quantities indicating eye movements based on information detected by a sensor that acquires information on the eye movements of a person to be evaluated while the person is performing a predetermined task, and evaluating the quality of the predetermined task performed by the person based on the acquired feature quantities, wherein the feature quantities include at least one feature quantity from among drift, microsaccades, saccades, smooth tracking eye movements, convergence and divergence eye movements, and blinking.

[0010] One aspect of the present invention is a learning method comprising: a learning step of learning a trained model that outputs an evaluation of the quality of the predetermined work of a person to be judged, by using a combination of feature quantities indicating the movement of the eyeballs of a person when he is performing a predetermined task and the quality of the predetermined task performed by the person as training data, and taking newly input feature quantities indicating the movement of the eyeballs obtained based on information detected by a sensor that acquires information on the movement of the eyeballs of a person to be judged when he is performing a predetermined task, wherein the feature quantities include at least one feature quantity from among drift, microsaccades, saccades, smooth tracking eye movements, convergence and divergence eye movements, and blinking.

[0011] One aspect of the present invention is a computer program for causing a computer to function as the evaluation device described above.

[0012] One aspect of the present invention is a computer program for causing a computer to function as the learning device described above. [Effects of the Invention]

[0013] This invention makes it possible to easily evaluate the work performed by workers. [Brief explanation of the drawing]

[0014] [Figure 1] This is a schematic block diagram showing the system configuration of an evaluation system according to an embodiment of the present invention. [Figure 2] This is a schematic block diagram showing an example of the functional configuration of a learning device according to the same embodiment. [Figure 3] A schematic block diagram showing an example of the functional configuration of the evaluation device according to the same embodiment. [Figure 4] This is a schematic block diagram showing an example of the functional configuration of a terminal device according to the same embodiment. [Figure 5] This flowchart shows an example of processing by the learning device according to the same embodiment. [Figure 6] This flowchart shows an example of processing by the evaluation device according to the same embodiment. [Figure 7] This figure shows a schematic example of the hardware configuration of the information processing device according to the same embodiment. [Figure 8] This figure shows a modified example of the evaluation apparatus according to the same embodiment. [Figure 9] This figure shows a modified example of the evaluation apparatus according to the same embodiment. [Modes for carrying out the invention]

[0015] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0016] FIG. 1 is a schematic block diagram showing the system configuration of an evaluation system 100 according to an embodiment of the present invention. The evaluation system 100 acquires information on the movement of the eyes of a person to be judged, such as a plant monitor or a worker who assembles in a factory, by a sensor, and based on a feature amount indicating the movement of the eyes obtained based on the information detected by the sensor, evaluates the quality of a predetermined operation of the person to be judged. Here, at least one of drift, microsaccade, saccade, smooth pursuit eye movement, convergence / divergence eye movement, and blinking is used as the feature amount. In this way, time-series information indicating the movement of the line of sight is detected using a sensor that detects the movement of the eyes, and the evaluation is performed using the feature amount obtained from the detected information, so that the quality of the work of the person to be judged can be easily evaluated. For example, if the feature amount indicating the movement of the eyes of the person to be judged is similar to the feature amount indicating the movement of the eyes of a skilled monitor or worker, the object being paid attention to during monitoring and the time of gazing at the monitoring object, that is, the tendency of how much attention is being paid, are the same, and it is predicted that the quality of the work is high. Hereinafter, a plant monitor, a worker who assembles in a factory, etc. are collectively referred to as a worker.

[0017] The evaluation system 100 includes a learning device 10, an evaluation device 20, a terminal device 30, and a measurement device 50. The learning device 10, the evaluation device 20, the terminal device 30, and the measurement device 50 may be communicably connected via a network 70. Also, the evaluation device 20, the terminal device 30, and the measurement device 50 are communicably connected via the network 70. The network 70 may be a network using wireless communication or a network using wired communication. The network 70 may be configured using, for example, the Internet or a local area network (LAN). The network 70 may be configured by combining a plurality of networks.

[0018] The measuring device 50 is a sensor that detects information related to the movement of a human eyeball. As the measuring device 50, any existing eyeball movement measuring device can be used. The measuring device 50 outputs measurement information indicating a time-series of measurement values obtained by measuring the movement of the eyeball. Based on the time-series measurement values of the eyeball movement, it is possible to calculate feature amounts indicating the movement of the eyeball, such as drift, microsaccades, saccades, smooth pursuit eye movement, convergence / divergence eye movement, and blinking. Drift is a slow eyeball movement that occurs continuously when the line of sight is fixed, microsaccades are fast and small eyeball movements that occur intermittently when the line of sight is fixed, saccades are fast and large eyeball movements that occur when moving the line of sight from one point to another, smooth pursuit eye movement is a smooth eyeball movement that occurs when tracking a moving object, convergence / divergence eye movement is an eyeball movement in which both eyes move in opposite directions when focusing on a nearby or distant object, and blinking is an opening and closing movement of the eyelids accompanied by the disappearance of the line of sight.

[0019] Figure 2 is a schematic block diagram showing a specific example of the functional configuration of the learning device 10. The learning device 10 is configured using an information processing device such as a personal computer or a server device. The learning device 10 includes a communication unit 11, a storage unit 12, and a control unit 13.

[0020] The communication unit 11 is a communication device. The communication unit 11 may be configured, for example, as a network interface. The communication unit 11 performs data communication with other devices via the network 70 according to the control of the control unit 13. The communication unit 11 may be a device that performs wireless communication or a device that performs wired communication.

[0021] The storage unit 12 is configured using a storage device such as a magnetic hard disk device or a semiconductor storage device. The storage unit 12 stores data used by the control unit 13. The storage unit 12 may function, for example, as a teacher data storage unit 121, a preprocessed teacher data storage unit 122, and a learned model storage unit 123.

[0022] The training data storage unit 121 stores training data used in the learning process executed in the learning device 10. The training data stored in the training data storage unit 121 includes measurement information and evaluation information of a person performing a predetermined task, such as assembly in a factory or patrolling a plant. The measurement information is, for example, information showing time-series measurements obtained using the measuring device 50. The evaluation information shows an evaluation of the quality of the predetermined task being performed while the eye movements were being measured. For example, the evaluation information may be information that expresses the worker's proficiency or the quality of the work in quantitative numerical values. Alternatively, the evaluation information may be information that shows the evaluation for each of one or more evaluation items.

[0023] The pre-processed training data storage unit 122 stores pre-processed training data. Pre-processed training data is training data that includes information obtained by performing pre-processing on the training data. For example, pre-processed training data is data to which features obtained based on the measurement information shown in the training data have been added. The features include one or more of the following: drift, microsaccades, saccades, smooth tracking eye movements, convergence / divergence eye movements, and blinks.

[0024] The trained model storage unit 123 stores the trained model obtained by a training process using the pre-processed training data stored in the pre-processed training data storage unit 122.

[0025] The control unit 13 is composed of a processor such as a CPU (Central Processing Unit) and memory (main memory). The control unit 13 functions as an information control unit 131, a pre-processing control unit 132, and a learning control unit 133 when the processor executes a program. Note that all or part of the functions of the control unit 13 may be implemented using hardware such as an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), or an FPGA (Field Programmable Gate Array). The above program may be recorded on a computer-readable recording medium. Computer-readable recording media include, for example, portable media such as flexible disks, magneto-optical disks, ROMs, CD-ROMs, and semiconductor memory devices (e.g., SSDs: Solid State Drives), as well as storage devices such as hard disks and semiconductor memory devices built into computer systems. The above program may also be transmitted via a telecommunications line.

[0026] The information control unit 131 controls the input and output of information. For example, the information control unit 131 acquires training data from other devices (information processing devices or storage media) and records it in the training data storage unit 121. For example, the information control unit 131 transmits a trained model stored in the trained model storage unit 123 to another device (e.g., the evaluation device 20). The information control unit 131 may also acquire measurement information measured by the measuring device 50 while the worker is performing a predetermined task, as well as evaluation information of that worker. In this case, the information control unit 131 may receive the worker's evaluation information from the terminal device 30, read out worker evaluation information previously stored in the storage unit 12, or acquire it from information input by an input device (not shown) provided in the learning device 10. The information control unit 131 generates training data by associating the acquired measurement information and evaluation information.

[0027] The preprocessing control unit 132 generates preprocessed training data by performing predetermined preprocessing on the training data. For example, the preprocessing control unit 132 calculates feature quantities that indicate eye movement based on the measurement information contained in the training data. These feature quantities include one or more of the following: drift, microsaccades, saccades, smooth tracking eye movements, convergence / divergence eye movements, and blinks. The information control unit 131 generates preprocessed training data by adding the calculated feature quantities to the training data, or by replacing the measurement information of the training data with the calculated feature quantities.

[0028] The learning control unit 133 performs a learning process using the features and evaluation information indicated by the preprocessed training data stored in the preprocessed training data storage unit 122. Specific examples of such a learning process include supervised learning for classification, such as support vector machines, random forests, and neural networks. The learning control unit 133 generates a trained model for outputting evaluation information indicating the quality of work based on the input features by performing supervised learning using the preprocessed training data. The learning control unit 133 records the generated trained model in the trained model storage unit 123. The trained model obtained by the learning control unit 133 may be transmitted to the evaluation device 20 and recorded in the judgment model storage unit 221 of the evaluation device 20, as described in Figure 3 later. Such a trained model can obtain evaluation information as output by providing features obtained based on the measurement values ​​of the measuring device 50 as input.

[0029] The learning control unit 133 may acquire training data in which feature quantities and evaluation information have been set. In this case, the learning device 10 does not need to have a pre-processed training data storage unit 122 and a pre-processing control unit 132. The learning control unit 133 executes the learning process using the feature quantities and evaluation information indicated by the training data.

[0030] Figure 3 is a schematic block diagram showing a specific example of the functional configuration of the evaluation device 20. The evaluation device 20 is configured using information processing equipment such as a personal computer or a server device. The evaluation device 20 includes a communication unit 21, a storage unit 22, and a control unit 23.

[0031] The communication unit 21 is a communication device. The communication unit 21 may be configured, for example, as a network interface. The communication unit 21 communicates data with other devices via the network 70 in accordance with the control of the control unit 23. The communication unit 21 may be a wireless communication device or a wired communication device.

[0032] The storage unit 22 is configured using a storage device such as a magnetic hard disk drive or a semiconductor storage device. The storage unit 22 stores data used by the control unit 23. The storage unit 22 may also function as, for example, a decision model storage unit 221.

[0033] The decision model storage unit 221 stores the decision model used by the decision unit 233 when performing the decision processing. The decision model may be configured, for example, using information from a pre-trained model generated by a training process. Such training processing may be performed, for example, by another device (e.g., a training device 10) or by the device itself (evaluation device 20). The decision model does not necessarily have to be generated by a training process. The decision model may be configured, for example, using a lookup table that associates features with evaluation information, or it may be configured in other ways.

[0034] The control unit 23 is configured using a processor such as a CPU and memory. The control unit 23 functions as an information control unit 231, a pre-processing control unit 232, and a determination unit 233 when the processor executes a program. Note that all or part of the functions of the control unit 23 may be implemented using hardware such as an ASIC, PLD, or FPGA. The above program may be recorded on a computer-readable recording medium. Computer-readable recording media include, for example, portable media such as flexible disks, magneto-optical disks, ROMs, CD-ROMs, and semiconductor storage devices (e.g., SSDs), as well as storage devices such as hard disks and semiconductor storage devices built into computer systems. The above program may be transmitted via a telecommunications line.

[0035] The information control unit 231 acquires measurement information from the measuring device 50 regarding the eye movements of the person being judged while they are performing a predetermined task. The information control unit 231 may also acquire measurement information from other devices such as the terminal device 30. The information control unit 231 transmits the evaluation result regarding the quality of the predetermined task performed by the person being judged, obtained by the judgment unit 233, to the terminal device 30 or other devices. Such information exchange between the information control unit 231 and other devices may be carried out, for example, by communication via the communication unit 21.

[0036] The preprocessing control unit 232 obtains feature quantities indicating eye movement by performing predetermined preprocessing on the measurement information acquired by the information control unit 231. The preprocessing performed by the preprocessing control unit 232 is the same as the preprocessing performed when generating a trained model used by the determination unit 233. In other words, the processing that the preprocessing control unit 232 performs on the measurement information is the same as the processing that the preprocessing control unit 132 performs on the measurement information of the training data. By performing such preprocessing, the preprocessing control unit 232 obtains one or more feature quantities from among drift, microsaccades, saccades, smooth tracking eye movements, convergence / divergence eye movements, and blinks.

[0037] The determination unit 233 performs determination processing using the determination model stored in the determination model storage unit 221 and the feature quantities acquired by the preprocessing control unit 232. Through the determination processing, evaluation information is obtained that indicates an evaluation of the quality of a predetermined task performed by the person being judged.

[0038] Figure 4 is a schematic block diagram showing a specific example of the functional configuration of the terminal device 30. The terminal device 30 is configured using information devices such as a smartphone, tablet, personal computer, or dedicated device. The terminal device 30 includes a communication unit 31, an input unit 32, an output unit 33, a storage unit 34, and a control unit 35.

[0039] The communication unit 31 is a communication device. The communication unit 31 may be configured, for example, as a network interface. The communication unit 31 communicates data with other devices via the network 70 in accordance with the control of the control unit 35. The communication unit 31 may be a device that performs wireless communication or a device that performs wired communication.

[0040] The input unit 32 includes a keyboard, mouse, buttons, touch panel, etc., and receives information input through user operation.

[0041] The output unit 33 outputs information in a format that the user can recognize. The output unit 33 may be an image display device such as a liquid crystal display or an organic EL (Electro-Luminescence) display. The output unit 33 may also be an interface for connecting an image display device to the terminal device 30. In this case, the output unit 33 generates a video signal for displaying image data and outputs the video signal to the image display device connected to it. The output unit 33 may also be a device that outputs sound, such as a speaker. The output unit 33 may also be an interface for connecting an audio output device such as a speaker or headphones to the terminal device 30. In this case, the output unit 33 generates an audio signal for playing audio data and outputs the audio signal to the audio output device connected to it. The output unit 33 may also be configured as a touch panel integrated with the input unit 32.

[0042] The storage unit 34 is configured using a storage device such as a magnetic hard disk drive or a semiconductor storage device. The storage unit 34 stores data used by the control unit 35. The storage unit 34 stores data necessary when the control unit 35 performs processing.

[0043] The control unit 35 is configured using a processor such as a CPU and memory. The control unit 35 functions when the processor executes a program. Note that all or part of the functions of the control unit 35 may be implemented using hardware such as an ASIC, PLD, or FPGA. The above program may be recorded on a computer-readable recording medium. Computer-readable recording media include, for example, portable media such as flexible disks, magneto-optical disks, ROMs, CD-ROMs, and semiconductor storage devices (e.g., SSDs), as well as storage devices such as hard disks and semiconductor storage devices built into computer systems. The above program may be transmitted via a telecommunications line.

[0044] The control unit 35 may, for example, execute an application installed on its own device (terminal device 30). A specific example of such an application is an application provided to the terminal device 30 as a dedicated application for the evaluation system 100. Another specific example of such an application is a web browser application. Such an application may be pre-installed on the terminal device 30, or it may be downloaded each time an evaluation of a person to be judged is performed. For example, if it is implemented as a web browser application, the terminal device 30 may download and execute the application from a device specified by the web server (for example, the web server itself or another server) when the terminal device 30 connects to a specific web server. The control unit 35 operates according to the program of the application being executed.

[0045] The control unit 35 controls the terminal device 30 in response to user operations and information received from the evaluation device 20. For example, when the control unit 35 receives information transmitted from the evaluation device 20 via the network 70 at the communication unit 31, it generates screen data based on the received information and displays the screen data on the output unit 33. Such screen data includes images and characters that represent the information transmitted from the evaluation device 20. For example, when the control unit 35 receives information transmitted from the evaluation device 20 via the network 70 at the communication unit 31, it generates audio data based on the received information and outputs the audio data from the output unit 33.

[0046] Next, the operation of the evaluation system 100 will be explained. The evaluation system 100 performs the processing shown in Figures 5 and 6 for the same task. For example, in plant monitoring, if the plant being monitored is different or the monitoring route is different, it is considered a different task. Also, for example, in assembly work in a factory, if the object being assembled is different, it is considered a different task.

[0047] Figure 5 is a flowchart illustrating a specific example of the processing performed by the learning device 10. First, the information control unit 131 acquires training data (step S101). The training data may be input by a user, acquired by communication from another information device, or acquired from a recording medium connected to the learning device 10. The information control unit 131 may also acquire measurement information obtained when the measuring device 50 measures the eye movements of a worker while the worker is performing a predetermined task. The information control unit 131 acquires evaluation information of the worker and generates training data by associating the acquired received measurement information with the acquired evaluation information.

[0048] The preprocessing control unit 132 performs predetermined preprocessing on the training data to generate preprocessed training data (step S102). Specifically, the preprocessing control unit 132 calculates feature quantities indicating eye movement based on the measurement information of the training data, adds the calculated feature quantities to the training data, or rewrites the measurement information of the training data with the calculated feature quantities to generate preprocessed training data. The learning control unit 133 performs a learning process using the set of feature quantities and evaluation information contained in each of the multiple preprocessed training data, and records the generated trained model in the trained model storage unit 123 (step S103).

[0049] In step S101, the learning control unit 133 may acquire training data in which features obtained from measurement information are set, instead of measurement information. In this case, the learning device 10 does not need to perform the processing in step S102. In step S103, the learning control unit 133 executes the learning process using the set of features and evaluation information set in the training data to generate a trained model.

[0050] Figure 6 is a flowchart illustrating a specific example of the processing performed by the evaluation device 20. The measuring device 50 transmits measurement information to the evaluation device 20, which shows a time-series of measured values ​​obtained by measuring the eye movements of the person to be evaluated while they are performing a predetermined task. The information control unit 231 of the evaluation device 20 receives the measurement information from the measuring device 50 (step S201). Alternatively, the information control unit 231 may receive measurement information from the terminal device 30, which contains the time-series of measured values ​​obtained by the measuring device 50.

[0051] The preprocessing control unit 232 performs preprocessing on the measurement information received by the information control unit 231 in step S201 to calculate feature quantities indicating the eye movements of the person to be judged (step S202). The judgment unit 233 performs judgment processing using at least the feature quantities (step S203). For example, the judgment unit 233 reads a judgment model from the judgment model storage unit 221. The judgment unit 233 inputs the feature quantities calculated in step S202 into the read judgment model to obtain evaluation information indicating the evaluation of the quality of a predetermined task performed by the person to be judged as an evaluation result. The judgment unit 233 transmits the information indicating the evaluation result to the terminal device 30 (step S204). The control unit 35 of the terminal device 30 outputs the received evaluation result information to the output unit 33.

[0052] In step S201, the information control unit 231 may receive feature quantities calculated by the terminal device 30 based on the measurement information acquired from the measuring device 50. In this case, the evaluation device 20 does not need to perform the processing in step S202. In step S203, the determination unit 233 inputs the feature quantities received from the terminal device 30 into the determination model to obtain the evaluation result.

[0053] In the evaluation system 100 configured in this way, information regarding the quality of a person's work can be accurately estimated by using information on eye movements measured by the measuring device 50. Specifically, it works as follows: In the evaluation system 100, a learning process is performed using time-series measurement values ​​obtained by measuring the eye movements of a worker while the worker is performing a predetermined task, and multiple training data showing the evaluation of the quality of the worker's work, to obtain a trained model. The trained model shows the correspondence between features calculated from the eye movement measurements and the evaluation of the quality of the work. The evaluation system 100 then acquires new measurement information obtained by measuring the eye movements of a person while the person is performing a predetermined task. The features obtained from the measurement information are correlated with the information on the evaluation of the quality of the work. The evaluation system 100 outputs information on the evaluation of the quality of the work corresponding to the input features as an evaluation result.

[0054] Figure 7 is a schematic diagram of an example hardware configuration of an information processing device 90 applied to this embodiment. The information processing device 90 comprises a processor 91, main memory 92, communication interface 93, auxiliary storage device 94, input / output interface 95, and internal bus 96. The processor 91, main memory 92, communication interface 93, auxiliary storage device 94, and input / output interface 95 are connected to each other via the internal bus 96 so as to be able to communicate with each other. The information processing device 90 may be applied to, for example, a learning device 10 and an evaluation device 20. In this case, for example, the communication unit 11 and the communication unit 21 may be configured using the communication interface 93. For example, the storage unit 12 and the storage unit 22 may be configured using the auxiliary storage device 94. Also, the control unit 13 and the control unit 23 may be configured using the processor 91 and the main memory 92.

[0055] (modified version) In this embodiment, the evaluation device 20 and the terminal device 30 are configured as separate devices, but they may be configured as a single device. Figure 8 shows a modified example of the evaluation device 20 configured in this way. The evaluation device 20 shown in Figure 8 includes an input unit 24 and an output unit 25 in addition to the configuration shown in Figure 3. The input unit 24 and output unit 25 of the evaluation device 20 shown in Figure 8 function similarly to the input unit 32 and output unit 33 of the terminal device 30, respectively. The control unit 23 operates in response to operations on the input unit 24, performs judgment processing using the input measurement information, and outputs evaluation result information using the output unit 25.

[0056] In this embodiment, the learning device 10 and the evaluation device 20 are configured as separate devices, but they may be configured as a single integrated device. Figure 9 shows a modified example of the evaluation device 20 configured in this way. The storage unit 22 of the evaluation device 20 shown in Figure 9 also functions as a teacher data storage unit 222 and a pre-processed teacher data storage unit 223. The control unit 23 of the evaluation device 20 shown in Figure 9 also functions as a learning control unit 234. The judgment model storage unit 221, the teacher data storage unit 222, and the pre-processed teacher data storage unit 223 function similarly to the learned model storage unit 123, the teacher data storage unit 121, and the pre-processed teacher data storage unit 122 of the learning device 10, respectively. The pre-processing control unit 232 performs not only the pre-processing of the evaluation device 20 (pre-processing of the measurement information of the judgment target), but also the pre-processing performed by the pre-processing control unit 132 of the learning device 10 (pre-processing of the measurement information of the teacher data). The learning control unit 234 functions similarly to the learning control unit 133 of the learning device 10.

[0057] The learning device 10 may be implemented using multiple information processing devices. For example, the learning device 10 may be implemented using a cloud or other device. For example, in the learning device 10, the storage unit 12 and the control unit 13 may be implemented on different information processing devices. For example, the storage unit 12 of the learning device 10 may be distributed and implemented across multiple information processing devices. The evaluation device 20 may be implemented using multiple information processing devices. For example, the evaluation device 20 may be implemented using a cloud or other device. For example, in the evaluation device 20, the storage unit 22 and the control unit 23 may be implemented on different information processing devices. For example, the storage unit 22 of the evaluation device 20 may be distributed and implemented across multiple information processing devices.

[0058] The application running on the terminal device 30 may not be intended to determine the evaluation information itself, but rather to provide the user with information obtained by processing the evaluation information. Such an application may be one that processes using an API (Programming Interface) provided by the evaluation device 20. In this case, the output unit 33 may output to the terminal device 30 other information obtained by processing the evaluation information, instead of information indicating the evaluation information itself obtained from the evaluation device 20.

[0059] According to the embodiments described above, the evaluation system comprises a learning unit and a control unit. For example, the learning unit may be provided in a learning device, and the control unit may be provided in an evaluation device. The learning unit learns a trained model by performing a learning process using a combination of feature quantities indicating the eye movements of a person when performing a predetermined task and the quality of that person's predetermined task as training data. The trained model takes the feature quantities indicating the eye movements of a person when performing a predetermined task as new input and outputs evaluation information regarding the quality of the predetermined task of the person from which the input feature quantities were obtained. The feature quantities include at least one of drift, microsaccades, saccades, smooth tracking eye movements, convergence / divergence eye movements, and blinks.

[0060] The control unit acquires feature quantities related to eye movements based on information detected by a sensor that acquires information about the eye movements of the person being evaluated while they are performing a predetermined task. The control unit uses the trained model learned by the learning unit and the acquired feature quantities to evaluate the quality of the predetermined task performed by the person being evaluated.

[0061] While embodiments of this invention have been described in detail above with reference to the drawings, the specific configuration is not limited to these embodiments and includes designs and the like that do not depart from the spirit of this invention. [Explanation of Symbols]

[0062] 100…Evaluation system, 10…Learning device, 11…Communication unit, 12…Storage unit, 121…Teacher data storage unit, 122…Preprocessed teacher data storage unit, 123…Trained model storage unit, 13…Control unit, 131…Information control unit, 132…Preprocessing control unit, 133…Learning control unit, 20…Evaluation device, 21…Communication unit, 22…Storage unit, 221…Decision model storage unit, 23…Control unit, 231…Information control unit, 232…Preprocessing control unit, 233…Decision unit, 30…Terminal device, 31…Communication unit, 32…Input unit, 33…Output unit, 34…Storage unit, 35…Control unit, 50…Measurement device, 70…Network, 90…Information processing device, 91…Processor, 92…Main memory, 93…Communication interface, 94…Auxiliary memory, 95…Input / Output Interface, 96…Internal Bus

Claims

1. The system includes a control unit that acquires feature quantities indicating eye movements based on information detected by a sensor that acquires information regarding the eye movements of a person being evaluated while performing a predetermined task, and that evaluates the quality of the predetermined task performed by the person based on the acquired feature quantities, The aforementioned feature includes at least one of the following features: drift, microsaccades, saccades, smooth tracking eye movements, convergence-divergence eye movements, and blinking. Evaluation device.

2. The system includes a learning unit that learns a trained model by using a combination of feature quantities indicating eye movements when a person is performing a predetermined task and the quality of the predetermined task performed by the person as training data, and then taking newly acquired feature quantities indicating eye movements obtained based on information detected by a sensor that acquires information about the eye movements of the person being judged while performing the predetermined task as input, and outputting an evaluation of the quality of the predetermined task performed by the person being judged. The aforementioned feature includes at least one of the following features: drift, microsaccades, saccades, smooth tracking eye movements, convergence-divergence eye movements, and blinking. Learning device.

3. A learning unit learns a trained model that uses a combination of feature quantities indicating eye movements of a person performing a predetermined task and the quality of the person's predetermined task as training data, thereby taking the feature quantities indicating eye movements of a person performing a predetermined task as new input and outputting an evaluation of the quality of the person's predetermined task obtained from the input feature quantities. A control unit that acquires feature quantities indicating eye movements based on information detected by a sensor that acquires information regarding the eye movements of a person to be judged while they are performing a predetermined task, and that uses the acquired feature quantities and the trained model to evaluate the quality of the predetermined task performed by the person to be judged, Equipped with, The aforementioned feature includes at least one of the following features: drift, microsaccades, saccades, smooth tracking eye movements, convergence-divergence eye movements, and blinking. Evaluation system.

4. The control step includes acquiring a feature quantity indicating the eye movements based on information detected by a sensor that acquires information about the eye movements of a person to be judged while they are performing a predetermined task, and evaluating the quality of the predetermined task performed by the person based on the acquired feature quantity. The aforementioned feature includes at least one of the following features: drift, microsaccades, saccades, smooth tracking eye movements, convergence-divergence eye movements, and blinking. Evaluation method.

5. The system includes a learning step in which a learning process is performed using a combination of feature quantities indicating eye movements when a person is performing a predetermined task and the quality of the person's predetermined task as training data, thereby training a trained model that takes as new input feature quantities indicating eye movements obtained based on information detected by a sensor that acquires information about the eye movements of the person being judged while performing the predetermined task, and outputs an evaluation of the quality of the person's predetermined task. The aforementioned feature includes at least one of the following features: drift, microsaccades, saccades, smooth tracking eye movements, convergence-divergence eye movements, and blinking. Learning methods.

6. Computers A computer program for causing the evaluation device to function as described in claim 1.

7. Computers A computer program for causing a learning device to function as described in claim 2.

Images