State prediction system, member determination system, and state prediction method

The state prediction system forecasts future group and individual states by analyzing current values and communication dynamics, enabling proactive adjustments to maintain positive group interactions.

JP7582148B2Active Publication Date: 2024-11-13TOYOTA JIDOSHA KK
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
JP2021163089
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2021-10-01
Publication Date
2024-11-13
Estimated Expiration
2041-10-01

AI Technical Summary

Technical Problem

Existing technologies are unable to effectively predict and counteract deteriorating group sentiment, making it difficult to maintain positive communication dynamics within a group.

Method used

A state prediction system that acquires current state values and state propagation amounts from individuals within a group, using these to forecast future states and adjust communication patterns to maintain or improve group dynamics.

Benefits of technology

Enables the prediction of future group and individual states, allowing for proactive adjustments to communication to enhance group cohesion and maintain positive interactions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007582148000001
    Figure 0007582148000001
  • Figure 0007582148000002
    Figure 0007582148000002
  • Figure 0007582148000003
    Figure 0007582148000003
Patent Text Reader

Abstract

To provide a technique capable of predicting a future state of an individual in a population.SOLUTION: In a state prediction system (communication support system 1), a first acquisition unit 16 acquires a current state value representing a current status of a targeted individual in a population. A second acquisition unit 18 acquires the amount of state propagation representing state quantity propagated from the other to the individual through communication between the individual and others in the group. A personal state prediction unit 20 predicts a future state value that indicates the future state of the individual from the acquired current state value of the individual and the acquired amount of state propagation.SELECTED DRAWING: Figure 3
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to a technique for supporting communication in a group. [Background technology]

[0002] Patent Document 1 discloses an emotion estimation device that estimates group emotions, which are emotions in a place of human communication. In this technology, group emotions are estimated from information on current individual emotions and a state transition model. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2011-186521 Summary of the Invention [Problem to be solved by the invention]

[0004] The technology of Patent Document 1 can estimate that the current group emotion has deteriorated due to the deterioration of the current individual emotion, but cannot take any measures before the group emotion deteriorates. Even if measures are taken when the group emotion has deteriorated, it may be difficult to restore the atmosphere of the place. The present inventors have recognized that it is desirable to predict the future state of an individual in order to facilitate communication in a group.

[0005] An object of the present invention is to provide a technique capable of predicting the future state of individuals within a population. [Means for solving the problem]

[0006] In order to solve the above problem, a state prediction system of one embodiment of the present invention comprises a first acquisition unit that acquires a current state value indicating the current state of a target individual in a group, a second acquisition unit that acquires a state propagation amount indicating a state amount propagated from the individual to the individual through communication between the individual and others in the group, and an individual state prediction unit that predicts a future state value indicating the future state of the individual from the acquired current state value of the individual and the acquired state propagation amount. The second acquisition unit acquires a current state value indicating the current state of the other person, a current communication volume between the individual and the other person, and the influence of the other person on the state of the individual, derives a state propagation volume from the other person to the individual based on the acquired information, and derives a product of the current state value of the other person, the current communication volume between the individual and the other person, and the influence of the other person on the state of the individual as a state propagation volume from the other person to the individual. The individual state prediction unit determines a future state value of the individual to be the sum of the current state value of the individual and the state propagation volume from the other person to the individual. Another aspect of the present invention is a state prediction system. This state prediction system includes a first acquisition unit that acquires a current state value indicating a current state of a target individual in a group, a second acquisition unit that acquires a state propagation amount indicating a state amount propagated from the individual to the individual through communication between the individual and others in the group, and an individual state prediction unit that predicts a future state value indicating a future state of the individual from the acquired current state value of the individual and the acquired state propagation amount. The second acquisition unit acquires a current state value indicating a current state of the other, a current communication amount between the individual and the other, and an influence degree of the other on the individual's state, derives a state propagation amount from the other to the individual based on the acquired information, and derives, for each of a plurality of others in the group, a product of the current state value of the other, the current communication amount between the individual and the other, and the influence degree of the other on the individual's state as a state propagation amount from the other to the individual. The individual state prediction unit determines the sum of the current state value of the individual and the state propagation amount from the plurality of others to the individual as the future state value of the individual.

[0007] Another aspect of the present invention is a member determination system. This member determination system includes a provisional setting unit that provisionally sets a plurality of people who are candidates for constituting a group, a first acquisition unit that acquires, for each of the provisionally set people, a current state value indicating the current state of the person, a second acquisition unit that acquires, for each of the provisionally set people, a state propagation amount indicating a state amount propagated from the other person to the person, which is predicted based on a past communication amount between the person and the other person in the group, an individual state prediction unit that predicts, for each of the provisionally set people, a future state value indicating a future state of the person from the acquired current state value of the person and the acquired state propagation amount to the person, a group state prediction unit that predicts a group state value indicating a future state of the group based on the predicted future state values ​​of each of the people, and a determination unit that determines the provisionally set people as members of the group if the predicted future group state value satisfies a predetermined condition regarding goodness of state. The second acquisition unit acquires, for each of the provisionally set people, a current state value indicating the current state of the other person, a past communication amount between the person and the other person, and a degree of influence of the other person on the state of the person, derives a state propagation amount from the other person to the person based on the acquired information, and derives, for each of the provisionally set people, a product of the current state value of the other person, the past communication amount between the person and the other person, and the degree of influence of the other person on the state of the person as a state propagation amount from the other person to the person. The personal state prediction unit determines, for each of the provisionally set people, the sum of the current state value of the person and the state propagation amount from the other person to the person as a future state value of the person.

[0008] Yet another aspect of the present invention is a method for predicting a state, the method comprising the steps of: 1. A computer-implemented method for state prediction, comprising: Obtain a current state value that indicates the current state of a target individual in a population 1st acquisition and acquiring a state propagation quantity indicating a state quantity propagated from another person to the individual through communication between the individual and another person in the group. 2nd acquisition and predicting a future state value indicating a future state of the individual from the acquired current state value of the individual and the acquired state propagation amount. Personal condition predictionSteps. In the second acquisition step, a current state value indicating the current state of the other person, a current communication volume between the individual and the other person, and the influence of the other person on the state of the individual are acquired, a state propagation volume from the other person to the individual is derived based on the acquired information, and the product of the current state value of the other person, the current communication volume between the individual and the other person, and the influence of the other person on the state of the individual is derived as the state propagation volume from the other person to the individual. In the individual state prediction step, the sum of the current state value of the individual and the state propagation volume from the other person to the individual is set as the future state value of the individual. Effect of the Invention

[0009] According to the present invention, a technique capable of predicting the future state of individuals in a group can be provided. [Brief description of the drawings]

[0010] [Figure 1] FIG. 2 is a diagram for explaining functions of the communication support system according to the first embodiment. [Diagram 2] FIG. 2 is a diagram illustrating functions of the communication support system, following FIG. [Diagram 3] FIG. 1 illustrates a configuration of a communication support system according to a first embodiment. [Figure 4] FIG. 13 is a diagram showing an example of the current stress state values ​​and conversation volumes of members P1 to P3. [Diagram 5] FIG. 5 is a diagram showing a future stress state value predicted from the current stress state value and the amount of conversation in FIG. 4. [Figure 6] FIG. 13 is a diagram showing an example of the relationship between each of a plurality of conversation volume patterns, a future stress state value of an individual, and a future stress state value of a group. [Figure 7] 4 is a flowchart showing a communication support process of the communication support system of FIG. 3. [Figure 8] 13 is a flowchart showing another example of the communication support process. [Figure 9] FIG. 11 is a diagram illustrating a member determination function of the communication support system according to the second embodiment. [Figure 10] FIG. 10 is a diagram illustrating the member determination function of the communication support system, following FIG. [Figure 11] FIG. 11 illustrates a configuration of a communication support system according to a second embodiment. [Figure 12] 12 is a flowchart showing a member determination process of the communication support system of FIG. 11. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] (First embodiment) FIG. 1 is a diagram for explaining the function of a communication support system according to a first embodiment. The communication support system supports smooth communication in a group G1 in FIG. 1. Smooth communication means that each member (hereinafter also referred to as an individual or person) P1 to P4 constituting the group G1 communicates while maintaining a good state. There may be more than one member. An example of a meeting held by the group G1 will be roughly described below. Detailed processing of the system will be described later.

[0012] The communication support system periodically acquires current state values ​​S1(t)-S4(t) indicating the current state of each member P1-P4 of the group G1, and current communication amounts W12(t), W13(t), W14(t), W23(t), W24(t), and W34(t) between two members for each of a plurality of combinations of two members in the group G1. The present is assumed to be time t. For example, the current state value S1(t) is a numerical value indicating the current state of the member P1, and the communication amount W13(t) is a numerical value indicating the current communication amount between the members P1 and P3. There is no communication between the members P1 and P2, and the communication amount W12(t) is zero. In the example of FIG. 1, the magnitude of the current state values ​​S1(t)-S4(t) is represented by the length of the bar graph, and the magnitude of the communication amount W13(t) and the like is represented by the thickness of the solid line between the members.

[0013] The current state value may be, for example, a stress state value, an emotion value, a performance value, a value representing a degree of fatigue, or a value representing a degree of happiness. The current state value may be a value obtained by substituting at least two of these values ​​into a predetermined calculation formula. The predetermined calculation formula may be, for example, a formula for weighting each value and calculating a sum. The current state value may be detected by a known technique using a sensor or the like. For example, the emotion value may be obtained by analyzing an image of a member taken by a camera, analyzing the member's facial expression, and estimating the member's joy, anger, sadness, or happiness. The current state value may not be a detected value, but may be a numerical value declared by each member.

[0014] The current state value is, for example, a value in the negative to positive range, with a larger positive value indicating a worse state and a smaller negative value indicating a better state. For example, if the current state value indicates a stress state value, a larger positive value indicates a worse state and a smaller negative value indicates a better state. A larger positive value may indicate a better state and a smaller negative value may indicate a worse state. For example, if the current state value indicates happiness, a larger positive value indicates a better state and a smaller negative value indicates a worse state.

[0015] The communication amount is a numerical representation of the degree of communication between two members per unit time, such as the amount of conversation between two members per unit time, an amount derived based on the time one of the two members smiles at the other per unit time, an amount derived based on the time one of the two members looks at the other per unit time, or an amount derived based on the time gestures are made between the two members per unit time. The communication amount may be a value obtained by substituting at least two of these amounts into a predetermined calculation formula. The communication amount is a value equal to or greater than 0. The communication amount can be detected by known technology using a microphone, a camera, a sensor, or the like.

[0016] The communication support system acquires the state propagation amount between two members for each combination of two members in the group G1 based on the current state values ​​S1(t) to S4(t) and the current communication amounts W12(t) to W34(t). The state propagation amount indicates the state amount propagated from one member to the other member by the communication between the two members, and is a value ranging from negative to positive. The state propagation amount from the first member to the second member may be proportional to, for example, the current state value of the first member and the current communication amount between these members. The state propagation amount from the first member to the second member may further be proportional to a coefficient indicating the susceptibility of the second member to the influence of the other member's state. Therefore, for example, the state propagation amount from member P1 to P3 is highly likely to be different from the state propagation amount from member P3 to P1. Note that since the communication amount W12(t) between members P1 and P2 is zero, the state propagation amount from member P1 to P2 and the state propagation amount from member P2 to P1 are zero.

[0017] The communication support system predicts a future state value indicating the future state of each member P1 to P4 from the current state value S1(t) to S4(t) of the member and the state propagation amount from multiple other members to the member. The future is assumed to be time t+1. For example, the future state value S1(t+1) is a numerical value indicating the future state of member P1, and is obtained by adding the state propagation amount from member P2 to P1, the state propagation amount from member P3 to P1, and the state propagation amount from member P4 to P1 to the current state value S1(t) of member P1. The future state values ​​S2(t+1) to S4(t+1) can be obtained in a similar manner.

[0018] The communication support system predicts a group state value Sm indicating the future state of group G1 based on the future state values ​​S1(t+1) to S4(t+1). In the example of Fig. 1, it is assumed that the future group state value Sm is greater than a threshold value Th. If the group state value Sm is greater than the threshold value Th, the communication support system proposes to members P1 to P4 to change the amount of communication so that the future group state value Sm becomes smaller than the threshold value Th.

[0019] The communication support system, for example, suggests increasing the amount of communication between members P1 and P2, between P1 and P3, between P2 and P3, and between P3 and P4, and suggests decreasing the amount of communication between members P1 and P4, and between P2 and P4.

[0020] FIG. 2 is a diagram following FIG. 1 and explaining the function of the communication support system. It is assumed that each member P1 to P4 has changed the amount of communication in accordance with a suggestion from the communication support system. As a result, the future state values ​​S1(t+1) to S4(t+1) of each member newly predicted by the communication support system differ from the values ​​in FIG. 1. The future group state value Sm also differs from the value in FIG. 1 and becomes smaller than the threshold value Th. Therefore, compared to the state in FIG. 1, it becomes easier for each member to maintain a good state during the meeting, and communication in group G1 can proceed more smoothly.

[0021] An example in which the current state value and the future state value are stress state values ​​and the amount of communication is the amount of conversation will be described in detail below. The stress state value is, for example, a value ranging from negative to positive, with a larger positive value indicating a higher level of stress and a smaller negative value indicating a higher level of relaxation. The positive and negative values ​​may be reversed to indicate the stress state. The amount of conversation is a value equal to or greater than 0.

[0022] 3 shows the configuration of a communication support system 1 according to a first embodiment. The communication support system 1 includes a microphone 2, a camera 4, a sensor 6, a storage device 7, an output device 8, and a processing device 10. Although not shown, the communication support system 1 has a plurality of microphones 2, a plurality of cameras 4, and a plurality of sensors 6. The communication support system 1 can also be called a state prediction system.

[0023] The microphone 2 captures conversations between multiple members P1 to Pk (k is an integer equal to or greater than 2) constituting the group G1, and supplies the captured voice data to the processing device 10. The camera 4 captures images of the multiple members P1 to Pk, and supplies the captured image data to the processing device 10. The sensor 6 is attached to the body of each of the members P1 to Pk, detects the heart rate of each of the members P1 to Pk, and supplies the detected heart rate data to the processing device 10. The output device 8 includes, for example, at least one of a display capable of outputting images and an audio output device capable of outputting audio, and outputs various types of information. The output device 8 may be included in a mobile terminal, such as a smartphone, carried by each of the members P1 to Pk.

[0024] The processing device 10 includes a first analysis unit 12, a second analysis unit 14, a first acquisition unit 16, a second acquisition unit 18, an individual state prediction unit 20, a group state prediction unit 22, a derivation unit 24, and a suggestion unit 26. The processing device 10 may be, for example, a personal computer, a smartphone, or a server device.

[0025] The configuration of the processing device 10 can be realized in hardware by the CPU, memory, and other LSI of any computer, and in software by programs loaded into memory, but here the functional blocks realized by the cooperation of these are depicted. Therefore, it will be understood by those skilled in the art that these functional blocks can be realized in various forms by hardware alone, software alone, or a combination of both.

[0026] The second analysis unit 14 has a face image recognition function and identifies which registered user each of the multiple face images captured by the camera 4 belongs to. The storage device 7 stores features of the facial images of the registered users. The second analysis unit 14 compares the features of the facial images of the registered users stored in the storage device 7 with the features of the facial images of the image data, performs authentication processing of the facial images of each of the members P1 to Pk, and determines whether each of the members P1 to Pk is a registered user. When the second analysis unit 14 determines that each of the members P1 to Pk is a registered user, it supplies the identification information of the multiple registered users, which is the identification information of the multiple members P1 to Pk, to the first analysis unit 12 and the second acquisition unit 18. Note that an administrator or the like may input information for identifying the multiple members to an input unit (not shown) of the processing device 10.

[0027] The second analysis unit 14 periodically detects the amount of conversation Wij(t) (i, j≦k) between members Pi and Pj per unit time up to now by performing audio analysis of the audio data supplied from the microphone 2 and image analysis of the image data supplied from the camera 4. For example, the second analysis unit 14 derives a larger amount of conversation Wij(t) the longer the conversation time between members Pi and Pj per unit time. The second analysis unit 14 supplies the detected amount of conversation Wij(t) to the second acquisition unit 18.

[0028] The second analysis unit 14 has a speaker recognition function and identifies which registered user the voice data belongs to. The storage device 7 has registered voice templates for registered users, and the second analysis unit 14 identifies who the speaker is by comparing the voice templates stored in the storage device 7. The second analysis unit 14 identifies the position of each member P1 to Pk from the image data, and estimates which member the utterance is directed to based on the direction in which the face image of the speaking member is facing. The second analysis unit 14 may have a natural language processing function, and may analyze the conversation situation between the members and estimate which members are talking to each other based on the analysis results. A known technique may be used to detect the conversation volume Wij(t).

[0029] The first analysis unit 12 periodically detects the stress state values ​​S1(t)-Sk(t) of each of the members P1-Pk by analyzing the heart rate data of each of the members P1-Pk supplied from the sensor 6, and supplies the detected stress state values ​​S1(t)-Sk(t) to the first acquisition unit 16 and the second acquisition unit 18. Known techniques can be used to detect the stress state values. It is also possible to have an administrator or the like periodically input the level of stress declared by each of the members P1-Pk into an input unit (not shown) of the processing device 10 by numerical input or voice input, without providing the sensor 6. In this case, the first analysis unit 12 detects the stress state values ​​S1(t)-Sk(t) by analyzing the input information.

[0030] The first acquisition unit 16 and the second acquisition unit 18 perform the following process for each of the members P1 to Pk of the group G1.

[0031] The first acquisition unit 16 acquires the current stress state value Si(t) of the target member Pi detected by the first analysis unit 12. This process corresponds to the first acquisition unit 16 acquiring a current state value Si(t) indicating the current state of the target individual Pi in the group G1.

[0032] The second acquisition unit 18 acquires, for each of the multiple others in the group G1, a state propagation amount indicating a state amount propagated from the target member Pi to the target member Pj through communication between the target member Pi and the other person Pj in the group G1. Specifically, for each of the multiple others in the group G1, the second acquisition unit 18 acquires the current stress state value Sj(t) of the other person Pj detected by the first analysis unit 12, the current conversation amount Wij(t) between the target member Pi and the other person Pj detected by the second analysis unit 14, and the influence degree λ of the other person Pj on the state of the target member Pi. The influence degree λ is a value specific to the target member Pi. The second acquisition unit 18 derives, for each of the multiple others in the group G1, the product of the acquired current stress state value Sj(t) of the other person Pj, the current conversation volume Wij(t) between the target member Pi and the other person Pj, and the influence λ of the other person Pj on the state of the target member Pi as the state propagation amount from the other person Pj to the target member Pi.

[0033] This process corresponds to the second acquisition unit 18 acquiring, for each of the multiple others in the group G1, a current state value Sj(t) indicating the current state of the other person Pj, the current amount of communication Wij(t) between the target individual Pi and the other person Pj, and the influence λ of the other person Pj on the state of the individual Pi, and deriving the product of the acquired current state value Sj(t) of the other person Pj, the current amount of communication Wij(t) between the individual Pi and the other person Pj, and the influence λ of the other person Pj on the state of the individual Pi as the amount of state propagation from the other person Pj to the individual Pi.

[0034] The storage device 7 prestores an influence degree λ specific to each registered user in association with the identification information of the registered user. The influence degree λ is a value equal to or greater than 0. The influence degree λ is set for each registered user since it differs according to the individuality of the registered user. The second acquisition unit 18 acquires the identification information of the target member, and acquires the influence degree λ associated with the acquired identification information from the storage device 7.

[0035] The influence level λ may be set for each combination of an individual and another person. This allows the state propagation amount to reflect the difference in the degree to which the state of the other person affects the individual depending on whether the other person is good or bad, and allows a more accurate state propagation amount to be obtained.

[0036] The influence degree λ may change depending on the physical condition of the member. The influence degree λ may be a value declared by each member P1 to Pk before the meeting, inputted into the processing device 10 by an administrator or the like and stored in the storage device 7, or a value derived based on a detection value of a sensor (not shown) may be stored in the storage device 7. For example, the fatigue level or concentration level of the member may be detected periodically by a sensor, and the processing device 10 may periodically derive the influence degree according to the detection result. Alternatively, the sleeping hours and average sleeping hours of the previous day declared by the member may be inputted into the processing device 10, and the processing device 10 may derive the influence degree based on the ratio of the sleeping hours of the previous day to the average sleeping hours.

[0037] The individual state prediction unit 20 predicts the future stress state value Si(t+1) of the target member Pi for each of the multiple members P1 to Pk from the current stress state value Si(t) of the target member Pi acquired by the first acquisition unit 16 and the state propagation amount from multiple others to the target member Pi acquired by the second acquisition unit 18. That is, the individual state prediction unit 20 predicts the future state values ​​S1(t+1) to Sk(t+1) of each of the multiple members P1 to Pk in the group G1. Specifically, the individual state prediction unit 20 determines the sum of the current stress state value Si(t) of the target member Pi and the state propagation amount from multiple others to the target member Pi for each of the multiple members P1 to Pk as the future stress state value Si(t+1) of the target member Pi.

[0038] This process corresponds to the individual state prediction unit 20 predicting, for each of the multiple persons P1 to Pk in the group G1, a future state value Si(t+1) indicating the future state of the individual Pi from the current state value Si(t) of the individual Pi and the amount of state propagation from multiple others to the individual Pi.

[0039] Fig. 4 shows an example of the current stress state values ​​and conversation volumes of members P1 to P3, and Fig. 5 shows future stress state values ​​predicted from the current stress state values ​​and conversation volumes of Fig. 4.

[0040] 4, it is assumed that the current stress state value S1(t) of member P1 is "15", the current stress state value S2(t) of member P2 is "18", and the current stress state value S3(t) of member P3 is "10". It is assumed that the current volume of conversation W12(t) between members P1 and P2 is "1.0", the current volume of conversation W13(t) between members P1 and P3 is "0.2", and the current volume of conversation W23(t) between members P2 and P3 is "0".

[0041] In this example, the future stress state value S1(t+1) of the member P1 is expressed by the following formula (1) as described above. S1(t+1)=S1(t)+S2(t)×W12(t)×λ12+S3(t)×W13(t)×λ13...Equation (1)

[0042] Here, λ12 is the influence of member P2 on the state of member P1, and λ13 is the influence of member P3 on the state of member P1. As mentioned above, λ12 and λ13 may be equal. S2(t)×W12(t)×λ12 is the state propagation amount from member P2 to member P1. S3(t)×W13(t)×λ13 is the state propagation amount from member P3 to member P1.

[0043] For example, assuming λ12=0.1 and λ13=0.2, S1(t+1) becomes "17.2". In this way, the future stress state value S1(t+1) of member P1 can be predicted from the current stress state values ​​S1(t)-S3(t) of members P1 to P3 and the conversation volumes W12(t) and W13(t). Since the future state value of an individual is predicted based on the state propagation volume, it is possible to predict the future state value of an individual taking into account the influence of communication with others.

[0044] For example, if the stress state value Sj(t) of a communication partner Pj of a member Pi is negative, the state propagation amount from this partner Pj will be a negative value, and the future stress state value Si(t+1) of this member Pi will be lower than the current stress state value Si(t). In other words, if the partner is in a relaxed state, this member will be influenced by the partner's state through communication with the partner, and the member's stress state is expected to improve.

[0045] The individual state prediction unit 20 may predict the future state value Si(t+1) of the target member Pi for each of the multiple members P1 to Pk, based on the current state value of the target member Pi and the state propagation amount from one other person Pj to the target member Pi. That is, in a situation where the state propagation amount from multiple other people to the target member Pi is greater than 0, it is not necessary to consider all the state propagation amounts. In this case, the one other person Pj may be, for example, a member whose absolute value of the state propagation amount to the target member Pi is the largest. There may be two or more other people. Even if a state propagation amount with a relatively small absolute value is not used, by using a state propagation amount with the largest absolute value, it is possible to suppress a decrease in prediction accuracy of the future state value. In addition, the processing load can be reduced.

[0046] The group state prediction unit 22 predicts a stress state value Sm of the group G1 indicating the future state of the group G1 based on the future stress state values ​​S1(t+1) to Sk(t+1) of each of the multiple members P1 to Pk predicted by the individual state prediction unit 20. The group state prediction unit 22 sets the statistical value of the future stress state values ​​S1(t+1) to Sk(t+1) of each of the multiple members P1 to Pk as the stress state value Sm of the group G1. The statistical value is, for example, an average value.

[0047] This process corresponds to the group state prediction unit 22 predicting a group state value Sm indicating the future state of the group G1 based on the future state values ​​S1(t+1) to Sk(t+1) of each of the multiple persons P1 to Pk predicted by the individual state prediction unit 20.

[0048] When the predicted future stress state value Sm of the group G1 is greater than the threshold value Th, the derivation unit 24 derives a target conversation volume Wij_m(t) between the members P1 to Pk in the group G1 so that the predicted future stress state value Sm of the group G1 is improved. The threshold value Th can be appropriately determined by experiments or simulations.

[0049] This process corresponds to the derivation unit 24 deriving a target communication amount between multiple people P1 to Pk in group G1 so that the predicted future group state value Sm improves when the predicted future group state value Sm of group G1 satisfies a predetermined condition regarding the poor state.

[0050] The derivation unit 24 virtually sets a plurality of different conversation volume patterns, derives future stress state values ​​S1(t+1) to Sk(t+1) of each member P1 to Pk based on the current stress state values ​​S1(t) to Sk(t) of each member P1 to Pk for each of the plurality of patterns, and derives the average value of the derived future stress state values ​​S1(t+1) to Sk(t+1) as the stress state value Sm of the group G1. This makes it possible to estimate what conversation volume pattern will reduce the stress state value Sm of the group G1.

[0051] The derivation unit 24 sets the pattern of the amount of conversation in which the stress state value Sm of the group G1 is the smallest as the target amount of conversation Wij_m(t) between the multiple members P1 to Pk. The derivation unit 24 may set the pattern of the amount of conversation in which the stress state value Sm of the group G1 is equal to or less than a predetermined value as the target amount of conversation Wij_m(t) between the multiple members P1 to Pk.

[0052] 6 shows an example of the relationship between each of a plurality of conversation volume patterns, future stress state values ​​S1(t+1) to Sk(t+1), and the future stress state value Sm of a group G1. In this example, the plurality of conversation volume patterns cover all combinations of values ​​such that the conversation volume Wij(t) differs by 0.1.

[0053] 6, it is assumed that the stress state value Sm of group G1 is minimum in conversation volume pattern 1. Therefore, the conversation volume Wij(t) of pattern 1 is set as the target conversation volume Wij_m(t). Thus, for example, the target conversation volume W12_m(t) between members P1 and P2 is 0.1, the target conversation volume W13_m(t) between members P1 and P3 is 0.1, and the target conversation volume W14_m(t) between members P1 and P4 is 0.1.

[0054] When the stress state value Sm of group G1 is greater than the threshold value Th, the suggestion unit 26 compares, for each combination of two members Pi, Pj in group G1, the current conversation volume Wij(t) of the two members with a target conversation volume Wij_m(t), and suggests an increase in the conversation volume if the current conversation volume Wij(t) is smaller than the target conversation volume Wij_m(t), and suggests a decrease in the conversation volume if the current conversation volume Wij(t) is greater than the target conversation volume Wij_m(t). The suggestion unit 26 suggests a change in the conversation volume, for example, by having the output device 8 output an image or sound indicating the proposal.

[0055] This process corresponds to the proposing unit 26 comparing the current communication amount Wij(t) with the target communication amount Wij_m(t) for the two target people Pi and Pj in the group G1 when the future group state value Sm is greater than the threshold value Th, and proposing a change in the communication amount based on the comparison result. In this way, when it is predicted that the future state of the group G1 will worsen, it is possible to propose a change in the communication amount between the two people in the group G1 so that the state is less likely to worsen. Therefore, it is possible to allow the members to understand what measures should be taken to improve the future state of the group G1 from the prediction.

[0056] When the stress state value Sm of the group G1 is smaller than the threshold value Th, the proposing unit 26 does not propose a change in the amount of conversation. The processing device 10 periodically repeats the above processing.

[0057] Fig. 7 is a flowchart showing the communication support process of the communication support system 1 of Fig. 3. This process is started when a meeting is to start.

[0058] The second analysis unit 14 identifies k members P1 to Pk (k≦N) (S10), and if an instruction to end the process is not input (N in S12), the second analysis unit 14 detects the current conversation volume Wij(t) (i, j≦k) between members Pi and Pj (S14). The first analysis unit 12 detects the current stress state values ​​S1(t) to Sk(t) of each member P1 to Pk (S16), and the individual state prediction unit 20 derives the future stress state values ​​S1(t+1) to Sk(t+1) of each member P1 to Pk from the current conversation volume Wij(t) and the stress state values ​​S1(t) to Sk(t) (S18).

[0059] The group state prediction unit 22 derives the average value Sm of the future stress state values ​​S1(t+1) to Sk(t+1) of each member P1 to Pk (S20), and if the average value Sm is equal to or less than the threshold value Th (N in S22), returns to S12.

[0060] If the average value Sm is greater than the threshold value Th (Y of S22), the derivation unit 24 identifies a pattern of the target conversation volume Wij_m(t) that minimizes the average value Sm (S24), and derives Wij_s(t)=Wij(t)-Wij_m(t) (S26).

[0061] The proposing unit 26 prompts the members Pi and Pj who satisfy Wij_s(t)<0 to speak (S28), and prompts the members Pi and Pj who satisfy Wij_s(t)>0 to be silent (S30), and returns to S12. If an instruction to end the process is input (Y in S12), the process ends.

[0062] The method of determining the members to whom a change in the amount of conversation is to be proposed is not limited to the above example. Fig. 8 is a flowchart showing another example of the communication support process. Instead of S28 and S30 in Fig. 7, the processes from S42 to S50 in Fig. 8 are executed.

[0063] Next to S26 in FIG. 7, the derivation unit 24 derives Wij_s_m(t)=max(|Wij_s(t)|) (S42). max(|Wij_s(t)|) represents Wij_s(t) with the largest absolute value. That is, the derivation unit 24 sets Wij_s(t) with the largest absolute value as Wij_s_m(t).

[0064] If X < Wij_s_m(t) < Y (Y in S44), the process returns to S12. In this case, the proposal unit 26 does not propose a change in the conversation volume. X is the lower limit value and Y is the upper limit value, and these can be appropriately determined by experiments or simulations. For example, X is a negative value and Y is a positive value. That is, if Wij_s_m(t) is close to zero, the proposal unit 26 does not propose a change in the conversation volume.

[0065] If X < Wij_s_m(t) < Y is not satisfied (N in S44), and if Wij_s_m(t) ≤ X (Y in S46), the proposal unit 26 encourages members Pi and Pj to speak (S48), and the process returns to S12. If Wij_s_m(t) > X (N in S46), the proposal unit 26 encourages members Pi and Pj to be silent (S50), and the process returns to S12.

[0066] In this example, since a change in the conversation volume is proposed only for the two members with the largest absolute difference between the current conversation volume and the target conversation volume, it is possible to make a proposal that can improve the future group state value Sm while minimizing the members to whom the proposal is targeted.

[0067] Note that the process of S44 may be omitted, and after S42, the determination of S46 may be executed. In this case, the determination of S46 is changed. If Wij_s_m(t) < 0 (S46), the proposal unit 26 encourages members Pi and Pj to speak (S48), and the process returns to S12. If Wij_s_m(t) > 0 (S46), the proposal unit 26 encourages members Pi and Pj to be silent (S50), and the process returns to S12. If Wij_s_m(t) = 0 (S46), the process returns to S12. Also in this modification example, it is possible to make a proposal that can improve the future group state value Sm while minimizing the members to whom the proposal is targeted.

[0068] Also, in the process of FIG. 7, in S28, the proposal unit 26 may encourage members Pi and Pj who satisfy Wij_s(t) < X to speak, and in S30, the proposal unit 26 may encourage members Pi and Pj who satisfy Wij_s(t) > Y to remain silent. X and Y are the upper and lower limit values described above. In this modification, the members to be proposed can be limited to those members who are predicted to relatively greatly contribute to the improvement of the future group state value Sm.

[0069] As described above, when the stress state value Sm of the future group G1 is greater than the threshold value Th, an example has been described in which the pattern of the conversation volume that minimizes the stress state value Sm of the group G1 is set as the target conversation volume among a plurality of members P1 to Pk. However, it is also possible to propose a change in the conversation volume without deriving the target conversation volume.

[0070] Specifically, the proposal unit 26 compares the state propagation amounts from each of a plurality of other members in the group G1 to the target member, and based on the comparison result, proposes a change in the communication amount between the target member and the other members so that the predicted future state value of the target member is improved. The proposal unit 26 identifies the state propagation amount from the other member who is the largest and positive to the target member, and proposes a reduction in the communication amount between the member and the other member. By reducing the communication amount between the member and the other member, the state propagation amount from the other member to the member can be made smaller compared to before the reduction in the communication amount, and the future state value of the member can be made smaller.

[0071] The proposal unit 26 may identify the state propagation amount from the other member who is the smallest and negative to the target member, and propose an increase in the communication amount between the member and the other member. By increasing the communication amount between the member and the other member, the negative state propagation amount from the other member to the member can be made smaller compared to before the increase in the communication amount, and the future state value of the member can be made smaller.

[0072] In this modification, the suggestion unit 26 may determine the presence or absence of a suggestion for one or more members, and may not determine all members. In this case, the member to be judged may be registered in advance in the storage device 7 by an administrator or the like, may be a member whose influence degree λ of others on the member's state is equal to or greater than a predetermined value, or may be a member whose influence degree λ of others on the member's state is the largest. The second acquisition unit 18 may acquire only the state propagation amount to the member to be judged, and the individual state prediction unit 20 may predict only the future stress state value of the member to be judged.

[0073] In this modification, a change in the amount of communication between the target member and others is proposed, so that the member can understand what measures should be taken to improve the future state of the member. This can improve the future stress state value Sm of the group G1. In addition, since the target conversation amount is not derived, the process can be simplified.

[0074] (Second embodiment) In the second embodiment, a process of determining the members of the group G1 from among a plurality of people so that the future group state value indicates a good state is added to the first embodiment. The following mainly describes the differences from the first embodiment.

[0075] 9 is a diagram for explaining the member determination function of the communication support system according to the second embodiment. Before the start of a meeting, the communication support system provisionally determines, for example, four members P1 to P4 from seven people P1 to P7 who are candidates for constituting a group G1. At this point, the seven people P1 to P7 do not need to be close enough together to communicate with each other.

[0076] The communication support system acquires the current state values ​​S1(t) to S4(t) of each of the members P1 to P4 and the state propagation amount predicted based on the past communication amounts W12, W13, W14, W23, W24, and W34 between the two members for each of a plurality of combinations of two members in the group G1. The method of deriving the state propagation amount is the same as that of the first embodiment, and it is sufficient to use the past communication amount instead of the current communication amount.

[0077] The communication support system predicts a future state value indicating the future state of each member P1 to P4 from the current state value S1(t) to S4(t) of the member and the state propagation amount from multiple other members to the member. The communication support system predicts a future group state value Sm based on the future state values ​​S1(t+1) to S4(t+1). In the example of FIG. 9, it is assumed that the future group state value Sm is greater than a threshold value Th. In this case, since the members P1 to P4 are not suitable, the communication support system provisionally sets another member. The communication support system repeats the provisional setting of the member until the future group state value Sm becomes equal to or less than the threshold value Th.

[0078] FIG. 10 is a diagram for explaining the member determination function of the communication support system, which follows FIG. 9. The communication support system provisionally sets four members P1, P2, P5, and P6 as candidates for constituting the group G1 from among the people P1 to P7. The future state values ​​S1(t+1) to S4(t+1) of each member newly predicted by the communication support system are different from the values ​​in FIG. 9. The future group state value Sm is also different from the value in FIG. 9 and is assumed to be smaller than the threshold value Th. Therefore, the communication support system officially determines the members P1, P2, P5, and P6 as members of the group G1 and notifies the determined members P1, P2, P5, and P6. The members P1, P2, P5, and P6 who receive the notification gather together and start a meeting. Compared with the members P1 to P4 in FIG. 9, it becomes easier for each member P1, P2, P5, and P6 to maintain a good state during the meeting, and communication in the group G1 can be smoothly promoted. After the meeting starts, the communication support system executes the processing of the first embodiment.

[0079] Fig. 11 shows the configuration of a communication support system 1A according to the second embodiment. The communication support system 1A can also be called a member determination system. The processing device 10A further includes a provisional setting unit 30 and a determination unit 32 in addition to the configuration shown in Fig. 3. An example will be described in which the current state value and the future state value are stress state values, and the amount of communication is the amount of conversation.

[0080] The provisional setting unit 30 provisionally sets a plurality of people who are candidates for constituting the group G1. The first acquisition unit 16 acquires the current stress state value of each of the provisionally set persons.

[0081] The second acquisition unit 18 acquires the past conversation volume between each of the plurality of temporarily set persons and others within the group G1, and acquires a state propagation volume indicating the state volume propagated from the others to the person predicted based on the acquired past conversation volume. In the storage device 7, the past conversation volume between two registered users for each of a plurality of combinations of two registered users is stored. The second acquisition unit 18 acquires the past conversation volume from the storage device 7.

[0082] The individual state prediction unit 20 predicts the future stress state value of each of the plurality of temporarily set persons from the acquired current stress state value of the person and the acquired state propagation volume to the person.

[0083] The group state prediction unit 22 predicts the stress state value Sm of the future group G1 based on the predicted future stress state values of each of the plurality of persons.

[0084] When the predicted future stress state value Sm of the group G1 satisfies a predetermined condition regarding the goodness of the state, the determination unit 32 determines the plurality of temporarily set persons as members of the group G1, and causes the output device 8 to output information for specifying the determined members.

[0085] When the stress state value of the future group G1 does not satisfy a predetermined condition regarding the goodness of the state, the temporary setting unit 30 newly temporarily sets a plurality of persons who are candidates for constituting the group G1, and the first acquisition unit 16, the second acquisition unit 18, the individual state prediction unit 20, the group state prediction unit 22, and the determination unit 32 perform the above processing again.

[0086] FIG. 12 is a flowchart showing the member determination process of the communication support system 1A in FIG. 11. The temporary setting unit 30 temporarily sets k (k < N) members from N persons (S60). The second acquisition unit 18 acquires the past conversation volume between the members (S62), and the first analysis unit 12 detects the current stress state value of each member (S64). The individual state prediction unit 20 derives the future stress state value of each member from the past conversation volume and the current stress state value (S68).

[0087] The group state prediction unit 22 derives the average value Sm of the future stress state values ​​of the k members (S70), and if the average value Sm is greater than the threshold value Th (Y of S72), the process returns to S60. If the average value Sm is equal to or less than the threshold value Th (N of S72), the determination unit 32 determines the provisionally set members as official members of the meeting (S74), and ends the process.

[0088] During the member determination process, k may be a predetermined constant value, or k may be changed when the average value Sm is greater than the threshold value Th (Y of S72). When k is changed in Y of S72, the provisional setting unit 30 may increase k by a predetermined number or decrease k by a predetermined number before executing the process of S10.

[0089] According to this embodiment, it is possible to determine, from among a plurality of people, a plurality of members who are expected to relatively improve the future state of group G1 through communication.

[0090] The present invention has been described above based on the embodiments. The embodiments are merely examples, and it will be understood by those skilled in the art that various modifications are possible in the combination of each component and each processing step, and that such modifications are also within the scope of the present invention.

[0091] For example, the derivation unit 24 and the suggestion unit 26 may not be provided, and a change in the amount of communication may not be proposed. In this case, the first acquisition unit 16 causes the output device 8 to output the current state value of the individual so that the individual can be specified, and the individual state prediction unit 20 causes the output device 8 to output the future state value of the individual. The output device 8 may display, for example, FIG. 1 as an image. Based on the output current state value and future state value, it is possible to predict whether the state of the individual will deteriorate in the future, and it is possible to specify whether it is necessary to take some measures regarding communication for the individual. This makes it easier to keep the future state of the individual in a good state. Alternatively, the individual state prediction unit 20 may cause the output device 8 to output the future state value of the individual so that the individual can be specified only when the future state value of the individual is greater than a threshold value. Furthermore, the group state prediction unit 22 may cause the output device 8 to output the future group state value, or may cause the output device 8 to output the future group state value only when the future group state value is greater than a threshold value. Based on the future group state values, it is possible to predict whether the state of group G1 will deteriorate in the future, and therefore it is possible to identify whether any communication-related measures need to be taken for group G1. [Explanation of symbols]

[0092] 1,1A...communication support system, 10,10A...processing device, 12...first analysis unit, 14...second analysis unit, 16...first acquisition unit, 18...second acquisition unit, 20...individual state prediction unit, 22...group state prediction unit, 24...derivation unit, 26...proposal unit, 30...provisional setting unit, 32...determination unit.

Claims

1. a first acquisition unit that acquires a current state value indicating a current state of a target individual in the group; a second acquisition unit that acquires a state propagation quantity indicating a state quantity propagated from another person in the group to the individual through communication between the individual and the other person; an individual state prediction unit that predicts a future state value indicating a future state of the individual based on the acquired current state value of the individual and the acquired state propagation amount; Equipped with The second acquisition unit is acquiring a current state value indicating a current state of the other person, a current amount of communication between the individual and the other person, and a degree of influence of the other person on the state of the individual, and deriving a state propagation amount from the other person to the individual based on the acquired information; deriving a state propagation amount from the other person to the individual by a product of the current state value of the other person, a current communication amount between the individual and the other person, and a degree of influence of the other person on the state of the individual; the individual state prediction unit determines a sum of a current state value of the individual and an amount of state propagation from the other person to the individual as a future state value of the individual. A state prediction system comprising:

2. A first acquisition unit that acquires a current state value indicating a current state of a target individual in a group; a second acquisition unit that acquires a state propagation quantity indicating a state quantity propagated from another person in the group to the individual through communication between the individual and the other person; an individual state prediction unit that predicts a future state value indicating a future state of the individual based on the acquired current state value of the individual and the acquired state propagation amount; Equipped with The second acquisition unit is acquiring a current state value indicating a current state of the other person, a current amount of communication between the individual and the other person, and a degree of influence of the other person on the state of the individual, and deriving a state propagation amount from the other person to the individual based on the acquired information; For each of a plurality of others in the group, deriving a product of a current state value of the other, a current amount of communication between the individual and the other, and a degree of influence of the other on the state of the individual as a state propagation amount from the other to the individual; the individual state prediction unit determines a sum of a current state value of the individual and a state propagation amount from the plurality of others to the individual as a future state value of the individual; A state prediction system comprising:

3. The second acquisition unit acquires, for each of a plurality of others in the group, an amount of state propagation from the other to the individual; a suggestion unit that compares the acquired amounts of state propagation from the plurality of others to the individual, and based on a comparison result, suggests a change in the amount of communication between the individual and others so that a future state value of the individual is improved; 3. The state prediction system according to claim 1 or 2.

4. The individual state prediction unit predicts a future state value of each of a plurality of people in the group; a group state prediction unit that predicts a group state value indicating a future state of the group based on the predicted future state values ​​of each of the plurality of people; 3. The state prediction system according to claim 1 or 2.

5. A derivation unit that derives a target communication amount between the plurality of people so that a predicted future group state value is improved; a suggestion unit that compares a current communication amount between two target people in the group with a target communication amount and proposes a change in the communication amount based on a comparison result; The state prediction system according to claim 4, further comprising:

6. A provisional setting unit that provisionally sets a plurality of people who are candidates for constituting a group; A first acquisition unit that acquires, for each of the plurality of provisionally set persons, a current state value indicating a current state of the person; a second acquisition unit that acquires, for each of the plurality of provisionally set people, a state propagation amount indicating a state amount propagated from another person to the provisionally set person, the state propagation amount being predicted based on a past communication amount between the provisionally set person and another person in the group; an individual state prediction unit that predicts, for each of the plurality of provisionally set persons, a future state value indicating a future state of the person from the acquired current state value of the person and the acquired state propagation amount to the person; a group state prediction unit that predicts a group state value indicating a future state of the group based on the predicted future state values ​​of each of the plurality of people; a determination unit that determines the provisionally set persons as members of the group when the predicted future group state value satisfies a predetermined condition regarding goodness of state; Equipped with The second acquisition unit is For each of the plurality of provisionally set people, a current state value indicating a current state of the other person, a past communication amount between the person and the other person, and an influence degree of the other person on the state of the person are acquired, and a state propagation amount from the other person to the person is derived based on the acquired information; For each of the provisionally set people, deriving a product of the current state value of the other person, the amount of past communication between the person and the other person, and the influence of the other person on the state of the person as a state propagation amount from the other person to the person; the individual state prediction unit sets, for each of the provisionally set persons, a sum of a current state value of the person and an amount of state propagation from the other person to the person as a future state value of the person; A member determination system comprising:

7. A computer-implemented state prediction method, comprising: A first acquisition step of acquiring a current state value indicating a current state of a target individual in the population; a second acquisition step of acquiring a state propagation quantity indicating a state quantity propagated from another person in the group to the individual through communication between the individual and the other person; an individual state prediction step of predicting a future state value indicating a future state of the individual from the acquired current state value of the individual and the acquired state propagation amount; Equipped with In the second acquisition step, acquiring a current state value indicating a current state of the other person, a current amount of communication between the individual and the other person, and a degree of influence of the other person on the state of the individual, and deriving a state propagation amount from the other person to the individual based on the acquired information; deriving a state propagation amount from the other person to the individual by a product of the current state value of the other person, a current communication amount between the individual and the other person, and a degree of influence of the other person on the state of the individual; In the individual state prediction step, a sum of a current state value of the individual and a state propagation amount from the other person to the individual is set as a future state value of the individual. A state prediction method comprising:

Citation Information

Patent Citations

  • Operation support device and operation support method

    JP2004220217A

  • Communication analyzing device and method

    JP2007094850A

  • Organization communication visualization system

    JP2009009355A

  • Organization cooperative display system and processor

    JP2010198261A

  • Emotion estimation device and emotion estimation method

    JP2011186521A