Behavior analysis device, communication support system, behavior analysis method, and computer program

Abstract

To provide a technique for improving the accuracy of evaluating the quality of communication in a behavior analysis device.SOLUTION: A behavior analysis device is provided with an information acquisition unit for acquiring behavior information including data on physical movement for each of a plurality of participants participating in communication, an index calculation unit for using the behavior information that the information acquisition unit acquires to calculate a group synchronization index representing the degree to which the rhythms of physical movement are synchronized among the plurality of participants, and an index output unit for outputting the group synchronization index that the index calculation unit calculates.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to a behavior analysis apparatus, a communication support system, a behavior analysis method, and a computer program.

Background Art

[0002] Conventionally, a behavior analysis apparatus for analyzing the behavior of participants in meetings and the like has been known (Patent Document 1 and Non-Patent Document 1). Further, an analysis method for analyzing an individual's behavior rhythm has been known (Non-Patent Document 2).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Non-Patent Documents

[0004]

Non-Patent Document 1

Non-Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, even in prior arts such as Patent Document 1 and Non-Patent Documents 1 and 2, there was still room for improvement in the technology for improving the accuracy of evaluating the quality of communication in a behavior analysis device.

[0006] The present invention has been made to solve the above-described problems, and an object thereof is to provide a technology for improving the accuracy of evaluating the quality of communication in a behavior analysis device.

Means for Solving the Problems

[0007] The present invention has been made to solve at least a part of the above-described problems and can be realized in the following forms.

[0008] (1) According to one aspect of the present invention, there is provided a behavior analysis device that analyzes the behavior of each of a plurality of participants who participate in communication. This behavior analysis device includes an information acquisition unit that acquires behavior information including data related to body movements for each of the plurality of participants, an index calculation unit that calculates a group synchronization index representing the degree to which the rhythms of body movements are synchronized among the plurality of participants using the behavior information acquired by the information acquisition unit, and an index output unit that outputs the group synchronization index calculated by the index calculation unit.

[0009] According to this configuration, the index calculation unit uses the action information including the data related to the movement of the participants' bodies acquired by the information acquisition unit to calculate a group synchronization index representing the degree of synchronization of the rhythms of the movements of the bodies among a plurality of participants participating in the communication. Here, the "data related to the movement of the participants' bodies" does not only refer to the movements of the participants' heads and limbs, but also includes the direction of the line of sight due to the movement of the eyes. Generally, when communication is actively carried out, that is, when the quality of communication is high, the rhythms of the movements of the bodies of the participants participating in the communication are likely to be synchronized. Therefore, by calculating a group synchronization index representing the degree of synchronization of the rhythms of the movements of the bodies among a plurality of participants participating in the communication, the way the participants are involved in the communication can be specifically evaluated. Thereby, the accuracy of evaluating the quality of communication can be improved.

[0010] (2) In the action analysis apparatus of the above aspect, the index calculation unit may divide the target time zone for calculating the group synchronization index into a plurality of time intervals and calculate the group synchronization index in the target time zone using Equation (1). [Number] However, in Equation (1), GS is the value of the group synchronization index in the target time zone, p is the number of divisions when the target time zone is divided into a plurality of the time intervals, and Z k is the value obtained by normalizing the data in each time interval of each of the plurality of participants for each participant, and ave_Z k is the average value among the plurality of participants of the normalized data for each time interval. According to this configuration, the index calculation unit calculates the group synchronization index as a numerical value using Equation (1). Thereby, since the quality of communication can be evaluated with a specific numerical value, the accuracy of evaluating the quality of communication can be further improved.

[0011] (3) In the behavior analysis apparatus of the above-described form, the information acquisition unit may acquire the behavior information including data related to the movement of the head for each of the plurality of the participants. According to this configuration, in communication by a plurality of participants, the information acquisition unit acquires behavior information including data related to the movement of the head, in which the way the participants are involved in the communication appears accurately. Thereby, the group synchronization index calculated using the movement of the head can more accurately represent the way the participants are involved in the communication. Therefore, the accuracy of evaluating the quality of communication can be further improved.

[0012] (4) In the behavior analysis apparatus of the above-described form, the information acquisition unit has an imaging device that images an image of the face including the eyes for each of the plurality of the participants, and uses the images of the faces of the plurality of the participants imaged by the imaging device to acquire the behavior information including data related to the line-of-sight direction of each of the plurality of the participants. According to this configuration, in communication by a plurality of participants, the information acquisition unit acquires behavior information including data related to the line-of-sight direction, in which the way the participants are involved in the communication appears accurately. Thereby, the group synchronization index calculated using the line-of-sight direction can more accurately represent the way the participants are involved in the communication. Therefore, the accuracy of evaluating the quality of communication can be further improved.

[0013] (5) According to another form of the present invention, a communication support system is provided. This communication support system includes the above-described behavior analysis apparatus and a support execution unit that changes the environment in which the communication is being performed and supports the mood change of the plurality of the participants using the group synchronization index output by the index output unit. According to this configuration, the support execution unit changes the environment in which the communication is being performed so that the participants in the communication can change their mood using the group synchronization index output by the index output unit of the behavior analysis apparatus. Thereby, support for the participants to improve the quality of communication can be accurately performed.

[0014] (6) In the communication support system of the above-described form, the behavior analysis device includes an information input unit to which information regarding the start time of the communication is input, and the index calculation unit determines whether or not the group synchronization index calculated by the index calculation unit is equal to or greater than a predetermined value each time a predetermined time elapses after the start time of the communication input by the information input unit. When the index calculation unit determines that the group synchronization index is less than the predetermined value, the support execution unit outputs an image for promoting a mood change of the plurality of participants. According to this configuration, the index calculation unit determines whether or not the group synchronization index is equal to or greater than a predetermined value each time a predetermined time elapses after the start time of the communication. When the group synchronization index is less than the predetermined value, the support execution unit outputs an image for promoting a mood change of the plurality of participants. Thereby, the communication support system can promote a mood change of the participants according to the quality of the communication during the communication. Therefore, it is possible to support the participants so that the quality of the communication is maintained.

[0015] (7) According to still another aspect of the present invention, there is provided a behavior analysis method for analyzing the behavior of each of a plurality of participants participating in communication. This behavior analysis method includes an information acquisition step of acquiring behavior information including information related to body movements for each of the plurality of participants, and using the behavior information acquired in the information acquisition step, calculating a group synchronization index representing the degree to which the rhythm of the body movements of each of the plurality of participants is synchronized with the rhythm of the body movements of other participants. And an index output step of outputting the group synchronization index calculated in the index calculation step. According to this configuration, in the index calculation step, using the behavior information including data related to the body movements of the participants acquired in the information acquisition step, an index representing the degree to which the rhythm of the body movements of the participants is synchronized, which is a group synchronization index related to the quality of communication, is calculated. Thereby, since the way the participants are involved in the communication can be specifically evaluated, the accuracy of evaluating the quality of communication can be improved.

[0016] (8) According to still another aspect of the present invention, there is provided a computer program for causing a computer to analyze the actions of each of a plurality of participants participating in communication. This computer program causes the computer to execute an information acquisition function for acquiring action information including information on body movements for each of the plurality of participants, an index calculation function for calculating a group synchronization index representing the degree to which the rhythm of the body movements of each of the plurality of participants is synchronized with the rhythm of the body movements of other participants using the action information acquired by the information acquisition function, and an index output function for outputting the group synchronization index calculated by the index calculation function. According to this configuration, the index calculation function calculates a group synchronization index, which is an index representing the degree to which the rhythms of the body movements of the participants are synchronized, using the action information including data on the body movements of the participants acquired by the information acquisition function and which is related to the quality of communication. Thereby, since the way in which the participants are involved in the communication can be specifically evaluated, the accuracy of evaluating the quality of communication can be improved.

[0017] Note that the present invention can be realized in various forms, for example, a system including an action analysis device, a control method for an action analysis device and a communication support system, a computer program for causing action analysis to be executed in these devices and systems, a server device for distributing the computer program, a non-transitory storage medium storing the computer program, and the like. BRIEF DESCRIPTION OF THE DRAWINGS

[0018]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Embodiments for Carrying Out the Invention

[0019] <First Embodiment> FIG. 1 is a schematic diagram for explaining the outline of the action analysis device according to the first embodiment. The action analysis device 1 according to the present embodiment calculates an index related to the degree of involvement in a meeting (communication) for each of a plurality of participants P1 participating in the meeting. In the present embodiment, the index calculated by the action analysis device 1 is output after the meeting to grasp the degree of involvement of the participant P1 in the meeting, and is used as a guideline for implementing measures to improve the degree of involvement of the participant P1, for example. Thereby, since the quality of the meeting can be improved, the productivity of the meeting can be improved. In the present embodiment, the action analysis device 1 includes a headband 21, glasses 22, and a personal computer (hereinafter simply referred to as "PC") 30.

[0020] The headband 21 is provided on the head of the conference participant P1. The headband 21 incorporates a three-axis acceleration sensor that measures the moving direction and acceleration of the head of the participant P1 wearing the headband 21. The headband 21 can transmit, as a signal, data regarding the moving direction and acceleration of the head measured by the three-axis acceleration sensor. The signal transmitted by the headband 21 is received by the PC 30.

[0021] The glasses 22 are provided on the head of the conference participant P1. The glasses 22 incorporate a three-axis acceleration sensor that measures the moving direction and acceleration of the head of the participant P1 wearing the glasses 22. The glasses 22 can transmit, as a signal, data regarding the moving direction and acceleration of the head measured by the three-axis acceleration sensor. The signal transmitted by the glasses 22 is received by the PC 30. In this embodiment, it is sufficient for a plurality of participants P1 to wear either the headband 21 or the glasses 22.

[0022] The PC 30 calculates, using the signals transmitted by the headband 21 and the glasses 22, a numerical value regarding the degree of synchronization of the rhythm of body movements in a plurality of participants P1, and outputs the calculated numerical value. The PC 30 includes an input unit 31, a storage medium 32, a CPU (Central Processing Unit) 33, and an output unit 34. The input unit 31 is at least one of a keyboard, a mouse, an interface with an external recording device such as a USB memory or a flash memory, a receiver capable of receiving an external signal, etc. The input unit 31 is used for inputting information regarding the meeting, inputting information regarding the participant P1, and receiving the signals transmitted by the headband 21 and the glasses 22. The storage medium 32 is a general term for memory devices, and various types of storage devices such as a ROM (Read Only Memory), a RAM (Random Access Memory), a solid state drive (SSD), a hard disk drive (HDD), a flash memory card, etc. can be used. The storage medium 32 stores various information input via the input unit 31, and accommodates a computer program for calculating a numerical value regarding the degree of synchronization of the rhythm of body movements. The CPU 33 executes the functions of various programs by expanding the programs stored in the ROM of the storage medium 32 into the RAM. Details of the functions executed by the CPU 33 will be described later. The output unit 34 is at least one of a display for displaying information, an interface with an external recording device, a transmitter for outputting a signal to the outside, etc. In the present embodiment, the output unit 34 is a display, and displays the numerical value calculated by the CPU 33 on the screen. Note that in the present embodiment, the behavior analysis device 1 is provided with one PC 30, but may be composed of a plurality of arithmetic units.

[0023] FIG. 2 is a diagram showing a schematic configuration of the behavior analysis device 1 according to the first embodiment. FIG. 2 is a diagram showing the relationship between the respective parts of the behavior analysis device 1. The behavior analysis device 1 functions as a behavior information acquisition unit 11, an information input unit 12, an index calculation unit 13, a storage unit 14, and an information output unit 15.

[0024] The action information acquisition unit 11 acquires action information including data on the movement of the body for each of a plurality of participants P1. In the present embodiment, the action information acquisition unit 11 corresponds to the headband 21 and the glasses 22. The headband 21 and the glasses 22 of the present embodiment measure the moving direction of the head and the magnitude of the acceleration for each of the plurality of participants P1 using triaxial acceleration sensors built therein.

[0025] The information input unit 12 receives input of information other than the action information from the outside, such as the scheduled start time and end time of the meeting, and information regarding the plurality of participants P1. In the present embodiment, the information input unit 12 corresponds to a keyboard, a mouse (not shown), and an interface with an external recording device such as a USB memory or a flash memory.

[0026] The index calculation unit 13 calculates a group synchronization index representing the degree to which the rhythms of the body movements are synchronized among the plurality of participants P1 using the action information acquired by the action information acquisition unit 11. In the present embodiment, the index calculation unit 13 corresponds to the index calculation function of the CPU 33. In the present embodiment, the index calculation unit 13 calculates the group synchronization index GS every time a predetermined time elapses after the meeting starts. The index calculation unit 13 outputs the calculated group synchronization index to the storage unit 14. Details of the function of the index calculation unit 13 will be described later.

[0027] The storage unit 14 stores the group synchronization index calculated by the index calculation unit 13 and stores various information input using the information input unit 12. The storage unit 14 outputs the stored group synchronization index to the index calculation unit 13. In the present embodiment, the storage unit 14 corresponds to the storage medium 32.

[0028] The information output unit 15 outputs the group synchronization index calculated by the index calculation unit 13, which is stored in the storage unit 14. In the present embodiment, the information output unit 15 corresponds to the display of the output unit 34.

[0029] Figure 3 is a flowchart of the behavior analysis method of the present embodiment. Next, the behavior analysis method using the behavior analysis apparatus 1 will be described. The behavior analysis method of the present embodiment can be executed in accordance with the start of a meeting, for example, by previously inputting the start time and end time of the meeting into the PC 30 using the information input unit 12 (keyboard of the PC 30). In the behavior analysis method of the present embodiment, prior to starting a meeting, a plurality of participants participating in the meeting wear the headband 21 or the glasses 22. Note that the timing for starting the behavior analysis method of the present embodiment is not limited to this.

[0030] First, as an "information acquisition step", behavior information is acquired for each of the participants participating in the meeting (step S11). In step S11, the headband 21 and the glasses 22 measure the direction and magnitude of the acceleration of the head for each of the participants in the meeting. In the present embodiment, the headband 21 and the glasses 22 measure the direction and magnitude of the acceleration of the participant's head, for example, at intervals of 5 seconds. The headband 21 and the glasses 22 transmit the measured data of the direction and magnitude of the head acceleration as signals. The transmitted signals are received by the PC 30.

[0031] Next, as an "index calculation step", a group synchronization index is calculated (step S12). In step S12, the CPU 33 corresponding to the index calculation unit 13 calculates the behavior data X from the direction and magnitude of the acceleration of the head of the participant P1 measured by the headband 21 or the glasses 22 using Equation (2). In the present embodiment, as the behavior data X, the vector magnitude (square root of the sum of the squares of each axis) is calculated at a predetermined interval, for example, every 5 seconds.

Equation

[0032] The index calculation unit 13 uses the calculated behavior data X to standardize the value of the behavior data X for each of a plurality of participants to obtain a value Z k and calculates it. The index calculation unit 13 uses the calculated value Z k to calculate the group synchronization index GS defined by Equation (1) for the entire communication time. The group synchronization index GS is an index representing the average variance among participants for each of a plurality of time intervals, and represents, in the range from 0 to 1, the degree to which the rhythm (magnitude of movement) of actions by participants matches among participants, that is, the synchronization level of actions [Number] However, in Equation (1), GS is the value of the group synchronization index in the target time period, p is the number of divisions when the target time period is divided into a plurality of time intervals, Z k is the value obtained by standardizing the data for each time interval of each of a plurality of participants for each participant, and ave_Z k is the average value among a plurality of participants of the standardized data for each time interval

[0033] In the present embodiment, the index calculation unit 13 divides the meeting time into a plurality of target time periods so as to calculate a plurality of group synchronization indexes for one meeting. The index calculation unit 13 divides one target time period, for example, 5 minutes, into 5 - second (time interval) time intervals, which is the time interval for measuring the direction and magnitude of the acceleration of the heads of participants by the above - mentioned headband 21 and glasses 22, and calculates the value Z k obtained by standardizing for each participant the data regarding the direction and magnitude of the acceleration of the heads of participants measured every 5 seconds. The index calculation unit 13 sums up the values Z k obtained by standardizing the respective data of a plurality of participants for each time interval, and divides by the number of participants to obtain the average value ave_Z kCalculate it. When the group synchronization index calculated by Equation (1) is output externally after implementing the behavior analysis method of this embodiment, the group synchronization index calculated by the index calculation unit 13 for the entire meeting time is the average value obtained by dividing the sum of a plurality of group synchronization indexes calculated for each target time zone by the number of target time zones.

[0034] In this embodiment, as described above, when calculating the group synchronization index GS, for each of the plurality of participants, the value Z obtained by normalizing the behavior data X for each participant k is used. As a result, for each of the plurality of participants, the average of all the behavior data X acquired by the behavior information acquisition unit 11 becomes 0, and the variance of all the behavior data X becomes approximately 1. Therefore, for example, even for meetings held on different days, the calculated group synchronization indexes GS can be compared.

[0035] Next, the group synchronization index is stored (step S13). In step S13, the storage unit 14 stores the calculated group synchronization index output by the index calculation unit 13 every 5 minutes.

[0036] Next, it is determined whether to output the group synchronization index externally (step S14). In step S14, the CPU 33 corresponding to the index calculation unit 13 determines whether to output the group synchronization index stored in the storage unit 14 based on the relationship between the time when the behavior analysis method is being executed and the implementation time of the meeting calculated from the start time and end time of the meeting stored in the storage unit 14. If the index calculation unit 13 determines that the time when the behavior analysis method is being executed is longer than the implementation time of the meeting (step S14: YES), the process proceeds to the process of step S15. If the index calculation unit 13 determines that the time when the behavior analysis method is being executed is shorter than the implementation time of the meeting (step S14: NO), the process proceeds to the process of step S11.

[0037] In step S14, if the index calculation unit 13 determines that the time for executing the behavior analysis method is longer than the meeting execution time, then as the "index output step", the group synchronization index is output (step S15). In step S15, the group synchronization index calculated during the meeting is displayed on the display of the PC 30. The group synchronization index displayed on the display may be the average value obtained by dividing the sum of the plurality of group synchronization indexes calculated for each target time period, as described above, by the number of target time periods, or it may be a graph showing the change over time of the group synchronization index during the meeting.

[0038] In step S14, if the index calculation unit 13 determines that the time for executing the behavior analysis method is shorter than the meeting execution time, then in step S11, the behavior information of the participants participating in the meeting is acquired again (step S11). In the behavior analysis method of the present embodiment, in this way, according to the determination result in step S14, steps S11 to S13 are repeated to accumulate the group synchronization index during the meeting. As a result, after the meeting ends, the participants in the meeting can check the group synchronization index during the meeting.

[0039] Next, the group synchronization index output by the behavior analysis device 1 of the present embodiment will be described. Generally, in a meeting where the set goal is achieved, that is, in a high-quality meeting (communication), the participants in the meeting tend to actively speak and actively discuss. In such a meeting, when the participants are speaking themselves or listening to the speeches of other participants, their body movements increase, while when they are thinking, their body movements decrease. Also, in a meeting, the higher the level of empathy among the participants, the higher the level of synchronization of the movements of each participant tends to be. When the movements of multiple participants are synchronized, it is said that a sense of trust and unity is felt. Therefore, in a high-quality meeting, among the participants in the meeting, the rhythm of body movements, that is, the timing when body movements become relatively large when speaking oneself or listening to the speech of other participants, and the timing when body movements become relatively small when thinking, have a high degree of coincidence. Also, in communication, it is said that a high level of psychological stability is required to speak frankly and confidently without fear of failure. As factors for enhancing psychological safety, the design of a mutually supportive environment and the influence of support from other participants are considered to be large, and it is considered important that the participants in the meeting are mutually supportive.

[0040] Figure 4 is a diagram for explaining the relationship between the group synchronization index and psychological safety. Here, the relationship between the level of synchronization of the body movements of the participants in communication, that is, the group synchronization index of the present embodiment, and the psychological safety of the participants will be described. Figure 4 shows the results of an evaluation test in which each of the group synchronization index and the psychological safety of the participants was evaluated based on an actual meeting participated in by multiple participants. This evaluation test was conducted under the following conditions. · Number of groups in which the meeting was held: 4 groups · Number of people included in each group (number of people for which behavioral data is measured in each group) 3 (2), 6 (4), 4 (4), 4 (3) · Method for calculating the group synchronization index During a meeting with an implementation time of around 30 minutes, the three-axis acceleration of the head of the person to be measured was measured at 5-second intervals, and the group synchronization index for the entire meeting was calculated using Equation (1). · Method for calculating a numerical value representing psychological safety In each of the groups that held the meeting, the average value of the results of the subjective evaluations of the participants was calculated.

[0041] The figure shown in FIG. 4 shows the magnitude of the group synchronization index (GS) on the horizontal axis and the magnitude of the psychological safety (PS) of the participants on the vertical axis. As a result of this evaluation test, a positive correlation was recognized between the group synchronization index and psychological safety (correlation coefficient r = 0.90). Therefore, it was confirmed that the group synchronization index may reflect the psychological safety of the group. Thus, it can be said that the group synchronization index of the present embodiment evaluates the level of psychological safety of the participants attending the meeting.

[0042] Next, the test results of evaluating the relationship between the state of the meeting participants and the group synchronization index using the model data of the meeting will be described. In this evaluation test, the change in the group evaluation index was evaluated when the number of participants whose actions were synchronized and the number of participants whose actions were not synchronized and random were changed under the condition that the number of participants in the meeting was fixed. This evaluation test was conducted under the following conditions. · Number of participants in the meeting: 10 · Combinations of participant states "Sy10": 10 participants are completely synchronized "Sy10 - ": 10 participants are synchronized to some extent "Sy9 - / R1": 9 participants are synchronized to some extent + 1 participant is random "Sy8 - / R2": 8 participants are synchronized to some extent + 2 participants are random "Sy6 - / R4": 6 participants are synchronized to some extent + 4 participants are random "Sy4 - / R6": 4 participants are synchronized to some extent + 6 participants are random 「Sy2 - / R8」: Two participants are synchronized to a certain extent + eight participants are random 「R10」: Ten participants are random

[0043] Figure 5 is a diagram for explaining the combination of participants' states. Figure 5 shows the relationship between time and the standardized behavior data for each of the four types of meeting model data with different participant states. Figure 5(a) shows the relationship between time and the standardized behavior data in the state "Sy10" where the behaviors of all ten participants are completely synchronized. In the state Sy10 shown in Figure 5(a), since the behaviors of the meeting participants are completely synchronized, it can be seen that the ten behavior data completely overlap. Figure 5(b) shows the relationship between time and the standardized behavior data in the state "Sy10 - " where ten participants are synchronized to a certain extent, and Figure 5(c) shows the relationship between time and the standardized behavior data in the state "Sy9 - / R1" where nine participants are synchronized to a certain extent and one participant has random behavior. Furthermore, Figure 5(d) shows the relationship between time and the standardized behavior data in the state "R10" where the behaviors of all ten participants are random. That is, looking at Figure 5(a), Figure 5(b), Figure 5(c), and Figure 5(d) in order, the change in the synchronization level of the behaviors of the ten participants can be understood.

[0044] Figure 6 is a diagram for explaining the relationship between the synchronization level of participants' behaviors and the group synchronization index. Figure 6 shows the group synchronization index obtained for each of the eight types of participant states described above. As shown in Figure 6, it was confirmed that the higher the synchronization level of the participants' behaviors, the higher the group synchronization index.

[0045] According to the behavior analysis apparatus 1 of the present embodiment described above, the index calculation unit 13 calculates a group synchronization index representing the degree of synchronization of the body movement rhythms among a plurality of participants participating in the meeting, using the behavior information including the movement direction and the magnitude of acceleration of the heads of the participants, which is acquired by the behavior information acquisition unit 11. Generally, when a meeting is actively held, that is, when the quality of the meeting is high, the body movement rhythms of the participants participating in the meeting are likely to be synchronized. Therefore, by calculating a group synchronization index representing the degree of synchronization of the body movement rhythms among a plurality of participants participating in the meeting, the way the participants are involved in the meeting can be specifically evaluated. Thereby, the accuracy of evaluating the quality of the meeting can be improved.

[0046] Moreover, according to the behavior analysis apparatus 1 of the present embodiment, the index calculation unit 13 calculates the group synchronization index GS as a numerical value using the formula (1). Thereby, since the quality of the meeting can be evaluated with a specific numerical value, the accuracy of evaluating the quality of the meeting can be further improved.

[0047] According to the behavior analysis apparatus 1 of the present embodiment, for each of the plurality of participants, the group synchronization index GS is calculated using the formula (1) including the standardized value Z of the plurality of data acquired in the target time period for each of the plurality of participants. k Thereby, comparisons between meetings held on different days, comparisons between meetings by different groups, etc. can be performed.

[0048] Moreover, according to the behavior analysis apparatus 1 of the present embodiment, the behavior information acquisition unit 11 acquires behavior information including data related to the movement of the head, in which the way the participants are involved in the meeting appears accurately, in a meeting by a plurality of participants. Thereby, the group synchronization index calculated using the movement of the head can more accurately represent the way the participants are involved in the meeting. Therefore, the accuracy of evaluating the quality of the meeting can be further improved.

[0049] Also, according to the behavior analysis method of the present embodiment, in step S12, a group synchronization index is calculated using the behavior information including the moving direction and the magnitude of acceleration of the participant's head obtained in step S11. As a result, the way the participant is involved in the meeting can be specifically evaluated, so that the accuracy of evaluating the quality of the meeting can be improved.

[0050] Also, according to the computer program of the present embodiment, the index calculation function of the CPU 33 calculates a group synchronization index using the behavior information including the moving direction and the magnitude of acceleration of the participant's head obtained by the headband 21 and the glasses 22. As a result, the way the participant is involved in the meeting can be specifically evaluated, so that the accuracy of evaluating the quality of the meeting can be improved.

[0051] <Second Embodiment> FIG. 7 is a diagram showing an overview of the communication support system according to the second embodiment. FIG. 8 is a diagram showing the configuration of the communication support system 200 according to the second embodiment. The communication support system 200 according to the second embodiment supports the participants so that the communication among the participants in the meeting becomes active.

[0052] The communication support system 200 according to the second embodiment includes a behavior analysis device 2 and a display 23. The behavior analysis device 2 includes a headband 21 and glasses 22 as a behavior information acquisition unit 11, an information input unit 12, an index calculation unit 13, a storage unit 14, an information output unit 15, and a support control unit 16.

[0053] The support control unit 16 controls the display 23 according to the determination result regarding the group synchronization index by the index calculation unit 13. In the present embodiment, the support control unit 16 corresponds to the support control function of the CPU 33.

[0054] The display 23 displays a specific image under the control of the support control unit 16. In the present embodiment, as shown in FIG. 1, the display 23 is a conference display that displays information used in a conference, and switches the displayed image in response to an instruction from the behavior analysis device 2. Note that the display 23 may be prepared separately from the conference display. The display 23 corresponds to the "support unit" in the claims.

[0055] FIG. 9 is a flowchart of the communication support method of the present embodiment. Next, a communication support method using the communication support system 200 will be described. In the communication support method of the present embodiment, the degree of participants' involvement in the conference is evaluated during the conference using the group synchronization index calculated by the behavior analysis method described in the first embodiment, and the participants during the conference are supported according to the evaluation result.

[0056] In the communication support method of the present embodiment, similar to the behavior analysis method of the first embodiment, the behavior information of the participants participating in the conference is acquired using the headband 21 or the glasses 22 (step S21), and the group synchronization index is calculated (step S22). In the present embodiment, the entire conference is divided into a plurality of time segments, and the group synchronization index is calculated for each time segment. For example, in a one-hour conference, the time segment is set to 10 minutes so that the conference is divided into six parts, and the group synchronization index is calculated every 10 minutes after the start of the conference. The time segment may be set in advance or may be changeable during the conference. The calculated group synchronization index is stored in the storage unit 14 (step S23).

[0057] Next, it is determined whether to output the group synchronization index (step S24). In step S24, the CPU 33 corresponding to the index calculation unit 13 determines whether the group synchronization index stored in the storage unit 14 is equal to or greater than a predetermined value, for example, 0.2 or more. The determination in step S24 is performed every time a predetermined time period (10 minutes) elapses. If the index calculation unit 13 determines that the group synchronization index is less than the predetermined value (step S24: YES), the process proceeds to step S25. If the index calculation unit 13 determines that the group synchronization index is equal to or greater than the predetermined value (step S24: NO), the process proceeds to step S21, and the behavior information of the participants is acquired again using the headband 21 or the glasses 22.

[0058] In step S24, when the index calculation unit 13 determines that the group synchronization index is less than the predetermined value, a specific video is displayed on the display 23 (step S25). The fact that the group synchronization index is less than the predetermined value means that the degree of involvement of the participants in the meeting is decreasing, suggesting that the communication in the meeting is not active. Therefore, in step S25, the support control unit 16 supports the mood change of the participants by displaying a video, such as a waterfall video, on the display 23 that refreshes the mood of the participants and activates the mind and body, and activates the communication between the participants.

[0059] Next, it is determined whether to end the display of the video on the display 23 (step S26). In step S26, the support control unit 16 counts the elapsed time since the start of the display of the video on the display 23 and determines whether the elapsed time is equal to or greater than a predetermined time. If it is determined that the elapsed time since the start of the display of the video is equal to or greater than the predetermined time (step S26: YES), the process proceeds to step S27. If it is determined that the elapsed time since the start of the display of the video is less than the predetermined time (step S26: NO), the process proceeds to step S25, and the display of the specific video on the display 23 is continued (step S25).

[0060] In step S26, when the support control unit 16 determines that the elapsed time since the start of the video display is equal to or longer than a predetermined time, the display of the video on the display 23 is terminated (step S27). As a result, the present communication support method is once terminated. However, when the meeting continues, the communication support method shown in FIG. 9 is executed again. In the communication support method of the present embodiment, in this way, according to the magnitude of the calculated group synchronization index, by changing the environment in which the communication is being performed, the mood changes of a plurality of participants are supported so that the communication among the participants becomes active.

[0061] According to the communication support system 200 of the present embodiment described above, the display 23 uses the group synchronization index calculated by the index calculation unit 13 of the behavior analysis device 1 to change the environment in which the meeting is being held so that a plurality of participants can change their moods. As a result, it is possible to accurately support the participants for improving the quality of the meeting.

[0062] Also, according to the communication support system 200 of the present embodiment, the index calculation unit 13 determines whether or not the group synchronization index is 0.2 or more each time a predetermined time elapses after the start time of the meeting. When the group synchronization index is less than 0.2, the display 23 outputs an image of a waterfall that encourages a mood change of a plurality of participants. As a result, during the meeting, it is possible to encourage a mood change of the participants according to the quality of the meeting. Therefore, it is possible to support the participants so that the quality of the meeting is maintained.

[0063] <Third Embodiment> FIG. 10 is a diagram showing an outline of the behavior analysis device 3 according to the third embodiment. The behavior analysis device 3 according to the third embodiment differs from the behavior analysis device 1 (FIG. 1) according to the first embodiment in the content of the behavior information acquired by the information acquisition unit.

[0064] The behavior analysis device 3 of this embodiment includes a headband 24, glasses 25, and a PC 30. Each of the headband 24 and the glasses 25 incorporates a sensor for measuring the orientation of each participant's face, for example, a six-axis sensor including a three-axis acceleration sensor and a three-axis gyro sensor.

[0065] The index calculation unit 13 included in the behavior analysis device 3 calculates behavior data X using the acceleration in each of the x-axis direction, y-axis direction, and z-axis direction, and the angular velocity in each of the roll direction, yaw direction, and pitch direction, measured by the six-axis sensors provided in the headband 24 and the glasses 25. In this embodiment, the index calculation unit 13 calculates the behavior data X, for example, every 5 seconds. In this embodiment, when the left and right face orientations of the participant are used as the behavior data X, the behavior data X is calculated from the sensor value in the yaw direction among the six-axis sensors. The index calculation unit 13 uses the calculated behavior data X to standardize the value of the behavior data X for each participant to obtain a value Z k is calculated. In this embodiment, the index calculation unit 13 k uses the value Z

[0066] to calculate the group synchronization index GS defined by Equation (1) for the entire duration of the meeting. The storage unit 14 stores the group synchronization index GS calculated by the index calculation unit 13.

[0067] According to the behavior analysis device 3 of this embodiment described above, the index calculation unit 13 uses the behavior information including the moving direction of the participant's head, the magnitude of the acceleration, and the tilting direction of the head, which are acquired by the headband 24 and the glasses 25, to calculate the group synchronization index. Thereby, the accuracy of evaluating the quality of the meeting can be improved.

[0068] <Fourth Embodiment> FIG. 11 is a diagram showing an overview of the behavior analysis apparatus according to the fourth embodiment. The behavior analysis apparatus 4 according to the fourth embodiment is different from the behavior analysis apparatus (FIG. 1) according to the first embodiment in that, as an information acquisition unit, it includes a plurality of cameras 26 instead of the headband 21 and the glasses 22.

[0069] FIG. 12 is a diagram showing the configuration of the behavior analysis apparatus 4 according to the present embodiment. The behavior analysis apparatus 4 according to the present embodiment includes a plurality of cameras 26 and a PC 30. The plurality of cameras 26 capture images of the face including the eyes for each of the conference participants P1. Each of the plurality of cameras 26 is electrically connected to the PC 30 and transmits the captured image including the face of the participant P1 to the PC 30 as a signal. The signals transmitted by the plurality of cameras 26 are received by the PC 30.

[0070] The PC 30 includes an image analysis unit 17 that acquires, as behavior information, data regarding the line-of-sight direction of the participant P1, for example, a line-of-sight vector or a line-of-sight movement speed vector indicating the speed of line-of-sight movement, using the image including the face of the participant P1 captured by the plurality of cameras 26. In the present embodiment, the image analysis unit 17 corresponds to the image analysis function of the CPU 33.

[0071] The index calculation unit 13 calculates, as behavior data X, the vector magnitude of the line-of-sight vector or the line-of-sight movement speed vector using the behavior information acquired by the image analysis unit 17. In the present embodiment, the index calculation unit 13 calculates the behavior data X, for example, every 5 seconds. The index calculation unit 13 uses the calculated behavior data X to calculate a value Z obtained by normalizing the value of the behavior data X for each participant. k is calculated. The index calculation unit 13 uses the calculated behavior data X to calculate a value Z obtained by normalizing the value of the behavior data X for each participant. k is calculated. In the present embodiment, the index calculation unit 13 uses the value Z k to calculate the group synchronization index GS defined by Equation (1) for the entire conference time. The storage unit 14 stores the group synchronization index GS calculated by the index calculation unit 13.

[0072] According to the action analysis device 4 of the present embodiment described above, the index calculation unit 13 calculates a group synchronization index using action information including data regarding the line-of-sight direction of the participants, which is acquired by the plurality of cameras 26 and the image analysis unit 17. Thereby, the accuracy of evaluating the quality of the meeting can be improved.

[0073] Also, according to the action analysis device 4 of the present embodiment, the plurality of cameras 26 and the image analysis unit 17 acquire action information including data regarding the line-of-sight direction, in which the way the participants are involved in the meeting appears accurately, in a meeting by a plurality of participants. Thereby, the group synchronization index calculated using the line-of-sight direction can more accurately represent the way the participants are involved in the meeting. Therefore, the accuracy of evaluating the quality of the meeting can be further improved.

[0074] <Modification Example of the Present Embodiment> The present invention is not limited to the above-described embodiment, and can be implemented in various aspects without departing from the gist thereof. For example, the following modifications are also possible.

[0075] [Modification Example 1] In the first embodiment and the second embodiment, it is assumed that the moving direction and acceleration of the head are measured as data regarding the movement of the body. In the third embodiment, as data regarding the movement of the body, in addition to the moving direction and acceleration of the head, the angular velocity in each of the roll direction, yaw direction, and pitch direction of the head is measured. In the fourth embodiment, it is assumed that the line-of-sight direction is measured as data regarding the movement of the body. However, the data regarding the movement of the body is not limited to these. The movement of the hands and feet, the way the body is tilted, the direction the face is facing, and the moving speed of the face may be used as data regarding the movement of the body. Also, data obtained by adding the line-of-sight direction to the moving direction and acceleration of the head may be used as data regarding the movement of the body.

[0076] [Modification Example 2] In the above embodiment, it is assumed that the group synchronization index is calculated using Equation (1). However, the method for calculating the group synchronization index is not limited to this. In the case of a plurality of participants participating in the communication, any index that represents the degree of synchronization of the rhythm of body movements may be used. Further, in Equation (1), the value Z k obtained by normalizing the behavior data X for each participant is used. However, the group synchronization index may also be calculated using the behavior data X. In this case, Equation (3) is used. [Equation] However, in Equation (3), GS is the value of the group synchronization index in the target time period, N is the total number of data, p is the number of divisions when the target time period is divided into a plurality of time intervals, Xi is individual data (participant, time interval), ave_X is the average value of all data, and ave_X k is the average value among a plurality of participants of the data for each time interval.

[0077] [Modification Example 3] In the first embodiment, it is assumed that the group synchronization index stored in the storage unit 14 is displayed on the display of the output unit 34 after the meeting ends. The method for providing information on the group synchronization index is not limited to this. The change over time of the group synchronization index may be output. Further, it may be displayed so as to be compared with the group synchronization index in past meetings, or it may be displayed so as to be compared with the group synchronization index of meetings by other participants.

[0078] [Modification Example 4] In the first embodiment, as the behavior data X, the vector magnitude, which is the square root of the sum of the squares of each of a plurality of axes, is used. However, the behavior data X is not limited to this. When the data related to body movements has a plurality of dimensions, one of the one-dimensional values may be used as the behavior data X.

[0079] [Modification Example 5] In the second embodiment, when the index calculation unit 13 determines that the group synchronization index is smaller than a predetermined value, in step S25, the support control unit 16 causes the display 23 to display a specific video. However, the method of support for promoting the mood change of the participants is not limited to this. By changing the environment of the place where the meeting is being held, methods such as refreshing the mood of the participants to activate the mind and body, prompting to resume the discussion after taking a break, and proposing ways to move the body may also be used.

[0080] As a specific example of the method of changing the environment where the meeting is being held, in addition to displaying a video that refreshes the mood and activates the mind and body on the display installed in the place where the meeting is being held as in the second embodiment, the following methods may also be used. · Supply a scent that refreshes the mood and activates the mind and body, for example, a scent that evokes an image of a forest, indoors where the meeting is being held. · Play a sound that refreshes the mood and activates the mind and body, for example, the sound of birds or a waterfall, in the place where the meeting is being held.

[0081] As a method of prompting to resume the discussion after taking a break, a sentence such as "The meeting has exceeded one hour. Let's take a break for about 10 minutes." may be displayed on the display installed in the place where the meeting is being held. Also, in the method of proposing to move the body, a sentence such as "The meeting has exceeded one hour. It is recommended to change your mood by standing up from your chair or walking around indoors while having the meeting." may be displayed on the display installed in the place where the meeting is being held, and it may be proposed to communicate while standing up or walking, or to change the height of the desk.

[0082] [Modification Example 6] In the communication support method according to the second embodiment, in step S26 shown in FIG. 9, it was determined that the display of the video on the display 23 was based on the elapsed time since the video was displayed. However, the determination criterion in step S26 is not limited to the elapsed time. For example, when a support display different from the display 23 is installed in the environment where the meeting is held, and it is possible to display a video for promoting the mood change of the participants on the support display during the meeting, after starting the display of the video, it may be determined whether to end the display of the video using a newly calculated group synchronization index.

[0083] FIG. 13 is a flowchart of a modified example of the communication support method according to the second embodiment. In the communication support method shown in FIG. 13, in step S25, after displaying a specific video on the display 23, the process proceeds to step S251, and the action information of the participants participating in the meeting is newly acquired using the headband 21 or the glasses 22 (step S251). Next to step S251, a group synchronization index is newly calculated using the structure information acquired in step S251 (step S252). In step S26 following step S252, the support control unit 16 determines whether the group synchronization index newly calculated in step S252 is less than or equal to a predetermined value, and based on this determination, determines whether to end the display of the video. In this case, it is desirable that the "predetermined value" in step S26 is larger than the "predetermined value" used in the determination in step S24. Specifically, when the "predetermined value" used in the determination in step S24 is 0.2, it is desirable that the "predetermined value" used in the determination in step S26 is 0.3. However, in the flowchart of the modified example of the communication support method shown in FIG. 13, the magnitude relationship between the "predetermined value" used in the determination in step S24 and the "predetermined value" used in the determination in step S26 is not limited to this. Note that in FIG. 13, it is assumed that a video is displayed so that a plurality of participants can change their moods. However, as described in Modified Example 5, during the meeting, scents, sounds, etc. that refresh the mood and activate the mind and body may be provided.

[0084] As described above, the present aspect has been described based on the embodiments and modified examples. However, the embodiments of the above-described aspects are for facilitating the understanding of the present aspect and do not limit the present aspect. The present aspect can be changed and improved without departing from its spirit and the scope of the claims, and equivalents thereof are included in the present aspect. Also, if the technical features are not described as essential in this specification, they can be deleted as appropriate.

[0085] <Application Example 1> An action analysis device that analyzes the actions of each of a plurality of participants participating in communication, an information acquisition unit that acquires action information including data related to body movements for each of the plurality of participants; an index calculation unit that calculates a group synchronization index representing the degree to which the rhythms of body movements are synchronized among the plurality of participants using the action information acquired by the information acquisition unit; an index output unit that outputs the group synchronization index calculated by the index calculation unit, and an action analysis device. <Application Example 2> The action analysis device according to Application Example 1, wherein the index calculation unit divides the target time zone for calculating the group synchronization index into a plurality of time intervals, and calculates the group synchronization index in the target time zone using Equation (1). An action analysis device.

Number

Explanation of symbols

[0086] 1, 2, 3, 4... Behavior analysis device 11... Behavior information acquisition unit 12... Information input unit 13... Index calculation unit 15... Information output unit 21, 24... Headband 22, 25... Glasses 23... Display 26... Camera P1... Participant 200... Communication support system

Claims

1. An action analysis device that analyzes the actions of each of a plurality of participants participating in communication, an information acquisition unit that acquires action information including data related to body movements for each of the plurality of participants; an index calculation unit that calculates a group synchronization index representing the degree to which the rhythms of body movements are synchronized among the plurality of participants using the action information acquired by the information acquisition unit; an index output unit that outputs the group synchronization index calculated by the index calculation unit, comprising: Action analysis device.

2. The action analysis device according to claim 1, wherein the index calculation unit divides the target time zone for calculating the group synchronization index into a plurality of time intervals, and calculates the group synchronization index in the target time zone using formula (1). Action analysis device. 【Equation 1】 However, in formula (1), GS is the value of the group synchronization index in the target time zone, p is the number of divisions when the target time zone is divided into a plurality of the time intervals, Z k is the value obtained by normalizing the data in each time interval of each of the plurality of participants for each participant, ave_Z k is the average value among the plurality of participants of the normalized data for each time interval.

3. The action analysis device according to claim 1 or claim 2, wherein the information acquisition unit acquires the action information including data related to head movements for each of the plurality of participants. Action analysis device.

4. The action analysis device according to claim 1 or claim 2, The information acquisition unit has an imaging device that images the face including the eyes for each of the plurality of participants, and acquires the behavior information including data regarding the line-of-sight direction of each of the plurality of participants by using the images of the faces of each of the plurality of participants imaged by the imaging device. Behavior analysis device.

5. A communication support system, the behavior analysis device according to claim 1 or claim 2, and a support execution unit that changes the environment in which the communication is performed by using the group synchronization index output by the index output unit and supports the mood change of the plurality of participants. Communication support system.

6. The communication support system according to claim 5, wherein the behavior analysis device includes an information input unit to which information regarding the start time of the communication is input, the index calculation unit determines whether or not the group synchronization index calculated by the index calculation unit is equal to or greater than a predetermined value each time a predetermined time has elapsed after the start time of the communication input by the information input unit, and the support execution unit outputs an image for prompting the mood change of the plurality of participants when the index calculation unit determines that the group synchronization index is less than the predetermined value. Communication support system.

7. A behavior analysis method for analyzing the behavior of each of a plurality of participants participating in communication, an information acquisition step of acquiring behavior information including information regarding the movement of the body for each of the plurality of participants, an index calculation step of calculating a group synchronization index representing the degree to which the rhythms of the body movements are synchronized among the plurality of participants by using the behavior information acquired in the information acquisition step, An index output step of outputting the group synchronization index calculated in the index calculation step, and comprising A behavior analysis method.

8. A computer program for causing a computer to execute analysis of the behaviors of a plurality of participants participating in communication, For each of the plurality of participants, an information acquisition function of acquiring behavior information including information related to body movements, Using the behavior information acquired by the information acquisition function, an index calculation function of calculating a group synchronization index representing the degree to which the rhythms of body movements are synchronized among the plurality of participants, Causing the computer to execute an index output function of outputting the group synchronization index calculated by the index calculation function, A computer program.

Images