JP7658151B2 - Conference management device, method, program and conference management system - Google Patents

Description

The present invention relates to a conference management device, method, program, and conference management system.

In a meeting, it is desirable to reach a satisfactory conclusion within the scheduled time. To achieve this, it is important that meeting participants feel psychological safety in the meeting. A state in which participants feel psychological safety is, for example, a state in which each participant is aware that they will not be disadvantaged or feel uncomfortable as a result of what they say. If participants feel psychological safety, they are more likely to share information and ideas, and the meeting is expected to produce good results.

In addition, to improve the outcome of a meeting, it is also important that the meeting proceeds smoothly. For example, Patent Document 1 discloses a method for ensuring that a meeting proceeds smoothly. Specifically, this method determines who will speak based on at least one of the following: the degree of agreement between the skills of the meeting participants and the agenda, the number of comments, the level of frustration, and the level of understanding. This method can encourage participants who have skills related to the agenda, participants who speak little, participants who are frustrated because they want to speak, or participants who do not understand the content of the meeting to speak.

JP 2020-42720 A

However, while the method disclosed in Patent Document 1 can adjust the amount of speech each participant makes, it is not expected to improve how each participant feels about the meeting, for example, to increase the psychological safety of each participant in the meeting.

Therefore, the present invention has been made in consideration of the above problems, and the object of the present invention is to provide a new and improved conference management device, method, program, and conference management system that can improve how each participant feels about the conference.

In order to solve the above problem, according to one aspect of the present invention, a conference system includes a speech and behavior data acquisition unit that acquires speech and behavior data of multiple participants participating in a conference, an advice unit that determines advice data including advice to at least any of the participants in accordance with the speech and behavior data and one or more advice rules, a detection unit that detects how the multiple participants felt about the conference by analyzing the speech and behavior data, a learning unit that learns the relationship between the advice rules in one or more conferences including the conference and a result of detection by the detection unit, and a setting unit that sets one or more new advice rules based on the relationship obtained by the learning, and a learning unit learns a relationship between a parameter group including the threshold parameter, a number of participants parameter indicating the number of participants in the conference, and a pre-start parameter indicating how the multiple participants feel about the conference before the conference starts, and a result of detection by the detection unit; and a setting unit applies the number of participants parameter and the pre-start parameter for a new conference to the relationship, and sets a new threshold parameter for each advice rule so that, in the relationship after application, the result of detection by the detection unit is improved over the pre-start parameter .

The detection unit may detect the psychological safety of the multiple participants in the conference by detecting how the multiple participants felt about the conference.

The detection unit may detect the psychological safety based on at least one of the evenness of speech among the multiple participants, each participant's receptivity to the speech of others, the multiple participants' sense of satisfaction with the conclusion of the conference, or the physical movements of the multiple participants.

The speech and behavior data may include data indicating the type of statements made by the participant and data indicating the type of reaction to statements made by other participants.

The conference management device may further include a conference screen control unit that generates a conference screen including a statement type selection display for selecting a statement type and a reaction type selection display for selecting a reaction type, and a communication unit that transmits the conference screen to a conference terminal used by the multiple participants, and the speech and behavior data acquisition unit may acquire speech and behavior data indicating the statement type selected on the conference screen and speech and behavior data indicating the reaction type selected on the conference screen.

In order to solve the above problem, according to another aspect of the present invention, a method includes acquiring speech and behavior data of a plurality of participants participating in a conference, determining advice data including advice to at least any of the participants according to the speech and behavior data and one or more advice rules, detecting how the plurality of participants felt about the conference by analyzing the speech and behavior data, learning a relationship between the advice rules in one or more conferences including the conference and a result of the detection of how the plurality of participants felt about the conference, and setting one or more new advice rules based on the relationship obtained by the learning , a computer-implemented method is provided in which each of the advice rules includes a condition including a threshold parameter and advice content when the condition is met, the learning includes learning a relationship between a group of parameters including the threshold parameter, a number of participants parameter indicating the number of participants in the meeting, and a pre-start parameter indicating how the plurality of participants feel about the meeting before the start of the meeting, and a result of the detection, and the setting includes applying the number of participants parameter and the pre-start parameter for a new meeting to the relationship, and setting a new threshold parameter for each advice rule such that, in the relationship after application, the result of the detection is improved over the pre-start parameter .

Further, in order to solve the above-mentioned problem, according to another aspect of the present invention, a computer is made to function as a speech and behavior data acquisition unit that acquires speech and behavior data of multiple participants participating in a conference, an advice unit that determines advice data including advice to at least any of the participants in accordance with the speech and behavior data and one or more advice rules, a detection unit that detects how the multiple participants felt about the conference by analyzing the speech and behavior data, a learning unit that learns the relationship between the advice rules in one or more conferences including the conference and a result of detection by the detection unit, and a setting unit that sets one or more new advice rules based on the relationship obtained by the learning, and the one or more advice rules are set based on the relationship obtained by the learning. a learning unit learns a relationship between a parameter group including the threshold parameter, a number of participants parameter indicating the number of participants in the meeting, and a pre-start parameter indicating how the multiple participants feel about the meeting before the start of the meeting, and a result of detection by the detection unit; and a setting unit applies the number of participants parameter and the pre-start parameter for a new meeting to the relationship, and sets a new threshold parameter for each advice rule such that, in the relationship after application, the result of detection by the detection unit is improved over the pre-start parameter .

Further, in order to solve the above-mentioned problems, according to another aspect of the present invention, there is provided a conference management system having one or more conference terminals used by multiple participants participating in a conference, and a conference management device, the conference management device including a speech and behavior data acquisition unit that acquires speech and behavior data of the multiple participants from the one or more conference terminals, an advice unit that determines advice data including advice to at least any of the participants in accordance with the speech and behavior data and one or more advice rules, a detection unit that detects how the multiple participants felt about the conference by analyzing the speech and behavior data, a learning unit that learns the relationship between the advice rules in one or more conferences including the conference and a result of detection by the detection unit, and one or more new advice rules based on the relationship obtained by the learning. and a setting unit that sets a new advice rule, each of the one or more advice rules including a condition including a threshold parameter and advice content when the condition is satisfied, the learning unit learns a relationship between a group of parameters including the threshold parameter, a number of participants parameter indicating the number of participants in the conference, and a pre-start parameter indicating how the multiple participants feel about the conference before the start of the conference, and a result of detection by the detection unit, and the setting unit applies the number of participants parameter and the pre-start parameter for the new conference to the relationship, and sets a new threshold parameter for each advice rule so that, in the relationship after application, the result of detection by the detection unit is improved over the pre-start parameter .

The present invention described above makes it possible to improve how each participant feels about the conference.

1 is an explanatory diagram showing a configuration of a conference management system according to an embodiment of the present invention; A specific example of the conference screen will be described. FIG. 2 is an explanatory diagram showing the configuration of a conference management server 20 according to an embodiment of the present invention. FIG. 4 is an explanatory diagram showing an example of data included in the conference setting data. FIG. 11 is an explanatory diagram showing a specific example of an advice rule. 13 is an explanatory diagram showing a storage structure of parameters and psychological safety by the storage unit 240. FIG. 10 is a flowchart showing an operation up to setting conference setting data as preparation for starting a conference; 1 is a flow chart showing operations during and after a conference. FIG. 2 is a block diagram showing a hardware configuration of the conference management server 20.

The following describes in detail an embodiment of the present invention with reference to the accompanying drawings. Note that in this specification and the drawings, components having substantially the same functional configuration are designated by the same reference numerals to avoid redundant description.

In addition, in this specification and drawings, multiple components having substantially the same functional configuration may be distinguished by adding different letters after the same reference numeral. For example, multiple components having substantially the same functional configuration or logical meaning may be distinguished as necessary, such as conference terminals 10A, 10B, and 10C. However, if there is no need to particularly distinguish between multiple components having substantially the same functional configuration, only the same reference numeral is assigned to each of the multiple components. For example, if there is no need to particularly distinguish between conference terminals 10A, 10B, and 10C, each conference terminal will be simply referred to as conference terminal 10.

<Overview of the conference management system>
An embodiment of the present invention relates to a conference management system for managing a conference in which a plurality of participants take part. Hereinafter, an overview of the conference management system according to an embodiment of the present invention will be described with reference to FIG.

Figure 1 is an explanatory diagram showing the configuration of a conference management system according to one embodiment of the present invention. As shown in Figure 1, the conference management system according to one embodiment of the present invention has multiple conference terminals 10A to 20E and a conference management server 30.

These conference terminals 10A-10E and the conference management server 30 are connected via a network 12. The network 12 is a wired or wireless transmission path for information transmitted from devices connected to the network 12. For example, the network 12 may include public line networks such as the Internet, telephone line networks, and satellite communication networks, as well as various LANs (Local Area Networks) including Ethernet (registered trademark), and WANs (Wide Area Networks). The network 12 may also include a dedicated line network such as an IP-VPN (Internet Protocol-Virtual Private Network).

In the example shown in FIG. 1, participant A uses conference terminal 10A, participant B uses conference terminal 10B, participant C uses conference terminal 10C, participant D uses conference terminal 10D, and participant E uses conference terminal 10E. However, the number of conference terminals 10 constituting the conference management system and the number of participants (users) using the conference management system may be fewer or greater.

(Conference terminal 10)
The conference terminal 10 is an information processing device used by each participant. A headset 11 worn by the participant is connected to the conference terminal 10. The headset 11 acquires voice data of the voice uttered by the participant and transmits the voice data to the conference terminal 10 by wired or wireless communication. The conference terminal 10 transmits the voice data to the conference management server 20. The conference terminal 10 also receives voice data of other participants from the conference management server 20 and transmits the voice data to the headset 11. The headset 11 outputs the voice of the other participants based on the voice data received from the conference terminal 10. This makes it possible to hold a remote conference via voice between multiple participants.

The conference terminal 10 also acquires speech and behavior data of participants using the conference terminal 10, and transmits the speech and behavior data to the conference management server 20. When a participant using the conference terminal 10 makes a statement, the speech and behavior data includes text data indicating the type of statement and the content of the statement. When a participant using the conference terminal 10 responds to a statement made by another participant, the speech and behavior data includes body movement data indicating the type of reaction and body movement. The body movement data may be, for example, data obtained based on the detection of acceleration by an acceleration sensor built into the headset 11.

The above-mentioned types of comments and types of reactions can be obtained, for example, by participants operating the conference screen displayed on the conference terminal 10. The conference screen is generated by the conference management server 20 and transmitted from the conference management server 20 to the conference terminal 10. Below, a specific example of the conference screen displayed on the conference terminal 10 will be described with reference to FIG. 2.

Figure 2 illustrates a specific example of a conference screen. As shown in Figure 2, the conference screen includes a purpose display area 41, an elapsed time display area 42, a progress status display area 43, a comment status display area 44, an advice display area 45, a comment type selection area 46, and a reaction type selection area 47.

The purpose display area 41 is an area that displays the purpose of the meeting. The purpose of the meeting is included in the meeting setting data that is set, for example, by the organizer before the start of the meeting. The elapsed time display area 42 is an area that displays the time that has elapsed since the start of the meeting. The progress status display area 43 is an area that displays the items that should currently be on the agenda of the meeting based on the time that has elapsed since the start of the meeting and the meeting progress schedule (timetable). The meeting progress schedule (timetable) is included in the meeting setting data.

The speech status display area 44 is an area that displays the total speech time for each participant and the speech time of the current speech. The advice display area 45 is an area that displays advice determined by the conference management server 20.

The comment type selection area 46 is an area that includes multiple comment type selection displays. FIG. 2 shows an example of multiple comment type selection displays, each corresponding to a comment type selection display, such as report, contact, consultation, challenge, support, objection, question, impression, and others. When making a comment, a participant selects a comment type selection display corresponding to the comment type from the comment type selection area 46. The conference terminal 10 transmits the comment type to the conference management server 20 based on the participant's selection of the comment type selection display.

The reaction type selection area 47 is an area that includes a plurality of reaction type selection displays. FIG. 2 shows examples of a plurality of reaction type selection displays, each of which corresponds to agree, agree, disagree, nice follow-up, nice challenge, unique idea, going off topic, talking too much, and other. A participant selects a reaction type selection display from the reaction type selection area 47 that corresponds to his or her own reaction to the remarks of other participants. The conference terminal 10 transmits the reaction type to the conference management server 20 based on the participant's selection of the reaction type selection display.

The same conference screen may be displayed on the conference terminals 10 of all participants, or different conference screens may be displayed depending on the conference terminal 10. For example, a conference screen including the speech status display area 44 may be displayed on the conference terminal 10 of a participant who is also the organizer of the conference, and a conference screen not including the speech status display area 44 may be displayed on the conference terminals 10 of other participants. Furthermore, the contents of the advice may be displayed in the advice display area 45 only on the conference terminal 10 of the participant who is the target of the advice, or the contents of the advice may be displayed in the advice display area 45 only on the conference terminal 10 of the participant who is also the organizer of the conference.

The conference terminal 10 may also have an imaging unit that acquires video data of each participant. In this case, each conference terminal 10 may transmit the video data of the participants to the conference management server 20, and the conference management server 20 may generate a conference screen including the video data of each participant. With this configuration, each participant can hold a remote conference using video in addition to audio. It is also possible to detect the body movements of each participant from the video data of each participant.

(Conference management server 20)
The conference management server 20 is a conference management device that manages a remote conference using a plurality of conference terminals 10. The conference management server 20 receives voice data from each conference terminal 10 and transmits the voice data to each conference terminal 10. The conference management server 20 also receives speech and behavior data of participants from each conference terminal 10, and arranges advice for increasing the psychological safety felt by each participant in the conference on the conference screen based on the speech and behavior data. A state of high psychological safety is, for example, a state in which each participant has a strong awareness that the participant will not be disadvantaged or feel uncomfortable because of what the participant says. If participants have psychological safety, they will actively share information and ideas, and it is expected that the results of the conference will be improved. Below, the detailed configuration and operation of such a conference management server 20 will be described in detail one by one.

<Configuration of conference management server 20>
3 is an explanatory diagram showing the configuration of the conference management server 20 according to an embodiment of the present invention. As shown in FIG. 3, the conference management server 20 according to an embodiment of the present invention has a communication unit 220, a setting unit 224, an advice unit 228, a conference screen control unit 232, a psychological safety calculation unit 236, and a storage unit 240.

(Communication unit 220)
The communication unit 220 communicates various data with each conference terminal 10. For example, the communication unit 220 functions as a voice data communication unit that transmits and receives voice data of participants to and from each conference terminal 10, a speech and behavior data acquisition unit that receives speech and behavior data of participants from each conference terminal 10, a setting data communication unit that transmits and receives conference setting data to and from each conference terminal 10, and a conference screen transmission unit that transmits a conference screen to each conference terminal 10.

(Setting unit 224)
The setting unit 224 sets conference setting data for supporting the progress of the conference before the conference starts. The conference setting data includes, for example, ten types of data shown in FIG.

Figure 4 is an explanatory diagram showing an example of data included in the meeting setting data. As shown in Figure 4, the types of meeting setting data include #1 purpose, #2 schedule, #3 number of participants, #4 psychological safety before the meeting, #5 decision-making method, #6 praise for a nice challenge, #7 recommendation of physical movement, #8 upper limit of speaking time, #9 standard for total speaking volume per participant, and #10 reaction level when p2 is 0.5 or less.

#1 Objective is data describing the agenda and goals of the meeting. #2 Progress chart is data describing the progress and time schedule of the meeting. #3 Number of people is data indicating the number of participants in the meeting, and is represented by parameter p1 as a number of people parameter. #4 Psychological safety before the meeting is an example of a pre-start parameter that indicates how multiple participants feel about the meeting before it starts. More specifically, #4 Psychological safety before the meeting is data indicating the psychological safety each participant feels about the meeting before it starts, and is represented by parameter p2.

Decision-making method #5 is data that describes the method for deciding the outcome of a meeting. In decision-making method #5, parameter p3 is defined, which indicates the number of people required to make a decision, whether the leader decides the outcome, the majority vote, or unanimously.

Data #6 to #10 are the code of conduct expected of participants. #6, "praise for a nice challenge," is data describing the percentage of other participants who should be actively praised when the comments of other participants are full of challenging elements, and is represented by parameter p4.

The recommended body movement in #7 is data indicating the magnitude of body movement (reaction body movement level) such as nodding that is recommended to a participant when they agree with or consent to what another participant has said, and is represented by parameter p5.

#8 The upper limit of speech time is data that specifies the upper limit of the time for a single speech other than reports and communications, and is expressed by parameter p6, which indicates the upper limit of speech time excluding reports and communications, and parameter p7, which indicates the percentage of participants who indicate that their speech is long, in order to determine whether to suppress the speech.

The standard for the total amount of speech per participant in #9 is data describing the equality of speech required among participants, and is expressed by parameter p8, which indicates the ratio of the total amount of speech (time) per participant to the average amount of speech that should be ensured as a minimum.

The reaction level when p2 in #10 is 0.5 or less is data indicating the reaction level of each participant recommended when a team with low psychological safety holds a meeting, and is expressed by parameter p9. The reaction level is expressed as a value between 0 and 1 based on the frequency of occurrence of some comment types ("support," "dissent," "question," "impression") and some reaction types (reactions excluding "going off topic" and "long comment") selected by the participants on the meeting screen with reference to Figure 2, and the reaction body movement level.

Of such conference setting data, data #1 to #3 are input by the participants to the conference terminal 10 before the start of the conference, and the conference terminal 10 transmits data #1 to #3 to the conference management server 20, and the setting unit 224 sets the data. Furthermore, if a conference has been held with the same participants before, the setting unit 224 sets the psychological safety calculated for a conference held with the same participants and stored in the storage unit 240 as parameter p2 indicating psychological safety before the conference #4.

On the other hand, if a meeting has not been held with the same participants before, the memory unit 240 conducts a questionnaire survey of the participants and calculates parameter p2 indicating psychological safety before the meeting #4 based on the responses to the questionnaire.

For example, the questionnaire survey may include questions such as, "Does this team have a relationship where everyone can speak equally, without a particular person doing the talking unilaterally?" (equality of speech), "Does this team have a relationship where people help each other, accept values different from their own, and can talk constructively?" (acceptance of others), "Do you think that in this team, everyone is often in agreement with the conclusion of discussions?" (conclusion satisfaction), "Does this team have a relationship where people feel free to express their feelings, such as by expressing their opinions or nodding, when they can empathize with others?" (body movement), and "Do members of this team understand how their words affect others, and can read what they really want to convey from their facial expressions and behavior?" (social sensitivity).

Furthermore, the setting unit 224 sets parameters p3 to p9 indicating #5 to #10 based on the parameters p1 and p2. As described below, when each conference is held, the parameter group (parameters p1 to p9) applied to the conference is associated with the psychological safety after the conference and stored in the storage unit 240. Furthermore, the learning unit 244 learns the relationship between the parameter groups in multiple conferences and the psychological safety after the conference, and the storage unit 240 stores data indicating the relationship obtained by learning. Using this relationship, the setting unit 224 identifies what parameters p3 to p9 should be set in addition to the already set parameters p1 and p2 to increase the psychological safety after the conference compared to the psychological safety before the conference (parameter p2), and sets such parameters p3 to p9.

The setting unit 224 may transmit the set parameter group to the conference terminal 10 via the communication unit 220, and the conference terminal 10 may display a confirmation screen for the parameter group. When a participant makes a change to the parameter group by operating the confirmation screen, the conference terminal 10 may transmit information indicating the change to the conference management server 20, and the setting unit 224 may update the parameter group.

Furthermore, the setting unit 224 sets one or more advice rules and outputs the set advice rules to the advice unit 228. Each advice rule includes a condition including a threshold parameter, and advice content when the condition is satisfied. For example, the above-mentioned parameters p3 to p9 may be used as threshold parameters. In this case, setting parameters p3 to p9 can be said to be setting an advice rule. Below, a specific example of an advice rule is described with reference to FIG. 5.

Figure 5 is an explanatory diagram showing specific examples of advice rules. Figure 5 shows seven types of advice rules, #1 to #7.

The advice rule #1 includes the condition that x minutes have elapsed since the start of the meeting, and advice to encourage a conclusion. x is a value according to the schedule set as the progress chart of #2 in the meeting setting data.

Advice rule #2 includes a condition that the number of "convinced" responses after advice based on advice rule #1 is given is less than parameter p3, and advice content that encourages continuing the discussion or leaving the decision to the leader.

The advice rule for #3 includes the condition that the number of "nice challenge" responses (praising the challenge) to a comment made by a certain participant exceeds parameter p4, and the advice content is to praise the speaker's actions.

The advice rule #4 includes the condition that a certain participant A has responded in favor and the reaction body movement level is less than parameter p5, and the advice content is to encourage the participant A to express approval in a more exaggerated manner.

The advice rule #5 includes the condition that the speech duration of a certain participant A exceeds parameter p6 and the number of other participants who respond that the speech is long exceeds parameter p7, and includes advice recommending that the participant A limit the amount of speech he or she makes.

The advice rule #6 includes the condition that the total amount of speech time of a certain participant A is less than parameter p8, and advice content that encourages the participant A to increase the amount of speech.

The advice rule for #7 includes the condition that the parameter p2 is less than 0.5 and the reaction body movement level of other participants after a participant speaks is less than the parameter p9, and the advice content is to encourage each participant to increase their reaction.

(Advice Unit 228)
The advice unit 228 determines advice data including advice to at least any of the participants according to the speech and behavior data received from each conference terminal 10 by the communication unit 220 and the advice rule set by the setting unit 224. The advice unit 228 outputs the determined advice data to the conference screen control unit 232.

For example, if the total amount of speaking time of participant B is less than parameter p8 based on the speech and behavior data received from each conference terminal 10 by the communication unit 220, the advice unit 228 determines advice data including advice such as "It seems that B is not making many comments. How about having B speak more?" according to advice rule #6 shown in FIG. 5.

(Conference Screen Control Unit 232)
The conference screen control unit 232 generates a conference screen based on the speech and behavior data received from each conference terminal 10 by the communication unit 220, the advice data input from the advice unit 228, and the like. The configuration of the conference screen is as described with reference to Fig. 2. The conference screen control unit 232 inserts the contents of advice into the advice display area 45 based on the advice data input from the advice unit 228.

(Psychological safety calculation unit 236)
The psychological safety calculation unit 236 is an example of a detection unit, and detects the degree of psychological safety that participants had in the conference after the end of the conference by analyzing the speech and behavior data received from each conference terminal 10 by the communication unit 220. For example, the psychological safety calculation unit 236 detects psychological safety based on at least one of the following: evenness of remarks among multiple participants (index A), receptivity of each participant to the remarks of others (index B), satisfaction of multiple participants with the conclusion of the conference (index C), or body movements of multiple participants (index D). Each index is normalized within the range of 0 to 1, and the psychological safety calculation unit 236 may calculate the average value or weighted average value of each index as psychological safety. Each index will be supplemented below.

Index A is calculated based on the standard deviation of speaking time among participants. Index A is calculated to be closer to 1 if speaking time is uniform, and closer to 0 if speaking is concentrated in one person.

Index B is calculated based on the type of statements and reactions that are accepting of others. Index B is calculated so that the more positive statements and reactions there are, the closer it is to 1, and the fewer positive statements and reactions there are, the closer it is to 0.

Index C is calculated based on the participants' reactions of satisfaction with the conclusion. Index C is calculated so that the higher the satisfaction, the closer it is to 1, and the lower the satisfaction, the closer it is to 0. Note that the psychological safety calculation unit 236 may estimate the emotions of each participant from text data indicating the content of each participant's comments, and calculate index C based on the estimated emotions.

Index D is calculated based on the amount of body movement of the participant. The more body movement there is, the closer Index D is to 1, and the less body movement there is, the closer Index D is to 0.

(Memory unit 240)
The storage unit 240 stores various data used in the operation of the conference management server 20. For example, the storage unit 240 stores the conference setting data or the parameters p1 to p9 applied as advice rules and the psychological safety calculated by the psychological safety calculation unit 236 in association with each other.

Figure 6 is an explanatory diagram showing the storage structure of parameters and psychological safety by the storage unit 240. In Figure 6, k is the ID of each conference. The parameter group applied to each conference is p1 to p9, and the psychological safety calculated by the psychological safety calculation unit 236 after the conference ends is y. In this way, the storage unit 240 stores the parameters p1 to p9 and psychological safety y for multiple conferences in association with each other.

(Learning unit 244)
The learning unit 244 learns the relationship between the parameters p1 to p9 and psychological safety y for multiple conferences stored in the storage unit 240. For example, the learning unit 244 can learn the relationship between the parameters p1 to p9 and psychological safety y by a method such as statistical learning or machine learning, or by regression analysis. Below, an example will be described in which the learning unit 244 learns the relationship between the parameters p1 to p9 and psychological safety y by regression analysis.

First, psychological safety y is expressed by the following linear regression model.

The error between the psychological safety calculated by the linear regression model and the actual psychological safety is expressed by the following formula (2): In formula (2), p _{i k} represents the parameter p _i applied to the conference with conference ID k, and y _k represents the psychological safety calculated for the conference with conference ID k.

Then, the learning unit 244 can calculate β _i (i=0, 1, ... 9) as data indicating the relationship between the parameters p1 to p9 and psychological safety y by solving σE/σβ _i = 0 (i=0, 1, ... 9) by the least squares method. The storage unit 240 stores the calculated or updated β _i (i=0, 1, ... 9) in the learning unit 244. This enables the setting unit 224 to set the parameters p3 to p9 to be applied to a new conference using the β _i (i=0, 1, ... 9).

<Operation of the conference management server 20>
The configuration of the conference management server 20 according to an embodiment of the present invention has been described above. Next, the operation of the conference management server 20 according to an embodiment of the present invention will be summarized with reference to Figs.

(Before the meeting begins)
Fig. 7 is a flowchart showing the operation before the start of a conference. As shown in Fig. 7, if the scheduled conference has been held with the same participants before (S304/Yes), the participants input conference setting data #1 to #3 to the conference terminal 10, and the conference management server 20 receives the conference setting data #1 to #3 from the conference terminal 10 (S308). In addition, the setting unit 224 reads out the psychological safety calculated for the conference after a conference held with the same participants in the past from the storage unit 240 (S312).

On the other hand, if the scheduled conference has not been held with the same participants before (S304/No), the conference management server 20 sends a questionnaire regarding psychological safety to the conference terminal 10 (S316). The participants then input the conference setting data #1-#3 and the questionnaire responses to the conference terminal 10, and the conference management server 20 receives the conference setting data #1-#3 and the questionnaire responses from the conference terminal 10 (S320). The setting unit 224 calculates the psychological safety of the conference before the conference starts based on the received questionnaire responses (S324).

Then, the setting unit 224 calculates parameters p3 to p9 based on parameter p1 which is conference setting data #3, parameter p2 obtained as psychological safety in S312 or S324, and the above-mentioned β _i (i=0, 1, . . . , 9) (S328).

Then, the communication unit 220 transmits each parameter to the conference terminal 10 (S332). Then, if the parameters are changed in the conference terminal 10 (S336), the communication unit 220 receives information indicating the changes from the conference terminal 10, and the setting unit 224 updates the parameters in accordance with the information (S340). As a result, an advice rule that includes each parameter as a condition is set.

(Operations during and after the meeting)
8 is a flow chart showing operations during and after the conference. As shown in FIG 8, when the conference starts, the communication unit 220 receives voice data and speech and behavior data from each conference terminal 10 (S352).

Then, the advice unit 228 determines whether the conditions of any advice rule are satisfied based on the speech and behavior data received from the communication unit 220 (S356). If the conditions of any advice rule are satisfied (S356/Yes), the advice unit 228 generates advice data according to the advice rule whose conditions are satisfied, and outputs the advice data to the conference screen control unit 232 (S360). The conference screen control unit 232 then generates a conference screen including an advice display based on the advice data, and the communication unit 220 transmits the conference screen to each conference terminal 10 (S364).

On the other hand, if none of the advice rules are satisfied (S356/No), the conference screen control unit 232 generates a conference screen that does not include an advice display, and the communication unit 220 transmits the conference screen to each conference terminal 10 (S368). The processes of S352 to S368 are repeated until the conference ends (S372).

When the conference ends (S372/Yes), the psychological safety calculation unit 236 analyzes the speech and behavior data received from each conference terminal 10 by the communication unit 220 during the conference to calculate the degree of psychological safety that participants had in the conference after the conference ended (S376). The storage unit 240 then associates the conference setting data or parameters p1 to p9 applied as advice rules with the psychological safety calculated by the psychological safety calculation unit 236 and stores them (S380).

Furthermore, the learning unit 244 learns the relationship between the parameters p1 to p9 and psychological safety y for multiple conferences stored in the storage unit 240, and stores data indicating the relationship in the storage unit 240 (S384). The data indicating the relationship may be, for example, β _i (i=0, 1, ... 9) included in the above-mentioned formula (1).

<Action and effect>
According to the embodiment of the present invention described above, various operational effects can be obtained. For example, according to the embodiment of the present invention, the setting unit 224 uses the relationship calculated in advance between the parameters p1 to p9 and psychological safety y to identify what parameters p3 to p9 should be set to increase psychological safety after the conference compared to psychological safety before the conference (parameter p2), and sets an advice rule that includes such parameters p3 to p9 as conditions. Therefore, it is expected that advice to increase psychological safety will be given during the conference. In other words, it is expected that the way each participant feels about the conference will be improved, and more specifically, that psychological safety will be increased.

Furthermore, according to one embodiment of the present invention, the psychological safety calculation unit 236 detects psychological safety based on at least one of the following: evenness of speech among multiple participants (index A), each participant's receptivity to other participants' speech (index B), the multiple participants' sense of satisfaction with the conclusion of the meeting (index C), or the body movements of multiple participants (index D). Therefore, it is possible to obtain valid psychological safety.

Furthermore, according to one embodiment of the present invention, the conference screen includes a statement type selection area 46 and a reaction type selection area 47 as shown in FIG. 2. Therefore, conference participants can explicitly select a statement type, a reaction type, and the like on the conference screen. This makes it possible to determine whether the conditions of the advice rule are met based on highly reliable statement types and reaction types, thereby enabling more appropriate advice to be provided.

<Modification>
An embodiment of the present invention has been described above. In the following, some modified examples of the above-described embodiment will be described. Note that each modified example described below may be applied alone to the above-described embodiment, or may be applied in combination to the above-described embodiment. Also, each modified example may be applied in place of the configuration of the above-described embodiment, or may be applied in addition to the configuration of the above-described embodiment.

For example, while the above describes an example of setting advice rules and detecting psychological safety for each conference, the conference management server 20 may also set advice rules and detect psychological safety in the middle of a conference. In this case, it is possible to dynamically change advice rules during the conference.

In addition, although the above embodiment has been described assuming that the participants are in physically distributed environments, the participants may be in the same space. Even when the participants are in the same space, it is possible to obtain the same effect as the above-described embodiment.

In addition, although data #1 to #10 are described above as conference setting data, the types of conference setting data are not limited to 10 types. Similarly, although rules #1 to #7 are described above as advice rules, the types of advice rules are not limited to 7 types.

In addition, although an example has been described above in which the psychological safety calculation unit 236 calculates psychological safety based on four indicators, the psychological safety calculation unit 236 may also calculate psychological safety based on other indicators.

In addition, in the above example, the questionnaire survey for calculating psychological safety before a meeting was described as being based on five perspectives: equality of speech, acceptability of others, satisfaction with the conclusion, body movement, and social sensitivity, but questionnaire surveys based on other perspectives may also be conducted.

<Hardware Configuration>
The above describes the embodiments of the present invention. The information processing, such as the determination of advice data and the detection of psychological safety, described above, is realized by cooperation between software and the hardware of the conference management server 20, which will be described below.

Figure 9 is a block diagram showing the hardware configuration of the conference management server 20. The conference management server 20 includes a CPU (Central Processing Unit) 201, a ROM (Read Only Memory) 202, a RAM (Random Access Memory) 203, and a host bus 204. The conference management server 20 also includes a bridge 205, an external bus 206, an interface 207, an input device 208, a display device 209, an audio output device 210, a storage device (HDD) 211, a drive 212, and a network interface 215.

The CPU 201 functions as an arithmetic processing device and control device, and controls the overall operation of the conference management server 20 in accordance with various programs. The CPU 201 may also be a microprocessor. The ROM 202 stores programs and arithmetic parameters used by the CPU 201. The RAM 203 temporarily stores programs used in the execution of the CPU 201 and parameters that change appropriately during the execution. These are interconnected by a host bus 204 consisting of a CPU bus and the like. The functions of the setting unit 224, advice unit 228, conference screen control unit 232, psychological safety calculation unit 236, learning unit 244, and the like shown in FIG. 3 can be realized by the cooperation of the CPU 201, ROM 202, and RAM 203 with software.

The host bus 204 is connected to an external bus 206, such as a PCI (Peripheral Component Interconnect/Interface) bus, via a bridge 205. Note that the host bus 204, bridge 205, and external bus 206 do not necessarily need to be configured separately, and these functions may be implemented on a single bus.

The input device 208 is composed of input means for the user to input information, such as a mouse, keyboard, touch panel, button, microphone, sensor, switch, and lever, and an input control circuit that generates an input signal based on the user's input and outputs it to the CPU 201. A user of the conference management server 20 can input various data and instruct processing operations to the conference management server 20 by operating the input device 208.

The display device 209 includes display devices such as a liquid crystal display (LCD) device, a projector device, an OLED (Organic Light Emitting Diode) device, and a lamp. The audio output device 210 includes audio output devices such as a speaker and headphones.

The storage device 211 is a data storage device configured as an example of a storage unit of the conference management server 20 according to this embodiment. The storage device 211 may include a storage medium, a recording device that records data on the storage medium, a reading device that reads data from the storage medium, and a deleting device that deletes data recorded on the storage medium. The storage device 211 is configured, for example, by a HDD (Hard Disk Drive) or an SSD (Solid Storage Drive), or a memory having equivalent functions. This storage device 211 drives the storage and stores the programs executed by the CPU 201 and various data.

The drive 212 is a reader/writer for storage media, and is built into the conference management server 20 or attached externally. The drive 212 reads information recorded on a removable storage medium 24, such as an attached magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, and outputs the information to the RAM 203 or the storage device 211. The drive 212 can also write information to the removable storage medium 24.

The network interface 215 is, for example, a communication interface configured with a communication device for connecting to the network 12. The network interface 215 may be a wireless LAN (Local Area Network) compatible communication device or a wired communication device that performs wired communication.

The hardware configuration of the conference management server 20 described above can also be applied to the conference terminal 10.

<Additional Information>
Although the preferred embodiment of the present invention has been described in detail above with reference to the accompanying drawings, the present invention is not limited to such an example. It is clear that a person having ordinary knowledge in the technical field to which the present invention pertains can conceive of various modified or altered examples within the scope of the technical ideas described in the claims, and it is understood that these also naturally belong to the technical scope of the present invention.

For example, each step in the processing of the conference management server 20 in this specification does not necessarily have to be processed chronologically in the order described in the sequence diagram or flowchart. For example, each step in the processing of the conference management server 20 may be processed in an order different from the order described in the flowchart, or may be processed in parallel.

It is also possible to create a computer program for causing hardware such as the CPU, ROM, and RAM built into the conference terminal 10 and the conference management server 20 to perform functions equivalent to those of the above-mentioned components of the conference terminal 10 and the conference management server 20. A storage medium on which the computer program is stored is also provided.

10 Conference terminal 20 Conference management server 220 Communication unit 224 Setting unit 228 Advice unit 232 Conference screen control unit 236 Psychological safety calculation unit 240 Storage unit 244 Learning unit

Claims (8)

A speech and behavior data acquisition unit that acquires speech and behavior data of a plurality of participants participating in a conference;
an advice unit that determines advice data including advice to at least any of the participants according to the speech and behavior data and one or more advice rules;
a detection unit that detects how the plurality of participants felt about the conference by analyzing the speech and behavior data;
a learning unit that learns a relationship between the advice rule and a result of detection by the detection unit in one or more conferences including the conference;
a setting unit that sets one or more new advice rules based on the relationship obtained by the learning;
Equipped with
Each of the one or more advice rules includes a condition including a threshold parameter and advice content when the condition is satisfied;
the learning unit learns a relationship between a parameter group including the threshold parameter, a number-of-participants parameter indicating the number of participants in the conference, and a pre-start parameter indicating how the plurality of participants feel about the conference before the start of the conference, and a result of the detection by the detection unit;
The setting unit applies the number of people parameter and the pre-start parameter for a new conference to the relationship, and sets new threshold parameters for each advice rule so that the detection result by the detection unit in the relationship after application is improved compared to the pre-start parameters . The conference management device according to claim 1, wherein the detection unit detects the psychological safety of the multiple participants in the conference by detecting how the multiple participants felt about the conference. The conference management device according to claim 2, wherein the detection unit detects the psychological safety based on at least one of the following: uniformity of speech among the multiple participants, each participant's receptivity to other participants' speech, the multiple participants' sense of satisfaction with the conclusion of the conference, or the body movements of the multiple participants. The conference management device according to any one of claims 1 to 3, wherein the speech and behavior data includes data indicating a type of a statement made by a participant and data indicating a type of a reaction to a statement made by another participant. The conference management device includes:
a conference screen control unit that generates a conference screen including a comment type selection display for selecting a comment type and a reaction type selection display for selecting a reaction type;
a communication unit that transmits the conference screen to a conference terminal used by the plurality of participants;
Further equipped with
The conference management device according to claim 4 , wherein the speech and behavior data acquisition unit acquires speech and behavior data indicating a comment type selected on the conference screen, and speech and behavior data indicating a reaction type selected on the conference screen. Acquiring speech and behavior data of multiple participants participating in a conference;
determining advice data including advice to at least any of the participants according to the behavior data and one or more advice rules;
analyzing the behavioral data to detect how the plurality of participants perceived the conference;
learning a relationship between the advisory rules in one or more conferences including the conference and a result of detecting how the plurality of participants perceived the conference;
setting one or more new advice rules based on the relationships obtained by the learning;
Including,
Each of the one or more advice rules includes a condition including a threshold parameter and advice content when the condition is satisfied;
The learning includes learning a relationship between a group of parameters including the threshold parameter, a number of participants parameter indicating the number of participants in the conference, and a pre-start parameter indicating how the plurality of participants feel about the conference before the start of the conference, and a result of the detection;
A computer-implemented method in which the setting applies the number of people parameters and the pre-start parameters for a new meeting to the relationship, and sets new threshold parameters for each advisory rule such that the detection result in the relationship after application is improved over the pre-start parameters . Computer,
A speech and behavior data acquisition unit that acquires speech and behavior data of a plurality of participants participating in a conference;
an advice unit that determines advice data including advice to at least any of the participants according to the speech and behavior data and one or more advice rules;
a detection unit that detects how the plurality of participants felt about the conference by analyzing the speech and behavior data;
a learning unit that learns a relationship between the advice rule and a result of detection by the detection unit in one or more conferences including the conference;
a setting unit that sets one or more new advice rules based on the relationship obtained by the learning;
Function as a
Each of the one or more advice rules includes a condition including a threshold parameter and advice content when the condition is satisfied;
the learning unit learns a relationship between a parameter group including the threshold parameter, a number-of-participants parameter indicating the number of participants in the conference, and a pre-start parameter indicating how the plurality of participants feel about the conference before the start of the conference, and a result of the detection by the detection unit;
The setting unit applies the number of people parameter and the pre-start parameter for a new meeting to the relationship, and sets new threshold parameters for each advice rule so that the detection result by the detection unit in the relationship after application is improved compared to the pre-start parameters . A conference management system including one or more conference terminals used by a plurality of participants participating in a conference and a conference management device,
The conference management device includes:
A speech and behavior data acquisition unit that acquires speech and behavior data of a plurality of participants from the one or more conference terminals;
an advice unit that determines advice data including advice to at least any of the participants according to the speech and behavior data and one or more advice rules;
a detection unit that detects how the plurality of participants felt about the conference by analyzing the speech and behavior data;
a learning unit that learns a relationship between the advice rule and a result of detection by the detection unit in one or more conferences including the conference;
a setting unit that sets one or more new advice rules based on the relationship obtained by the learning;
Equipped with
Each of the one or more advice rules includes a condition including a threshold parameter and advice content when the condition is satisfied;
the learning unit learns a relationship between a parameter group including the threshold parameter, a number-of-participants parameter indicating the number of participants in the conference, and a pre-start parameter indicating how the plurality of participants feel about the conference before the start of the conference, and a result of the detection by the detection unit;
The setting unit applies the number of people parameter and the pre-start parameter for a new conference to the relationship, and sets new threshold parameters for each advice rule so that the detection result by the detection unit in the relationship after application is improved compared to the pre-start parameters .

Images