Communication device, communication method, and communication program

Abstract

To provide a communication device, method, and program in which a reaction changes according to the state of a person to be evaluated.SOLUTION: A communication device 100 comprises: an information acquisition unit that acquires brain wave information of a person to be evaluated; a reaction determination unit that determines a first reaction of the communication device on the basis of the brain wave information; and a control unit that controls the communication device according to the first reaction determined by the reaction determination unit. The reaction determination unit determines the details of an utterance to be made by the communication device on the basis of the brain wave information, and the control unit controls the communication device according to the details of the utterance determined by the reaction determination unit.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The present invention relates to a communication device, a communication method, and a communication program.

Background Art

[0002] Patent Document 1 describes "enhancing the satisfaction of dialogue by an interactive agent device" (abstract). Patent Document 2 describes "accurately estimating the target image that the subject is thinking of" (abstract). [Prior Art Documents] [Patent Documents] [Patent Document 1] Japanese Patent Application Laid-Open No. 2021-114004 [Patent Document 2] International Publication No. 2019 / 235458

Summary of the Invention

[0003] In a first aspect of the present invention, there is provided a communication device whose reaction changes according to the state of the evaluated person. The communication device includes an information acquisition unit that acquires electroencephalogram information of the evaluated person, a reaction determination unit that determines a first reaction of the communication device based on the electroencephalogram information, and a control unit that controls the communication device according to the first reaction determined by the reaction determination unit.

[0004] The reaction determination unit may determine the content of the utterance of the communication device based on the electroencephalogram information. The control unit may control the communication device according to the content of the utterance determined by the reaction determination unit.

[0005] In any of the above communication devices, the information acquisition unit may further acquire biometric information of the evaluated person. The reaction determination unit may determine the first reaction based on the electroencephalogram information and the biometric information.

[0006] In any of the above communication devices, the information acquisition unit may further acquire biological information after the first response. The response determination unit may determine a second response of the communication device based on the electroencephalogram information and the biological information after the first response. The control unit may control the communication device in accordance with the second response.

[0007] In any of the above communication devices, the information acquisition unit may acquire changes in electroencephalogram (EEG) information before and after the first response of the communication device. The response determination unit may generate state information indicating the state of the person being evaluated based on the changes in EEG information and biological information, and determine a second response based on the generated state information.

[0008] In any of the above communication devices, the response determination unit may generate state information based on the change from the ratio of the amplitude of brain waves in a predetermined frequency band to the total amplitude in the brainwave information before the first response to the ratio of the amplitude of brain waves in a frequency band to the total amplitude in the brainwave information after the first response, and the ratio of the magnitude of the first power spectrum of the evaluated person's heartbeat to the magnitude of the second power spectrum. The total amplitude is the sum of the amplitudes of alpha waves, beta waves, theta waves, gamma waves, and delta waves. The frequency band of the second power spectrum is a higher frequency band than the frequency band of the first power spectrum.

[0009] In any of the above-mentioned communication devices, the response determination unit may generate state information based on the change from the ratio of the amplitude of brain waves in a predetermined frequency band to the total amplitude in the brainwave information before the first response to the ratio of the amplitude of brain waves in the said frequency band to the total amplitude in the brainwave information after the first response, and the relationship between the ratio of the magnitude of the first power spectrum to the magnitude of the second power spectrum after the first response and a predetermined threshold for the ratio of the magnitude of the first power spectrum to the magnitude of the second power spectrum.

[0010] In any of the above communication devices, the state information may include information relating to multiple states of the person being evaluated. The reaction determination unit may generate state information relating to one of the multiple states based on the change and the ratio of the magnitude of the first power spectrum to the magnitude of the second power spectrum.

[0011] The brainwaves in a predetermined frequency band may be at least one of delta waves, theta waves, low alpha waves, and medium alpha waves.

[0012] The brainwaves in a predetermined frequency band may be at least one of high alpha waves, low beta waves, high beta waves, and gamma waves.

[0013] In any of the above-mentioned communication devices, if the state after the first response, based on the brainwave information of the person being evaluated, is a predetermined state, the response determination unit may determine a predetermined response as the second response.

[0014] Any of the above communication devices may further include a state learning unit that generates a state inference model that infers the state of the person being evaluated after the first response based on the brainwave information before the first response and the first response, by machine learning the relationship between the first response and changes in brainwave information.

[0015] In any of the above-described communication devices, the information acquisition unit may acquire electroencephalogram (EEG) information after the first response of the communication device. The response determination unit may determine the second response of the communication device based on the EEG information after the first response and the state of the person being evaluated inferred by a state inference model.

[0016] In any of the above-described communication devices, the response determination unit may determine a predetermined response as a second response if the difference between the state of the person being evaluated based on electroencephalogram information after the first response and the state of the person being evaluated inferred by the state inference model exceeds a predetermined threshold.

[0017] In any of the above-described communication devices, the response determination unit may determine the first response based on the time at which the first response is determined, or on the environment surrounding the person being evaluated.

[0018] In any of the above-described communication devices, the control unit may change the biological information presented to the response display unit depending on the person being evaluated.

[0019] A second aspect of the present invention provides a communication method in which the response changes according to the state of the person being evaluated. The communication method comprises an information acquisition step in which an information acquisition unit acquires electroencephalogram (EEG) information of the person being evaluated; a response determination step in which a response determination unit determines a first response of the communication device based on the EEG information; and a control step in which a control unit controls the communication device according to the first response determined in the response determination step.

[0020] In a third aspect of the present invention, a communication program is provided. The communication program causes a computer to perform an information acquisition step of acquiring brainwave information of a person being evaluated, a response determination step of determining a first response of a communication device based on the brainwave information, and a control step of controlling the communication device in accordance with the first response determined by the response determination unit.

[0021] It should be noted that the above summary of the invention does not enumerate all of its features. Furthermore, subcombinations of these features may also constitute an invention. [Brief explanation of the drawing]

[0022] [Figure 1] This figure shows an example of communication between the person being evaluated 120 and the communication device 100. [Figure 2] This figure shows an example of communication between the person being evaluated 120 and the communication device 100. [Figure 3]It is a block diagram showing an example of a communication device 100 according to an embodiment of the present invention. [Figure 4] It is a diagram showing an example of an electroencephalograph 14. [Figure 5] It is a diagram showing an example of state information Is. [Figure 6] It is a diagram showing an example of a state inference model 42. [Figure 7] It is a flowchart showing an example of a communication method according to an embodiment of the present invention. [Figure 8] It is a diagram showing an example of a computer 2200 in which the communication device 100 according to an embodiment of the present invention may be wholly or partially embodied.

Mode for Carrying Out the Invention

[0023] Hereinafter, the present invention will be described through embodiments of the invention. However, the following embodiments do not limit the invention according to the claims. Also, not all combinations of features described in the embodiments are essential for the solution means of the invention.

[0024] FIG. 1 and FIG. 2 are diagrams showing an example of communication between an evaluatee 120 and a communication device 100. In this example, the evaluatee 120 is a human. The communication device 100 may be a device that simulates a human or an animal. The communication device 100 may be a physical object such as a robot, or may be a living body 110 on a computer. The living body 110 may be a virtual person or a virtual animal. The living body 110 may be presented to a reaction presenting unit 30 (described later).

[0025] Let State S be the state of person 120 being evaluated. State S may be the latent state of person 120 being evaluated. The latent state of person 120 being evaluated is the psychological state of person 120 that they are not aware of. Figures 1 and 2 show an example of person 120 being evaluated after waking up. Let State S1 be the first state of person 120 being evaluated before receiving the first response R1 (described later). Let S2 be the second state of person 120 being evaluated after receiving the first response R1 (described later) and before receiving the second response R2 (described later). The dashed lines in Figures 1 and 2 show the first state S1 and the second state S2 of person 120 being evaluated. In the example in Figure 1, before receiving the first response R1 (described later), person 120 being evaluated feels "refreshed after waking up. Not tired, and lighthearted." In the example in Figure 2, before receiving the first response R1 (described later), the person being evaluated, 120, felt "tired and unwell. Anxious and stressed."

[0026] The response of the communication device 100 changes according to the state S of the person being evaluated 120. The response of the communication device 100 refers to the speech, actions, or facial expressions of the communication device 100. The electroencephalogram (EEG) information Ib1 and Ib2 in Figures 1 and 2 will be described later.

[0027] Figure 3 is a block diagram showing an example of a communication device 100 according to one embodiment of the present invention. The communication device 100 comprises an information acquisition unit 10, a response determination unit 20, and a control unit 90. The communication device 100 may also comprise a response presentation unit 30, a state learning unit 40, and a storage unit 50. The information acquisition unit 10 may include a recognition unit 12. The response presentation unit 30 is, for example, a display, a monitor, etc.

[0028] Part or all of the communication device 100 may be implemented by a computer. The control unit 90 may be the CPU (Central Processing Unit) of the computer. If the communication device 100 is implemented by a computer, the computer may have a program installed to allow it to function as the communication device 100, and may also have a program installed to execute the communication method described later.

[0029] The electroencephalogram (EEG) information of the person being evaluated 120 is denoted as EEG information Ib. The information acquisition unit 10 acquires EEG information Ib of the person being evaluated 120. EEG information Ib may be information that reproduces at least a portion of the temporal waveform of the person being evaluated 120. EEG information Ib may include data sampled from the temporal waveform of the EEG, may include data indicating the magnitude of frequency components of the EEG at one or more frequencies, and may include other data. For example, EEG information Ib may include data indicating the magnitude of at least one component of alpha waves, beta waves, theta waves, delta waves, and gamma waves.

[0030] Alpha waves may be further classified into high alpha waves, medium alpha waves, and low alpha waves depending on their frequency band. Beta waves may be classified into high beta waves and low beta waves. EEG information Ib may include data indicating the magnitude of at least one of the high alpha waves, medium alpha waves, and low alpha waves. EEG information Ib may also include data indicating the magnitude of at least one of the high beta waves and low beta waves.

[0031] EEG information Ib may include information on the time waveform of one or more brain waves measured at one or more locations on the head, including the head and face, of the person being evaluated 120. For example, EEG information Ib may be obtained by measuring the time waveform of the potential of electrodes placed at equal intervals near the scalp of the person being evaluated 120, as in the International 10-20 method, or by other methods. The electrodes placed on the scalp do not have to be at equal intervals. The electrodes may be provided on a wearable device attached to the head of the person being evaluated 120, such as a headgear, headphones, earphones, or glasses. EEG information Ib may also be information obtained by wireless communication from electrical signals at electrodes implanted in the body of the person being evaluated 120. In the examples of Figures 1 and 2, EEG information Ib is transmitted wirelessly to the control unit 90.

[0032] The response determination unit 20 determines a first response of the communication device 100 based on the electroencephalogram (EEG) information Ib1. This first response is referred to as the first response R1. The EEG information Ib1 is the EEG information Ib prior to the first response R1. For example, the response determination unit 20 determines the first response R1 or the second response R2 (described later) based on the magnitude of a specific frequency component of the brainwaves of the person being evaluated 120. The response determination unit 20 may determine the first response R1 or the second response R2 (described later) based on the magnitude of one or more components among alpha waves, beta waves, theta waves, delta waves, and gamma waves.

[0033] The total amplitude As is defined as the sum of the amplitudes of alpha waves (8Hz to less than 14Hz), beta waves (14Hz to less than 26Hz), theta waves (4Hz to less than 8Hz), gamma waves (26Hz to less than 40Hz), and delta waves (less than 4Hz) at a given time. For example, if the proportion of delta wave amplitude (less than 4Hz) in the total amplitude As of subject 120 is greater than the proportion of alpha wave amplitude, beta wave amplitude, theta wave amplitude, and gamma wave amplitude, subject 120 may be presumed to be in a sleep state. For example, if the proportion of theta wave amplitude in the total amplitude As of subject 120 increases over time, it may be presumed that subject 120 is experiencing increased fatigue and drowsiness.

[0034] For example, if the proportion of the sum of the amplitudes of low alpha waves (8 Hz to less than 10 Hz) and medium alpha waves (10 Hz to less than 12 Hz) in subject 120 to the total amplitude As increases over time, it can be inferred that subject 120's level of relaxation is increasing.

[0035] For example, if the proportion of the sum of the amplitudes of high alpha waves (12Hz to less than 14Hz) and low beta waves (14Hz to less than 18Hz) in subject 120 to the total amplitude As increases over time, it can be inferred that subject 120 is experiencing an increasing balance between relaxation and concentration. This balance between relaxation and concentration is what is commonly known as a state of immersion.

[0036] The larger the proportion of the sum of the amplitudes of low alpha waves and medium alpha waves of the person being evaluated (120) to the total amplitude As, the higher the probability that the person being evaluated (120) is relaxed. In this case, the response determination unit 20 may determine a first response R1 or a second response R2 (described later) to the person being evaluated (120) who is in a relaxed state. The larger the proportion of the sum of the amplitudes of high alpha waves and low beta waves of the person being evaluated (120) to the total amplitude As, the higher the probability that the person being evaluated (120) is engrossed. In this case, the response determination unit 20 may determine a first response R1 or a second response R2 (described later) to the person being evaluated (120) who is in a engrossed state.

[0037] The response determination unit 20 may determine a first response R1 or a second response R2 (described later) by combining multiple components of the alpha, beta, theta, delta, and gamma waves of the person being evaluated 120. For example, the larger the value obtained by dividing the magnitude of the alpha waves of the person being evaluated 120 by the magnitude of the beta waves, the higher the probability that the person being evaluated 120 is relaxed. For this reason, the response determination unit 20 may determine a first response R1 or a second response R2 (described later) for the person being evaluated 120 who is in a relaxed state.

[0038] The first response R1 and the second response R2 (described later) may be utterances, actions, or facial expressions from the communication device 100. In the examples in Figures 1 and 2, the response determination unit 20 determines the content of the utterances from the communication device 100 based on the electroencephalogram information Ib1 and determines the content of other utterances from the communication device 100 based on the electroencephalogram information Ib2 (described later).

[0039] The control unit 90 controls the communication device 100 according to the first response R1 determined by the response determination unit 20. In the examples of Figures 1 and 2, the control unit 90 controls the communication device 100 according to the content of the utterance determined by the response determination unit 20. In the examples of Figures 1 and 2, the control unit 90 controls the content of the utterance of the communication device 100.

[0040] The electroencephalogram (EEG) information Ib1 may reflect the subject 120's potential first state S1. The first response R1 is determined based on the EEG information Ib1. Therefore, the first response R1 is likely to be a response that corresponds to the subject 120's potential first state S1. In the example in Figure 1, the EEG information Ib1 may reflect the subject 120's first state S1 of "waking up refreshed." Therefore, in the example in Figure 1, the first response R1 is the utterance, "It's a nice morning. Shall we go for a walk?" In the example in Figure 2, the EEG information Ib1 may reflect the subject 120's first state S1 of "tired and not refreshed." Therefore, in the example in Figure 2, the first response R1 is the utterance, "You seem down. Are you feeling unwell?"

[0041] The electroencephalogram (EEG) information Ib of the person being evaluated 120 after the first response R1 is defined as EEG information Ib2. EEG information Ib2 is the EEG information Ib of the person being evaluated 120 after receiving the first response R1 from the communication device 100. The information acquisition unit 10 may acquire the changes in EEG information Ib before and after the first response R1. The change in EEG information Ib before and after the first response R1 is the change from EEG information Ib1 to EEG information Ib2.

[0042] The response determination unit 20 may determine a second response based on electroencephalogram (EEG) information Ib and biological information Ig (described later) after the first response R1. This second response will be referred to as the second response R2. The response determination unit 20 may determine the second response R2 of the communication device 100 based on the change from EEG information Ib1 to EEG information Ib2. The response determination unit 20 may determine the second response R2 based on the change from EEG information Ib1 to EEG information Ib2 and biological information Ig (described later). The control unit 90 may control the communication device 100 according to the second response R2 determined by the response determination unit 20. The response determination unit 20 may determine the second response R2 based on the first response R1 and the change from EEG information Ib1 to EEG information Ib2.

[0043] If the ratio of the sum of the amplitudes of low alpha waves and medium alpha waves in EEG information Ib2 to the total amplitude As is greater than the ratio of the sum of the amplitudes of low alpha waves and medium alpha waves in EEG information Ib1 to the total amplitude As, there is a high probability that the level of relaxation of the person being evaluated 120 is increasing. In this case, the response determination unit 20 may determine a second response R2 to the person being evaluated 120 who is in a relaxed state. If the ratio of the sum of the amplitudes of high alpha waves and low beta waves in EEG information Ib2 to the total amplitude As is greater than the ratio of the sum of the amplitudes of high alpha waves and low beta waves in EEG information Ib1 to the total amplitude As, there is a high probability that the level of immersion of the person being evaluated 120 is increasing. In this case, the response determination unit 20 may determine a second response R2 to the person being evaluated 120 who is in an immersive state.

[0044] The electroencephalogram (EEG) information Ib2 may reflect the subject 120's potential second state S2 after receiving the first response R1. The second response R2 is determined based on the EEG information Ib2. Therefore, the second response R2 is likely to be a response that corresponds to the subject 120's potential second state S2. In the example in Figure 1, subject 120, after receiving the first response R1, feels "That's great!". In the example in Figure 2, subject 120, after receiving the first response R1, feels "Thank you. I feel a little better."

[0045] Figure 4 shows an example of an electroencephalograph 14. In this example, the electroencephalograph 14 is a headgear type. The electroencephalograph 14 may also be an earphone type. In this example, the person being evaluated 120 may communicate with the communication device 100 while wearing a headgear type or earphone type electroencephalograph. The electroencephalograph 14 acquires electroencephalogram information Ib. In this example, the information acquisition unit 10 (see Figure 3) wirelessly acquires the electroencephalogram information Ib acquired by the electroencephalograph 14.

[0046] The response display unit 30 may be a display, monitor, etc., installed separately from the housing of the headgear shown in Figure 4. If the response display unit 30 is a sound generating device such as a speaker, the response display unit 30 may or may not be housed in the housing of the headgear shown in Figure 4. If the response display unit 30 is a headgear such as a VR (Virtual Reality) headset, the response display unit 30 may be housed in the housing of the headgear shown in Figure 4.

[0047] The biological information of the person being evaluated 120 is denoted as biological information Ig. Biological information Ig may be the biological information of the person being evaluated 120 (see Figures 1 and 2) while they are communicating with the communication device 100. Biological information Ig may include at least one of the heart rate information, sweat amount information, and body temperature information of the person being evaluated 120. The biological information Ig of the person being evaluated 120 may be acquired by a sensor provided on a wearable device worn by the person being evaluated 120 (for example, a headgear-type electroencephalograph 14 shown in Figure 4).

[0048] The information acquisition unit 10 (see Figure 3) may further acquire the biological information Ig of the person being evaluated 120. The response determination unit 20 (see Figure 3) may determine the first response R1 based on the electroencephalogram information Ib and the biological information Ig. The biological information Ig tends to reflect the latent state S of the person being evaluated 120. For example, if the person being evaluated 120 is experiencing stress, the sympathetic nervous system is likely to be more dominant than the parasympathetic nervous system. When the sympathetic nervous system is more dominant than the parasympathetic nervous system, the heart rate variability of the person being evaluated 120 tends to be smaller and the amount of sweating tends to be larger. Therefore, by determining the first response R1 based on the electroencephalogram information Ib and the biological information Ig, the response determination unit 20 (see Figure 3) can determine a first response R1 that can more appropriately respond to the latent state S1 of the person being evaluated 120. The information acquisition unit 10 may acquire biological information Ig before the first reaction R1, and may acquire biological information Ig after the first reaction R1.

[0049] The response determination unit 20 may generate state information Is based on electroencephalogram information Ib and biological information Ig. State information Is is information based on the latent state S of the person being evaluated 120. The response determination unit 20 may generate state information Is based on the change from electroencephalogram information Ib1 to electroencephalogram information Ib2 and biological information Ig. The response determination unit 20 may determine a second response R2 based on state information Is.

[0050] Let LF be the magnitude of the first power spectrum and HF be the magnitude of the second power spectrum at the heartbeat of the person being evaluated (120). The frequency band of the second power spectrum is a higher frequency band than that of the first power spectrum. The frequency bands of the first and second power spectra do not need to overlap. For example, the frequency band of the first power spectrum is 0.04-0.15 Hz. For example, the frequency band of the second power spectrum is 0.15-0.4 Hz.

[0051] Change C1 is defined as the change from the ratio of the amplitudes of high beta waves (18 to less than 26 Hz) and gamma waves to the total amplitude As in EEG information Ib1 to the ratio of the amplitudes of high beta waves and gamma waves to the total amplitude As in EEG information Ib2. The response determination unit 20 may generate state information Is based on change C1 and the ratio of LF to HF (LF / HF).

[0052] For example, if the ratio of the sum of the amplitudes of high beta waves and gamma waves of the person being evaluated 120 to the total amplitude As after the first response R1 is greater than the ratio of the sum of the amplitudes of high beta waves and gamma waves of the person being evaluated 120 to the total amplitude As before the first response R1, and if the ratio of LF to HF (LF / HF) after the first response R1 is above a threshold, it can be inferred that the person being evaluated 120's irritability, nervousness, or stress state is increasing. In this case, the response determination unit 20 may determine a second response R2 corresponding to the person being evaluated 120's irritability, nervousness, or stress state.

[0053] If the ratio of LF to HF (LF / HF) is above a threshold, the person being evaluated 120 may be judged to have a state in which the sympathetic nervous system is dominant over the parasympathetic nervous system. If the ratio of LF to HF (LF / HF) is below the threshold, the person being evaluated 120 may be judged to have a state in which the parasympathetic nervous system is dominant over the sympathetic nervous system. The threshold may be 2, 3, 4, or 5.

[0054] For example, if the ratio of the sum of the amplitudes of the high beta waves and gamma waves of the person being evaluated 120 to the total amplitude As after the first response R1 is greater than the ratio of the sum of the amplitudes of the high beta waves and gamma waves of the person being evaluated 120 to the total amplitude As before the first response R1, and the ratio of LF to HF (LF / HF) after the first response R1 is less than a threshold, then it can be inferred that the excited state of the person being evaluated 120 is increasing. In this case, the response determination unit 20 may determine a second response R2 corresponding to the excited state of the person being evaluated 120.

[0055] The reaction determination unit 20 may generate state information Is based on the relationship between the ratio of LF to HF (LF / HF) after the first reaction R1, the threshold value of the ratio of LF to HF, and the change C1. The threshold value may be predetermined. The reaction determination unit 20 may generate state information Is indicating that the sense of caution of the person being evaluated 120 is increasing if the ratio of the sum of the amplitudes of the high beta waves and gamma waves of the person being evaluated 120 to the total amplitude As after the first reaction R1 is greater than the ratio of the sum of the amplitudes of the high beta waves and gamma waves of the person being evaluated 120 to the total amplitude As before the first reaction R1, and the ratio of LF to HF (LF / HF) after the first reaction R1 is greater than or equal to the threshold value. The response determination unit 20 may generate state information Is indicating that the excitability of the person being evaluated 120 is increasing if, after the first response R1, the ratio of the sum of the amplitudes of the high beta waves and gamma waves of the person being evaluated 120 to the total amplitude As is greater than the ratio of the sum of the amplitudes of the high beta waves and gamma waves of the person being evaluated 120 to the total amplitude As before the first response R1, and if the ratio of LF to HF (LF / HF) after the first response R1 is less than a threshold.

[0056] Figure 5 shows an example of state information Is. State information Is may include information relating to multiple states of the person being evaluated 120 (1st state Is-1 to nth state Is-n). In this example, state information Is includes information relating to four states of the person being evaluated 120 (1st state Is-1 to 4th state Is-4). In Figure 5, low-frequency f1 brainwaves refer to at least one of delta waves, theta waves, low alpha waves, and medium alpha waves, and high-frequency f2 brainwaves refer to at least one of high alpha waves, low beta waves, high beta waves, and gamma waves.

[0057] Amplitude Af is the amplitude of the brainwave of the person being evaluated 120 in a predetermined frequency band. Amplitude Af1 is the amplitude of the brainwave of the person being evaluated 120 before the first response R1. Amplitude Af2 is the amplitude of the brainwave of the person being evaluated 120 after the first response R1. The brainwave in the predetermined frequency band may be at least one of low alpha waves, medium alpha waves, high alpha waves, low beta waves, high beta waves, gamma waves, and theta waves.

[0058] The reaction determination unit 20 may generate state information Is based on the change from the ratio of amplitude Af1 to the total amplitude As to the ratio of amplitude Af2 to the total amplitude As, and the ratio of LF to HF (LF / HF). This state information Is may be state information Is related to one of the multiple states of the person being evaluated 120 (any of the first state Is-1 to the nth state Is-n).

[0059] In this example, the first state Is-1 is the state of the person being evaluated 120 when, in the electroencephalogram of low frequency f1, the ratio of amplitude Af2 to the total amplitude As is greater than the ratio of amplitude Af1 to the total amplitude As, and the ratio of LF to HF (LF / HF) after the first response R1 is above a threshold. When the person being evaluated 120 is in the first state Is-1, it can be inferred that the fatigue and drowsiness of the person being evaluated 120 are increasing. When the person being evaluated 120 is in the first state Is-1, the response determination unit 20 (see Figure 3) may generate state information Is indicating that the fatigue and drowsiness of the person being evaluated 120 are increasing. Based on the state information Is related to the first state Is-1, the response determination unit 20 may determine the second response R2.

[0060] In this example, the second state Is-2 is the state of the person being evaluated 120 when, in the electroencephalogram of low frequency f1, the ratio of amplitude Af2 to the total amplitude As is greater than the ratio of amplitude Af1 to the total amplitude As, and the ratio of LF to HF (LF / HF) after the first response R1 is below a threshold. When the person being evaluated 120 is in the second state Is-2, it can be inferred that the person being evaluated 120's relaxation level is increasing. When the person being evaluated 120 is in the second state Is-2, the response determination unit 20 (see Figure 3) may generate state information Is indicating that the person being evaluated 120's level of reassurance is increasing. Based on the state information Is related to the second state Is-2, the response determination unit 20 may determine the second response R2. The utterance "Let's go" from the communication device 100 in Figure 1 is an example of a second response R2 based on the relaxed state of the person being evaluated 120.

[0061] In this example, the third state Is-3 is the state of the person being evaluated 120 when, in the high-frequency f2 electroencephalogram, the ratio of amplitude Af2 to the total amplitude As is greater than the ratio of electroencephalogram Af1 to the total amplitude As, and the ratio of LF to HF (LF / HF) after the first response R1 is above a threshold. When the person being evaluated 120 is in the third state Is-3, it can be inferred that the person being evaluated 120's irritability, nervousness, or stress level is increasing. When the person being evaluated 120 is in the third state Is-3, the response determination unit 20 (see Figure 2) may generate state information Is indicating that the person being evaluated 120's irritability, nervousness, or stress level is increasing. Based on the state information Is related to the third state Is-3, the response determination unit 20 (see Figure 3) may determine the second response R2. The utterance "How about going for a walk? It'll be a nice change of pace" from the communication device 100 in Figure 1 is an example of a second response R2 based on the stress state of the person being evaluated 120.

[0062] In this example, the fourth state Is-4 is the state of the person being evaluated 120 when, in the high-frequency f2 electroencephalogram, the ratio of amplitude Af2 to the total amplitude As is greater than the ratio of electroencephalogram Af1 to the total amplitude As, and the ratio of LF to HF (LF / HF) after the first response R1 is below a threshold. When the person being evaluated 120 is in the fourth state Is-4, it can be inferred that the state of immersion, exhilaration, and excitement of the person being evaluated 120 is increasing. When the person being evaluated 120 is in the fourth state Is-4, the response determination unit 20 (see Figure 3) may generate state information indicating that the state of immersion of the person being evaluated 120 is increasing. Based on the state information Is related to the fourth state Is-4, the response determination unit 20 may determine the second response R2.

[0063] Figure 6 shows an example of the state inference model 42. The state learning unit 40 (see Figure 3) learns the relationship between the first response R1 and the change from EEG information Ib1 to EEG information Ib2. The state learning unit 40 generates the state inference model 42 by learning the relationship between the first response R1 and the change from EEG information Ib1 to EEG information Ib2.

[0064] The state inference model 42 infers the second state S2 of the person being evaluated 120 based on the electroencephalogram (EEG) information Ib1 and the first response R1. This inferred second state S2 is designated as the second state S2'. The second state S2' inferred based on the EEG information Ib1 and the first response R1 is the state S of the person being evaluated 120 based on the EEG information Ib2'. Since the state inference model 42 has learned the relationship between the first response R1 and the change from EEG information Ib1 to EEG information Ib2 through machine learning, the second state S2' can be inferred based on the EEG information Ib1 and the first response R1. As a result, the person being evaluated 120 can infer their own second state S2' after the first response R1. The state inference model 42 may be stored in the memory unit 50 (see Figure 3).

[0065] The state learning unit 40 (see Figure 3) may learn the relationship between the first response R1 and the change from EEG information Ib1 to EEG information Ib2 for multiple subjects 120. The state learning unit 40 may generate a state inference model 42 by learning the relationship between the first response R1 and the change from EEG information Ib1 to EEG information Ib2 for multiple subjects 120.

[0066] The communication device 100 may include a recognition unit 12 (see Figure 3) that recognizes the person being evaluated 120. The recognition unit 12 may be included in the information acquisition unit 10. The recognition unit 12 is, for example, an image sensor, a microphone, etc. If the recognition unit 12 is an image sensor, the recognition unit 12 distinguishes one person being evaluated 120 from another person being evaluated 120 by the captured image. If the recognition unit 12 is a microphone, the recognition unit 12 distinguishes one person being evaluated 120 from another person being evaluated 120 by the frequency of the voice of one person being evaluated 120 and the frequency of the voice of the other person being evaluated 120.

[0067] The state learning unit 40 may use machine learning to learn the relationship between the first response R1 and the change from EEG information Ib1 to EEG information Ib2 for each person being evaluated 120 recognized by the recognition unit 12. The state learning unit 40 may also generate a state inference model 42 for each person being evaluated 120.

[0068] The information acquisition unit 10 (see Figure 3) may acquire electroencephalogram (EEG) information Ib2. The response determination unit 20 (see Figure 3) may determine the second response R2 based on the EEG information Ib2 and the second state S2'. As described above, the second state S2' is inferred by the state inference model 42. The state inference model 42 has learned the relationship between the first response R1 and the change from EEG information Ib1 to EEG information Ib2 through machine learning. Therefore, by determining the second response R2 based on the EEG information Ib2 and the second state S2', the second response R2 can become a more appropriate response to the person being evaluated 120.

[0069] The difference between the second state S2 based on the electroencephalogram (EEG) information Ib2 and the second state S2' is denoted as difference d. Difference d may be the difference between the magnitude of a specific frequency component in any of the alpha, beta, theta, delta, and gamma waves in the EEG information Ib2 and the magnitude of the same specific frequency component in the EEG information Ib2', or it may be the difference between the value obtained by dividing the magnitude of one of the components among the alpha, beta, theta, delta, and gamma waves in the EEG information Ib2 by the magnitude of the other components and the value obtained by that division in the EEG information Ib2'.

[0070] The response determination unit 20 (see Figure 3) may determine a predetermined response as the second response R2 if the difference d exceeds a predetermined threshold dth. The difference d exceeding the threshold dth occurs when the second state S2 of the person being evaluated 120 deviates from the inferred second state S2'. The predetermined response is, for example, an apology or confirmation. When the second state S2 and the second state S2' deviate, the second response R2 determined based on the second state S2' is highly likely to be an inappropriate response to the person being evaluated 120. For this reason, the control unit 90 (see Figure 3) controls the communication device 100 to show the predetermined response. For example, if the second state S2 is a stressful state for the person being evaluated 120, but the state inference model 42 infers a second state S2' that indicates a state of reassurance, the response decision unit 20 may decide that the second response R2 will be either an apologetic utterance such as "I'm sorry I didn't understand how you feel" or an acknowledgment such as "You're still feeling anxious, aren't you?"

[0071] The response determination unit 20 (see Figure 3) may determine the first response R1 based on the electroencephalogram (EEG) information Ib1 and the time at which the first response R1 is determined. The subject 120's potential first state S1 (see Figures 1 and 2) may vary depending on the time at which the first response R1 is determined. For example, if the time at which the first response is determined is early morning, the subject 120 may be in a state of tension; if the time is after lunch, the subject 120 may be in a relaxed state; if the time is in the evening, the subject 120 may be in a stressed state; and if the time is late at night, the subject 120 may be in a sleepy state. Therefore, by determining the first response R1 based on the EEG information Ib1 and the time at which the first response R1 is determined, the first response R1 can be a more appropriate response to the subject 120.

[0072] The state learning unit 40 (see Figure 3) may learn the relationship between the first response R1 and the change from EEG information Ib1 to EEG information Ib2 for each time period. As described above, the potential first state S1 of the person being evaluated 120 may differ depending on the time. Therefore, by having the state learning unit 40 learn the relationship between the first response R1 and the change from EEG information Ib1 to EEG information Ib2 for each time period, the state inference model 42 can more accurately infer the second state S2' of the person being evaluated 120. As a result, the response decision unit 20 (see Figure 3) can determine a more appropriate second response R2 for each time period based on the EEG information Ib2 and the second state S2'.

[0073] The response determination unit 20 (see Figure 3) may determine the first response R1 based on the electroencephalogram information Ib1 and the environment surrounding the person being evaluated 120. The environment surrounding the person being evaluated 120 may be acquired by the information acquisition unit 10 (see Figure 3). If the recognition unit 12 (see Figure 3) is an image sensor, the environment surrounding the person being evaluated 120 may be acquired by the image sensor.

[0074] The potential first state S1 of the person being evaluated (see Figures 1 and 2) may vary depending on the environment surrounding the person being evaluated. For example, if the surroundings of the person being evaluated are sunny, the person being evaluated may be in a state of reassurance, while if the surroundings are cloudy, the person being evaluated may be in a state of anxiety. Therefore, by determining the first response R1 based on the electroencephalogram information Ib1 and the environment surrounding the person being evaluated, the first response R1 can become a more appropriate response to the person being evaluated.

[0075] The control unit 90 may change the living organism 110 presented to the response presentation unit 30 in accordance with the person being evaluated 120. Changing the living organism may mean changing a virtual person, or it may mean changing a virtual animal such as a dog or cat. When the control unit 90 changes a virtual person, the control unit 90 may change the gender or age group of the virtual person.

[0076] The recognition unit 12 (see Figure 3) may recognize the gender or age group of the person being evaluated 120. In the examples of Figures 1 and 2, a young woman is presented as a virtual person in the response presentation unit 30. In the examples of Figures 1 and 2, if the person being evaluated 120 is female, the control unit 90 may change the virtual person presented in the response presentation unit 30 to a male virtual person.

[0077] If the second state S2 of the person being evaluated 120 is a predetermined state of the person being evaluated 120, the response determination unit 20 (see Figure 3) may determine a predetermined response as the second response R2. The response determination unit 20 may determine whether the person being evaluated 120 is in a predetermined state based on the magnitude of any of the frequency components of alpha waves, beta waves, theta waves, delta waves, and gamma waves in the electroencephalogram information Ib. A predetermined state is a state in which it is difficult to change the second state S2 of the person being evaluated 120 by the second response R2. Examples of predetermined states include a state of deep irritation, a state of deep disappointment, a state of deep ecstasy, etc. The case in which the person being evaluated 120 is in such a predetermined state may refer to a case in which the first response R1 could not be a response that corresponds to the potential first state S1 of the person being evaluated 120. In such a case, the response determination unit 20 may determine a predetermined response as the second response R2. A predetermined response is an utterance that confirms the second state S2 of the person being evaluated, such as "I'm sorry I can't find the right words," when the predetermined state is a state of deep frustration.

[0078] Figure 7 is a flowchart showing an example of a communication method according to one embodiment of the present invention. The communication method according to one embodiment of the present invention will be explained using the communication device 100 shown in Figure 3 as an example.

[0079] The communication method comprises an information acquisition step S100, a response determination step S102, and a control step S110. The communication method may also comprise an information acquisition step S104, a state learning step S106, and a response determination step S108.

[0080] The information acquisition step S100 is the step in which the information acquisition unit 10 acquires electroencephalogram (EEG) information Ib1 of the person being evaluated 120. The response determination step S102 is the step in which the response determination unit 20 determines the first response R1 of the communication device 100 based on the EEG information Ib1. The control step S110 is the step in which the control unit 90 controls the communication device 100 according to the first response R1 determined in the response determination step S102.

[0081] The response determination step S102 may be a step in which the response determination unit 20 determines the content of the next utterance of the communication device 100 based on the electroencephalogram information Ib1. The control step S110 may be a step in which the communication device 100 is controlled according to the content of the utterance determined in the response determination step S102.

[0082] The information acquisition step S100 may be a step in which the information acquisition unit 10 further acquires the biological information Ig of the person being evaluated 120. The information acquisition step S100 may be a step in which the information acquisition unit 10 further acquires the biological information Ig of the person being evaluated 120 before the first response R1. The response determination step S102 may be a step in which the response determination unit 20 determines the first response R1 based on the electroencephalogram information Ib and the biological information Ig.

[0083] The information acquisition step S104 may be a step in which the information acquisition unit 10 acquires electroencephalogram (EEG) information Ib2 after the first response R1 of the communication device 100. The information acquisition step S104 may be a step in which the information acquisition unit 10 further acquires biological information Ig of the person being evaluated 120 after the first response R1 of the communication device 100. The response determination step S108 may be a step in which the response determination unit 20 determines the second response R2 of the communication device 100 based on the EEG information Ib2 and the biological information Ig. The control step S110 may be a step in which the control unit 90 controls the communication device 100 in accordance with the second response R2.

[0084] The information acquisition step S104 is a step in which the information acquisition unit 10 acquires changes in electroencephalogram (EEG) information Ib before and after the first response R1 of the communication device 100. The information acquisition step S104 may be a step in which the information acquisition unit 10 acquires EEG information Ib2 after the first response R1. The information acquisition step S104 may be a step in which the information acquisition unit 10 acquires changes from EEG information Ib1 to EEG information Ib2.

[0085] The response determination step S108 may be a step in which the response determination unit 20 generates state information Is based on the changes in electroencephalogram information Ib and biological information Ig acquired in the information acquisition step S104, and determines the second response R2 based on the generated state information Is. It may also be a step in which the second response R2 of the communication device 100 is determined.

[0086] The response determination step S108 may be a step in which the response determination unit 20 generates state information Is based on the change from the ratio of the amplitude of the brain waves in a predetermined frequency band to the total amplitude As in the brainwave information Ib before the first response R1 to the ratio of the amplitude of the brain waves in the said frequency band to the total amplitude As in the brainwave information Ib after the first response R1, and the ratio of LF to HF (LF / HF) in the heartbeat of the person being evaluated 120.

[0087] The response determination step S108 may be a step in which the response determination unit 20 generates state information Is based on the change from the ratio of the amplitude of the brain waves in a predetermined frequency band to the total amplitude As in the brain wave information Ib before the first response R1 to the ratio of the amplitude of the brain waves in the said frequency band to the total amplitude As in the brain wave information Ib after the first response R1, and the relationship between the ratio of LF to HF (LF / HF) after the first response R1 and a predetermined threshold for the ratio of LF to HF.

[0088] The state information Is may include information relating to multiple states of the person being evaluated 120. The response determination step S108 may be a step in which the response determination unit 20 generates state information Is relating to one of multiple states of the person being evaluated 120, based on the change from the ratio of the amplitude of the brainwave in a predetermined frequency band to the total amplitude As in the brainwave information Ib before the first response R1 to the ratio of the amplitude of the brainwave in the said frequency band to the total amplitude As in the brainwave information Ib after the first response R1, and the ratio of LF to HF in the heartbeat of the person being evaluated 120 (LF / HF).

[0089] The response determination step S102 may be a step in which the response determination unit 20 determines a predetermined response as the second response R2 if the second state S2 based on the electroencephalogram information Ib2 of the person being evaluated is a predetermined state of the person being evaluated 120.

[0090] The state learning step S106 is a step in which a state inference model is generated that infers the state S2' of the person being evaluated after the first response R1, based on the electroencephalogram information Ib1 before the first response R1 and the first response R1, by machine learning the relationship between the first response R1 and the changes in electroencephalogram information Ib.

[0091] The information acquisition step S104 may be a step in which the information acquisition unit 10 acquires electroencephalogram (EEG) information Ib2 after the first response R1 of the communication device 100. The response determination step S108 may be a step in which the response determination unit 20 determines the second response R2 of the communication device 100 based on the second state S2 of the person being evaluated based on the EEG information Ib2 acquired in the information acquisition step S104 and the second state S2' of the person being evaluated inferred in the state learning step S106. The response determination step S108 may be a step in which the response determination unit 20 determines a predetermined response as the second response R2 if the difference d between the second state S2 and the second state S2' exceeds a predetermined threshold.

[0092] The reaction determination step S102 may be a step in which the reaction determination unit 20 determines the first reaction R1 based on the time of determination of the first reaction R1 or the environment surrounding the person being evaluated 120. The control step S110 may be a step in which the control unit 90 changes the biological organism 110 presented to the reaction presentation unit 30 according to the person being evaluated 120.

[0093] Figure 8 shows an example of a computer 2200 in which a communication device 100 according to one embodiment of the present invention may be fully or partially embodied. A program installed on the computer 2200 can cause the computer 2200 to function as an operation associated with the communication device 100 according to an embodiment of the present invention, or as one or more sections of the communication device 100, or to execute such operation or one or more sections, or to cause the computer 2200 to execute each step (see Figure 7) of the method of the present invention. The program may be executed by the CPU 2212 to cause the computer 2200 to perform a specific operation associated with some or all of the blocks in the flowchart (Figure 7) and block diagram (Figure 3) described herein.

[0094] A computer 2200 according to one embodiment of the present invention includes a CPU 2212, RAM 2214, a graphics controller 2216, and a display device 2218. The CPU 2212, RAM 2214, graphics controller 2216, and display device 2218 are interconnected by a host controller 2210. The computer 2200 further includes input / output units such as a communication interface 2222, a hard disk drive 2224, a DVD-ROM drive 2226, and an IC card drive. The communication interface 2222, hard disk drive 2224, DVD-ROM drive 2226, and IC card drive are connected to the host controller 2210 via an input / output controller 2220. The computer further includes legacy input / output units such as a ROM 2230 and a keyboard 2242. The ROM 2230 and keyboard 2242 are connected to the input / output controller 2220 via an input / output chip 2240.

[0095] The CPU 2212 controls each unit by operating according to programs stored in the ROM 2230 and RAM 2214. The graphics controller 2216 retrieves the image data generated by the CPU 2212 and places it in the frame buffer or other location provided in RAM 2214, or in RAM 2214 itself, so that the image data is displayed on the display device 2218.

[0096] The communication interface 2222 communicates with other electronic devices via a network. The hard disk drive 2224 stores programs and data used by the CPU 2212 in the computer 2200. The DVD-ROM drive 2226 reads programs or data from the DVD-ROM 2201 and provides the read programs or data to the hard disk drive 2224 via the RAM 2214. The IC card drive reads programs and data from or writes programs and data to the IC card.

[0097] ROM2230 stores boot programs executed by computer 2200 upon activation, or programs that depend on the computer 2200's hardware. The input / output chip 2240 may connect various input / output units to the input / output controller 2220 via parallel ports, serial ports, keyboard ports, mouse ports, etc.

[0098] The program is provided on a computer-readable medium such as a DVD-ROM 2201 or an IC card. The program is read from the computer-readable medium and installed on a hard disk drive 2224, RAM 2214, or ROM 2230, which are also examples of computer-readable medium, and executed by the CPU 2212. The information processing described within these programs is read by the computer 2200, resulting in coordination between the program and the various types of hardware resources described above. The apparatus or method may be configured to realize the manipulation or processing of information in accordance with the use of the computer 2200.

[0099] For example, when communication is performed between a computer 2200 and an external device, the CPU 2212 may execute a communication program loaded into RAM 2214 and instruct the communication interface 2222 to perform communication processing based on the processing described in the communication program. Under the control of the CPU 2212, the communication interface 2222 reads transmission data stored in a transmission buffer processing area provided in a recording medium such as RAM 2214, a hard disk drive 2224, a DVD-ROM 2201, or an IC card, transmits the read transmission data to the network, or writes received data received from the network to a reception buffer processing area provided on the recording medium.

[0100] The CPU 2212 may read all or necessary parts of a file or database stored on an external recording medium such as a hard disk drive 2224, a DVD-ROM drive 2226 (DVD-ROM 2201), or an IC card into the RAM 2214. The CPU 2212 may perform various types of processing on the data in the RAM 2214. The CPU 2212 may then write the processed data back to the external recording medium.

[0101] Various types of information, such as various types of programs, data, tables, and databases, may be stored on the recording medium and processed. The CPU 2212 may perform various types of processing on the data read from the RAM 2214, including various types of operations, information processing, conditional decisions, conditional branching, unconditional branching, information retrieval, or replacement, as specified by the program instruction sequence described in this disclosure. The CPU 2212 may write the results back to the RAM 2214.

[0102] CPU2212 may search for information in files, databases, etc., within the recording medium. For example, if multiple entries are stored in the recording medium, each having an attribute value of a first attribute associated with the attribute value of a second attribute, CPU2212 may search among the multiple entries for an entry that matches the specified condition for the attribute value of the first attribute, read the attribute value of the second attribute stored within that entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

[0103] The program or software module described above may be stored on or on a computer-readable medium of the computer 2200. A recording medium such as a hard disk or RAM provided within a server system connected to a dedicated communication network or the Internet can be used as a computer-readable medium. The program may be provided to the computer 2200 via such a recording medium.

[0104] Although the present invention has been described above using embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various modifications or improvements can be made to the above embodiments. It will be clear from the claims that such modified or improved forms may also be included in the technical scope of the present invention.

[0105] It should be noted that the execution order of operations, procedures, steps, and stages in the apparatus, systems, programs, and methods shown in the claims, specifications, and drawings is not explicitly stated as "before," "prior to," etc., and that these can be implemented in any order unless the output of a previous process is used in a later process. Even if the operation flow in the claims, specifications, and drawings is described using phrases such as "first," "next," etc. for convenience, it does not mean that it is essential to perform the operations in that order. [Explanation of Symbols]

[0106] 10...Information acquisition unit, 12...Recognition unit, 14...Electroencephalograph, 20...Response determination unit, 30...Response presentation unit, 40...State learning unit, 42...State inference model, 50...Memory unit, 90...Control unit, 100...Communication device, 110...Biological device, 120...Evaluated person, 2200...Computer, 2201...DVD-ROM, 2210...Host controller, 2212...CPU, 2214...RAM, 2216...Graphics controller, 2218...Display device, 2220...Input / output controller, 2222...Communication interface, 2224...Hard disk drive, 2226...DVD-ROM drive, 2230...ROM, 2240...Input / output chip, 2242...Keyboard

Claims

1. A communication device whose response changes depending on the state of the person being evaluated, An information acquisition unit that acquires electroencephalogram information of the person being evaluated, A response determination unit that determines the first response of the communication device based on the electroencephalogram information, A control unit controls the communication device in accordance with the first reaction determined by the reaction determination unit, Equipped with, The information acquisition unit acquires the changes in the electroencephalogram information before and after the first response of the communication device. The response determination unit generates state information indicating the state of the person being evaluated based on the changes in the electroencephalogram information, and determines the second response of the communication device based on the generated state information. Communication device.

2. The response determination unit determines the content of the communication device's utterance based on the electroencephalogram information. The control unit controls the communication device according to the content of the utterance determined by the response determination unit. The communication device according to claim 1.

3. The information acquisition unit further acquires the biological information of the person being evaluated, The response determination unit determines the first response based on the electroencephalogram information and the biological information. The communication device according to claim 1 or 2.

4. The information acquisition unit further acquires the biological information after the first reaction, The reaction determination unit determines a second reaction of the communication device based on the biological information after the first reaction. The control unit controls the communication device in response to the second reaction. The communication device according to claim 3.

5. The response determination unit generates state information indicating the state of the person being evaluated based on the changes in the electroencephalogram information and the biological information, and determines the second response based on the generated state information. The communication device according to claim 4.

6. The response determination unit generates the state information based on the change from the ratio of the amplitude of the brain waves in a predetermined frequency band to the total amplitude in the brainwave information before the first response to the ratio of the amplitude of the brain waves in the frequency band to the total amplitude in the brainwave information after the first response, and the ratio of the magnitude of the first power spectrum of the heartbeat of the person being evaluated to the magnitude of the second power spectrum. The total amplitude is the sum of the amplitudes of alpha waves, beta waves, theta waves, gamma waves, and delta waves. The frequency band of the second power spectrum is a higher frequency band than the frequency band of the first power spectrum. The communication device according to claim 5.

7. The reaction determination unit generates the state information based on the change, the ratio of the magnitude of the first power spectrum to the magnitude of the second power spectrum after the first reaction, and a predetermined threshold value for the ratio of the magnitude of the first power spectrum to the magnitude of the second power spectrum. The communication device according to claim 6.

8. The aforementioned status information includes information relating to multiple states of the person being evaluated, The reaction determination unit generates state information relating to one of the plurality of states based on the change and the ratio of the magnitude of the first power spectrum to the magnitude of the second power spectrum. The communication device according to claim 6.

9. The communication device according to claim 8, wherein the brainwaves in the frequency band are at least one of delta waves, theta waves, low alpha waves, and medium alpha waves.

10. The communication device according to claim 8, wherein the brainwaves in the aforementioned frequency band are at least one of high alpha waves, low beta waves, high beta waves, and gamma waves.

11. A communication device whose response changes according to the state of the person being evaluated, An information acquisition unit that acquires electroencephalogram information of the person being evaluated, A response determination unit that determines the first response of the communication device based on the electroencephalogram information, A control unit controls the communication device in accordance with the first reaction determined by the reaction determination unit, Equipped with, If the state of the person being evaluated, based on the electroencephalogram information, after the first response is a predetermined state, the response determination unit determines a predetermined response as the second response of the communication device. Communication device.

12. The response determination unit determines the content of the speech of the communication device based on the electroencephalogram information, The control unit controls the communication device according to the content of the utterance determined by the response determination unit. The communication device according to claim 11.

13. The information acquisition unit further acquires the biological information of the person being evaluated, The response determination unit determines the first response based on the electroencephalogram information and the biological information. The communication device according to claim 11.

14. The information acquisition unit further acquires the biological information after the first reaction, The response determination unit determines the second response of the communication device based on the electroencephalogram information and the biological information after the first response. The control unit controls the communication device in response to the second reaction. The communication device according to claim 13.

15. The communication device according to claim 5, further comprising a state learning unit that generates a state inference model for inferring the state of the person being evaluated after the first reaction, based on the brainwave information before the first reaction and the first reaction, by machine learning the relationship between the first reaction and the changes in the brainwave information.

16. The information acquisition unit acquires the electroencephalogram information after the first response of the communication device, The response determination unit determines the second response of the communication device based on the electroencephalogram information after the first response and the state of the person being evaluated inferred by the state inference model. The communication device according to claim 15.

17. The communication device according to claim 15, wherein the response determination unit determines a predetermined response as the second response if the difference between the state of the person being evaluated based on the electroencephalogram information after the first response and the state of the person being evaluated inferred by the state inference model exceeds a predetermined threshold.

18. The communication device according to claim 1 or 2, wherein the reaction determination unit determines the first reaction based on the time at which the first reaction is determined, or the environment surrounding the person being evaluated.

19. The communication device according to claim 1 or 2, wherein the control unit changes the biological information presented to the response presentation unit according to the person being evaluated.

20. A communication method in which the response changes depending on the state of the person being evaluated. The information acquisition unit performs a first information acquisition step in which it acquires the electroencephalogram information of the person being evaluated, The response determination unit performs a first response determination step in which it determines a first response of the communication device based on the electroencephalogram information, A first control step in which the control unit controls the communication device in accordance with the first reaction determined in the first reaction determination step, The information acquisition unit performs a second information acquisition step in which it acquires changes in the electroencephalogram information before and after the first response of the communication device, The response determination unit generates state information indicating the state of the person being evaluated based on the changes in the electroencephalogram information, and determines the second response of the communication device based on the generated state information in a second response determination step. The control unit performs a second control step in which it controls the communication device in accordance with the second reaction determined in the second reaction determination step, A communication method that incorporates these features.

21. A communication method in which the response changes depending on the state of the person being evaluated. The information acquisition unit performs a first information acquisition step in which it acquires the electroencephalogram information of the person being evaluated, The response determination unit performs a first response determination step in which it determines a first response of the communication device based on the electroencephalogram information, A first control step in which the control unit controls the communication device in accordance with the first reaction determined in the first reaction determination step, If the state based on the electroencephalogram information of the person being evaluated, and the state after the first response, is a predetermined state, the response determination unit performs a second response determination step in which it determines a predetermined response as the second response of the communication device. The control unit performs a second control step in which it controls the communication device in accordance with the second reaction determined in the second reaction determination step, A communication method that incorporates these features.

22. A communication program for causing a computer to perform the communication method described in claim 20 or 21.

Images