Information processing device, decision method, and program

Abstract

An information processing device (1X) mainly has an acquisition means (15X), an estimation means (16X), and a determination means (17X). The acquisition means (15X) acquires task evaluation information related to an evaluation of task execution by a subject. The estimation means (16X) estimates a state of the subject during the task execution. The determination means (17X) determines a mode of acting on the subject on the basis of the task evaluation information and the state of the subject.

Description

Technical Field

[0001] The present disclosure relates to the technical field of an information processing apparatus, a determination method, and a storage medium that determine an encouragement related to task execution. Background Art

[0002] An apparatus or system for determining the appropriateness of a task performed by a subject is known. For example, Patent Literature 1 discloses a work appropriateness determination system that determines work appropriateness by observing changes in work load and changes in biological information, and estimating stress associated with current work in real time. Prior Art Literature Patent Literature

[0003] Patent Literature 1 Japanese Unexamined Patent Publication No. 2022-82547 Summary of the Invention Problem to be Solved by the Invention

[0004] When a subject executes tasks continuously or intermittently, the system can accurately encourage the subject to execute tasks efficiently by appropriately encouraging the subject when each individual task is completed. On the other hand, the mode of such encouragement needs to be appropriately determined in accordance with the state of the subject and the task execution status.

[0005] In view of the above problem, an object of the present disclosure is to provide an information processing apparatus, a determination method, and a storage medium that can accurately determine a mode of encouragement to a subject regarding task execution. Means for Solving the Problem

[0006] One aspect of the information processing apparatus includes: acquisition means for acquiring task evaluation information related to evaluation of task execution by a subject; and Estimation means for estimating the state of the subject during the execution of the task, The system includes a determination means for determining the manner of intervention with the subject based on the task evaluation information and the estimated state of the subject. death, The estimation means estimates the state of the subject based on information observed of the subject during a predetermined period of time while the task is being performed. The estimation means shortens the predetermined period as the evaluation is higher. It is an information processing device. Other embodiments of the information processing apparatus include: A means for obtaining task evaluation information regarding the evaluation of the subject's performance on the task, Estimation means for estimating the state of the subject during the execution of the task, A determination means for determining the manner of intervention with the subject based on the task evaluation information and the estimated state of the subject, It has an output control means that outputs information based on the manner of the interaction, The output control means is Information based on the manner of the aforementioned intervention, Information regarding the reliability of the evaluation, calculated based on the estimated state of the subject, It is an information processing device that outputs [something].

[0007] One method of determination is: Computers We obtain task evaluation information regarding the evaluation of the subject's performance on the task. Based on information obtained by observing the subject during a predetermined period while the task is being performed, The state of the subject during the execution of the aforementioned task is estimated, The higher the evaluation, the shorter the predetermined period. Based on the task evaluation information and the estimated state of the subject, the manner of intervention with the subject is determined. This is the method of determination. Note that "computer" includes all electronic devices (including processors contained within electronic devices) and may be composed of multiple electronic devices.

[0008] One aspect of the program is: We obtain task evaluation information regarding the evaluation of the subject's performance on the task. Based on information obtained by observing the subject during a predetermined period while the task is being performed, The state of the subject during the execution of the aforementioned task is estimated, The higher the evaluation, the shorter the predetermined period. A program that causes a computer to execute a process of determining a mode of intervention for the subject based on said task evaluation information and the estimated state of said subject. [Effects of the Invention]

[0009] According to an example effect of the present disclosure, it is possible to appropriately determine a mode of intervention for a subject regarding task execution. [Brief Description of Drawings]

[0010] [Figure 1] Fig. 1 shows a schematic configuration of a task evaluation and intervention system in a first embodiment. [Figure 2] Fig. 2 shows a hardware configuration of an information processing apparatus common to each embodiment. [Figure 3] Fig. 3 is an example of functional blocks of an information processing apparatus in the first embodiment. [Figure 4] Fig. 4 is a block diagram for a case where state estimation of a subject is performed based on a face image. [Figure 5] (A) is a table showing a correspondence relationship between concentration level, correct answer rate and intervention mode when intervention mode is determined based on concentration level, which is an example of a state index, and correct answer rate, which is an example of an evaluation index related to task execution indicated by task evaluation information. (B) is a table showing a correspondence relationship between arousal level, correct answer rate and intervention mode when intervention mode is determined based on arousal level, which is an example of a state index, and correct answer rate. (C) is a table showing a correspondence relationship between tension level, correct answer rate and intervention mode when intervention mode is determined based on tension level, which is an example of a state index, and correct answer rate. [Figure 6] Fig. 5 is an example of a display screen when a task is a test. [Figure 7] Fig. 6 is an example of a flowchart showing a processing procedure of an information processing apparatus when a subject executes a task. [Figure 8] Fig. 7 shows a display screen according to Modification 4. [Figure 9] Fig. 8 shows a second display screen according to Modification 4. [Figure 10] Fig. 9 is an example of functional blocks of an information processing apparatus in a second embodiment. [Figure 11] (A) A table showing the correspondence between arousal level, an example of a state indicator, and the correct answer rate, an example of an evaluation indicator related to task execution, and the corresponding confidence score. (B) A table showing the correspondence between arousal level and concentration level and the corresponding confidence score. [Figure 12] This is an example of a display screen in the second embodiment. [Figure 13] The schematic configuration of the task evaluation and intervention system in the third embodiment is shown. [Figure 14] This is a block diagram of the information processing device in the fourth embodiment. [Figure 15] This is an example of a flowchart executed by the information processing device in the fourth embodiment. [Modes for carrying out the invention]

[0011] The following describes embodiments of the information processing device, determination method, and storage medium with reference to the drawings.

[0012] <First Embodiment> (1) System Configuration Figure 1 shows a schematic configuration of the task evaluation and intervention system 100 according to the first embodiment. The task evaluation and intervention system 100 evaluates the performance of each task and provides intervention to the subject based on the evaluation when the subject performs multiple tasks sequentially, either continuously or intermittently. This promotes more effective task performance by the subject and improvements in their approach to tasks tailored to their individual needs.

[0013] Here, "task" refers to the work that the subject is to perform, and includes tests to measure the subject's predetermined functions, abilities, and skills, learning such as e-learning aimed at improving the subject's predetermined functions, abilities, and skills, or training such as games (so-called brain training) to train the brain. For example, the tests, learning, and training mentioned above may be tests, learning, and training related to cognitive functions in at least one of the following categories: intelligence (verbal comprehension, perceptual organization, working memory, processing speed), attention function, frontal lobe function, language, memory, visuospatial cognition, and directional attention.

[0014] The task evaluation and intervention system 100 mainly comprises an information processing device 1, an input device 2, an output device 3, and a storage device 4. The information processing device 1 communicates data with the input device 2 and the output device 3 via a communication network or by direct wireless or wired communication.

[0015] The information processing device 1 determines the evaluation of the subject's task execution and the manner of intervention (also called the "intervention manner") based on the input signals supplied from the input device 2 and the information stored in the storage device 4. The information processing device 1 then generates an output signal "S2" based on the determined task execution evaluation and intervention manner, and supplies the generated output signal S2 to the output device 3.

[0016] Input device 2 generates input signals based on operations performed by the subject or the subject's measurement results. Input device 2 includes a user input interface that accepts operations (external input) from the subject and sensors that perform observation (sensing) of the subject. The user input interface is, for example, a touch panel, buttons, a keyboard, a mouse, or a voice input device. The sensors are, for example, a camera, a lidar, or a measuring instrument that measures biosignals (including vital information). Hereafter, the input signal output by the user input interface operated by the subject will be called "user input signal Su1," and the input signal output by the sensor that observes the subject will be called "observation input signal Ss1." Input device 2 may be a wearable terminal worn by the subject, a camera that photographs the subject, a microphone that generates audio signals of the subject's speech, or a terminal such as a personal computer or smartphone operated by the subject.

[0017] The output device 3 displays or outputs sound information based on the intervention method determined by the information processing device 1, based on the output signal S2 supplied from the information processing device 1. Here, "user" may be the subject themselves, or a person who manages or supervises the subject's activities (doctor, caregiver, supervisor, etc.). The output device 3 may be, for example, a display, projector, speaker, etc.

[0018] The storage device 4 is a memory that stores various information necessary for the processing performed by the information processing device 1. For example, the storage device 4 includes information about each task that the subject may perform. The task information includes, for example, display information and sound information to be output to the output device 3 when the subject performs the task, information for evaluating the results of task performance (for example, correct answer information for each question), and information about the difficulty level of the task. The storage device 4 also includes information necessary to estimate the subject's state and information necessary to determine the intervention method based on the evaluation of task performance. The storage device 4 may be an external storage device such as a hard disk connected to or built into the information processing device 1, or it may be a storage medium such as flash memory. The storage device 4 may also be a server device that communicates data with the information processing device 1. Furthermore, the storage device 4 may be composed of multiple devices.

[0019] The configuration of the task evaluation and intervention system 100 shown in Figure 1 is an example, and various modifications may be made to this configuration. For example, the input device 2 and the output device 3 may be configured as a single unit. In this case, the input device 2 and the output device 3 may be configured as tablet terminals that are integrated with or separate from the information processing device 1. Furthermore, the information processing device 1 may be composed of multiple devices. In this case, the multiple devices constituting the information processing device 1 exchange information among themselves that is necessary to execute pre-assigned processes. In this case, the information processing device 1 functions as a system.

[0020] (2) Hardware configuration Figure 2 shows the hardware configuration of the information processing device 1. The information processing device 1 includes a processor 11, memory 12, and interface 13 as hardware components. The processor 11, memory 12, and interface 13 are connected via a data bus 10.

[0021] The processor 11 functions as a controller (arithmetic unit) that controls the entire information processing device 1 by executing programs stored in memory 12. The processor 11 is, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or a TPU (Tensor Processing Unit). The processor 11 may consist of multiple processors. The processor 11 is an example of a computer.

[0022] Memory 12 is composed of various volatile and non-volatile memories such as RAM (Random Access Memory), ROM (Read Only Memory), and flash memory. Memory 12 also stores programs for executing processes performed by the information processing device 1. Some of the information stored in Memory 12 may be stored in one or more external storage devices capable of communicating with the information processing device 1, or in a storage medium that is removable from the information processing device 1.

[0023] Interface 13 is an interface for electrically connecting the information processing device 1 with other devices. These interfaces may be wireless interfaces such as network adapters for wirelessly transmitting and receiving data with other devices, or they may be hardware interfaces for connecting with other devices via cables, etc.

[0024] The hardware configuration of the information processing device 1 is not limited to the configuration shown in Figure 2. For example, the information processing device 1 may include at least one of the input device 2 or the output device 3. Furthermore, the information processing device 1 may be connected to or have a built-in sound output device such as a speaker.

[0025] (3) Functional Blocks Figure 3 shows an example of the functional blocks of the information processing device 1. Functionally, the processor 11 of the information processing device 1 includes a task evaluation information acquisition unit 15, a state estimation unit 16, an intervention mode determination unit 17, and an output control unit 18. In Figure 3, blocks where data is exchanged are connected by solid lines, but the combination of blocks where data is exchanged is not limited to this. The same applies to the diagrams of other functional blocks described later.

[0026] The task evaluation information acquisition unit 15 receives a user input signal Su1 generated by the input device 2 during the subject's task execution via the interface 13, and generates task evaluation information indicating the subject's evaluation of the task execution based on the user input signal Su1. The task evaluation information includes calculated values ​​of indicators (also called "task evaluation indicators") related to the evaluation of task execution (for example, an evaluation indicating whether the task was successful or not). For example, if the task is a test, the task evaluation indicators indicate the overall correct answer rate or score for each question included in the test performed by the subject, and if the task is learning or training, they indicate the correct answer rate or score for the acquisition check questions included in the learning or training received by the subject. In addition, the task evaluation information may include not only calculated values ​​of task evaluation indicators, but also information such as the task execution start time, task execution completion time, time required to execute the task (duration), and the difficulty level of the executed task. The task evaluation information acquisition unit 15 supplies the generated task evaluation information to the intervention mode determination unit 17.

[0027] The state estimation unit 16 receives an observation input signal Ss1 generated by an input device 2, such as a sensor, that measures the subject while the subject is performing a task, via the interface 13, and estimates the subject's state based on the observation input signal Ss1. The state estimation unit 16 then supplies information indicating the estimated subject's state (also called "subject state information") to the intervention mode determination unit 17.

[0028] In this case, the state estimation unit 16 calculates estimated values ​​of one or more indicators (also called "state indicators") that represent the subject's state. Examples of "state indicators" include concentration level, arousal level, tension level, etc. In this case, the observation input signal Ss1 includes, for example, a time-series facial image of the subject's face, and the state estimation unit 16 calculates estimated values ​​of the state indicators based on the facial image. The state estimation unit 16 supplies the calculated estimated values ​​of the state indicators to the intervention mode determination unit 17. Note that the observation input signal Ss1 used by the state estimation unit 16 to calculate the estimated values ​​of the state indicators is not limited to facial images, but may also include the subject's voice signal, biosignals, or other various information usable for estimating a person's state. Furthermore, the state estimation unit 16 may calculate estimated values ​​of the state indicators using observation input signals Ss1 obtained during the period in which the task to be evaluated is being performed (task execution period), or it may calculate estimated values ​​of the state indicators using observation input signals Ss1 obtained during a portion of the task execution period. Furthermore, if the state estimation unit 16 has calculated estimated values ​​of state indicators at multiple time points during the task execution period, it may calculate a representative value, such as the average of the above estimated values ​​during the task execution period, for each state indicator. The state estimation unit 16 then supplies the subject state information, which indicates the estimated values ​​of state indicators during the task execution period, to the intervention mode determination unit 17.

[0029] Furthermore, the memory device 4 may store trained parameters of a state estimation model that has been trained to output estimated values ​​of state indices when data based on the observation input signal Ss1 (for example, the time-series data of the face image described above) is input. The state estimation model is, for example, a model based on any machine learning, such as a neural network or a support vector machine (including statistical models; the same applies hereinafter). In this case, the state estimation unit 16 constructs a state estimation model based on these parameters and obtains estimated values ​​of state indices output by the state estimation model when data in tensor format of a predetermined number of ranks, such as a face image, is input to the state estimation model. If the state estimation model described above is a model based on a neural network, such as a convolutional neural network, the information processing device 1 stores in advance information on various parameters, such as the layer structure, the neuron structure of each layer, the number and size of filters in each layer, and the weights of each element of each filter.

[0030] The intervention method determination unit 17 determines the method of intervention (i.e., intervention method) for the subject based on the task evaluation information supplied from the task evaluation information acquisition unit 15 and the subject's state information supplied from the state estimation unit 16. In this case, the intervention method determination unit 17 determines the intervention method based, for example, on the calculated values ​​of one or more task evaluation indicators indicated by the task evaluation information and the estimated values ​​of one or more state indicators indicated by the subject's state information. In this case, for example, the intervention method determination unit 17 determines the intervention method by referring to a predetermined table that shows the correspondence between the calculated values ​​of the task evaluation indicators, the estimated values ​​of the state indicators, and the intervention method to be implemented. The aforementioned table is, for example, stored in advance in the storage device 4. In this case, for example, the intervention method determination unit 17 determines the method of intervention related to the next task the subject will undertake. In another example, the intervention method determination unit 17 determines the method of intervention related to changes in the subject's physical and mental state. The method by which the intervention method determination unit 17 determines the intervention method will be described later. The intervention mode determination unit 17 then supplies the output control unit 18 with information specifying the determined intervention mode (also called "intervention mode specification information").

[0031] The output control unit 18 controls the output of information based on the intervention type determined by the intervention type determination unit 17, based on the intervention type specification information supplied from the intervention type determination unit 17. In this case, the output control unit 18 transmits an output signal S2 to the output device 3, for example, based on the intervention type specification information, which indicates a display and / or audio output to prompt the subject to perform a different task that is more or less difficult than the previously performed task, or a task of a different type than the previously performed task. In another example, the output control unit 18 transmits an output signal S2 to the output device 3, based on the intervention type specification information, which indicates a display and / or audio output to encourage a change in the subject's physical and mental state. Encouraging a change in the subject's physical and mental state includes notifying the user when it is time to stop the task or providing a notification to encourage a break.

[0032] The output control unit 18 may further receive task evaluation information, etc., from the task evaluation information acquisition unit 15 and generate an output signal S2 that includes information regarding the task execution result. Similarly, the output control unit 18 may receive subject state information from the state estimation unit 16 and generate an output signal S2 that includes information regarding the estimated state of the subject during task execution. Specific examples of output control of the output device 3 by the output control unit 18 will be described later with reference to Figure 6, etc.

[0033] Furthermore, the components of the task evaluation information acquisition unit 15, state estimation unit 16, intervention mode determination unit 17, and output control unit 18, as described in Figure 3, can be realized, for example, by the processor 11 executing a program. Alternatively, the necessary programs may be recorded on any non-volatile storage medium and installed as needed to realize each component. At least a portion of these components are not limited to being realized by software programs, but may also be realized by a combination of hardware, firmware, and software. Furthermore, at least a portion of these components may be implemented using, for example, an FPGA (Field-Programmable Gate Array). y) Or it may be implemented using a user-programmable integrated circuit such as a microcontroller. In this case, the program consisting of the above components may be implemented using this integrated circuit. Furthermore, at least a part of each component may be an ASSP (Application Specific Standard Produce), an ASIC (Application Specific Integrated Circuit), or This may be composed of a quantum processor (quantum computer control chip). Thus, each component may be realized by various hardware. The same applies to other embodiments described later. Furthermore, each of these components may be realized by the cooperation of multiple computers, for example, using cloud computing technology.

[0034] (4) Concrete examples of state estimation Next, we will explain a specific example of estimating the subject's state using a camera. Figure 4 is a block diagram that clearly shows the information generated in the task evaluation information acquisition unit 15, the state estimation unit 16, and the intervention mode determination unit 17 when estimating the subject's state based on the face image output by the camera 21 included in the input device 2. In Figure 4, the oval frames indicate information (data).

[0035] In this case, the input device 2 has a visible light camera 21. The camera 21 may be, for example, a camera attached to a device such as a smartphone, tablet, or personal computer used by the subject. The camera 21 generates a facial image of the subject's face and supplies it to the information processing device 1. In this case, the camera 21 continuously generates and supplies facial images to the information processing device 1, for example, from the start of the task to the end of the task.

[0036] The state estimation unit 16 of the information processing device 1 generates various information (blinking information, gaze information, facial expression information, facial movement information, skin tone information, etc.) about the state of the subject's face during task execution, based on the face image generated by the camera 21 and using arbitrary image recognition technology. Here, blinking information is, for example, information about the frequency of blinking; gaze information is, for example, information about the direction of the gaze; facial expression information is, for example, information about the classification of facial expressions such as joy, anger, sadness, etc.; facial movement information is, for example, information about the brightness, hue, and movement of each part of the face for red, blue, and green respectively; and skin tone information is, for example, information about the classification of skin tone. In this case, for example, the state estimation unit 16 may generate the above-mentioned information using the eye area, the non-moving part of the skin, etc. of the face image. Alternatively, the state estimation unit 16 may generate the above-mentioned information based on an inference unit that has been trained to output various information about the state of the face in the face image when a face image is input. In this case, the trained parameters of the above-mentioned inference unit are stored in advance in, for example, the memory device 4. Furthermore, since camera 21 is a visible light camera, the state estimation unit 16 may estimate the heart rate based on the G channel of the RGB of the face image.

[0037] Furthermore, the state estimation unit 16 calculates estimated values ​​of state indicators based on the various information described above. Here, the state estimation unit 16 estimates the level of concentration during task execution based on gaze information, facial expression information, and facial movement information. The state estimation unit 16 also estimates the level of alertness during task execution based on blinking information. Furthermore, the state estimation unit 16 estimates the level of tension during task execution based on biometric information related to heart rate variability and heart rate estimated from facial movement information and complexion information. In this case, the state estimation unit 16 may calculate the estimated values ​​of the various state indicators from the various information about the state of the face using an inference unit that has been trained to output estimated values ​​of each state indicator from the various information about the state of the face described above. In another example, the state estimation unit 16 may calculate estimated values ​​of each state indicator from the various information about the state of the face based on a predetermined lookup table or formula that shows the correspondence between the various information about the state of the face and each state indicator. In this case, the trained parameters of the inference unit or the above-mentioned lookup table or formula are stored in advance, for example, in the memory device 4. The state estimation unit 16 then supplies the calculated concentration level, alertness level, and tension level to the intervention method determination unit 17.

[0038] Furthermore, the state estimation unit 16 is not required to calculate all of the concentration level, alertness level, and tension level; it may calculate at least one of them. Also, the state indicators calculated by the state estimation unit 16 are not limited to concentration level, alertness level, and tension level, but may be any one or more indicators related to stress, drowsiness, concentration, tension, alertness, fatigue, pleasure or displeasure, etc.

[0039] Furthermore, the state estimation unit 16 may calculate each state index using arbitrary information such as, in addition to the face image generated by the camera 21, an audio signal representing the subject's speech recorded during task execution, and the subject's biometric information measured directly or indirectly from the subject during task execution. "Measured indirectly" includes, for example, cases where the subject's heart rate or respiration is measured non-contactually by the reflection of radio waves.

[0040] The intervention mode determination unit 17 determines the optimal difficulty level of the task to be performed by the subject, and, if the task is learning, determines the timing for stopping the learning (stopping time), based on the level of concentration, level of arousal, and level of tension supplied from the state estimation unit 16 and the task evaluation information supplied from the task evaluation information acquisition unit 15. The intervention mode determination unit 17 then generates the result of the determination of the optimal difficulty level of the task to be performed by the subject (optimal difficulty level determination result) and the result of the determination of the timing for stopping the learning (stopping time determination result), and supplies the generated determination results to the output control unit 18. As a result, the output control unit 18 can suitably determine the mode of intervention regarding the subject's task performance based on the subject's state and the evaluation of the task performance results.

[0041] (5) Specific examples of determining the type of intervention Next, we will explain a specific example of how the intervention method to be executed by the intervention method determination unit 17 is determined.

[0042] Figure 5(A) is a table showing the correspondence between concentration level, correct response rate, and intervention type when determining the intervention type based on concentration level (an example of a state indicator) and correct response rate (an example of an evaluation indicator related to task execution shown in task evaluation information). Figure 5(B) is a table showing the correspondence between arousal level, correct response rate, and intervention type when determining the intervention type based on arousal level (an example of a state indicator) and correct response rate. Figure 5(C) is a table showing the correspondence between tension level, correct response rate, and intervention type when determining the intervention type based on tension level (an example of a state indicator) and correct response rate. In Figures 5(A) to 5(C), the type and degree of intervention are shown, and the degree is, for example, divided into three levels from Level 1 to Level 3 (Level 3 being the highest degree). Also, in Figures 5(A) to 5(C), each state indicator is classified into three levels, low, medium, and high, for example. Furthermore, "normal response" refers to a situation where no intervention is made, for example, by ensuring that the next task is performed as scheduled without changing the difficulty level of the task.

[0043] In the example in Figure 5(A), if the student is able to concentrate but the evaluation of their task performance is poor (i.e., high concentration and low accuracy, or high concentration and medium accuracy), the intervention mode determination unit 17 selects an intervention mode that either lowers the difficulty of the next task or encourages review of the previously performed task. Here, the level of intervention is one step higher when the concentration level is high and the accuracy is low than when the concentration level is high and the accuracy is medium. Therefore, for example, the intervention mode determination unit 17 lowers the difficulty of the task to a greater extent when the concentration level is high and the accuracy is low than when the concentration level is high and the accuracy is medium. In other examples, the intervention mode determination unit 17 recommends review to a greater extent when the concentration level is high and the accuracy is low than when the concentration level is high and the accuracy is medium.

[0044] Furthermore, if the evaluation of task execution is good (i.e., the accuracy rate is "high"), the intervention method determination unit 17 increases the difficulty level of the next task. In this case, the lower the concentration level, the greater the degree to which the difficulty level of the next task is increased. Also, if the concentration is low and the evaluation of task execution is unsatisfactory (low concentration level and low accuracy rate, or low concentration level and medium accuracy rate), the intervention method determination unit 17 encourages a break or encourages repeating the same task. Here, the level of intervention is one step higher when the concentration level is "low" and the accuracy rate is "low" than when the concentration level is "low" and the accuracy rate is "medium". Therefore, for example, the intervention method determination unit 17 defaults to performing a break or repeating the same task when the concentration level is "low" and the accuracy rate is "low", and proposes a break or repeating the same task as one of the options when the concentration level is "low" and the accuracy rate is "medium". Furthermore, the intervention method determination unit 17 may, if the user is unable to concentrate and the evaluation of task execution is unsatisfactory, initially encourage the user to repeat the same task, and if the user continues to be unable to concentrate on the subsequent task and the evaluation of task execution remains unsatisfactory, then determine an intervention method that encourages the user to take a break.

[0045] Similarly, in the examples in Figure 5(B) or Figure 5(C), if the level of arousal is high or the level of tension is low (i.e., the person is relaxed) but the evaluation of task performance is poor, the intervention method determination unit 17 selects an intervention method that lowers the difficulty of the next task or encourages a review of the previously performed task. Also, if the evaluation of task performance is good (i.e., the accuracy rate is "high"), the intervention method determination unit 17 increases the difficulty of the next task. In this case, the intervention method determination unit 17 increases the degree to which the difficulty of the next task is increased, the lower the level of arousal or the higher the level of tension. Furthermore, if the level of arousal is high or the level of tension is low and the evaluation of task performance is poor, the intervention method determination unit 17 encourages a break or encourages repeating the same task.

[0046] In the examples in Figures 5(A) to 5(C), the estimated values ​​of the status indicators and the calculated values ​​of the task evaluation indicators shown in the task evaluation information are classified into three stages. However, this is not limited to this classification; each may be classified into two stages, or into four or more stages.

[0047] Furthermore, when determining the intervention method based on estimated values ​​of multiple state indicators, the intervention method determination unit 17 may determine the intervention method corresponding to the estimated value of each state indicator and then determine the intervention method by majority vote, or it may randomly select one intervention method from the intervention methods corresponding to the estimated value of each state indicator. In yet another example, a table or the like showing the correspondence between the estimated values ​​of multiple state indicators and the intervention methods is pre-stored in the storage device 4, and the intervention method determination unit 17 may determine one intervention method from the estimated values ​​of multiple state indicators by referring to this table or the like.

[0048] Here, we will provide a supplementary explanation of the advantages of determining the intervention method based on estimated values ​​of multiple state indicators. For example, if the intervention method is determined based on the estimated value of only one state indicator, it is not possible to capture the subject's state during task execution from a single perspective, and it is difficult to accurately grasp whether the subject's state during task execution is suitable for task execution based solely on the quality of the estimated value of that state indicator. For example, if only the level of arousal is used, the same intervention method would be applied to a subject who is not sleepy but unable to concentrate, and to a subject who is not sleepy but can concentrate. Taking the above into consideration, in a suitable example, the intervention method determination unit 17 determines an appropriate intervention method that is in line with the actual state of the subject by identifying the subject's state during task execution from multiple perspectives based on estimated values ​​of multiple state indicators.

[0049] (6) Display example Figure 6 shows an example of a display screen that the output control unit 18 displays on the output device 3 when the task is a test. After the subject performs the task, the output control unit 18 generates an output signal S2 based on the intervention type specification information generated by the intervention type determination unit 17, and supplies the output signal S2 to the output device 3 via the interface 13, thereby causing the output device 3 to display the display screen shown in Figure 6.

[0050] The output control unit 18, as shown in Figure 6, mainly provides a test result display area 31, an estimated status display area 32, a message display area 33, and a test start button 34.

[0051] Based on the information received from the task evaluation information acquisition unit 15, the output control unit 18 displays the results (evaluation) of the test performed immediately before the test, along with the average score, on the test result display area 31. Furthermore, based on the information received from the state estimation unit 16, the output control unit 18 displays the estimated values ​​of each state indicator (concentration level, alertness level, tension level) of the subject during task execution, calculated by the state estimation unit 16, on the estimated state display area 32. Here, the estimated values ​​for each state indicator range from 0 to 100.

[0052] Furthermore, the output control unit 18 displays a message on the message display area 33 based on the intervention mode specification information generated by the intervention mode determination unit 17. Here, since the test results were good, the message display area 33 indicates that the next test will be one with increased difficulty according to the degree of the status indicator. When the output control unit 18 detects that the test start button 34 has been selected based on user operation by the input device 2, it displays the execution screen for a test with a higher difficulty level than the previous test on the output device 3. Note that the display method of the various numerical values ​​shown in Figure 6 is just one example. Therefore, the output control unit 18 may, for example, present these numerical values ​​to the user in a way that allows them to understand the degree of the results at a glance, such as using a bar graph or pie chart.

[0053] In this way, the confidence calculation unit 19 can output a display to the output device 3 based on the intervention method determined based on the subject's condition and the evaluation of the test results.

[0054] Note that the display example shown in Figure 6 is just one example, and various modifications may be made. For example, if the task is training, the confidence calculation unit 19 may not need to provide the estimated state display area 32 in order to allow the subject to concentrate on performing the task.

[0055] (7) Processing flow Figure 7 is an example flowchart showing the processing procedure of the information processing device 1 when a subject performs a task. The information processing device 1 executes the flowchart processing, for example, when the subject starts performing the task or when the task is completed. In the latter case, the information processing device 1 stores the observation input signal Ss1 generated by the input device 2 during task execution in the memory 12 or storage device 4, and then executes the flowchart processing after the task is completed based on the stored observation input signal Ss1.

[0056] First, the information processing device 1 estimates the subject's state during task execution (step S11). In this case, the information processing device 1 may immediately estimate the subject's state in a time series based on the observation input signal Ss1 obtained during task execution, or it may calculate the subject's state during task execution based on the observation input signal Ss1 obtained during task execution after the task execution is completed. If the information processing device 1 calculates the time series values ​​of the subject's state index, it may set the average or other representative value of the calculated values ​​as the estimated value of the state index to be used in subsequent processing.

[0057] Next, the information processing device 1 acquires task evaluation information for the task performed by the subject (step S12). In this case, the information processing device 1 generates task evaluation information, including calculated values ​​of evaluation indicators related to task performance, such as the correct answer rate or score, based on the user input signal Su1 generated based on the subject's operation to the input device 2. The subject's operation in this case may be a gesture recognizable by image analysis, or an utterance recognizable by speech signal analysis. Note that steps S11 and S12 are not in any order, and step S12 may be performed before step S11.

[0058] Next, the information processing device 1 determines the manner of intervention (i.e., intervention manner) for the subject based on the estimated state of the subject and the task evaluation information (step S13). Then, the information processing device 1 controls the output device 3 and outputs based on the determined intervention manner (step S14). In this case, for example, the information processing device 1 supplies an output signal S2 to the output device 3 so that the output device 3 displays or outputs audio information (including information for performing the next task) based on the determined intervention manner. As a result, the information processing device 1 can perform more effective learning and training tailored to the subject, thereby maintaining and improving the efficiency of learning and training.

[0059] (8) Variation A suitable modification of the above-described embodiment will now be explained. The modifications may be arbitrarily combined and applied to the above-described embodiment.

[0060] (Variation 1) The state estimation unit 16 may perform state estimation of the subject based on the observation input signal Ss1, such as a face image, generated by the input device 2 during a predetermined period of the task execution period.

[0061] In the first example, the information processing device 1 stores the observation input signal Ss1 obtained during the task execution period in a storage device 4 or the like, associated with time information indicating the acquisition time. Then, after the task is executed, the state estimation unit 16 identifies the period during the task execution period in which the subject gave an incorrect answer (also called the "incorrect answer period"), and acquires the observation input signal Ss1, such as a face image, corresponding to the identified incorrect answer period from the storage device 4. Then, the state estimation unit 16 calculates an estimated value of a state index that estimates the subject's state based on the observation input signal Ss1 during the incorrect answer period. In this case, the task evaluation information acquisition unit 15 stores, for example, the reception time (i.e., response time) of the user input signal Su1 corresponding to each answer to each question in the task, and at least answer-related information indicating whether each answer is correct or incorrect, in the storage device 4 or the like. The state estimation unit 16 then extracts the observation input signal Ss1 corresponding to the period of incorrect responses from the observation input signals Ss1 stored in the storage device 4 during the task execution period, based on the response-related information, and calculates an estimated value of the state index based on the extracted observation input signal Ss1. The period of incorrect responses is defined, for example, as a predetermined time period including the response time. According to the first example, the information processing device 1 can suitably reduce the amount of computation required to estimate the subject's state.

[0062] In the second example, when the state estimation unit 16 estimates the subject's state based on the observation input signal Ss1 generated during a predetermined period of the task execution period, it shortens the predetermined period as the task evaluation information indicates a higher evaluation of the task execution. In this case, after the task execution, the state estimation unit 16 shortens the predetermined period as the accuracy rate or score indicated by the task evaluation information calculated by the task evaluation information acquisition unit 15 is higher, and estimates the subject's state based on the observation input signal Ss1 during that predetermined period. In this case, the state estimation unit 16 may define the predetermined period as a period extracted from the task execution period based on a predetermined rule, or it may define the predetermined period as a period selected from all or part of the period of incorrect answers. In the second example as well, the information processing device 1 can suitably reduce the amount of computation without reducing the accuracy of the subject's state estimation.

[0063] (Modification 2) The intervention method determination unit 17 may determine the current intervention method by taking into consideration the results of past interventions.

[0064] In this case, for example, a database of information relating previously determined intervention methods, task evaluation information and subject status information at the time the intervention method was determined, and intervention results showing the results of implementing the intervention method is pre-stored in the storage device 4. The aforementioned intervention results are, for example, information indicating whether the intervention using the previously determined intervention method was successful or not, and are generated, for example, based on the user input signal Su1 (i.e., user input) supplied from the input device 2. The intervention method determination unit 17 then provisionally determines the intervention method based on the task evaluation information and subject status information, and searches the database for a record that is identical to the task evaluation information and subject status information used to determine the intervention method. If a corresponding record exists and the intervention result included in that record indicates a failure of the intervention, the intervention method determination unit 17 reduces the degree of the intervention of the determined intervention method or suspends the execution of the intervention method. Furthermore, even if the intervention method determination unit 17 has postponed the execution of an intervention method, if the subject continues to perform the task thereafter and determines the same intervention method that was postponed for a predetermined number of consecutive times, the unit may execute the postponed intervention method.

[0065] This effectively prevents the immediate decision to apply the same intervention (e.g., increasing the difficulty of the task) in the same situation if a past intervention (e.g., increasing the difficulty of the task) has resulted in undesirable outcomes. For example, if an undesirable outcome was obtained in the past as a result of increasing the difficulty of the task, the difficulty can be avoided in the same situation. Instead, the difficulty can be increased only after a predetermined number of consecutive correct answer rates have been observed to be consistently high.

[0066] Furthermore, the intervention type specification information may be stored in the storage device 4 after generation and used on a different day. For example, if the task execution interval is a predetermined number of days (e.g., 1 day), the intervention type determination unit 17 stores the determined intervention type specification information in the storage device 4. Then, when it is time to execute the next task, the output control unit 18 determines the difficulty level of the task, etc., based on the intervention type specification information stored in the storage device 4, and outputs information for the subject to perform the task.

[0067] (Variation 3) The output control unit 18 may notify a person other than the subject of information based on the intervention. In this case, the output control unit 18 may, for example, send an output signal to a terminal device used by a person other than the subject (e.g., an instructor or supervisor) to display the display screen shown in Figure 6. In this case, the output control unit 18 may also send information based on the intervention to a communication address, such as an email address, owned by a person other than the subject.

[0068] Furthermore, the output control unit 18 may change the notification destination for each subject. For example, the storage device 4 stores information associating the user ID of the subject with the communication address to which information based on the intervention will be sent, and the output control unit 18 sends information based on the intervention information to the communication address associated with the subject's user ID. The output control unit 18 may also send information based on the intervention to a terminal device used by someone other than the subject only if it determines that both the evaluation of task execution and the estimated state of the subject have remained worse than a predetermined standard for a predetermined number of times or more. In this case, if the output control unit 18 does not determine that the condition has continued for the predetermined number of times or more, it outputs the above information to the input device 2 viewed by the subject.

[0069] (Modification 4) The output control unit 18 may display various elements other than those shown on the display screen in Figure 6. For example, the output control unit 18 may display the average age of the subjects.

[0070] Figure 8 shows the display screen according to the modified example 4. The output control unit 18 provides a test result display area 31A, an estimated status display area 32A, a message display area 33, and a test start button 34 on the display screen shown in Figure 8.

[0071] Based on the information received from the task evaluation information acquisition unit 15, the output control unit 18 displays the results (evaluation) of the test performed immediately before the test on the test result display area 31A, along with the average score of other test takers in the same age group as the test taker (in this case, 75 points). The output control unit 18 may also display the distribution of the average scores of other test takers in the same age group as the test taker (for example, the range in which the average scores are distributed).

[0072] Furthermore, based on the information received from the state estimation unit 16, the output control unit 18 displays the estimated values ​​of each state index (concentration level, arousal level, tension level) of the subject during task execution, calculated by the state estimation unit 16, on the estimated state display area 32A. Here, the output control unit 18 visually displays the estimated values ​​of each state index by making the donut-shaped filled area larger according to the magnitude of the value. It also displays a message based on the intervention method specification information generated by the intervention method determination unit 17 on the message display area 33. When the output control unit 18 detects that the test start button 34 has been selected based on user operation by the input device 2, it displays the execution screen of a test with a higher difficulty level than the previous test on the output device 3.

[0073] According to this embodiment, the output control unit 18 can display the subject's test results in a manner comparable to the average age of the subject.

[0074] In other examples, the output control unit 18 may display the results of the actions described in Modification 2 along with the test result history.

[0075] Figure 9 shows the second display screen according to Modification 4. The output control unit 18 displays a plot on the display screen shown in Figure 9, in which the subject's past test results (in this case, test results for the most recent month as an example) are plotted chronologically using plot points P1 to P5. The test results may be acquired on a daily basis or at any arbitrary interval. Furthermore, the period for which the test results are displayed on the display screen may be any period specified by the user.

[0076] In this case, the output control unit 18 displays an average score line 51 showing the average test score per test for past subjects indicated by plot points P1 to P5, and a distribution range line 52 showing the distribution of average test scores (in this case, the range in which the average value is distributed) for other subjects of the same age as the subject. In addition to the distribution range line 52, or instead, the output control unit 18 may also display the distribution of average scores for other subjects of the same age when a certain state index (e.g., concentration level) is above a predetermined level and when it is below a predetermined level. Furthermore, for plot point P5 selected by the user, the output control unit 18 displays a callout 52 showing the estimated values ​​of each state index at the time of test execution.

[0077] Furthermore, the output control unit 18 displays pairs of intervention types and intervention results for plot points P1 to P5 corresponding to tests immediately following the implementation of interventions based on the determined intervention type, by referring to the database described in Modification Example 2. Here, symbols A to D classifying the intervention type are explicitly shown as an example of information identifying the intervention type, and success or failure is explicitly shown as an example of the intervention result. The output control unit 18 also displays the specific details of the intervention types corresponding to symbols A to D on window 55.

[0078] According to this embodiment, the output control unit 18 can suitably present to the user the history of test results and the history of the results of the actions.

[0079] <Second Embodiment> In the second embodiment, the information processing device 1 differs from the information processing device 1 of the first embodiment in that it calculates a confidence level (also called "evaluation confidence level") for the evaluation of task execution and further processes the output of the calculated confidence level. Hereafter, the same reference numerals will be used for components identical to those in the first embodiment, and their descriptions will be omitted. Furthermore, the configuration of the task evaluation and intervention system 100 in the second embodiment is assumed to be the same as the configuration shown in Figure 1, and the hardware configuration of the information processing device 1 in the second embodiment is assumed to be the same as the configuration shown in Figure 2.

[0080] Figure 10 shows an example of the functional blocks of the processor 11 of the information processing device 1 in the second embodiment. Functionally, the processor 11 includes a task evaluation information acquisition unit 15, a state estimation unit 16, an intervention mode determination unit 17, an output control unit 18, and a reliability calculation unit 19. The processing performed by the task evaluation information acquisition unit 15, the state estimation unit 16, and the intervention mode determination unit 17 is the same as described in Figure 3, so its explanation is omitted.

[0081] The reliability calculation unit 19 calculates the evaluation reliability based on the subject status information output by the status estimation unit 16. In this case, for example, a table or formula that associates the expected values ​​of one or more status indicators used to calculate the evaluation reliability with the evaluation reliability to be set for each value is pre-stored in the storage device 4 or the like. The reliability calculation unit 19 then calculates the evaluation reliability based on the estimated values ​​of the status indicators indicated by the subject status information and the aforementioned table or formula. A specific example of how the reliability calculation unit 19 calculates the evaluation reliability will be described later. The reliability calculation unit 19 then supplies information regarding the calculated evaluation reliability to the output control unit 18.

[0082] The output control unit 18 controls the output from the output device 3 based on the intervention mode specification information supplied from the intervention mode determination unit 17 and the evaluation reliability information supplied from the reliability calculation unit 19. Specific examples of the output from the output device 3 will be described later.

[0083] Figure 11(A) is a table showing the correspondence between a state indicator, such as arousal level, and an evaluation indicator related to task execution, such as accuracy, and the corresponding evaluation confidence score (also called the "confidence score"). Here, the confidence score takes a value range from 1 to 10, with 10 representing the highest evaluation confidence. As shown in Figure 11(A), the confidence calculation unit 19 determines the confidence score based on the subject's state indicator (in this case, arousal level), regardless of the subject's evaluation of task execution (in this case, accuracy). Specifically, the confidence calculation unit 19 sets a higher confidence score the higher the arousal level. Furthermore, when concentration level is used as a state indicator, the confidence calculation unit 19 sets a higher confidence score the higher the concentration level. Similarly, when tension level is used as a state indicator, the confidence calculation unit 19 sets a higher confidence score the lower the tension level. Thus, the confidence calculation unit 19 assigns a higher confidence score the more favorable the subject's condition is for task execution. In the example in Figure 11(A), the state index values ​​are classified into three stages, but this is not limited to this; each may be classified into two stages, or into four or more stages.

[0084] Furthermore, the confidence calculation unit 19 may determine the confidence score based on multiple state indicators. Figure 11(B) is a table showing the correspondence between the level of alertness and the level of concentration and the corresponding confidence score. As shown in Figure 11(B), in this case, when the level of concentration is fixed, the higher the level of alertness, the higher the confidence score, and when the level of alertness is fixed, the higher the level of concentration, the higher the confidence score. In this way, the confidence calculation unit 19 can suitably determine the confidence score from multiple state indicators by referring to a table showing the correspondence between each value or level of the multiple state indicators and the confidence score.

[0085] Figure 12 shows an example of a display screen that the output control unit 18 displays on the output device 3 in the second embodiment. After the subject performs a task (in this case, a test), the output control unit 18 generates an output signal S2 based on intervention type specification information and evaluation reliability information, etc., and supplies the output signal S2 to the output device 3 via the interface 13, thereby causing the output device 3 to display the display screen shown in Figure 12.

[0086] The output control unit 18, as shown in Figure 12, mainly provides a test result display area 31, an estimated status display area 32, a message display area 33, a test start button 34, and an evaluation reliability display area 35. The test result display area 31, the estimated status display area 32, the message display area 33, and the test start button 34 are the same as those shown in Figure 6, so their explanation is omitted.

[0087] The output control unit 18 displays a message based on the evaluation reliability on the evaluation reliability display area 35. In this example, the output control unit 18 displays a message indicating that the evaluation (in this case, the test result) shown in the test result display area 31 is reliable because the reliability score indicating the evaluation reliability was higher than a predetermined threshold. In addition to the above message, the output control unit 18 may also display the reliability score on the evaluation reliability display area 35.

[0088] According to this display screen, the output control unit 18 can suitably notify the user of the confidence level of the task execution evaluation.

[0089] <Third Embodiment> Figure 13 shows a schematic configuration of the task evaluation and intervention system 100A in the third embodiment. The task evaluation and intervention system 100A according to the third embodiment is a server-client model system, in which the information processing device 1A, which functions as a server device, performs the processing of the information processing device 1 in the first embodiment. Hereafter, the same reference numerals are used for components that are the same as in the first embodiment, and their descriptions are omitted as appropriate.

[0090] The task evaluation and intervention system 100A mainly comprises an information processing device 1A that functions as a server, a storage device 4 that stores data similar to that of the first embodiment, and a terminal device 8 that functions as a client. The information processing device 1A and the terminal device 8 communicate data via a network 7.

[0091] Terminal device 8 is a terminal having input, display, and communication functions, and functions as input device 2 and output device 3 shown in Figure 1. Terminal device 8 may be, for example, a personal computer, a tablet terminal, or a PDA (Personal Digital Assistant). Terminal device 8 transmits biological signals output by sensors (not shown) or input signals based on user input to information processing device 1A.

[0092] Information processing device 1A has the same hardware and functional configuration as, for example, information processing device 1. Information processing device 1A receives information acquired by information processing device 1 from input device 2 via network 7 from terminal device 8, and generates subject status information, task evaluation information, and intervention type specification information based on the received information. Information processing device 1A also transmits an output signal indicating information based on the intervention type indicated by the intervention type specification information to terminal device 8 via network 7. In this case, terminal device 8 functions as output device 3 in the first or second embodiment. As a result, information processing device 1A presents information based on the determined intervention type to the user of terminal device 8 in a suitable manner.

[0093] <Fourth Embodiment> Figure 14 is a block diagram of the information processing device 1X in the fourth embodiment. The information processing device 1X mainly includes an acquisition means 15X, an estimation means 16X, and a determination means 17X. The information processing device 1X may be composed of multiple devices. The information processing device 1X can be, for example, the information processing device 1 in the first embodiment (including modified versions, the same applies hereinafter) or the second embodiment, or the information processing device 1A in the third embodiment.

[0094] The acquisition means 15X acquires task evaluation information relating to the evaluation of the subject's performance of the task. Here, "evaluation" refers to the evaluation of the task's performance (more specifically, the results of the task's performance). For example, if the task includes questions, it refers to the evaluation of the correctness of the subject's answers to those questions (e.g., the correct answer rate). The acquisition means 15X can be the task evaluation information acquisition unit 15 in the first to third embodiments.

[0095] The estimation means 16X estimates the subject's state during task execution. "The subject's state during task execution" may refer to the subject's state during a portion of the task execution period. The estimation means 16X can be the state estimation unit 16 in the first to third embodiments.

[0096] The determination means 17X determines the manner of intervention towards the subject based on the task evaluation information and the subject's condition. The determination means 17X can be the intervention manner determination unit 17 in the first to third embodiments.

[0097] Figure 15 is an example of a flowchart executed by the information processing device 1X in the fourth embodiment. The acquisition means 15X acquires task evaluation information relating to the subject's evaluation of task execution (step S21). Next, the estimation means 16X estimates the subject's state during task execution (step S22). The determination means 17X determines the manner of intervention with the subject based on the task evaluation information and the subject's state (step S23).

[0098] According to the fourth embodiment, the information processing device 1X can suitably determine the manner in which it interacts with the subject.

[0099] In each of the embodiments described above, the program is stored using various types of non-transitory computer-readable medium. It can be supplied to a computer, such as a processor. Non-temporary computer-readable media include various types of tangible storage media. Examples of computer-readable media include magnetic storage media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical storage media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / Ws, and semiconductor memory (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs). This includes RAM (Random Access Memory). Also, programs are stored on various types of temporary computer-readable media. Temporary computer-readable media may be supplied to a computer. Examples of temporary computer-readable media include electrical signals, optical signals, and electromagnetic waves. Temporary computer-readable media can supply programs to a computer via wired communication channels such as electric wires and optical fibers, or via wireless communication channels.

[0100] Furthermore, some or all of the above embodiments may also be described as follows, but are not limited to these.

[0101] [Note 1] A means for obtaining task evaluation information regarding the evaluation of the subject's performance on the task, Estimation means for estimating the state of the subject during the execution of the task, A determination means for determining the manner of intervention with the subject based on the task evaluation information and the estimated state of the subject, An information processing device having [Note 2] The estimation means is an information processing device according to Appendix 1, which estimates the state of the subject based on a facial image of the subject captured by a visible light camera. [Note 3] The aforementioned evaluation is an evaluation of the correctness of the subject's answers to the questions included in the task, as described in Appendix 1 of the information processing device. [Note 4] The estimation means is an information processing device as described in Appendix 3, which estimates the state of the subject based on information observed of the subject during the period in which the erroneous answer was given. [Note 5] The estimation means estimates the state of the subject based on information observed of the subject during a predetermined period of time while the task is being performed. The estimation means shortens the predetermined period as the evaluation is higher, as described in Appendix 2 of the information processing apparatus. [Note 6] The information processing apparatus according to any one of the appendices 1 to 5, wherein the determination means determines the current mode of intervention based on the task evaluation information, the estimated state of the subject, and the mode of intervention determined in the past and the results of said intervention. [Note 7] The information processing apparatus according to any one of the appendices 1 to 5, further comprising output control means for outputting information based on the manner of the aforementioned interaction. [Note 8] The output control means is Information based on the manner of the aforementioned intervention, Information regarding the reliability of the evaluation, calculated based on the estimated state of the subject, An information processing device described in Appendix 7 that outputs the following. [Note 9] The determination means is an information processing device according to any one of the appendices 1 to 5, which determines the manner of the intervention relating to the task the subject will next undertake. [Note 10] The determination means is an information processing device according to any one of the appendices 1 to 5, which determines the manner of intervention regarding changes in the mental and physical state of the subject. [Note 11] Computers We obtain task evaluation information regarding the evaluation of the subject's performance on the task. The state of the subject during the execution of the aforementioned task is estimated, Based on the task evaluation information and the estimated state of the subject, the manner of intervention with the subject is determined. How to decide. [Note 12] We obtain task evaluation information regarding the evaluation of the subject's performance on the task. The state of the subject during the execution of the aforementioned task is estimated, A storage medium containing a program that causes a computer to perform a process to determine the manner of intervention with the subject based on the task evaluation information and the estimated state of the subject.

[0102] Although the present invention has been described above with reference to embodiments, the present invention is not limited to the above embodiments. Various modifications to the structure and details of the present invention can be made that are understandable to those skilled in the art within the scope of the present invention. That is, the present invention naturally includes the full disclosure, including the claims, and various modifications and alterations that those skilled in the art could make in accordance with the technical idea. Furthermore, each disclosure of the above-mentioned patent documents and other references is incorporated herein by reference. [Industrial applicability]

[0103] For example, it can be used in services related to self-learning and self-training. [Explanation of Symbols]

[0104] 1, 1A, 1X Information Processing Device 2 Input devices 3. Output device 4 Storage device 8 Terminal devices 100, 100A Task Evaluation and Intervention System

Claims

1. A means for obtaining task evaluation information regarding the evaluation of the subject's performance on the task, Estimation means for estimating the state of the subject during the execution of the task, The system includes a determination means for determining the manner of intervention with the subject based on the task evaluation information and the estimated state of the subject, The estimation means estimates the state of the subject based on information observed of the subject during a predetermined period of time while the task is being performed. The estimation means is an information processing device that shortens the predetermined period as the evaluation is higher.

2. The information processing apparatus according to claim 1, wherein the estimation means estimates the state of the subject based on a facial image of the subject captured by a visible light camera.

3. The information processing apparatus according to claim 1, wherein the evaluation is an evaluation of the correctness of the subject's answers to the questions included in the task.

4. The information processing apparatus according to claim 3, wherein the estimation means estimates the state of the subject based on information observed of the subject during the period in which the erroneous answer was given.

5. The information processing apparatus according to any one of claims 1 to 4, wherein the determination means determines the current mode of intervention based on the task evaluation information, the estimated state of the subject, and the mode of intervention determined in the past and the results of said intervention.

6. An acquisition means for acquiring task evaluation information relating to the evaluation of the subject's performance of a task, Estimation means for estimating the state of the subject during the execution of the task, A determination means for determining the manner of intervention with the subject based on the task evaluation information and the estimated state of the subject, It has an output control means that outputs information based on the manner of the interaction, The output control means is Information based on the manner of the aforementioned intervention, Information regarding the reliability of the evaluation, calculated based on the estimated state of the subject, An information processing device that outputs [something].

7. The information processing apparatus according to any one of claims 1 to 4, wherein the determination means determines the manner of the intervention relating to the task the subject will next undertake.

8. The information processing apparatus according to any one of claims 1 to 4, wherein the determination means determines the manner of the intervention relating to the change in the mental and physical state of the subject.

9. Computers We obtain task evaluation information regarding the evaluation of the subject's performance on the task. Based on the information obtained by observing the subject during a predetermined period while the task is being performed, the state of the subject during the task is estimated. The higher the evaluation, the shorter the predetermined period. Based on the task evaluation information and the estimated state of the subject, the manner of intervention with the subject is determined. How to decide.

10. We obtain task evaluation information regarding the evaluation of the subject's performance on the task. Based on the information obtained by observing the subject during a predetermined period while the task is being performed, the state of the subject during the task is estimated. The higher the evaluation, the shorter the predetermined period. A program that causes a computer to perform a process to determine the manner of intervention with the subject based on the task evaluation information and the estimated state of the subject.

Images