Psychological distance estimation device, psychological distance estimation method, and psychological distance estimation program

Abstract

To provide a psychological distance estimation device capable of estimating human relationships.SOLUTION: A psychological distance estimation device includes: a vital data acquisition unit 32 for acquiring vital data in an autonomic nervous system activity of each of a plurality of measurement objects for each predetermined time. a standard normalization unit 33 for normalizing the vital data acquired by the vital data acquisition unit 32; and a synchronization degree calculation unit 35 for calculating a synchronization degree among the measurement objects in the plurality of measurement objects on the basis of the vital data normalized by the standard normalization unit 33.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to a psychological distance estimation device, a psychological distance estimation method, and a psychological distance estimation program. [Background technology]

[0002] It has been pointed out that in order to live a healthy and satisfying life both physically and mentally, not only physical health is important, but also emotional connections between people, which are related to the quality of human relationships. As opportunities for communication have decreased due to restrictions on activities caused by the COVID-19 pandemic, it is important to quantitatively indicate emotional distance, which is an indicator of connections with others.

[0003] In this regard, in order to understand a person's mental state, technologies have been proposed that estimate emotions using images and know an individual's emotions using autonomic nervous indices such as electroencephalograms and heart rate.

[0004] However, because it is difficult to separate physical and mental activity in autonomic nervous activity during free movement, it has been said that it is difficult to capture mental fluctuations using only the autonomic nervous system and central nervous system. Therefore, the above technology captures one-to-one emotions in a situation where the stimulus (input) is specific, and it is difficult to show the distance between the hearts of a group.

[0005] In order to solve the above problems, a technique has been proposed as described in Patent Document 1. The invention described in Patent Document 1 is capable of estimating the relationships between multiple subjects who are accompanied by each other. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Patent No. 6126540 Summary of the Invention [Problem to be solved by the invention]

[0007] However, the technology described in the above Patent Document 1 detects a person's activity state, such as the number of steps, and only determines the person's activity state. Therefore, there is a problem that it is not possible to estimate the interaction between people, that is, human relationships. In other words, there is a problem that it is not possible to determine who is on bad terms with whom and who is on good terms with whom, etc., based on the person's activity state alone.

[0008] In view of the above, an object of the present invention is to provide a psychological distance estimation device, a psychological distance estimation method, and a psychological distance estimation program capable of estimating human relationships. [Means for solving the problem]

[0009] The above object of the present invention can be achieved by the following means. Note that the parentheses indicate reference symbols of the embodiments described below, but the present invention is not limited thereto.

[0010] The psychological distance estimation device according to claim 1 includes: an acquisition means (e.g., a vital data acquisition unit 32 shown in FIG. 2 ) for acquiring vital data (e.g., pulse data) in the autonomic nervous activity of each of a plurality of subjects at predetermined time intervals; The device is characterized by comprising a calculation means (e.g., synchronization degree calculation unit 35 shown in FIG. 2) that calculates the degree of synchronization between the multiple measurement subjects based on the vital data (e.g., pulse data) acquired by the acquisition means (e.g., vital data acquisition unit 32 shown in FIG. 2).

[0011] The psychological distance estimation device of claim 2 is characterized in that, in the psychological distance estimation device described in claim 1, it further has a generation means (e.g., self-organizing map generation unit 36 ​​shown in Figure 2) that generates a self-organizing map based on the synchronization degree calculated by the calculation means (e.g., synchronization degree calculation unit 35 shown in Figure 2).

[0012] A psychological distance estimation device according to claim 3 is the psychological distance estimation device according to claim 1 or 2, further comprising standard normalization means (e.g., standard normalization unit 33 shown in FIG. 2) for normalizing the vital data (e.g., pulse data) acquired by the acquisition means (e.g., vital data acquisition unit 32 shown in FIG. 2), The calculation means (e.g., synchronization degree calculation unit 35 shown in FIG. 2) is characterized in that it calculates the degree of synchronization between the measurement subjects among the multiple measurement subjects based on the vital data (e.g., pulse data) normalized by the standard normalization means (e.g., standard normalization unit 33 shown in FIG. 2).

[0013] A psychological distance estimation method according to claim 4 is a psychological distance estimation method executed by a predetermined device (for example, the psychological distance estimation device 3 shown in FIG. 1 ), A step of acquiring vital data (e.g., pulse data) on the autonomic nervous system activity of each of a plurality of subjects at predetermined time intervals (e.g., step S1 shown in FIG. 3 ); The method further includes a step of calculating a degree of synchronization between the plurality of measurement subjects based on the acquired vital data (e.g., pulse data) (e.g., step S4 shown in FIG. 3).

[0014] The psychological distance estimation program according to claim 5 comprises: A computer (for example, the psychological distance estimation device 3 shown in FIG. 1) A first process (see, for example, the vital data acquisition unit 32 shown in FIG. 2 ) of acquiring vital data (e.g., pulse data) on the autonomic nervous system activity of each of a plurality of subjects at predetermined time intervals; and executing a second process (see, for example, synchronization degree calculation unit 35 shown in FIG. 2) of calculating the degree of synchronization between the multiple measurement subjects based on the vital data (for example, pulse data) acquired in the first process. Effect of the Invention

[0015] Next, the effects of the present invention will be described with reference to the drawings. Note that the reference symbols in the parentheses are those of the embodiments described below, but the present invention is not limited thereto.

[0016] According to the invention of claims 1, 4 and 5, the degree of synchronization between a plurality of subjects is calculated based on acquired vital data (e.g., pulse data), so that human relationships can be estimated.

[0017] According to the invention as set forth in claim 2, a self-organizing map is generated based on the calculated degree of synchrony, so that human relationships can be inferred at a glance.

[0018] According to the invention of claim 3, since the acquired vital data (for example, pulse data) is normalized, the accuracy of the subsequent data processing is improved. [Brief description of the drawings]

[0019] [Figure 1] 1 is a schematic overall view of a psychological distance visualization system according to an embodiment of the present invention; [Diagram 2] FIG. 2 is a functional configuration diagram of the psychological distance estimation device according to the embodiment. [Diagram 3] 4 is a flowchart illustrating the process of the psychological distance estimation device according to the embodiment. FIG. [Figure 4] FIG. 4 is a flowchart showing the creation of the degree of synchronization shown in FIG. [Diagram 5] FIG. 4 is a flow chart showing the creation of the self-organizing map shown in FIG. 3. [Figure 6] FIG. 1A shows the waveform of the heart rate of one of the multiple subjects, and FIG. 1B shows the waveform extracting the trend in the heart rate of one of the multiple subjects. [Figure 7] FIG. 13 is a diagram showing waveforms obtained by aligning time series trends in pulse data from three subjects out of a plurality of subjects. [Figure 8](a) shows the correlation analysis results using the heat map during “setting up a tent”, (b) shows the correlation analysis results using the heat map during “eating”, and (c) shows the correlation analysis results using the heat map during “making a bonfire”. [Figure 9] These show the self-organizing maps during the “pitching tent” phase. (a) shows the clustering of subjects based on the density of green and red colors, and (b) shows the clustering of subjects based on their proximity to two neurons. [Figure 10] These figures show self-organizing maps during a meal, where (a) shows the clustering of subjects based on the intensity of green and red colors, and (b) shows the clustering of subjects based on their proximity to two neurons. [Figure 11] These show the self-organizing maps during the “bonfire” period. (a) shows the clustering of subjects based on the density of green and red colors, and (b) shows the clustering of subjects based on their proximity to two neurons. [Figure 12] The figures show one-to-one self-organizing maps generated by measuring vital data on autonomic nervous system activity other than pulse rate. (a) shows the clustering of subjects based on the intensity of green and red colors, and (b) shows the clustering of subjects based on their proximity to two neurons. [Figure 13] These are self-organizing maps of multiple people generated by measuring vital data on autonomic nervous system activity other than pulse rate. (a) shows the clustering of subjects based on the intensity of green and red colors, and (b) shows the clustering of subjects based on their proximity to two neurons. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0020] Hereinafter, an embodiment of a psychological distance visualization system using a psychological distance estimation device according to the present invention will be described in detail with reference to the drawings. In the following description, when directions such as up, down, left, and right are indicated, they refer to up, down, left, and right when viewed from the front of the illustration.

[0021] <Outline of the psychological distance visualization system> The psychological distance visualization system according to this embodiment is capable of estimating human relationships. To explain this in detail, previous research (Dimitris Xygalatas, "Quantifying collective effervescence: Heart-rate dynamics at a fire-walking ritual", BIOLOGY, Nov 2011) has shown that the heart rate variability of people who gather for a ritual increases in similarity. In other words, it is known that the synchronization phenomenon of autonomic nervous behavior occurs between individuals (between measurement subjects).

[0022] Therefore, the inventors hypothesized that the overall results of behavior and psychological activity are reflected in autonomic nervous activity. Based on this hypothesis, the inventors came up with the idea that it might be possible to visualize psychological distance by measuring autonomic nervous activity and observing the synchronization (degree of empathy) between individuals (between measurement subjects), and came to invent a psychological distance visualization system 1 as shown in Fig. 1. The contents of the psychological distance visualization system 1 will be described in detail below with reference to the drawings.

[0023] 1, the psychological distance visualization system 1 is made up of a vital sign measuring device 2 and a psychological distance estimation device 3. Each component will be described in detail below.

[0024] <Explanation of vital signs measuring device> The vital sign measuring device 2 is composed of a wristwatch-type biosensor such as Apple Watch (registered trademark) or Fitbit (registered trademark) as shown in Fig. 1. Such a vital sign measuring device 2 is worn by the subject on the body, such as the arm, and is capable of measuring vital signs (pulse, blood pressure, slight sweating, body temperature, respiration, etc.) in the activity of the subject's autonomic nervous system. This vital sign measuring device 2 is capable of outputting the measured vital sign data, i.e., vital data, to the psychological distance estimation device 3 shown in Fig. 1.

[0025] <Explanation of the psychological distance estimation device> The psychological distance estimation device 3 is composed of a smartphone, a PC (Personal Computer), etc. Specifically, as shown in Fig. 1, the psychological distance estimation device 3 is composed of a CPU 3a that executes and controls each function of the psychological distance estimation device 3, an input unit 3b that can input predetermined data to the psychological distance estimation device 3 from the outside using a mouse, a keyboard, a touch panel, etc., an output unit 3c that can output predetermined data to the outside of the psychological distance estimation device 3, a ROM 3d consisting of a writable flash ROM or the like that stores predetermined programs, etc., a RAM 3e that functions as a working area, a buffer memory, etc., and a display unit 3f consisting of an LCD (Liquid Crystal Display), etc. The functions and processing of the psychological distance estimation device 3 described later are realized by the CPU 3a reading out a program stored in the ROM 3d and executing this program.

[0026] <Explanation of Functional Configuration of Psychological Distance Estimation Device> Next, the functional configuration of the psychological distance estimation device 3 will be described with reference to Fig. 2. As shown in Fig. 2, the functional configuration of the psychological distance estimation device 3 includes a judgment unit 30, a storage unit 31, a vital data acquisition unit 32, a standard normalization unit 33, a trend extraction unit 34, a synchronization degree calculation unit 35, and a self-organizing map generation unit 36. Each component will be described below.

[0027] The determination unit 30 exchanges information between the functional blocks based on the state held by the determination unit 30 or the state held by each functional block. Furthermore, the determination unit 30 also exchanges information with the vital sign measuring device 2.

[0028] The storage unit 31 stores data necessary for processing.

[0029] The vital data acquiring section 32 acquires vital data on the autonomic nervous activity of the subject measured by the vital sign measuring device 2 at predetermined time intervals (for example, every 5 minutes).

[0030] The standard normalization unit 33 normalizes the vital data acquired at predetermined time intervals by the vital data acquisition unit 32 as data preprocessing for calculation processing in the trend extraction unit 34, the synchronization degree calculation unit 35, and the self-organizing map generation unit 36, which will be described later. In particular, in this embodiment, standardization (for example, mean 0, variance 1) is performed as the normalization process.

[0031] The trend extraction unit 34 extracts a trend in the vital data in order to eliminate individual differences of the measurement subject in the vital data normalized by the standard normalization unit 33 and to reduce the influence of autonomic nerve reactions in a short period of time. Specifically, the trend extraction unit 34 calculates a moving average over a predetermined time period (e.g., 300 seconds) in the vital data normalized by the standard normalization unit 33, and extracts a trend in the vital data.

[0032] The synchronization degree calculation unit 35 calculates the degree of synchronization between the measurement subjects in the trend extracted by the trend extraction unit 34. Specifically, the trend extracted by the trend extraction unit 34 is represented by a waveform as shown in Fig. 6(b). Therefore, the synchronization degree calculation unit 35 calculates the degree of synchronization between the measurement subjects represented by the waveform as shown in Fig. 6(b) using known methods such as correlation coefficient, least squares method, Kuramoto model, dynamic time warping (DTW), etc.

[0033] The self-organizing map generating unit 36 ​​generates a self-organizing map that represents the clustering of the measurement subjects by using a neural network of the self-organizing map to calculate the degree of synchronization between the measurement subjects calculated by the synchronization degree calculating unit 35. Note that the self-organizing map is a type of neural network that is applied to important fields in the real world, such as process analysis, control, search systems, and even information analysis for management, and is an algorithm for clustering high-dimensional input data without any preliminary information such as a teacher signal (output that is considered ideal for the input data).

[0034] <An example of how to use the psychological distance visualization system> Next, an example of use of the psychological distance visualization system 1 according to this embodiment will be described with reference to the flowcharts shown in Figures 3 to 5. In the following, a specific example will be given to help the reader better understand the contents of the psychological distance visualization system 1 according to this embodiment.

[0035] As a premise, in one example of use of this embodiment, a plurality of people (10 people in this embodiment) were gathered as measurement subjects and engaged in camping activities. At this time, all of the measurement subjects were asked to wear the vital sign measuring device 2 shown in Fig. 1 and then engaged in camping activities. In this embodiment, the pulse rate of the measurement subjects is measured by the vital sign measuring device 2 as vital sign data.

[0036] Thus, in this state, the judgment unit 30 shown in Fig. 2 receives the pulse data of the measurement subjects measured by the vital sign measuring device 2, and outputs it to the vital data acquisition unit 32 shown in Fig. 2. In response to this, the vital data acquisition unit 32 acquires the pulse data of each of the multiple measurement subjects at predetermined time intervals (e.g., every 5 minutes) (step S1). The result is the waveform shown in Fig. 6(a). Note that the waveform shown in Fig. 6(a) shows the waveform of the heart rate of one measurement subject out of the multiple measurement subjects.

[0037] Next, the judgment unit 30 receives the pulse data of each of the multiple measurement subjects acquired by the vital data acquisition unit 32 shown in Fig. 2 from the vital data acquisition unit 32, and outputs it to the standard normalization unit 33 shown in Fig. 2. In response to this, the standard normalization unit 33 normalizes the pulse data of each of the multiple measurement subjects acquired at predetermined time intervals by the vital data acquisition unit 32 by standardizing (for example, to a mean of 0 and a variance of 1) (step S2).

[0038] Next, the judgment unit 30 receives the pulse data of each of the multiple measurement subjects normalized by the standard normalization unit 33 shown in Fig. 2 from the standard normalization unit 33, and outputs it to the trend extraction unit 34 shown in Fig. 2. In response to this, the trend extraction unit 34 calculates a moving average of the normalized pulse data of each of the multiple measurement subjects over a predetermined time period (e.g., 300 seconds) and extracts a trend in the pulse data of each of the multiple measurement subjects (step S3). The result is the waveform shown in Fig. 6(b). Note that the waveform shown in Fig. 6(b) shows a waveform in which a trend in the heart rate of one measurement subject out of the multiple measurement subjects is extracted.

[0039] Next, the judgment unit 30 receives trends in the pulse data of each of the multiple measurement subjects extracted by the trend extraction unit 34 shown in FIG. 2 from the trend extraction unit 34, and outputs them to the synchronization degree calculation unit 35 shown in FIG. 2. In response to this, the synchronization degree calculation unit 35 calculates the synchronization degree of the trends in the pulse data of each of the multiple measurement subjects extracted by the trend extraction unit 34 shown in FIG. 2 (step S4). To explain this point using a specific example, as shown in FIG. 4, the synchronization degree calculation unit 35 first aligns the time series of data that is a moving average over a predetermined time period (e.g., 300 seconds) (step S10). Specifically, as shown in FIG. 7, the synchronization degree calculation unit 35 aligns the time series of trends in the pulse data of each of the multiple measurement subjects. Note that in FIG. 7, the time series of trends in the pulse data of three people (illustrated as sub5, sub7, and sub8 in the figure) out of the multiple measurement subjects are aligned.

[0040] Next, the synchronization degree calculation unit 35 calculates a correlation coefficient between the measurement targets for each scene (step S11). Specifically, as shown in Fig. 7, the trend around 60 minutes indicates a scene of "setting up a tent" in the camping activity, the trend around 180 minutes to 240 minutes indicates a scene of "eating" in the camping activity, and the trend around 300 minutes indicates a scene of "making a bonfire" in the camping activity. Therefore, the synchronization degree calculation unit 35 calculates a correlation coefficient between the measurement targets for each scene shown in Fig. 7 in this embodiment, which is a known method.

[0041] Next, the synchronization degree calculation unit 35 creates a heat map based on the calculated correlation coefficient between the measurement targets for each scene shown in FIG. 7 (step S12). The results are shown in FIG. 8. FIG. 8(a) shows the correlation analysis result using the heat map at the time of "setting up a tent" among the camping activities, FIG. 8(b) shows the correlation analysis result using the heat map at the time of "eating" among the camping activities, and FIG. 8(c) shows the correlation analysis result using the heat map at the time of "making a campfire" among the camping activities. The correlation analysis result using the heat map shown in FIG. 8 will be displayed on the display unit 3f shown in FIG. 1.

[0042] By the way, the correlation analysis results using such a heat map can be confirmed as follows. For example, by focusing on sub7 and sub15 among multiple measurement subjects and looking at the heat map shown in Figure 8, it can be seen that the measurement subject's sub7 and sub15 both have low correlation coefficients with other measurement subjects at the time of "setting up tent" shown in Figure 8(a). From this, it can be seen that the measurement subject's sub7 and sub15 have a psychological distance from the other measurement subjects at this point.

[0043] On the other hand, the correlation coefficient of the measurement subject sub7 at the time of "meal" shown in Figure 8(b) is significantly higher than the correlation coefficient shown in Figure 8(a). This shows that the psychological distance between the measurement subject sub7 and the other measurement subjects has been reduced at this point.

[0044] On the other hand, the correlation coefficient of the measurement subject's sub15 at the time of "eating" shown in Figure 8(b) is slightly higher than that shown in Figure 8(a). This shows that the psychological distance between the measurement subject's sub15 and the other measurement subjects at this point in time has been slightly reduced compared to the time of "setting up a tent" shown in Figure 8(a).

[0045] On the other hand, the correlation coefficient of the measurement subject sub7 at the time of "bonfire" shown in Figure 8(c) is higher than that shown in Figure 8(b). This shows that the psychological distance between the measurement subject sub7 and the other measurement subjects has been significantly reduced at this point.

[0046] On the other hand, the correlation coefficient of the measurement subject's sub15 at the time of "bonfire" shown in Figure 8(c) is higher than that shown in Figure 8(b). This shows that the psychological distance between the measurement subject's sub15 and the other measurement subjects at this point in time has been significantly reduced compared to the time of "meal" shown in Figure 8(b).

[0047] Therefore, since the correlation coefficients of the sub7 and sub15 of the subjects are higher during the "bonfire" period compared to when "pitching the tent" was performed, it can be seen that the psychological distance between the subjects and the other subjects was significantly reduced during the "bonfire" period.

[0048] In this regard, when all subjects were asked in advance what scene they enjoyed, both sub7 and sub15 subjects answered "bonfire." Therefore, the results of this questionnaire show that there is a correlation between the pulse rates of subjects in the same psychological state.

[0049] Thus, in this way, it is possible to estimate human relationships.

[0050] However, as described above, by only calculating the degree of synchronization of trends in the pulse data of each of the measurement subjects by the synchronization degree calculation unit 35 (calculating the correlation coefficient in this embodiment), it is difficult to estimate human relationships without checking the numerical values. In other words, it is difficult to estimate human relationships at a glance.

[0051] Therefore, in this embodiment, in order to enable an estimation of human relationships at a glance, after completing the process of creating the synchronization degree shown in FIG. 3 (step S4), a self-organizing map is created as shown in FIG. 3.

[0052] Specifically, the judgment unit 30 receives the degree of synchronization of trends in the pulse data of each of the subjects from the degree of synchronization calculation unit 35 shown in FIG. 2, and outputs it to the self-organizing map generation unit 36 ​​shown in FIG. 2. In response to this, the self-organizing map generation unit 36 ​​uses the neural network of the self-organizing map to generate a self-organizing map representing the clustering of the subjects, based on the degree of synchronization between the subjects calculated by the degree of synchronization calculation unit 35 (step S5). To explain this point using a specific example, as shown in FIG. 5, the self-organizing map generation unit 36 ​​first sets a reference vector (step S20). Specifically, of the correlation coefficients shown in FIG. 8 calculated by the degree of synchronization calculation unit 35, for example, the value of the correlation coefficient between sub7 and sub15 is set as the reference vector.

[0053] Next, the self-organizing map generating unit 36 ​​compares the input data with the reference vector (step S21). That is, if the input data is, for example, the correlation coefficient between sub2 at the time of "setting up the tent" shown in Fig. 8(a) and other subjects, the self-organizing map generating unit 36 ​​compares the correlation coefficient between sub2 at the time of "setting up the tent" shown in Fig. 8(a) and other subjects with the reference vector set in step S20.

[0054] Next, the self-organizing map generating unit 36 ​​determines the vector that is closest to the reference vector among the input data compared in step S21 as a winning vector (step S22).

[0055] Next, the self-organizing map generating unit 36 ​​replaces the input data with the position of the winning vector (step S23), and updates the surrounding vectors to approximate values ​​of the winning vector (step S24).

[0056] In this manner, the self-organizing map generating unit 36 ​​repeats the processes of steps S21 to S24 until all inputs have been completed (step S25: NO), such as the correlation coefficient between sub3 at "pitching the tent" and other subjects shown in Fig. 8(a), the correlation coefficient between sub5 at "pitching the tent" and other subjects, etc. Then, when all inputs have been completed (step S25: YES), the self-organizing map generating unit 36 ​​ends the process.

[0057] Thus, as a result, the self-organizing map as shown in FIG. 9 to FIG. 11 is generated. Specifically, FIG. 9 is a self-organizing map at the time of "setting up a tent", FIG. 9(a) shows the clustering of the subjects by the density of green and red colors, and FIG. 9(b) shows the clustering of the subjects by the closeness to two neurons. FIG. 10 is a self-organizing map at the time of "eating", FIG. 10(a) shows the clustering of the subjects by the density of green and red colors, and FIG. 10(b) shows the clustering of the subjects by the closeness to two neurons. FIG. 11 is a self-organizing map at the time of "bonfire", FIG. 11(a) shows the clustering of the subjects by the density of green and red colors, and FIG. 11(b) shows the clustering of the subjects by the closeness to two neurons. The self-organizing maps shown in FIG. 9 to FIG. 11 are displayed on the display unit 3f shown in FIG. 1.

[0058] By the way, such a self-organizing map can be confirmed as follows. For example, if we focus on sub7 and sub15 among multiple measurement subjects, as shown in Figure 9(b), when "setting up tent", sub7 and sub15 are positioned farther away than the other measurement subjects, so it is clear at a glance that the psychological distance is quite large. In this regard, in Figure 9(a), the darker the red, the deeper the gap, and it is clear at a glance that there is a deep gap between sub7 and sub15 and the other measurement subjects.

[0059] On the other hand, when looking at FIG. 10(b) during "meal", sub7 is placed near the other measurement subjects, so it can be seen at a glance that the psychological distance between them is quite close. On the other hand, looking at FIG. 10(b), sub15 is placed near sub13, so it can be seen that the psychological distance between them is close, but since it is placed away from the other measurement subjects, it can be seen at a glance that there is still a psychological distance between them and the measurement subjects other than sub13. In this regard, looking at FIG. 10(a), it can be seen at a glance that the red color indicating the gap between sub7 and the other measurement subjects is lighter. On the other hand, since there is a dark red color between sub15 and the other measurement subjects other than sub13, it can be seen at a glance that there is still a deep gap between them.

[0060] On the other hand, when looking at the "bonfire" in FIG. 11(b), sub7 is placed closer to the other subjects compared to FIG. 10(b), so it is clear at a glance that the psychological distance between sub7 and the other subjects is much closer. On the other hand, when looking at FIG. 11(b), sub15 is placed closer to the other subjects, so it is clear at a glance that the psychological distance between sub15 and the other subjects is much closer. In this regard, when looking at FIG. 11(a), it is clear at a glance that the red color indicating the gap between sub7 and sub15 and the other subjects is lighter.

[0061] From the above, it is clear that the sub15 is closer to the other subjects during the bonfire. Furthermore, it can be inferred that the sub7 has higher communication skills than the sub15.

[0062] Thus, by generating a self-organizing map in this manner, it becomes possible to estimate human relationships at a glance.

[0063] Therefore, according to the present embodiment described above, it is possible to estimate human relationships.

[0064] <Description of Modifications> The shapes and the like shown in this embodiment are merely examples, and various modifications and changes are possible within the scope of the gist of the present invention described in the claims. In this embodiment, pulse rate is exemplified as vital data, but any vital data related to the autonomic nervous activity of the subject, such as blood pressure, slight sweating, body temperature, and respiration, may be used.

[0065] In this embodiment, the vital sign measuring device 2 is a wristwatch type, but any type may be used as long as it can measure vital sign data in the activity of the autonomic nervous system. For example, the face of the subject is captured by a camera, and the dilation and contraction state of the blood vessels of the subject is detected from the captured image captured by the camera, thereby measuring the vital sign data in the activity of the autonomic nervous system of the subject. The result obtained by performing the processes of steps S2 to S5 shown in FIG. 3 described above using the vital sign data measured in this way is a self-organizing map as shown in FIG. 12 to FIG. 13. FIG. 12(a) and FIG. 13(a) show the clustering of the subjects by the density of green and red colors, and FIG. 12(b) and FIG. 13(b) show the clustering of the subjects by the closeness to two neurons. FIG. 12 shows the psychological distance between two people, sub14 and sub21, and FIG. 12(a) shows that there is a red color indicating a gap between sub14 and sub21. Furthermore, when looking at FIG. 12(b), it can be seen that the distance between sub14 and sub21 is far. This makes it clear at a glance that there is still a psychological distance between sub14 and sub21. On the other hand, FIG. 13 shows the psychological distance between many people. In this regard, focusing on "21.0", when looking at FIG. 13(a), it can be seen that there is a red color indicating a gap between "21.0" and the other subjects. Furthermore, when looking at FIG. 13(b), it can be seen that the distance between "21.0" and the other subjects is far. This makes it clear at a glance that there is a psychological distance between "21.0" and the other subjects. Therefore, even if vital data other than pulse is used, it is possible to estimate human relationships. Therefore, any vital data in the autonomic nervous system activity of the subject (for example, blood pressure, slight sweating, body temperature, respiration, etc., as exemplified above) may be used.

[0066] In addition, in this embodiment, the trend extraction unit 34 is used to extract trends in the vital data, but if unnecessary, it is not necessary to extract trends.

[0067] In the present embodiment, the normalization is performed by the standard normalization unit 33 as data pre-processing, but normalization is not required. However, normalization is preferable because it improves the accuracy of the subsequent data processing.

[0068] In addition, in this embodiment, an example has been shown in which a correlation coefficient is used as a calculation method by the synchronization degree calculation unit 35, but any method that can calculate the synchronization degree, such as the least squares method, the Kuramoto model, or dynamic time warping (DTW), may be used.

[0069] The psychological distance estimation device 3 exemplified in this embodiment may be provided as the psychological distance estimation device 3 as in this embodiment, or may be installed on the cloud. Also, it may be provided as an application program and installed on an existing smartphone, PC, or the like so that it can be used as the psychological distance estimation device 3. [Industrial Applicability]

[0070] Incidentally, the psychological distance visualization system in this embodiment can be used in any place that can be used to understand or improve human relationships, such as schools, nursing homes, or matching apps. It can also be used to understand or improve one-to-one human relationships. [Explanation of symbols]

[0071] 1. Psychological Distance Visualization System 3. Psychological distance estimation device (prescribed device, computer) 32 Vital data acquisition unit (acquisition means, first processing) 33 Standard normalization section (standard normalization means) 35 Synchronization degree calculation unit (calculation means, second processing) 36 Self-organizing map generation unit (generation means)

Claims

1. an acquisition means for acquiring vital data on autonomic nervous system activity of each of a plurality of subjects at predetermined time intervals; A psychological distance estimation device comprising: a calculation means for calculating a degree of synchronization between the plurality of measurement subjects based on the vital data acquired by the acquisition means.

2. 2. The psychological distance estimation device according to claim 1, further comprising a generating means for generating a self-organizing map based on the degree of synchrony calculated by said calculating means.

3. The method further includes a standard normalization means for normalizing the vital data acquired by the acquisition means, 3. The psychological distance estimation device according to claim 1, wherein the calculation means calculates a degree of synchronization between the plurality of subjects based on the vital data normalized by the standard normalization means.

4. A psychological distance estimation method executed by using a predetermined device, acquiring vital data on autonomic nervous system activity of each of a plurality of subjects at predetermined time intervals; and calculating a degree of synchronization between the plurality of subjects based on the acquired vital data.

5. On the computer, A first process of acquiring vital data on autonomic nervous system activity of each of a plurality of subjects at predetermined time intervals; A psychological distance estimation program that executes a second process of calculating the degree of synchronization between the multiple measurement subjects based on the vital data acquired in the first process.

Images