JP2021023492A - Concentration degree analysis device, concentration degree analysis method, and program - Google Patents

Abstract

To provide a technology to enable objective evaluation on relationships between a state of ambient environment and a state of a person's concentration.SOLUTION: A concentration degree analysis device includes: a concentration degree estimation unit for estimating a concentration degree, which is an index indicating a concentration degree of an object person, on the basis of data acquired from a first sensor for monitoring a state of the object person; a concentration environment degree estimation unit for estimating a concentration environment degree, which is an index indicating a degree of easiness of concentration in the environment, on the basis of data acquired from a second sensor for monitoring a state of the periphery of the object person; an output unit for temporally associating the concentration degree estimated by the concentration degree estimation unit and the concentration environment degree estimated by the concentration environment degree estimation unit, and outputting them.SELECTED DRAWING: Figure 2

Description

The present invention relates to a technique for grasping the relationship between the state of the surrounding environment and the state of concentration of people.

It is empirically known that in an unpleasant environment or a noisy environment, concentration is reduced and efficiency of work and study is reduced. Therefore, in recent years, some companies and educational institutions are trying to improve the environment in order to improve labor efficiency and learning efficiency.

However, at present, it is difficult to measure the effect of environmental improvement because there is no mechanism for objectively evaluating the relationship between the state of the surrounding environment and the state of concentration of people. In addition, various factors such as temperature, humidity, illuminance, and noise can be considered as factors that may affect people's concentration, and it is expected that which factor has the greatest effect will differ on a case-by-case basis. Will be done.

Patent Document 1 proposes a method of estimating the concentration of a car driver or a factory worker by image analysis of a camera. However, Patent Document 1 does not disclose a mechanism for objectiveizing the relationship between the state of the surrounding environment and the state of concentration of people.

Japanese Patent No. 6245398

The present invention has been made in view of the above circumstances, and an object of the present invention is to provide a technique capable of objectively evaluating the relationship between the state of the surrounding environment and the state of concentration of people. is there.

In order to achieve the above object, the present invention adopts the following configuration.

The first aspect of the present invention is concentration estimation, which is an index indicating the degree of concentration of the subject, based on the data obtained from the first sensor for monitoring the condition of the subject. Concentration ratio estimation that estimates the degree of concentration ratio, which is an index showing the degree of an environment in which it is easy to concentrate, based on the data obtained from the unit and the second sensor for monitoring the surrounding condition of the subject. It is characterized by having a unit, an output unit that outputs a concentration ratio estimated by the concentration degree estimation unit, and a concentration environment degree estimated by the concentration environment degree estimation unit in a timely manner. To provide a concentration ratio analyzer.

According to this configuration, the "degree of concentration of the target person" and the "state around the target person" are indexed (quantified) as the "degree of concentration" and the "degree of concentration environment", respectively, and they are temporally measured. It can be grasped in association with each other. This makes it possible to objectively and quantitatively grasp and evaluate the relationship between the state of the surrounding environment and the state of concentration of the subject.

The output unit may output a graph in which the time-series data of the concentration degree and the time-series data of the concentration environment degree are superimposed on the time axis. By observing such a graph, the user can objectively grasp the relationship between the state of the surrounding environment and the state of concentration.

The first sensor includes a camera for photographing the target person, and the concentration ratio estimation unit determines the concentration degree of the target person by analyzing the movement of the target person from an image obtained by the camera. You may estimate. For example, the movement of the subject may include at least one of a change in the position of the face, a change in the orientation of the face, and the degree of opening and closing of the eyes. According to the method using the image of the camera, the condition of the subject can be monitored in a non-contact and non-invasive manner.

The first sensor includes a vital sensor, and the concentration estimation unit estimates the concentration of the subject by analyzing changes in the vital data of the subject obtained by the vital sensor. May be good. By using vital data, it can be expected that the concentration state of the subject can be estimated with higher accuracy.

The second sensor includes an environment sensor capable of outputting data of at least two items of temperature, humidity, illuminance, atmospheric pressure, CO2 concentration, volatile organic compound concentration, and noise, and the centralized environmental degree estimation unit. May estimate the degree of centralized environment by integrating the data of a plurality of items obtained by the environmental sensor. By using the measurement data of a plurality of items, the accuracy and reliability of the degree of centralized environment can be improved.

It has an analysis unit that analyzes the time-series data of the centralized environment degree and / or the time-series data of the centralized degree, and the output unit may output the information obtained by the data analysis. It can be expected that the relationship between the environmental state and the concentration state can be grasped in more detail by grasping not only the concentration environment degree and the instantaneous value of the concentration degree but also the temporal change and tendency of the value.

For example, the analysis unit identifies a change in the concentration environment as a causative event of the decrease or increase in the concentration based on the correlation between the time-series data of the concentration environment and the time-series data of the concentration. You may. Further, when the concentration environment degree is estimated by aggregating the data of a plurality of items related to the environment, the analysis unit determines which item among the plurality of items related to the environment is the concentration as the cause event. It may be specified whether it contributes to the change in the degree of environment. By such factor analysis, it becomes easy to identify the cause of the decrease or increase in the degree of concentration. If the cause of the decrease or increase in the degree of concentration is known, the information can be used for improving the environment or automatically controlling the environment.

Based on the time-series data of the concentration of the subject, the analysis unit obtains a concentration evaluation value which is an index for evaluating both the high concentration of the subject and the length of time when the subject is concentrated. You may. By using such a concentration evaluation value, it is possible to objectively and quantitatively grasp the concentration ability of the subject.

The analysis unit may obtain statistical information based on the time-series data of the concentration degree of a plurality of subjects and / or the time-series data of the concentration environment degree in a plurality of environments. Useful information can be obtained by performing macro evaluation based on statistical information.

An abnormality detection unit that detects an abnormality of the first sensor may be further provided. This is because if there is an abnormality in the first sensor, the estimation of the concentration degree fails or the reliability of the estimation result is lowered.

The present invention may be regarded as a concentration analysis device having at least a part of the above means, or may be regarded as a concentration evaluation device, a concentration monitoring device, a concentration environment evaluation device, or the like. Further, the present invention can be regarded as a method including at least a part of the above processing, a program for realizing such a method, or a recording medium on which the program is recorded. The present invention can be constructed by combining each of the above means and treatments with each other as much as possible.

According to the present invention, it is possible to objectively evaluate the relationship between the state of the surrounding environment and the state of concentration of people.

FIG. 1 is a diagram showing an application example of the concentration ratio analysis device. FIG. 2 is a diagram showing a configuration example of the concentration analysis device of the first embodiment. FIG. 3 is a flowchart showing the flow of the concentration estimation process. FIG. 4 is a flowchart showing the flow of the centralized environment degree estimation process. FIG. 5 is a diagram showing a display example of the estimation results of the concentration degree and the concentration environment degree. FIG. 6 is a diagram showing a display example of the data analysis result. FIG. 7 is a diagram showing an example of the centralized evaluation value of the subject. FIG. 8 is a diagram showing a configuration example of the concentration analysis device of the second embodiment.

<Application example>
One of the application examples of the present invention will be described with reference to FIG. FIG. 1 shows an example in which an educational institution such as a school or a cram school applies the concentration analysis device 10 according to the embodiment of the present invention to grasp and analyze the concentration degree of students in class.

In the example of FIG. 1, the concentration analysis device 10 is installed on the desk of the subject (student) 11, and the concentration analysis device 10 is in the state of the subject 11 in class and around the subject 11. The condition is constantly monitored. The concentration analysis device 10 estimates the degree of concentration of the subject 11 (an index showing the degree of concentration) from the state of the subject 11, and also estimates the degree of concentration environment (an index showing the degree of concentration) from the surrounding state. ) Is estimated. Then, the concentration analysis device 10 outputs information in which the concentration degree and the concentration environment degree are temporally associated with each other. Further, the concentration analysis device 10 analyzes the time-series data of the concentration environment degree and / or the concentration degree, and outputs various information obtained by the data analysis. The information output destination may be a display device owned by the concentration analysis device 10 or connected to the concentration analysis device 10, or an external device 12. The external device 12 is, for example, a terminal used by the teacher, a server for management, a data storage, and the like.

According to such a concentration analysis device 10, the state of the surrounding environment of the target person 11 and the concentration state of the target person 11 can be compared and analyzed while taking a temporal correspondence, so that the surrounding environment and the degree of concentration can be analyzed. It becomes possible to objectively evaluate the relationship between. The obtained evaluation results and analysis results can be used, for example, as reference data for constructing an environment in which it is easy to concentrate on lessons, or for measuring the effect of environmental improvement on learning efficiency. ..

Although the present invention has been applied here to grasp and evaluate the degree of concentration of students in a learning institution, the scope of application of the present invention is not limited to this. For example, it is required to concentrate on things such as grasping and evaluating the degree of concentration of employees in offices and factories, and grasping and evaluating the degree of concentration of drivers (pilots) in automobiles, trains, airplanes, large machines, plants, etc. The present invention can be preferably applied to various scenes.

<First Embodiment>
A specific configuration example of the concentration analysis device 10 according to the embodiment of the present invention will be described with reference to FIG.

The concentration analysis device 10 generally includes a camera 20, an environment sensor 21, an information processing device 22, and a display device 23. The camera 20, the environment sensor 21, the information processing device 22, and the display device 23 may be integrally configured, or some of these configurations may be separated and connected by a cable or a bus. Further, the concentration analysis device 10 may be a dedicated device, or the concentration analysis device 10 may be configured by connecting the camera 20 or the environment sensor 21 to a general-purpose computer such as a personal computer or a smartphone. If the general-purpose computer has a built-in camera or sensor, they may be used. Alternatively, instead of installing a camera or an environment sensor for each target person, data may be acquired by wire or wirelessly from a sensor installed on a wall or ceiling.

(Camera 20)
The camera 20 is a first sensor for monitoring the state of the subject 11. In the present embodiment, the camera 20 is installed at a position where the face of the subject 11 is photographed. As the camera 20, either a monochrome camera or a color camera may be used. The camera 20 captures images at predetermined time intervals (for example, 30 fps). The image data obtained by the camera 20 is input to the information processing device 22.

(Environment sensor 21)
The environment sensor 21 is a second sensor for monitoring the surrounding state of the subject 11. The environment sensor 21 of the present embodiment has a plurality of types of sensor modules and communication modules, and can sense a plurality of items. Sensing items include, for example, temperature (air temperature), humidity, illuminance, atmospheric pressure, CO2 (carbon dioxide) concentration, VOC (volatile organic compound) concentration, noise and the like. The environmental sensor 21 may correspond to at least two or more of these items. The measurement data obtained by the environment sensor 21 is input to the information processing device 22.

(Information processing device 22)
The information processing device 22 is a processing unit that estimates the degree of concentration and the degree of concentration environment based on the image data of the target person 11 obtained from the camera 20 and the measurement data obtained by the environment sensor 21. As shown in FIG. 2, the information processing apparatus 22 of the present embodiment has mainly the image acquisition unit 220, the environment information acquisition unit 221 and the concentration estimation unit 222, the concentration environment degree estimation unit 223, and the analysis unit 224. It has an output unit 225 and a storage unit 226.

The image acquisition unit 220 has a function of acquiring image data from the camera 20. The environmental information acquisition unit 221 has a function of acquiring measurement data from the environment sensor 21. The concentration ratio estimation unit 222 has a function of estimating the concentration level of the subject 11 based on the image data obtained from the camera 20. The centralized environmental degree estimation unit 223 has a function of estimating the centralized environmental degree based on the measurement data obtained from the environment sensor 21. The analysis unit 224 has a function of analyzing the time series data of the concentration degree and the time series data of the concentration environment degree. The output unit 225 has a function of outputting the information obtained by the concentration estimation unit 222, the concentration environment estimation unit 223, the analysis unit 224, and the like to the display device 23 and the external device. The storage unit 226 has a function of storing image data, measurement data, concentration degree and concentration environment degree data, analysis results, and the like. Details of each of these parts will be described later.

The information processing device 22 may be composed of, for example, a general-purpose computer including at least a CPU (processor), a memory, and a non-volatile storage device. In that case, the above-described configuration of reference numerals 220 to 226 is realized by software by reading the program stored in the storage device into the memory and executing the program by the CPU. The configuration of the information processing device 22 is not limited to this, and for example, the configurations of reference numerals 220 to 226 may be realized by a plurality of devices by utilizing the techniques of distributed computing and cloud computing. Alternatively, part or all of the configurations of reference numerals 220 to 226 may be realized by a circuit such as FPGA or ASIC.

(Estimation of concentration ratio)
The flow of the concentration estimation process by the concentration analysis device 10 will be described with reference to the flowchart of FIG.

In step S30, the image acquisition unit 220 captures image data for a predetermined number of determination frames from the camera 20. The "determination frame number" is a parameter that determines the number of frames used for calculating the degree of concentration, and its value is set in advance. For example, in the image data of 30 fps, when the number of determination frames is set to 150, the degree of concentration is determined by analyzing the movement (behavior) of the subject 11 in the moving image for 5 seconds.

When a person is focused on things, the movement of the face and eyes tends to be small, and the degree of opening and closing of the eyes tends to be large. On the other hand, when attention is distracted or drowsiness occurs, the movement of the face and eyes tends to increase, and the degree of opening and closing of the eyes tends to decrease. Based on these findings, in this embodiment, three evaluations are made: "change in face position", "change in face orientation", and "eye opening / closing degree", and the total score of these evaluation points is "concentrated". Defined as "degree".

In step S31, the concentration ratio estimation unit 222 evaluates the change in the position of the face. Specifically, first, the concentration estimation unit 222 detects a face from each frame and obtains the center coordinates of the face. For example, the center of the bounding box surrounding the detected face may be regarded as the center of the face, the center of gravity of the contour of the face may be regarded as the center of the face, and the position of facial organs such as the nose may be regarded as the center of the face. May be regarded as. Next, the concentration estimation unit 222 calculates the amount of movement of the face for each frame. The amount of movement of the face is, for example, the absolute value of the difference between the center coordinates of the face between the target frame and the previous frame. Next, the concentration estimation unit 222 calculates the statistical value (Vc) of the movement amount of the face in the image data corresponding to the number of determination frames. The statistical value is, for example, an average value, an intermediate value, a mode value, a maximum value, a total value, and the like. Then, the concentration ratio estimation unit 222 obtains the evaluation point Sc of the change in the position of the face as follows by comparing the statistical value Vc of the movement amount with the threshold values THc1 and THc2.
Vc <THc1: Sc = 2 points THc1 ≦ Vc <THc2: Sc = 1 point THc2 ≦ Vc: Sc = 0 points That is, the smaller the change in the position of the face, the higher the evaluation point is given.

ここで、ｎは判定フレーム数、ｘ_ｉは各フレームでの顔向き、ｘ_ａは判定フレーム数分の画像データにおける顔向きの平均値である。次に、集中度推定部２２２は、上下方向の分散値と左右方向の分散値のうち大きい方を代表の分散値として採用し、代表の分散値ｓ^２から標準偏差ｓを計算する。そして、集中度推定部２２２は、代表の標準偏差をしきい値ＴＨｄ１、ＴＨｄ２と比較することにより、以下のように顔向きの変化の評価点Ｓｄを求める。
ｓ＜ＴＨｄ１ ：Ｓｄ＝２点
ＴＨｄ１≦ｓ＜ＴＨｄ２：Ｓｄ＝１点
ＴＨｄ２≦ｓ ：Ｓｄ＝０点
すなわち、顔向きの変化が小さいほど高い評価点が与えられる。 In step S32, the concentration ratio estimation unit 222 evaluates the change in face orientation. Specifically, first, the concentration ratio estimation unit 222 obtains the "direction" of the face detected from each frame. In the present embodiment, the face orientation in the vertical direction and the face orientation in the horizontal direction are calculated respectively. The face orientation may be a continuous value or a discrete value. Next, the concentration estimation unit 222 calculates the dispersion value of the face orientation in the image data for the number of determination frames in each of the vertical direction and the horizontal direction. The variance s ^{2 for the} face is calculated by the following formula.

Here, n is the number of determination frames, x _i is the face orientation in each frame, and x _a is the average value of the face orientation in the image data for the number of determination frames. Next, the concentration estimation unit 222 adopts the larger of the vertical variance value and the horizontal variance value as the representative variance value, and calculates the standard deviation s from the ^{representative variance value s 2.} Then, the concentration ratio estimation unit 222 obtains the evaluation point Sd of the change in face orientation as follows by comparing the representative standard deviation with the threshold values THd1 and THd2.
s <THd1: Sd = 2 points THd1 ≦ s <THd2: Sd = 1 point THd2 ≦ s: Sd = 0 points That is, the smaller the change in face orientation, the higher the evaluation point is given.

In step S33, the concentration ratio estimation unit 222 evaluates the degree of opening and closing of the eyes. Specifically, first, the concentration ratio estimation unit 222 obtains the "eye opening / closing degree" of the face detected from each frame. For example, the concentration ratio estimation unit 222 may determine the degree of opening and closing of the eyes from the shape of the eyes, the distance between the upper and lower eyelids, the relative relationship with other facial organs, and the like. In the present embodiment, the state in which the eyes are completely closed is 0, the state in which the eyes are most open is 10, and the degree of opening and closing of the eyes is determined in 10 steps. Next, the concentration estimation unit 222 calculates the statistical value (Ve) of the opening / closing degree of the eyes in the image data corresponding to the number of determination frames. The statistical value is, for example, an average value, an intermediate value, a mode value, a maximum value, a total value, and the like. Then, the concentration estimation unit 222 obtains the evaluation point Se of the opening / closing degree of the eyes as follows by comparing the statistical value Ve of the opening / closing degree of the eyes with the threshold value The.
Ve> The: Se = 1 point Ve ≦ The: Se = 0 point That is, the larger the degree of opening and closing of the eyes, the higher the evaluation point is given.

In step S34, the concentration estimation unit 222 sums the evaluation points Sc, Sd, and Se obtained in steps S31 to S33, and calculates the concentration = Sc + Sd + Se. However, if any one of Sc, Sd, and Se has 0 points, the concentration level is set to 0.

In step S35, the concentration ratio estimation unit 222 stores the evaluation result, the estimation result, and the like in the storage unit 226. The data recorded here may include at least the value of the degree of concentration and the shooting time of the image data used for the estimation, and further, the image data used for the estimation and the evaluation calculated in steps S31 to S33. Points Sc, Sd, Se and the like may be included.

(Estimation of centralized environment)
The flow of the concentration environment degree estimation process by the concentration level analysis device 10 will be described with reference to the flowchart of FIG. The process of FIG. 4 is executed at predetermined time intervals (for example, once every 5 seconds).

In step S40, the environmental information acquisition unit 221 acquires measurement data from the environment sensor 21. The measurement data of this embodiment includes five items of data: temperature (air temperature), humidity, illuminance, noise, and carbon dioxide concentration. In this embodiment, four "discomfort index", "illuminance", "noise", and "carbon dioxide concentration" obtained from temperature (air temperature) and humidity are evaluated, and the total score of these evaluation points is a "concentrated environment". Defined as "degree".

In step S41, the concentration environment degree estimation unit 223 evaluates the discomfort index DI. The discomfort index DI can be obtained by the following formula when the temperature (air temperature) is T [° C.] and the humidity is H [%].
DI = 0.81T + 0.01H x (0.99T-14.3) + 46.3
Then, the concentration environment degree estimation unit 223 obtains the evaluation point Sdi of the discomfort index DI as follows.
DI <55: Sdi = -2 points 55 ≤ DI <60: Sdi = -1 point 60 ≤ DI <65: Sdi = 2 points 65 ≤ DI <70: Sdi = 5 points 70 ≤ DI <75: Sdi = 2 points 75 ≤ DI <80: Sdi = -1 point 80 ≤ DI <85: Sdi = -3 points 85 ≤ DI: Sdi = -5 points

In step S42, the centralized environment degree estimation unit 223 obtains the evaluation point Sal of the illuminance AL [lp] as follows.
AL <50: Sal = -5 points 50 ≤ AL <100: Sal = -3 points 100 ≤ AL <150: Sal = -1 point 150 ≤ AL <1000: Sal = 3 points 1000 ≤ AL <2000: Sal = 1 Points 2000 ≤ AL <3000: Sal = -1 point 3000 ≤ AL: Sal = -3 points

In step S43, the centralized environment degree estimation unit 223 obtains the evaluation point Ssn of the noise SN [dB] as follows.
SN <40: Ssn = 5 points 40 ≦ SN <50: Ssn = 4 points 50 ≦ SN <60: Ssn = 3 points 60 ≦ SN <70: Ssn = 1 point 70 ≦ SN <80: Ssn = -1 point 80 ≦ SN <90: Ssn = -2 points 90 ≦ SN <100: Ssn = -3 points 100 ≦ SN: Ssn = -5 points

In step S44, the centralized environmental degree estimation unit 223 obtains the evaluation point Sco2 of the carbon dioxide concentration CO2 [ppm] as follows.
CO2 <500: Sco2 = 5 points 500 ≦ CO2 <700: Sco2 = 3 points 700 ≦ CO2 <1000: Sco2 = 1 point 1000 ≦ CO2 <10000: Sco2 = -2 points 10000 ≦ CO2: Sco2 = -5 points

In step S45, the concentration environment degree estimation unit 223 sums the evaluation points Sdi, Sal, Ssn, and Sco2 obtained in steps S41 to S44, and calculates the concentration environment degree = Sdi + Sal + Ssn + Sco2.

In step S46, the centralized environment degree estimation unit 223 stores the evaluation result, the estimation result, and the like in the storage unit 226. The data recorded here should include at least the value of the degree of concentration environment and the measurement time of the measurement data used for estimation, and further, the measurement data used for estimation and the evaluation points calculated in steps S41 to S44. Sdi, Sal, Ssn, Sco2 and the like may be included.

FIG. 5 is a display example of the estimation results of the concentration degree and the concentration environment degree by the output unit 225. In this example, a graph in which the time-series data of the concentration degree and the time-series data of the concentration environment are superimposed on the time axis is output. The horizontal axis is time, and the vertical axis is the degree of concentration (solid line) and the degree of concentration environment (dotted line). By observing such a graph, the user (administrator) can objectively grasp the relationship between the state of the surrounding environment and the state of concentration.

(Data analysis)
The analysis unit 224 analyzes the time-series data of the concentration degree and the time-series data of the concentration environment degree recorded and accumulated in the storage unit 226. The information obtained by the analysis unit 224 may be recorded in the storage unit 226 in association with the data of the degree of concentration and the degree of concentration environment. The content of the data analysis by the analysis unit 224 and the type of information to be acquired may be any, and may be appropriately selected according to the application or application situation of this device, the purpose of data analysis, and the like. An example of data analysis will be described below.

The analysis unit 224 may perform a correlation analysis between the time-series data of the concentration environment and the time-series data of the concentration. For example, when the environment deteriorates, such as when the classroom becomes hot and humid, the effect immediately appears as a decrease in concentration. That is, it is expected that the degree of concentration environment and the degree of concentration will change in almost the same way with a certain time delay. Therefore, it is possible to grasp the causal relationship between the change in the concentration environment and the change in the concentration ratio by performing the correlation analysis, and it is possible to identify the change in the concentration environment as the causative event of the decrease or increase in the concentration level. It becomes. For example, as shown in FIG. 6, when a decrease in the concentration environment is observed at a certain time t1 and a decrease in the concentration level appears at a time t2 several minutes later, the analysis unit 224 determines the concentration degree at the time t2. It is considered that the cause of the decrease is the decrease in the concentration ratio at time t1. At this time, the analysis unit 224 further analyzes the value of the measurement data of the environmental sensor 21 before and after the time t1 and its evaluation value, and which of the plurality of items (temperature, humidity, illuminance, carbon dioxide concentration, noise, etc.) It may be specified whether the item contributes to the change in the degree of concentration environment at time t1. By such factor analysis, it becomes easy to identify the cause of the decrease in concentration. As shown in FIG. 6, the output unit 225 may display the result of the factor analysis. Further, the output unit 225 may notify the control device such as air conditioning and illuminance of the result of the factor analysis and automatically control the environment.

The analysis unit 224 may calculate the concentration evaluation value of the target person 11 based on the time series data of the concentration degree of the target person 11. The intensive evaluation value is an index for evaluating both the high degree of concentration and the length of time that the subject 11 is concentrated. For example, in the present embodiment, the area of the portion shown by the hatching in FIG. 7, that is, the time integral of the degree of concentration is obtained as the concentration evaluation value. This concentration evaluation value represents the concentration ability of the subject 11.

The analysis unit 224 may obtain statistical information based on time-series data of the concentration degree of a plurality of subjects. The concentration statistical information may include, for example, an average value, an intermediate value, a mode value, a maximum value, a minimum value, and the like. In addition, the number of people or the ratio whose concentration level is equal to or higher than the threshold value may be obtained as statistical information. The analysis unit 224 may obtain statistical information based on time-series data of the degree of centralized environment in a plurality of environments. Here, the "concentrated environment degree in a plurality of environments" may include not only the centralized environment degree in different places but also the centralized environment degree in the same place at different dates and times. The statistical information of the degree of concentration environment may include, for example, an average value, an intermediate value, a mode value, a maximum value, a minimum value, and the like. In addition, the number or ratio of the concentration environment degree equal to or higher than the threshold value may be obtained as statistical information. The analysis unit 224 may obtain statistical information based on both the time-series data of the concentration degree of the plurality of subjects and the time-series data of the concentration environment degree of the plurality of environments.

<Second Embodiment>
FIG. 8 shows the configuration of the concentration ratio analysis device 10 according to the second embodiment of the present invention. The concentration analysis device 10 according to the second embodiment includes an abnormality detection unit 227. Since the other configurations are the same as those of the first embodiment, the parts different from those of the first embodiment will be mainly described below, and the description of the configurations common to the first embodiment will be omitted.

During the operation of the concentration analysis device 10, the direction of the camera 20 may change due to accidental touching of the camera 20 by a hand or an object, and the face of the subject 11 may be out of the field of view of the camera 20. In addition, some people have a negative feeling about being constantly monitored, and such a person may intentionally block the view of the camera 20 or change the direction of the camera 20. Failure to capture the face of the subject 11 with the camera 20 is not preferable because the estimation of the degree of concentration fails and the reliability of the estimation result is lowered.

Therefore, in the present embodiment, the abnormality detection unit 227 detects the abnormality of the camera 20. The "camera abnormality" here means that the face of the subject 11 cannot be normally photographed by the camera 20. For example, the field of view of the camera 20 is obstructed, the orientation of the camera 20 deviates from the face of the subject 11, the failure of the camera 20, and the like correspond to "camera abnormalities".

The abnormality detection unit 227 uses, for example, a gyro sensor, an acceleration sensor, a vibration sensor, or the like to detect that the orientation of the camera 20 has changed, that an abnormal force or vibration has been applied to the camera 20, and the like. May be good. Alternatively, the abnormality detection unit 227 may detect that the orientation of the camera 20 has changed by taking the difference between the image captured from the camera 20 and the image captured in the past, or the camera 20 may be used. By confirming whether or not the image captured from the camera contains a face, it is detected that the field of view of the camera 20 is obstructed and that the direction of the camera 20 is off the face of the subject 11. May be good.

When the abnormality detection unit 227 detects an abnormality in the camera 20, the output unit 225 may output that the abnormality has been detected. By notifying the abnormality, the subject 11 can be encouraged to use the concentration ratio analysis device 10 correctly.

<Modification example>
The above-described embodiment is merely an example of a configuration example of the present invention. The present invention is not limited to the above-mentioned specific form, and various modifications can be made within the scope of its technical idea.

For example, in the above embodiment, only the camera 20 is used as the first sensor, but a sensor other than the camera 20 may be used, or a plurality of sensors including the camera 20 may be used. For example, as the first sensor, a vital sensor that acquires vital data of the subject 11 may be used. The concentration ratio estimation unit 222 can estimate the concentration ratio of the subject 11 by analyzing changes in vital data (for example, electrocardiogram, pulse wave, respiration, sweating, etc.).

In the above embodiment, only the environment sensor 21 is used as the second sensor, but a sensor other than the environment sensor 21 may be used, or a plurality of sensors including the environment sensor 21 may be used. Further, the items measured by the second sensor may include items other than temperature, humidity, illuminance, carbon dioxide concentration, and noise. For example, atmospheric pressure, concentration of volatile organic compounds, etc. may be measured.

<Appendix 1>
(1) Based on the data obtained from the first sensor (20) for monitoring the state of the subject (11), the concentration ratio, which is an index showing the degree of concentration of the subject (11), is estimated. Concentration ratio estimation unit (222) and
Based on the data obtained from the second sensor (21) for monitoring the surrounding condition of the subject (11), the concentration that estimates the degree of concentration environment, which is an index indicating the degree of the environment in which it is easy to concentrate. Environmental degree estimation unit (223) and
The output unit (225) that outputs the concentration degree estimated by the concentration degree estimation unit (222) and the concentration environment degree estimated by the concentration environment degree estimation unit (223) in a time-related manner. ,
Concentration ratio analyzer (10).

10: Concentration analysis device 11: Target person 12: External device 20: Camera 21: Environment sensor 22: Information processing device 23: Display device

Claims (14)

Based on the data obtained from the first sensor for monitoring the state of the subject, the concentration estimation unit that estimates the concentration, which is an index showing the degree of concentration of the subject, and the concentration estimation unit.
Based on the data obtained from the second sensor for monitoring the surrounding condition of the subject, the concentration environment degree estimation unit that estimates the concentration environment degree, which is an index indicating the degree of the environment in which it is easy to concentrate,
An output unit that outputs the concentration degree estimated by the concentration degree estimation unit and the concentration environment degree estimated by the concentration environment degree estimation unit in a timely manner.
Concentration ratio analyzer characterized by having. The concentration analysis device according to claim 1, wherein the output unit outputs a graph in which the time-series data of the concentration degree and the time-series data of the concentration environment degree are superimposed on the time axis. .. The first sensor includes a camera that captures the subject.
The concentration ratio according to claim 1 or 2, wherein the concentration ratio estimation unit estimates the concentration ratio of the target person by analyzing the movement of the target person from an image obtained by the camera. Analyst. The concentration analysis device according to claim 3, wherein the movement of the subject includes at least one of a change in the position of the face, a change in the orientation of the face, and the degree of opening and closing of the eyes. The first sensor includes a vital sensor.
Any of claims 1 to 4, wherein the concentration ratio estimating unit estimates the concentration of the target person by analyzing changes in the vital data of the target person obtained by the vital sensor. The concentration analyzer according to item 1. The second sensor includes an environment sensor capable of outputting data of at least two items of temperature, humidity, illuminance, atmospheric pressure, carbon dioxide concentration, volatile organic compound concentration, and noise.
The centralized environment degree estimation unit according to any one of claims 1 to 5, characterized in that the centralized environmental degree estimation unit estimates the centralized environmental degree by integrating the data of a plurality of items obtained by the environmental sensor. Concentration analyzer. It has an analysis unit that analyzes the time-series data of the concentration environment and / or the time-series data of the concentration.
The concentration analysis device according to any one of claims 1 to 6, wherein the output unit outputs information obtained by data analysis. The analysis unit identifies the change in the concentration environment as a causative event of the decrease or increase in the concentration ratio based on the correlation between the time series data of the concentration environment and the time series data of the concentration ratio. The concentration analysis device according to claim 7, which is characterized. When the degree of centralized environment is estimated by combining data of multiple items related to the environment,
The concentration according to claim 8, wherein the analysis unit identifies which of the plurality of items related to the environment contributes to the change in the concentration environment as the cause event. Degree analyzer. Based on the time-series data of the concentration of the subject, the analysis unit obtains a concentration evaluation value which is an index for evaluating both the high concentration of the subject and the length of time when the subject is concentrated. The concentration ratio analyzer according to any one of claims 7 to 9, wherein the concentration ratio analyzer is characterized by the above. Claim 7 to claim 7, wherein the analysis unit obtains statistical information based on the time-series data of the concentration degree of a plurality of subjects and / or the time-series data of the concentration environment degree in a plurality of environments. The concentration analyzer according to any one of 10. The concentration analysis device according to any one of claims 1 to 11, further comprising an abnormality detecting unit for detecting an abnormality of the first sensor. Based on the data obtained from the first sensor for monitoring the condition of the subject, the step of estimating the degree of concentration, which is an index showing the degree of concentration of the subject, and
Based on the data obtained from the second sensor for monitoring the surrounding condition of the subject, the step of estimating the degree of concentration environment, which is an index indicating the degree of the environment in which it is easy to concentrate, and
A step of temporally associating the estimated concentration degree with the estimated concentration environment degree and outputting the step.
Concentration ratio analysis method characterized by having. A program for causing a processor to execute each step of the concentration analysis method according to claim 13.

Images