Proposal device, proposal method, and proposal program

Abstract

A proposal device (100) comprises: a model curve generation unit (152) that generates a model curve corresponding to the relationship between the ambiguity and the elapsed time from the start of a first conference performed in the past; an ambiguity calculation unit (153) that acquires text information by a participant of a second conference and calculates the ambiguity of the text information; and a proposal unit (154) that executes a proposal for the participant of the second conference so that the ambiguity of the text information approaches the ambiguity of the model curve at the timing of acquisition of the text information.

Description

Proposal device, proposal method, and proposal program

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

[0002] Ambiguous expressions can sometimes lead to misunderstandings, so in organizational meetings where the purpose is to make decisions, it is necessary to avoid ambiguous expressions that could lead to misunderstandings.

[0003] On the other hand, depending on the purpose and situation of the meeting, ambiguous expressions can be effective. For example, at the start of a meeting, ambiguous expressions with a variety of nuances may lead to the generation of good ideas.

[0004] For this reason, in the early stages of a meeting, it is better to speak freely and without restrictions than to avoid ambiguous language.

[0005] Patent Document 1 discloses a technique for periodically calculating risks involved in a meeting during or after communication.

[0006] International Publication No. 2024 / 089858

[0007] However, the above-mentioned conventional technology has a problem in that it is not possible to propose a speech policy that is appropriate for the situation of the conference.

[0008] The present invention has been made in view of the above, and has an object to provide a proposal device, a proposal method, and a proposal program that can propose a speech policy according to the situation of a conference.

[0009] In order to solve the above-mentioned problems and achieve the objective, the proposal device includes a model curve generation unit that generates a model curve corresponding to the relationship between the elapsed time from the start of a first conference that was held in the past and ambiguity, an ambiguity calculation unit that acquires text information from participants of a second conference and calculates the ambiguity of the text information, and a proposal unit that makes proposals to participants of the second conference so that the ambiguity of the text information approaches the ambiguity of the model curve at the time the text information is acquired.

[0010] According to the present invention, it is possible to propose a speech policy that is appropriate for the situation of the conference.

[0011] FIG. 1 is a diagram illustrating the prerequisites and assumptions in office communication. FIG. 2 is a diagram illustrating the variables in equation (1). FIG. 3 is a diagram (1) illustrating the basic processing of the proposed device. FIG. 4 is a diagram (2) illustrating the basic processing of the proposed device. FIG. 5 is a diagram (3) illustrating the basic processing of the proposed device. FIG. 6 is a diagram (4) illustrating the basic processing of the proposed device. FIG. 7 is a functional block diagram showing the configuration of the proposed device. FIG. 8 is a diagram illustrating an example of the data structure of a conference history table. FIG. 9 is a diagram illustrating an example of the data structure of a personal ambiguity table. FIG. 10 is a flowchart showing the processing procedure of the proposed device. FIG. 11 is a diagram illustrating an example of a computer that executes the proposed program.

[0012] Hereinafter, embodiments of the proposed device, proposed method, and proposed program disclosed in the present application will be described in detail with reference to the accompanying drawings. However, the present invention is not limited to these embodiments.

[0013] (Embodiment) (Premises and Assumptions in Office Communication) Before describing the proposed device in the embodiment, the prerequisites and assumptions in office communication will be described. Office communication is a meeting, etc. In principle, the goal of a meeting is to reach an agreement on a decision (a specific conclusion). In a meeting, it is ultimately required to converge on a very specific and unambiguous conclusion. On the other hand, abstract discussions of concepts, etc. are often important in the stage prior to agreeing on a specific conclusion.

[0014] FIG. 1 is a diagram for explaining the prerequisites and assumptions in office communication. Graph G1 in FIG. 1 is a graph showing the relationship between the elapsed time from the start of a meeting and ambiguity. The vertical axis of graph G1 corresponds to ambiguity. The horizontal axis of graph G1 corresponds to the elapsed time from the start of the meeting. Line L1 shows the relationship between the elapsed time and ambiguity.

[0015] The ambiguity is a score calculated based on the speech information of the meeting participants, and is calculated based on the number of ambiguous words contained in the speech information, the context, and the relationships between the participants. The greater the ambiguity, the more abstract the content of the speech, and the smaller the ambiguity, the more specific the content of the speech. The ambiguity may be calculated using any existing technology.

[0016] For example, the phase of line L1 changes depending on the elapsed time. In this embodiment, the phases are: beginning ph1, early stage ph2, middle stage ph3, final stage ph4, and conclusion ph5. The topic of the meeting is "deciding on a new business field." In the intention stage of the phase, the rate of change in ambiguity with respect to the elapsed time becomes large.

[0017] The opening phase, ph1, is the phase in which the background to the topic is explained from various angles, including specific issues and abstract policies. For example, the opening phase explains the current situation of the company and the need for a new business. Since the opening phase involves a mixture of specific and abstract discussions, the ideal ambiguity is "neutral."

[0018] The early stage, PH2, is the phase where discussions are held on the direction of the discussion and the goals to be achieved. For example, in the early stage, PH2, the conditions that must be met for the goal, such as the target business scale, are organized (detailing the initial explanation). In the early stage, PH2, it is desirable to have specific discussions, and the ideal ambiguity is "low ambiguity."

[0019] The middle phase, Ph3, is a phase in which the direction is determined through broad-based discussions. For example, in this phase, candidates for consideration are selected based on the future prospects of each major field, global trends, etc. In this phase, abstract discussions are desirable, and the ideal level of ambiguity is "high abstraction."

[0020] The final phase, Ph4, is the phase in which the direction taken in the middle phase, Ph3, is broken down into concrete terms. For example, in the final phase, Ph4, the broad fields are narrowed down to specific fields to advance into. In the final phase, Ph4, it is desirable to have specific discussions, and the ideal level of ambiguity is "low abstraction."

[0021] Conclusion ph5 is a phase for achieving a clear agreement. For example, there should be no ambiguity in conclusion ph5. The ideal ambiguity of conclusion ph5 is "minimal ambiguity."

[0022] The above explains the prerequisites and assumptions for office communication.

[0023] (Processing of Proposal Device) Next, an example of processing of the proposal device according to this embodiment will be described. In the following description, the proposal device according to this embodiment will be referred to as "proposal device 100." In this embodiment, multiple participants participating in a conference are referred to as participant A, participant B, and participant C. Also, it is assumed that such a conference has a moderator who leads the discussion.

[0024] The proposal device 100 stores in a storage unit the relationship between the elapsed time from the start time and the ambiguity of the speech information of the participants of good meetings that have been held in the past. The proposal device 100 generates a model curve based on this information. In the following description, the elapsed time from the start time of a meeting will be simply referred to as the elapsed time. The model curve shows the relationship between the elapsed time and the ambiguity. Note that the speech information is an example of text information.

[0025] For example, the proposing device 100 generates a model curve using equation (1). Fig. 2 is a diagram for explaining the variables in equation (1). t in equation (1) ｘ is the elapsed time for which ambiguity is to be calculated. ｘ ) is the elapsed time t ｘ is the ambiguity of the model curve at t １ , t ２ is the elapsed time over which the ambiguity is calculated in a good meeting. １ ) is the elapsed time t １ is the ambiguity of a good meeting in ２ ) is the elapsed time t ２ The ambiguity of a good meeting in １ is t １ From t ｘ The time until ２ is t ｘ From t ２ It is time until.

[0026]

[0027] Furthermore, the proposal device 100 acquires speech information of multiple participants using a microphone or the like, and calculates the ambiguity of the participants each time it acquires speech information.

[0028] The proposal device 100 makes suggestions to the participants based on the model curve and the ambiguity of the participants so that the ambiguity of the participants approaches the model curve. For example, if the ambiguity of the speech information by the participants at a certain elapsed time is greater than the ambiguity of the model curve at a certain elapsed time, the proposal device 100 makes suggestions to encourage the participants to speak more specifically. On the other hand, if the ambiguity of the speech information by the participants at a certain elapsed time is less than the ambiguity of the model curve at a certain elapsed time, the proposal device 100 makes suggestions to encourage the participants to speak more abstractly.

[0029] For example, when the proposal device 100 makes a proposal to the participants, the proposal text is displayed on the display unit of the proposal device 100 .

[0030] 3 to 6 are diagrams for explaining the basic processing of the proposed device. First, we will explain Fig. 3. The vertical axis of graph G2 in Fig. 3 corresponds to ambiguity, and the horizontal axis corresponds to elapsed time. The line on graph G2 is model curve L2.

[0031] The circle 10A on the graph G2 indicates the ambiguity of participant A at the corresponding elapsed time. The circle 10B indicates the ambiguity of participant B at the corresponding elapsed time. The circle 10C indicates the ambiguity of participant C at the corresponding elapsed time. The circle 10Z indicates the current elapsed time of the conference. The proposed device 100 moves the circle 10Z on the model curve L2 in accordance with the elapsed time.

[0032] Elapsed time t １－１ In the model curve L2, the ambiguity of participants A and B is higher than the ambiguity of the model curve L2. For example, the proposal device 100 displays a suggestion to participant A, "If you want to understand the problem, please wait for A to speak." The proposal device 100 displays a suggestion to participant B, "Let's dig a little deeper into the ambiguity uttered by B."

[0033] On the other hand, the elapsed time t １－１ In this case, the ambiguity of participant C is lower than the ambiguity of model curve L2. For example, the proposing device 100 displays a suggestion to participant C, "Why not try generalizing what C said?"

[0034] Elapsed time t １－２ In the model curve L1, the ambiguity of participants A and B is higher than the ambiguity of the model curve L2. The proposal device 100 displays a suggestion to participant A, "Let's make A's ambiguity a little more specific." The content of the suggestion made by the proposal device 100 to participant B will not be explained. １－２ The ambiguity of participant C is lower than the ambiguity of model curve L2. The content of the proposal made by the proposal device 100 to participant C will not be described. １－２ The circle 10Z in the figure is omitted.

[0035] Next, we will explain Fig. 4. Fig. 4 explains an example of a proposal made by the proposing device 100 to the moderator. The explanation of the vertical axis, horizontal axis, and each circle of the graph G3 shown in Fig. 4 is the same as that given in Fig. 3. For example, the proposing device 100 moves the circle 10Z on the model curve L2 in accordance with the elapsed time of the conference.

[0036] The proposing device 100 determines that the conference has transitioned to the next phase when the rate of change with respect to the elapsed time for the model curve L2 is a positive number and the rate of change is equal to or greater than a predetermined rate, and makes a proposal to the moderator. ２－１ In this case, it is determined that the rate of change (positive number) relative to the elapsed time has reached a predetermined rate or more, and a suggestion is displayed to the moderator saying, "Participant ambiguity has risen sharply. The phase of the meeting has changed from the early stage to the middle stage."

[0037] Furthermore, the proposing device 100 determines that the conference has transitioned to the next phase when the rate of change with respect to the elapsed time for the model curve L2 is a negative number and is less than a predetermined rate, and makes a proposal to the moderator. ２－２ In this case, the proposing device 100 determines that the rate of change (negative number) relative to the elapsed time is less than a predetermined rate. At this time, the proposing device 100 displays a suggestion to the moderator, saying, "The ambiguity of the participants has dropped sharply. The phase of the meeting has changed from the middle to the end. It is time to wrap things up."

[0038] Next, we will explain Figure 5. In the above explanation, the proposal device 100 makes a proposal for each participant based on the ambiguity of each participant and the ambiguity of the model curve, but as will be explained in Figure 5, the ambiguity of multiple participants may be handled collectively. The explanation of the vertical axis, horizontal axis, and each circle of G4 shown in Figure 5 is the same as that given in Figure 3.

[0039] The proposal device 100 calculates the average value of the ambiguity of multiple participants, and if the average value changes periodically, determines that the discussion has reached an impasse. In this case, the proposal device 100 displays a suggestion to participants A, B, and C: "Aren't you going around in circles? Why don't you go back and organize the points of contention and prerequisites?"

[0040] For example, the proposing device 100 calculates the average value of the ambiguity of each participant calculated during the same period in the graph G4. ３－１ The circles corresponding to the ambiguities of participants A, B, and C calculated within a predetermined time interval based on the elapsed time t are designated as 10A-1, 10B-1, and 10C-1, respectively. ３－２ The circles corresponding to the ambiguities of participants A, B, and C calculated within a predetermined time span based on the above are designated as 10A-2, 10B-2, and 10C-2, respectively.

[0041] Elapsed time t ３－３ The circles corresponding to the ambiguities of participants A, B, and C calculated within a predetermined time interval based on the elapsed time t are designated as 10A-3, 10B-3, and 10C-3, respectively. ３－４The circles corresponding to the ambiguities of participants A, B, and C calculated within a predetermined time span based on the above are designated as 10A-4, 10B-4, and 10C-4, respectively.

[0042] The proposal device 100 determines that the discussion has reached an impasse if the condition that the average value of the ambiguity of multiple participants becomes less than a predetermined ambiguity within a predetermined period of time and then becomes equal to or greater than the predetermined ambiguity is met a predetermined number of times (for example, twice).

[0043] For example, the elapsed time t ３－１ When the average ambiguity of the multiple participants becomes less than the predetermined ambiguity, and the elapsed time t ３－２ Assume that the average value of the ambiguities of the multiple participants becomes equal to or greater than a predetermined ambiguity. ３－３ When the average ambiguity of the multiple participants becomes less than the predetermined ambiguity, and the elapsed time t ３－４ In this case, if the average value of the ambiguities of the multiple participants becomes equal to or greater than a predetermined ambiguity, the proposal device 100 determines that the discussion has reached an impasse and displays the above proposal to participants A, B, and C.

[0044] The proposing device 100 may compare the average value of the ambiguities of the multiple participants with the ambiguity of the model curve L2, and make suggestions to the multiple participants so that the average value approaches the ambiguity of the model curve L2.

[0045] Next, Fig. 6 will be described. When the ambiguity of a participant increases rapidly over time, the proposal device 100 determines that the participant has made an abnormal utterance and makes a proposal. For example, the proposal device 100 displays "How about taking a break?"

[0046] The proposing device 100 calculates the tendency of change in the ambiguity for each participant based on the ambiguity for each participant calculated in past conferences. For example, the proposing device 100 calculates the rate of change with respect to the elapsed time for the ambiguity for participant C calculated in past conferences, and identifies the maximum rate of change.

[0047] The proposal device 100 calculates the ambiguity of the participant C and calculates the rate of change of the ambiguity with respect to the elapsed time. When the rate of change of the ambiguity is equal to or greater than a maximum value calculated in advance, the proposal device 100 determines that the participant C has made an abnormal statement. For example, in FIG. 6, the proposal device 100 calculates the ambiguity of the participant C with respect to the elapsed time t ４ In this case, when the rate of change in the ambiguity of participant C becomes equal to or greater than the maximum value, the above proposal is displayed to participant C.

[0048] The basic processing of the proposal device 100 has been described above with reference to Figures 3 to 6. Note that the proposal device 100 may output and display the graphs G2, G3, G4, and G5 shown in Figures 3 to 6 on a display unit.

[0049] (Configuration Example of Proposed Device) Next, a configuration example of the proposed device 100 shown in Fig. 1 will be described. Fig. 7 is a functional block diagram showing the configuration of the proposed device. As shown in Fig. 7, the proposed device 100 has a microphone 105, a timer 106, a communication control unit 110, an input unit 120, a display unit 130, a storage unit 140, and a control unit 150.

[0050] The microphone 105 collects speech from each participant in the conference. The microphone 105 outputs information about the collected speech to the control unit 150. The microphone 105 starts collecting speech when it receives information about the start of the conference.

[0051] The timer 106 outputs information about the current date and time to the control unit 150. The control unit 150 may obtain information about the current date and time from a server on the network.

[0052] The communication control unit 110 is realized by a NIC (Network Interface Card) or the like, and controls communication with terminals and the like connected to a network.

[0053] The input unit 120 is realized using input devices such as a keyboard and a mouse. A user operates the input unit 120 to input various pieces of information to the control unit 150. When a conference starts, the user operates the input unit 120 to input information that the conference has started to the control unit 150. When the conference ends, the user operates the input unit 120 to input information that the conference has ended to the control unit 150.

[0054] The display unit 130 is an output device that outputs information acquired from the control unit 150, and is realized by a display device such as a liquid crystal display. For example, the display unit 130 displays the model curve L2 described in Figures 3 to 6, the ambiguity of each participant described by the circles 10A, 10B, and 10C, and the current elapsed time of the conference described by the circle 10Z.

[0055] The storage unit 140 includes an utterance history buffer 141, a conference history table 142, and a personal ambiguity table 143. The storage unit 140 is realized by a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk.

[0056] The speech history buffer 141 stores speech information uttered by participants during a conference. For example, the speech information is text, and includes information identifying the elapsed time of the speech and the participant who made the speech.

[0057] The conference history table 142 holds various information related to conferences that have been held in the past. Fig. 8 is a diagram showing an example of the data structure of the conference history table. As shown in Fig. 8, the conference history table 142 includes conference identification information, flags, conference dates and times, and ambiguity information.

[0058] The conference identification information is information that uniquely identifies a conference. The flag indicates whether the conference in question was a good conference or not. For example, if the conference was a good conference, the flag is "on," and if the conference was not a good conference, the flag is "off." Whether the flag is on or off is set in advance.

[0059] For example, for a meeting to decide the specifications of a product or an object, the administrator judges whether the meeting is good or bad based on product sales and survey results and sets a flag. For a meeting to decide something like an experience, the administrator judges whether the meeting is good or bad based on the number of attendees and survey results and sets a flag. Note that the proposal device 100 may estimate the satisfaction level of the participants in the meeting and set a flag based on the estimated satisfaction level.

[0060] The date and time of the meeting indicates the date and time when the meeting was held. The ambiguity information includes a history of the elapsed time and ambiguity for each participant who attended the meeting. For example, the ambiguity of a participant at a certain elapsed time included in the ambiguity information is set as the ambiguity of the meeting at the certain elapsed time.

[0061] The individual ambiguity table 143 stores the relationship between the elapsed time and the ambiguity of each participant for a currently ongoing conference. Fig. 9 is a diagram showing an example of the data structure of the individual ambiguity table. As shown in Fig. 9, the individual ambiguity table 143 includes participant identification information and individual ambiguity information.

[0062] The participant identification information is information that uniquely identifies a participant. For example, a participant with participant identification information "U101" is referred to as participant A. A participant with participant identification information "U102" is referred to as participant B. A participant with participant identification information "U103" is referred to as participant C.

[0063] The individual ambiguity information is information that associates the elapsed time of a participant participating in a conference with the ambiguity.

[0064] Next, we will explain the control unit 150. The control unit 150 has an acquisition unit 151, a model curve generation unit 152, an ambiguity calculation unit 153, and a proposal unit 154. The control unit 150 is a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit).

[0065] The acquisition unit 151 acquires information about speech (voice) of the participants from the microphone 105 and converts the speech (voice) into text, thereby generating speech information. The acquisition unit 151 converts the voice into text using conventional voice recognition technology. The acquisition unit 151 adds, to the speech information, the date and time when the speech information was acquired and information for identifying the participant. The acquisition unit 151 may identify the participant based on the voice characteristics and the voice characteristics of the participant that have been set in advance.

[0066] The acquiring unit 151 registers the speech information in the speech history buffer 141. The acquiring unit 151 repeatedly executes the above process every time it acquires information on the speech (voice) of a participant from the microphone 105.

[0067] The model curve generation unit 152 generates a model curve based on the conference history table 142. For example, the model curve generation unit 152 obtains ambiguity information of conferences whose flags are "on" from the conference history table 142, and generates a model curve by calculating the relationship between elapsed time and ambiguity based on equation (1). The model curve is the model curve L2 described in FIGS. 1 to 6, etc. The model curve generation unit 152 outputs information about the model curve to the proposing unit 154.

[0068] The ambiguity calculation unit 153 calculates the ambiguity of the participant based on the utterance information registered in the utterance history buffer 141. The ambiguity calculation unit 153 associates information identifying the participant attached to the utterance information with the elapsed time and the ambiguity, and registers them in the personal ambiguity table 143.

[0069] The ambiguity calculation unit 153 calculates the ambiguity of the utterance information using an existing technology related to ambiguity calculation. For example, the ambiguity calculation unit 153 counts the number of synonyms included in the utterance information based on a synonym dictionary, and the greater the number of synonyms counted, the greater the ambiguity value. The ambiguity calculation unit 153 may calculate the ambiguity by evaluating the context of the utterance information, or may calculate the ambiguity based on the human relationships of the participants in the conference.

[0070] The ambiguity calculation unit 153 repeatedly executes the process of calculating the ambiguity every time utterance information is registered in the utterance history buffer 141 and registering the calculated ambiguity information in the personal ambiguity table 143 .

[0071] The proposing unit 154 makes a proposal to the participants based on the model curve generated by the model curve generating unit 152 and the ambiguity of each participant registered in the personal ambiguity table 143 .

[0072] The suggestion unit 154 makes suggestions to the participants based on the model curve and the ambiguity of the participants so that the ambiguity of the participants approaches the model curve. For example, if the ambiguity of the speech information of the participants at a certain elapsed time is greater than the ambiguity of the model curve at a certain elapsed time, the suggestion unit 154 makes a suggestion to encourage the participants to speak with specific content. On the other hand, if the ambiguity of the speech information of the participants at a certain elapsed time is less than the ambiguity of the model curve at a certain elapsed time, the suggestion unit 154 makes a suggestion to encourage the participants to speak with abstract content. The processing performed by the suggestion unit 154 in this process corresponds to the processing described in FIG. 3.

[0073] The proposing unit 154 makes the proposal using a table that stores text to be proposed when the ambiguity of the speech information by a participant at a certain elapsed time is greater than the ambiguity of the model curve at the certain elapsed time, and text to be proposed when the ambiguity of the speech information by a participant at a certain elapsed time is less than the ambiguity of the model curve at the certain elapsed time. Furthermore, such a table may store multiple patterns of text depending on the phase of the conference and the degree of deviation between the model curve and the ambiguity of the participants.

[0074] The proposal unit 154 also outputs information about the model curve L2 to the display unit 130 for display, and moves a circle 10Z (the current elapsed time of the conference) on the model curve L2 in accordance with the elapsed time of the conference. The proposal unit 154 determines that the conference has transitioned to the next phase at an elapsed time when the rate of change with respect to the model curve L2 is a positive number and the rate of change is equal to or greater than a predetermined rate, and makes a proposal to the moderator. The proposal unit 154 determines that the conference has transitioned to the next phase at an elapsed time when the rate of change with respect to the model curve L2 is a negative number and the rate of change is less than the predetermined rate, and makes a proposal to the moderator. The processing by the proposal unit 154 related to this processing corresponds to the processing described in FIG. 4.

[0075] The proposing unit 154 may determine a phase transition as follows: When the rate of change is initially less than a predetermined rate after the conference starts, the proposing unit 154 determines that the phase has transitioned from the beginning ph1 to the early stage ph2, and proposes to the moderator that the phase has transitioned from the beginning to the early stage.

[0076] When the rate of change first becomes equal to or greater than a predetermined rate after the phase of the conference has shifted to the early stage, the proposing unit 154 determines that the phase has shifted from early stage ph2 to middle stage ph3 and proposes to the chairperson that the phase has shifted from early stage to middle stage.

[0077] When the rate of change becomes less than a predetermined rate at the beginning after the phase of the conference has shifted to the middle, the proposing unit 154 determines that the phase has shifted from middle ph3 to end ph4, and proposes to the chairperson that the phase has shifted from middle to end.

[0078] When the rate of change becomes less than a predetermined rate at the beginning after the phase of the conference has shifted to the final stage, the proposing unit 154 determines that the phase has shifted from final stage ph4 to conclusion ph5, and proposes to the chairperson that the phase has shifted from final stage to conclusion.

[0079] Furthermore, the proposing unit 154 calculates the average value of the ambiguities of the multiple participants based on the personal ambiguity table 143, and when the average value changes periodically, determines that the discussion has reached an impasse and makes a proposal. The processing by the proposing unit 154 regarding this processing corresponds to the processing described in FIG. 5.

[0080] Furthermore, when the ambiguity of a participant increases rapidly over time based on the personal ambiguity table 143, the suggestion unit 154 determines that the participant has made an abnormal utterance and makes a suggestion. The processing by the suggestion unit 154 regarding this processing corresponds to the processing described in Fig. 6. Note that a threshold for determining whether or not an abnormal utterance has been made may be set in advance for each participant.

[0081] As described above, the proposing unit 154 executes the processes described with reference to Figures 3 to 6. The proposing unit 154 may output the graphs G2, G3, G4, and G5 shown in Figures 3 to 6 to the display unit 130 and display them.

[0082] The conference moderator may operate the input unit 120 in accordance with the conference progress information to adjust the position on the model curve L2 of the circle 10Z (the current elapsed time of the conference) displayed on the graph G2 (G3 to G5) displayed on the display unit 130. When the proposal unit 154 accepts the adjustment of the circle 10Z, it starts moving the circle 10Z again from the adjusted position.

[0083] The configuration example of the proposed device 100 has been described above.

[0084] (Processing Procedure of Proposal Device) Next, an example of the processing procedure of the proposal device 100 will be described. Fig. 10 is a flowchart showing the processing procedure of the proposal device. As shown in Fig. 10, the model curve generation unit 152 of the proposal device 100 generates a model curve based on the conference history database (step S101).

[0085] The acquisition unit 151 of the proposal device 100 acquires information on sounds uttered by the participants from the microphone 105 and generates utterance information (step S102). The acquisition unit 151 registers the utterance information in the utterance history buffer 141 (step S103).

[0086] The ambiguity calculation unit 153 of the proposal device 100 calculates the ambiguity corresponding to the elapsed time based on the utterance information registered in the utterance history buffer 141 (step S104). The ambiguity calculation unit 153 registers the calculation result of the ambiguity in the personal ambiguity table 143 (step S105).

[0087] The proposing unit 154 of the proposing device 100 makes a proposal based on the ambiguity of the model curve and the ambiguity of each participant registered in the personal ambiguity table 143 regarding the elapsed time of the current conference (step S106).

[0088] If the conference has not ended (step S107, No), the proposal device 100 proceeds to step S102. On the other hand, if the conference has ended (step S107, Yes), the proposal device 100 ends the process.

[0089] The processing procedure of the proposed device 100 has been described above.

[0090] (Effects of the Proposal Device) The proposal device 100 according to this embodiment generates a model curve from the elapsed time since the start of a past conference and the ambiguity, and calculates the ambiguity from the speech information of the participants of the current conference. The proposal device 100 makes a proposal such that the ambiguity of the speech information approaches the ambiguity of the model curve at the time the speech information is acquired. This makes it possible to propose a speech policy that suits the situation of the conference.

[0091] When the rate of change in the ambiguity of the model curve corresponding to the elapsed time since the start of the current conference is equal to or greater than a threshold, the proposing device 100 makes a proposal to advance the discussion phase of the current conference, thereby assisting the conference chairperson in progressing the conference.

[0092] The proposal device 100 calculates the average value of the ambiguity of multiple participants, and when the average value changes periodically, determines that the discussion is at an impasse and makes a proposal. This allows a policy that is in line with the flow of the meeting to be proposed to all participants.

[0093] (Other Configurations of the Proposal Device) In the above embodiment, the proposal device 100 acquires the speech of the conference participants using the microphone 105, but this is not limited to this. For example, if each conference participant uses a PC (Personal Computer) or the like to participate in a web conference, the proposal device 100 may acquire the speech of the participants from each user's PC.

[0094] Furthermore, the above embodiment is not limited to the use of voices of conference participants via microphones. For example, the proposal device 100 can also be applied to a conference in which participants exchange text without using voice, such as chat. In this case, the proposal device 100 acquires text information from each user's PC and calculates ambiguity based on the acquired text information. The rest of the description is the same as the description of the proposal device 100 above.

[0095] (Proposed Program) Next, an example of a computer that executes the proposed program will be described. Fig. 11 is a diagram showing an example of a computer that executes the proposed program. The computer 1000 includes, for example, a memory 1010, a CPU 1020, a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These components are connected by a bus 1080.

[0096] The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM 1012. The ROM 1011 stores a boot program such as a BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to a hard disk drive 1031. The disk drive interface 1040 is connected to a disk drive 1041. A removable storage medium such as a magnetic disk or optical disk is inserted into the disk drive 1041. The serial port interface 1050 is connected to a mouse 1051 and a keyboard 1052, for example. The video adapter 1060 is connected to a display 1061, for example.

[0097] Here, the hard disk drive 1031 stores, for example, an OS 1091, an application program 1092, a program module 1093, and program data 1094. The various pieces of information described in the above embodiments are stored in the hard disk drive 1031 or memory 1010, for example.

[0098] The proposed program is stored in the hard disk drive 1031 as a program module 1093 in which instructions to be executed by the computer 1000 are written. Specifically, the program module 1093 in which the processes for executing the acquisition unit 151, the model curve generation unit 152, the ambiguity calculation unit 153, and the proposal unit 154 described in the above embodiment are written is stored in the hard disk drive 1031.

[0099] Furthermore, data used in the proposal process by the proposal program is stored as program data 1094, for example, in the hard disk drive 1031. Then, the CPU 1020 reads the program module 1093 and the program data 1094 stored in the hard disk drive 1031 into the RAM 1012 as necessary, and executes each of the above-described procedures.

[0100] The program module 1093 and program data 1094 related to the proposed program are not limited to being stored in the hard disk drive 1031, and may be stored in a removable storage medium, for example, and read by the CPU 1020 via the disk drive 1041 or the like. Alternatively, the program module 1093 and program data 1094 related to the proposed program may be stored in another computer connected via a network such as a LAN or a WAN (Wide Area Network), and read by the CPU 1020 via the network interface 1070.

[0101] Although the present invention has been described above as an embodiment, the present invention is not limited to the descriptions and drawings that form part of the disclosure of the present invention. In other words, other embodiments, examples, and operational techniques that can be made by those skilled in the art based on the present invention are all included in the scope of the present invention.

[0102] REFERENCE SIGNS LIST 100 Proposal device 105 Microphone 106 Timer 110 Communication control unit 120 Input unit 130 Display unit 140 Storage unit 141 Speech history buffer 142 Conference history table 143 Personal ambiguity table 150 Control unit 151 Acquisition unit 152 Model curve generation unit 153 Ambiguity calculation unit 154 Proposal unit

Claims

1. A proposal device comprising: a model curve generation unit that generates a model curve corresponding to the relationship between the elapsed time from the start of a first conference held in the past and ambiguity; an ambiguity calculation unit that acquires text information from participants of a second conference and calculates the ambiguity of the text information; and a proposal unit that makes proposals to participants of the second conference so that the ambiguity of the text information approaches the ambiguity of the model curve at the time the text information was acquired.

2. The proposal device described in claim 1, characterized in that the proposal unit executes a proposal to advance the discussion phase of the second meeting when the rate of change in the ambiguity of the model curve corresponding to the elapsed time since the start of the second meeting becomes equal to or greater than a threshold value.

3. A proposal method executed by a proposal device, comprising: a model curve generation process for generating a model curve corresponding to the relationship between the elapsed time from the start of a first conference held in the past and ambiguity; an ambiguity calculation process for acquiring text information from participants of a second conference and calculating the ambiguity of the text information; and a proposal process for making a proposal to the participants of the second conference so that the ambiguity of the text information approaches the ambiguity of the model curve at the time the text information was acquired.

4. A proposal program for causing a computer to execute the following steps: a model curve generation step for generating a model curve corresponding to the relationship between the elapsed time from the start of a first conference held in the past and ambiguity; an ambiguity calculation step for acquiring text information from participants of a second conference and calculating the ambiguity of the text information; and a proposal step for making a proposal to participants of the second conference so that the ambiguity of the text information approaches the ambiguity of the model curve at the time when the text information was acquired.

Images