Estimation device, estimation system, estimation method, and control program

The estimation device calculates individual and space temperatures using speech and heat transfer formulas independent of participant count, effectively estimating communication atmosphere.

JP2026182571APending Publication Date: 2026-11-19KANSAI UNIVERSITY
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
JP2025078904
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2025-05-09
Publication Date
2026-11-19

AI Technical Summary

Technical Problem

Existing methods for estimating the atmosphere of a communication setting fail to account for the influence of individual participants, requiring the number of participants as a parameter, which limits their applicability.

Method used

An estimation device that calculates individual and space temperatures using speech information, weighted by simultaneous speech, and heat transfer amounts, expressed through formulas independent of participant count, to estimate the atmosphere.

Benefits of technology

Enables accurate estimation of communication atmosphere without considering participant numbers, aligning with subjective evaluations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2026182571000001_ABST
    Figure 2026182571000001_ABST
Patent Text Reader

Abstract

To estimate the level of excitement in a communication setting. [Solution] The estimation device (10) comprises an acquisition unit (11) that acquires speech information from each of the multiple participants, a first calculation unit (121) that weights the speech information based on whether or not the multiple participants are speaking simultaneously and calculates the individual temperature of each of the multiple participants, a second calculation unit (122) that calculates the temperature of the field using a first heat transfer amount between each of the multiple participants and the field, and an estimation unit (123) that estimates the atmosphere of the field using the temperature of the field, wherein the first heat transfer amount is expressed by a first formula that does not depend on the number of multiple participants.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical Field]

[0001] This invention relates to an estimation device, etc., for estimating the level of excitement in a dialogue setting involving multiple people. [Background technology]

[0002] People experience a sense of connection with others through feelings of unity and excitement in communication settings. However, the excitement of a setting is not visible and is only a sensory experience. Therefore, methods have been proposed to estimate the atmosphere of a conversation based on text information, or by measuring physiological indicators (such as sweating and heart rate variability). However, in actual communication, people perceive the invisible setting of the dialogue as an atmosphere, and each person exerts some kind of influence on that setting, shaping its state. To date, atmosphere estimation that takes such a setting into account has not been performed.

[0003] The inventors of this application have proposed a model for estimating the atmosphere of a space by simulating the communication space as a virtual temperature space (Patent Document 1). [Prior art documents] [Patent Documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2024-126580 [Overview of the project] [Problems that the invention aims to solve]

[0005] The technology described in Patent Document 1 requires parameters that correspond to the number of participants in the setting, and therefore the number of participants must be taken into consideration.

[0006] One aspect of the present invention aims to realize an estimation device, etc., that estimates the level of excitement at a venue without considering the number of participants. [Means for solving the problem]

[0007] To solve the aforementioned problems, an estimation device according to one aspect of the present invention is an estimation device for estimating the atmosphere of a communication space with multiple participants, comprising: an acquisition unit that acquires speech information, which is information relating to the utterances of each of the multiple participants; a first calculation unit that calculates an individual temperature, which indicates the state of each of the multiple participants as a temperature, by weighting the speech information based on whether or not the multiple participants are uttering simultaneously; a second calculation unit that calculates the temperature of the space using a first heat transfer amount between each of the multiple participants and the space; and an estimation unit that estimates the atmosphere of the space using the temperature of the space, wherein the first heat transfer amount is expressed by a first formula that does not depend on the number of the multiple participants.

[0008] To solve the aforementioned problems, an estimation system according to one aspect of the present invention includes an estimation device and a terminal device which is communicatively connected to the estimation device and which acquires the speech information of each participant from each participant, wherein the estimation device acquires the speech information from the terminal device.

[0009] To solve the aforementioned problems, an estimation method according to one aspect of the present invention is an estimation method for estimating the atmosphere of a communication space with multiple participants, comprising: an acquisition step of acquiring speech information which is information relating to the utterances of each of the multiple participants; a first calculation step of calculating an individual temperature which indicates the state of each of the multiple participants as a temperature by weighting the speech information based on whether or not the multiple participants are uttering simultaneously; a second calculation step of calculating the temperature of the space using a first heat transfer amount between each of the multiple participants and the space; and an estimation step of estimating the atmosphere of the space using the temperature of the space, wherein the first heat transfer amount is expressed by a first formula which does not depend on the number of the multiple participants.

[0010] Each aspect of the present invention may be implemented by a computer, in which case a control program for the estimation device that enables the computer to implement the estimation device by operating the computer as each part (software element) of the estimation device, and a computer-readable recording medium on which the program is recorded, also fall within the scope of the present invention. [Effects of the Invention]

[0011] According to one aspect of the present invention, in a dialogue involving multiple people, the atmosphere of the dialogue can be estimated without considering the number of participants. [Brief explanation of the drawing]

[0012] [Figure 1] This figure illustrates an overview of the estimation system according to Embodiment 1 of the present invention. [Figure 2] This is a functional block diagram showing the main components of the estimation system. [Figure 3] This is a flowchart showing the processing flow in the estimation device. [Figure 4] This figure compares evaluations by participants with evaluations by an estimation system. [Figure 5] This diagram illustrates the estimation accuracy of the estimation system. [Figure 6] This figure shows the estimation accuracy of the estimation system numerically. [Modes for carrying out the invention]

[0013] [Embodiment 1] The following describes in detail one embodiment of the present invention. First, with reference to Figure 1, an overview of the estimation system 1 (see Figure 2) according to this embodiment will be described. The estimation system 1 estimates the level of excitement in the atmosphere of a communication setting involving two or more people. More specifically, the estimation system 1 treats the communication setting as a virtual temperature space, sets heat capacities for the participants and the setting, and estimates the level of excitement in the atmosphere of the communication setting by calculating the temperature of the setting using the amount of heat transfer between the participants and the setting. Note that the temperature of the setting, the heat capacity of the setting, and the temperature and heat capacity of the participants described in this embodiment are set virtually and do not represent actual temperatures and heat capacities. Furthermore, although this embodiment uses communication with three or more people as an example, it is also possible to apply the estimation system 1 to a communication setting with two people to estimate the level of excitement.

[0014] Figure 1 shows an example of a situation where six participants (User 1 to User 6) are communicating. In estimation system 1, the communication space is defined as temperature space F, and the temperature of temperature space F is defined as T. F , heat capacity C F Set the following: Also, set the temperature to T1 to T6 and the heat capacity to C1 to C6 for each of the users 1 to 6. Then, Q is the amount of heat that moves from user n (n=1, 2, 3..., 6) to temperature space F. nF Q is the amount of heat that moves from user n to outside the temperature space F. nO Assuming that the temperature T of the temperature space F is obtained from the amount of heat transfer, F Using an estimation model that estimates the level of excitement in a communication setting, we estimate the personal temperature T of user n. n The method for calculating this will be described later. In the following, the communication space will also simply be referred to as "the space."

[0015] Figure 2 shows a functional block diagram of the estimation system 1. As shown in Figure 2, the estimation system 1 includes an estimation device 10 and user terminals (terminal devices) 20. The estimation device 10 is connected to multiple user terminals 20 in a communicative manner. The user terminals 20 are terminals owned by each participant in the communication. Participants may also participate in the communication remotely. In this case, it is sufficient that the user terminals 20 owned by the participants and the estimation device 10 are connected in a communicative manner via the network 30.

[0016] The estimation device 10 estimates the level of excitement in the atmosphere of a communication setting and includes an acquisition unit 11 and an estimation processing unit 12. The estimation device 10 may also include an output unit 13.

[0017] The acquisition unit 11 acquires speech information from the user terminal 20, which is the speech information of user n, a participant in the communication session. The acquisition unit 11 repeatedly acquires the speech information.

[0018] The estimation processing unit 12 estimates the level of excitement in the atmosphere of the communication setting using the speech information of user n acquired by the acquisition unit 11, and includes a first calculation unit 121, a second calculation unit 122, an estimation unit 123, and an estimation model 124.

[0019] The estimation model 124 includes calculation formulas used in the first calculation unit 121 and the second calculation unit 122.

[0020] The first calculation unit 121 uses the speech information of user n acquired by the acquisition unit 11 to calculate the personal temperature T indicating the state of user n. n The first calculation unit 121 uses the following equation (1) stored in the estimation model 124 to calculate the personal temperature T of user n. n Calculate.

[0021]

number

[0022] Here, i is the frame number, T n (i) is the temperature of user n in the i-th frame. W×OnOff n where W is a weighting constant for simultaneous speech, which is calculated using the following formula (2). OnOff n indicates the presence or absence of speech by user n, that is, a binarized version of the speech information. In other words, W×OnOff n is obtained by binarizing speech based on a preset threshold, and performing weighting based on the presence or absence of simultaneous speech among the participants. Note that the weighting based on the presence or absence of simultaneous speech is not limited to the case where all participants are speaking simultaneously. The weighting may be increased when at least two of the participants are speaking simultaneously. Further, the weighting value may vary according to the number of people speaking simultaneously. Furthermore, binarization of speech information is an example, and the present invention is not limited to this. Any type of information may be used as long as it can be quantified.

[0023] [Formula]

[0024] Here, N indicates the number of participants participating in the communication. Further, formula (2) is an example in a case where binarization is set to 0 and 1.

[0025] C n is the heat capacity of user n. C n may be, for example, 1.0. That is, for each i-th frame, the first calculation unit 121 calculates the personal temperature T of the current frame using the speech information acquired in the current frame and the personal temperature calculated in the previous frame n Note that the personal temperature of the previous frame used for the calculation is not limited to the immediately preceding frame, as long as it is calculated in a prior frame. That is, the frame is not limited to the previous frame (i-1), and may be the frame before the previous frame (i-2), or even earlier frames (i-3), ..., (i-n).

[0026] Also, Q nF (i) is the amount of heat transferred from user n to the field (first heat transfer amount), Q nO This represents the amount of heat transferred from user n to the outside (second heat transfer). These are calculated using the following equations (3) and (4).

[0027]

number

[0028] Here, K1 and K2 are constants that do not depend on N, that is, on the number of participants N. For example, K1 is 0.1 and K2 is 0.025. K1 and K2 are not limited to these values ​​and may be, for example, within the ranges K1 = 0.05 to 0.2 and K2 = 0.01 to 0.05.

[0029] As described above, the first heat transfer amount Q nF This can be expressed by equation (3) (the first equation), which includes a coefficient K1 that does not depend on the number of participants N, but does not include a coefficient that depends on the number of participants N. In other words, equation (3) (the first equation) can be said to be an equation that does not depend on the number of participants N. Also, the second heat transfer amount Q nO This can be expressed by equation (4) (the second equation), which includes a coefficient K2 that does not depend on the number of participants N, but does not include a coefficient that depends on the number of participants N. In other words, equation (4) (the second equation) can be said to be an equation that does not depend on the number of participants N.

[0030] The second calculation unit 122 uses the amount of heat transfer between the user n and the field to calculate the field temperature T F The temperature of the field T is calculated using the following equation (5). F The second calculation unit 122 calculates the field temperature T of the current frame using the field temperature calculated in the previous frame and the amount of heat transfer in the previous frame for each i-frame. FThe following is calculated. Note that the field temperature and heat transfer amount of the previous frame used in the calculation can be those calculated in the previous frame, and are not limited to the previous frame. That is, it is not limited to the previous frame (i-1), but may also be the frame before that (i-2), or even the frame before that (i-3), ... (in).

[0031]

number

[0032] Here, Q FO This is the amount of heat transferred from the field to the outside of the field (third heat transfer), and is calculated using the following equation (6).

[0033]

number

[0034] K3 is a constant that does not depend on N, that is, on the number of participants N. For example, K3 is 0.1. K3 is not limited to this and may be a value within the range of K3 = 0.05 to 0.2. Therefore, the third heat transfer amount Q FO It can be said that this can be expressed by equation (6) (the third equation), which includes a coefficient K3 that does not depend on the number of participants N, but does not include a coefficient that depends on the number of participants N. In other words, equation (6) (the third equation) can be said to be an equation that does not depend on the number of participants N.

[0035] Furthermore, K1 and K3 may have the same value, and K2 may have a value smaller than both K1 and K3.

[0036] C F is the heat capacity of the field. CF can be, for example, 1.0. That is, it is the heat capacity of the temperature space F, and if the amount of heat transfer from user n is the same, the smaller the heat capacity, the lower the temperature of the field T. F The larger the range of fluctuation, the greater the field temperature T FThe range of fluctuation becomes smaller. The heat capacity of the space is set according to the number of users participating in the space, the compatibility and relationships between users, the content of the space, etc. For example, if it is a small number of people, friends, or an online drinking party, the heat capacity of the space should be set to a small level; if it is a small number of people, teachers and students, or an online presentation, the heat capacity of the space should be set to a medium level; and if it is a large number of people, many of whom are meeting for the first time, or a seminar, the heat capacity of the space may be set to a large level.

[0037] The estimation unit 123 calculates the field temperature T calculated by the second calculation unit 122. F Based on this, the level of excitement in the atmosphere of the communication setting is estimated. The estimation of the level of excitement is, for example, based on temperature T F It is acceptable to estimate that the atmosphere is lively when the value is higher than a threshold. Alternatively, the degree of liveliness may be estimated in multiple stages.

[0038] The estimation processing unit 12 may estimate the level of excitement of each user n participating in the communication. In this case, the individual temperature T calculated by the first calculation unit 121 n Using this, the estimation unit 123 estimates the level of excitement of the user n.

[0039] As described above, the acquisition unit 11 acquires speech information for each i-frame, and the estimation unit 123 performs estimation for each i-frame. In other words, the acquisition unit 11 repeatedly acquires speech, and each time the acquisition unit 11 acquires speech, the first calculation unit 121 calculates the personal temperature T n The second calculation unit 122 calculates the field temperature T F The estimation unit 123 calculates the value and performs the estimation.

[0040] The user terminal 20 may be a terminal used by user n for communication. In this case, the user terminal 20 may be equipped with a microphone. By being equipped with a microphone, the voice of user n can be acquired and transmitted to the estimation device 10 as speech information.

[0041] The output unit 13 outputs the surge level, which is the estimation result estimated by the estimation processing unit 12. The output unit 13 may output the surge level to an external device and display the surge level on that external device, or it may output to a user terminal 20 and display the surge level on the user terminal 20. Alternatively, the output unit 13 may include a monitor, speaker (not shown), etc., and the surge level may be displayed by the monitor, speaker, etc.

[0042] In this embodiment, the voice of user n is acquired by the user terminal 20, but it is also possible for each user n to be fitted with a microphone, and the estimation device 10 to acquire the voice from each user n's microphone.

[0043] As described above, the estimation device 10 according to this embodiment estimates the atmosphere of a communication setting involving multiple participants. The estimation device 10 includes an acquisition unit 11, a first calculation unit 121, a second calculation unit 122, and an estimation unit 123. The acquisition unit 11 acquires speech information, which is information related to the utterances of each of the multiple participants. The first calculation unit 121 weights the speech information based on whether or not there is simultaneous utterance among the multiple participants, and expresses the state of each of the multiple participants as a temperature, called an individual temperature T. n The second calculation unit 122 calculates the first heat transfer amount Q between each of the multiple participants and the field. nF Using the field temperature T F The estimation unit 123 calculates the field temperature T. F The atmosphere of the field is estimated using this method. Then, the first heat transfer amount Q nF This can be expressed by a formula that does not depend on the number of participants N.

[0044] Furthermore, the second calculation unit 122 calculates the second heat transfer amount Q between each of the multiple participants and the outside. nO , and the third heat transfer amount Q between the field and the outside. FO Using the field temperature T F It may be used to calculate the second heat transfer amount Q. nO The third heat transfer amount Q may be expressed by an equation that does not depend on the number of participants N. FOThis expression can be represented by a formula that does not depend on the number of participants N.

[0045] [Processing flow] Next, with reference to Figure 3, the processing flow in the estimation device 10 will be explained. Figure 3 is a flowchart showing the processing flow of the estimation device 10.

[0046] As shown in Figure 3, the estimation device 10 first has an acquisition unit 11 that acquires user n's speech information from the user terminal 20 of user n participating in the communication via the network 30 (S101, acquisition step). Next, the estimation processing unit 12 uses the speech information acquired by the acquisition unit 11 to estimate the level of excitement in the atmosphere of the communication space (S102). In detail, the first calculation unit 121 uses user n's speech information to calculate the personal temperature indicating user n's state (first calculation step). The second calculation unit 122 uses the amount of heat transfer between user n and the space to calculate the temperature of the space (second calculation step). Then, the estimation unit 123 calculates the temperature T of the space calculated in the second calculation step. F Based on this, the level of excitement in the atmosphere of the communication setting is estimated (estimation step).

[0047] Finally, the output unit 13 outputs the estimated degree of elevation (S103). This concludes the processing flow in the estimation device 10.

[0048] As described above, the estimation device 10 according to this embodiment is an estimation device 10 that estimates the atmosphere of a communication space involving multiple participants. The estimation device 10 comprises an acquisition unit 11, an estimation processing unit 12, and an output unit 13. The acquisition unit 11 acquires speech information, which is information about the speech of each of the multiple participants. The estimation processing unit 12 comprises a first calculation unit 121, a second calculation unit 122, and an estimation unit 123. The first calculation unit 121 binarizes the speech information for each of the multiple participants, weights it based on whether or not the multiple participants are speaking simultaneously, and calculates an individual temperature that indicates the state of the participant as a temperature. The second calculation unit 122 calculates the temperature of the space using the amount of heat transfer between each of the multiple participants and the space. The estimation unit 123 estimates the atmosphere of the space using the temperature of the space.

[0049] As a result, the estimation device 10 can estimate the atmosphere of a situation in communication involving multiple people.

[0050] [Verification Results] Figures 4 to 6 show the results of estimating the atmosphere of a situation using Estimation System 1. Figure 4 shows the evaluation of a communication situation by four participants. Figure 401 shows the subjective evaluation by the four participants. Here, 10 evaluators evaluated the level of excitement for a 3-minute segment extracted from a 30-minute conversation between the four participants. Each evaluator assigned a score of 1 if they judged the situation to be exciting, and 0 if they did not, and the scores of each evaluator were added together. Figure 402 shows the level of excitement of the situation estimated by Estimation System 1 for the same conversation. Since Estimation System 1 fixes the coefficients K1, K2, and K3, Figure 402 is labeled as evaluation using fixed parameters. Comparing Figures 401 and 402, it can be seen that the estimation results by Estimation System 1 are similar to the evaluation results by the evaluators.

[0051] Figure 5 shows the results of an analysis of a 3-minute segment extracted from a 30-minute conversation between four participants, using the cross-correlation function C(τ) shown below. Here, the analysis interval was set to 30 seconds, and the time delay (the deviation from the estimation result by estimation system 1 based on subjective evaluations) was set to ±5 seconds. The relationship of time variation was then analyzed using the cross-correlation function C(τ).

[0052]

number

[0053] The parameters are as follows: x(i): Subjective level of excitement (number of evaluators who rated it as "exciting" at time i) y(i): Estimated value of the excitement level of the field estimated by estimation system 1 at time i. μ x ,μ y :Average values ​​of x,y N: Number of data points i: Drawing frame τ: Time delay Figure 5, section 502, shows the relationship between the cross-correlation function C(τ) and the time delay (seconds) in the analysis interval shown in section 501A. As shown in Figure 5, the analysis reveals a strong positive correlation between the subjective evaluation by the evaluators and the estimation results by estimation system 1 around 0 seconds. In other words, there is almost no discrepancy between the evaluators' evaluations and the estimation results by estimation system 1. Furthermore, a positive correlation can be observed at all time points. Therefore, it can be said that the evaluators' evaluations and the estimation results by estimation system 1 agree well.

[0054] Figure 6 shows the results of evaluations conducted in multiple groups with 2 to 5 participants. Figure 6, section 601, shows the positive correlation coefficient between the evaluators' evaluation results and the estimation results from estimation system 1. Figure 6, section 602, shows the time lag between the evaluators' evaluation results and the estimation results from estimation system 1. As shown in Figure 6, a strong positive correlation is observed in all cases, from 2 to 5 people, and there is virtually no time lag. From the above, it can be seen that estimation system 1 can estimate the atmosphere of a communication setting.

[0055] Although the above explanation uses examples of six participants, or two to five participants, the estimation system 1 disclosed herein is not limited to these cases and can also be applied to estimating the atmosphere of a communication setting with seven or more participants.

[0056] [Embodiment 2] Other embodiments of the present invention are described below. For the sake of clarity, components having the same function as those described in the above embodiments will be denoted by the same reference numerals, and their descriptions will not be repeated.

[0057] In addition to the speech information described above, non-speech information may also be acquired and used to estimate the atmosphere of the situation. Non-speech information refers to information other than user n's speech, and includes information such as user n's facial expressions, gaze direction, presence or absence of body movements, presence or absence of blinking, pupil size, heart rate, blood pressure, sweating, and respiration.

[0058] Of these, user n's facial expression, gaze direction, presence or absence of body movement, presence or absence of blinking, and pupil size can be obtained, for example, by analyzing images captured by the camera (not shown) of user terminal 20. It is also possible to extract facial expression, gaze direction, presence or absence of body movement, presence or absence of blinking, pupil size, etc. from the captured images. Furthermore, user n's respiratory rate and heart rate can be measured and obtained, for example, by applying filtering to the captured images. In addition, user n's heart rate, blood pressure, amount of sweat, etc. may be detected, for example, by a sensor terminal (not shown) worn by the user and obtained via user terminal 20.

[0059] When non-speech information is also used, W × OnOff in equation (1) above. n Instead, the following Behavior n(i) can be used. That is, a linear combination of spoken information and multiple types of non-spoken information can be used. Behavior n (i) = W × OnOff n +W GAZE ×Gaze(θ n )+W FACE ×Face(F n )+W BODY ×OnOff n +W BLINK ×OnOff n +W PUPIL ×Pupil(P n )+W heartbeat ×HR (HR n )+W Sweat ×OnOff n +W Respiration ×R(R n )+W blood pressure ×BP (BP n ) The meanings of each item are as follows: W GAZE ×Gaze(θ n ):W GAZE Gaze(θ) is the weighting constant for the direction of the line of sight. n ) is a value based on the direction of the line of sight. W FACE ×Face(F n ):W FACE This is the weighting constant for facial expressions, Face(F n ) is a value based on facial expression. W BODY ×OnOff n :W BODY This is a weighting constant for body movements, On / Off n This refers to the presence or absence of physical movement. W BLINK ×OnOff n :W BLINK This is the blinking weighting constant, On / Off n The difference lies in whether or not you blinked. W PUPIL ×Pupil(P n ):W PUPIL Pupil(P) is the weighting constant for pupil size. n ) is the size of the pupil. W heartbeat×HR(HR n ):W heartbeat is a weighting constant for heart rate, and HR(HR n )is the heart rate. W Sweat ×OnOff n :W Sweat is a weighting constant for sweating, and OnOff n indicates the presence or absence of sweating. W Respiration ×R(R n ):W Respiration is a weighting constant for respiration, and R(R n )is a value indicating the respiration rate. W blood pressure ×BP(BP n ):W blood pressure is a weighting constant for blood pressure, and BP(BP n )is a value corresponding to the blood pressure value.

[0060] The non-speech information only needs to be two or more types, and it is not required to use all the non-speech information described herein.

[0061] [Example of Implementation by Software] The functions of the estimation device 10 (hereinafter referred to as "the device") can be implemented by a program for causing a computer to function as the device, which is a program for causing the computer to function as each control block of the device (particularly each unit included in the estimation processing unit 12).

[0062] In this case, the device includes a computer having at least one control device (e.g., a processor) and at least one storage device (e.g., a memory) as hardware for executing the program. By executing the above program with this control device and storage device, each function described in the above embodiments is implemented.

[0063] The program may be recorded on one or more computer-readable recording media, not temporary ones. These recording media may or may not be provided by the device. In the latter case, the program may be supplied to the device via any wired or wireless transmission medium.

[0064] Furthermore, some or all of the functions of each of the control blocks can also be realized by logic circuits. For example, an integrated circuit in which logic circuits functioning as each of the control blocks are formed is also included in the scope of the present invention. In addition, it is also possible to realize the functions of each of the control blocks using, for example, a quantum computer.

[0065] Furthermore, each of the processes described in the above embodiments may be performed by AI (Artificial Intelligence). In this case, the AI ​​may operate on the control device, or it may operate on other devices (for example, an edge computer or a cloud server).

[0066] The present invention is not limited to the embodiments described above, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention. For example, in this embodiment, the first calculation unit for calculating personal temperature and the second calculation unit for calculating the temperature of the environment are described separately, but both functions may be given to a single calculation unit. That is, the first calculation unit and the second calculation unit may be the same. Also, the first calculation unit, the second calculation unit, and the estimation unit may be the same.

[0067] 〔summary〕 An estimation device according to Embodiment 1 of the present disclosure is an estimation device for estimating the atmosphere of a communication space with multiple participants, comprising: an acquisition unit that acquires speech information which is information relating to the speech of each of the multiple participants; a first calculation unit that calculates an individual temperature which indicates the state of each of the multiple participants as a temperature by weighting the speech information based on whether or not the multiple participants are speaking simultaneously; a second calculation unit that calculates the temperature of the space using a first heat transfer amount between each of the multiple participants and the space; and an estimation unit that estimates the atmosphere of the space using the temperature of the space, wherein the first heat transfer amount is expressed by a first formula which does not depend on the number of the multiple participants.

[0068] The estimation device according to Embodiment 2 of the present disclosure, in Embodiment 1, further calculates the temperature of the field using a second heat transfer amount between each of the plurality of participants and the outside, and a third heat transfer amount between the field and the outside, wherein the second heat transfer amount is expressed by a second formula that does not depend on the number of participants, and the third heat transfer amount is expressed by a third formula that does not depend on the number of participants.

[0069] In the estimation device according to embodiment 2 of this disclosure, in embodiment 1 or 2, the estimation unit estimates the state of the individual using the individual's temperature.

[0070] The estimation device according to Embodiment 4 of the present disclosure, in Embodiment 2, the acquisition unit repeatedly acquires the utterance, and each time the acquisition unit acquires the utterance, the first calculation unit calculates the personal temperature, the second calculation unit calculates the field temperature, and the estimation unit performs the estimation, the first calculation unit calculates the current personal temperature using the utterance information acquired this time and the personal temperature calculated last time, the second calculation unit calculates the current field temperature using the field temperature calculated last time and the first and third heat transfer amounts up to the previous time, and the estimation unit performs the estimation using the current field temperature.

[0071] The estimation device according to Embodiment 5 of the present disclosure, in any of Embodiments 1 to 4, wherein the acquisition unit acquires multiple types of non-verbal information, which is information other than the utterances of each of the multiple participants, and the first calculation unit calculates the individual temperature by weighting and linearly combining the multiple types of non-verbal information.

[0072] In the estimation device according to embodiment 6 of the present disclosure, in embodiment 5, the first calculation unit calculates the individual temperature using at least two of the following as non-verbal information: facial expression, gaze, body movements, blinking, pupil size, heart rate, blood pressure, amount of sweat, and respiration of each participant.

[0073] In the estimation apparatus according to embodiment 7 of the present disclosure, in any of embodiments 1 to 6, the second calculation unit calculates the temperature of the field using the heat capacity of the field set according to the compatibility between each of the participants.

[0074] An estimation device according to embodiment 8 of the present disclosure includes, in any of embodiments 1 to 7, an output unit that outputs the estimation result of the estimation unit, and the output unit causes the estimation result to be displayed on a destination device.

[0075] An estimation system according to aspect 9 of the present disclosure includes an estimation device and a terminal device which is communicatively connected to the estimation device and which acquires the utterance information of each participant from each participant, wherein the estimation device acquires the utterance information from the terminal device.

[0076] The estimation system according to embodiment 10 of the present disclosure, in embodiment 9, includes a terminal device that acquires estimation results from the estimation device and displays the atmosphere of the place which is the acquired estimation result.

[0077] An estimation method according to aspect 11 of the present disclosure is an estimation method for estimating the atmosphere of a communication space with multiple participants, comprising: an acquisition step of acquiring speech information which is information relating to the utterances of each of the multiple participants; a first calculation step of calculating an individual temperature which indicates the state of each of the multiple participants as a temperature by weighting the speech information based on whether or not the multiple participants are uttering simultaneously; a second calculation step of calculating the temperature of the space using a first heat transfer amount between each of the multiple participants and the space; and an estimation step of estimating the atmosphere of the space using the temperature of the space, wherein the first heat transfer amount is expressed by a first formula which does not depend on the number of the multiple participants.

[0078] A control program according to aspect 12 of the present invention is a control program for causing a computer to function as an estimation device of any of aspects 1 to 8, wherein the computer functions as the first calculation unit, the second calculation unit, and the estimation unit. [Explanation of Symbols]

[0079] 1 Estimation System 10 Estimation device 11 Acquisition Department 12 Estimation Processing Unit 121 First Calculation Unit 122 Second Calculation Unit 123 Estimation Department 124 Estimated Models 13 Output section 20 User Terminals 30 Networks

Claims

1. An estimation device for estimating the atmosphere of a communication setting involving multiple participants, An acquisition unit that acquires speech information, which is information related to the speech of each of the aforementioned multiple participants, A first calculation unit that weights the utterance information based on whether or not the multiple participants are uttering simultaneously, and calculates an individual temperature that represents the state of each of the multiple participants as a temperature, A second calculation unit calculates the temperature of the field using a first heat transfer amount between each of the aforementioned participants and the field, The system includes an estimation unit that estimates the atmosphere of the field using the temperature of the field, The estimation device wherein the first heat transfer amount is expressed by a first formula that does not depend on the number of participants.

2. The second calculation unit further calculates the temperature of the field using the second heat transfer amount between each of the multiple participants and the outside, and the third heat transfer amount between the field and the outside. The second heat transfer amount is expressed by a second equation that does not depend on the number of participants, The estimation apparatus according to claim 1, wherein the third heat transfer amount is expressed by a third formula that does not depend on the number of participants.

3. The estimation device according to claim 1, wherein the estimation unit estimates the state of the individual using the individual's temperature.

4. The acquisition unit repeatedly acquires the utterance, Each time the acquisition unit acquires the utterance, The first calculation unit calculates the personal temperature, The second calculation unit calculates the temperature of the field, The estimation unit performs the estimation, The first calculation unit calculates the current personal temperature using the speech information acquired this time and the personal temperature calculated last time. The second calculation unit calculates the current field temperature using the field temperature calculated previously and the first and third heat transfer amounts up to the previous time. The estimation device according to claim 2, wherein the estimation unit performs the estimation using the temperature of the field in the present case.

5. The acquisition unit acquires multiple types of non-speech information, which is information other than the utterances of each of the multiple participants. The estimation device according to claim 1, wherein the first calculation unit calculates the personal temperature by weighting and linearly combining the multiple types of non-speech information.

6. The estimation device according to claim 5, wherein the first calculation unit calculates the individual temperature using at least two of the following as non-verbal information: facial expression, gaze, body movements, blinking, pupil size, heart rate, blood pressure, amount of sweat, and respiration of each participant.

7. The estimation apparatus according to claim 1, wherein the second calculation unit calculates the temperature of the field using the heat capacity of the field set according to the compatibility between each of the participants.

8. The system includes an output unit that outputs the estimation result of the estimation unit, The estimation device according to claim 1, wherein the output unit causes the estimation result to be displayed on a destination device.

9. An estimation device according to any one of claims 1 to 8, The estimation device is connected to a terminal device that enables communication, and includes a terminal device that acquires the speech information of each participant from each participant, The estimation device is an estimation system that acquires the speech information from the terminal device.

10. The estimation system according to claim 9, wherein the terminal device includes a display unit that acquires estimation results from the estimation device and displays the atmosphere of the place, which is the acquired estimation result.

11. An estimation method for estimating the atmosphere of a communication setting involving multiple participants, The acquisition step involves acquiring speech information, which is information about the utterances of each of the aforementioned multiple participants. A first calculation step involves weighting the utterance information based on whether or not the multiple participants are uttering simultaneously, and calculating an individual temperature that represents the state of each of the multiple participants as a temperature. A second calculation step involves calculating the temperature of the field using a first heat transfer amount between each of the aforementioned participants and the field, The estimation step includes estimating the atmosphere of the field using the temperature of the field, The estimation method wherein the first heat transfer amount is expressed by a first formula that does not depend on the number of participants.

12. A control program for causing a computer to function as an estimation device according to claim 1, wherein the computer functions as the first calculation unit, the second calculation unit, and the estimation unit.

Citation Information

Patent Citations

  • Estimation apparatus, estimation system, estimation method, and control program

    JP2024126580A