Information processing program, information processing device, and information processing method

Abstract

To appropriately prompt utterance in an online conference.SOLUTION: An information processing program makes a computer execute the processing of: receiving an expression of intention 103 of a first person 101 in an online conference which is selected by the first person 101 among a plurality of persons participating in the online conference; specifying, when the received expression of intention 103 satisfies a condition, text according to the condition which prompts the first person 101 to make utterance; and presenting the specified text to a second person 101 different from the first person 101 among the plurality of persons.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an information processing program, an information processing device, and an information processing method. [Background technology]

[0002] Remote work has become widespread due to the COVID-19 pandemic. Because remote work reduces communication, it can be difficult to promote teamwork. Teamwork, such as meetings, can sometimes be held online when working remotely.

[0003] A known prior art technique for supporting the progress of online meetings is to calculate the level of activity in discussions in a meeting, recognize the timing at which the facilitator should encourage participants to speak, and support the facilitator. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] International Publication No. 2023 / 038125 [Patent Document 2] Japanese Patent Publication No. 2022-068904 [Patent Document 3] Japanese Patent Publication No. 2022-139436 [Patent Document 4] U.S. Patent Publication No. 2014 / 0145936 Summary of the Invention [Problem to be solved by the invention]

[0005] However, simply specifying the timing to encourage speaking may not necessarily lead to encouraging speaking, as some may not know how to encourage speaking. For example, the facilitator may not know how to encourage speaking and may not encourage speaking at all, or may encourage speaking but not effectively, resulting in the target participant not being able to speak.

[0006] One aspect of the present invention is to enable appropriate prompting of participants to speak in online meetings. [Means for solving the problem]

[0007] In one aspect, the information processing program causes a computer to execute a process of accepting an expression of intent from a first person in an online conference selected by the first person among a plurality of people participating in the online conference, and if the accepted expression of intent satisfies a condition, identifying text that complies with the condition and encourages the first person to speak, and presenting the identified text to a second person among the plurality of people that is different from the first person. [Effects of the Invention]

[0008] On the one hand, it allows for appropriate prompts to speak up during online meetings. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a block diagram illustrating a configuration example of an online conference system according to an embodiment. [Figure 2] FIG. 2 is a block diagram schematically illustrating an example of the software configuration of the online conference system shown in FIG. 1. [Figure 3] 2 is a table illustrating intention expression pattern conditions in the online conference system shown in FIG. 1. [Figure 4] FIG. 2 is a diagram illustrating an example of a speech prompt screen in the online conference system shown in FIG. 1. [Figure 5]2 is a table illustrating prompt success / failure information in the online conference system shown in FIG. 1. [Figure 6] FIG. 2 is a diagram showing details of the intention expression area on the online conference screen shown in FIG. 1. [Figure 7] 10 is a flowchart illustrating a process for determining an intention expression pattern in an embodiment. [Figure 8] 10 is a flowchart illustrating a process for determining a notification destination and a prompt destination in an embodiment. [Figure 9] 10 is a flowchart illustrating a process for determining whether prompting is successful or not in the embodiment. [Figure 10] FIG. 1 is a block diagram illustrating an example of a hardware configuration of an information processing device according to an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0010] [A] Embodiment An embodiment will be described below with reference to the drawings. However, the embodiment described below is merely an example, and is not intended to exclude various modifications or application of techniques not explicitly stated in the embodiment. In other words, this embodiment can be implemented with various modifications within the scope of its purpose. Furthermore, each figure does not intend to include only the components shown in the figure, but may include other components, etc.

[0011] [A-1] Software configuration example FIG. 1 is a block diagram schematically illustrating an example of the configuration of an online conference system 100 according to an embodiment.

[0012] 1 collects, via a network 102, expressions of intent (see dashed arrows) sent by multiple participants 101 in an online conference. The online conference system 100 then stores the sent expressions of intent in an expression of intent database 103, and sends notifications to people with a higher speaking rate, encouraging people with a lower speaking rate to speak, according to the patterns of the stored expressions of intent.

[0013] As shown in Fig. 1, an online conference screen 10 displays an intention expression area 110 in addition to images of participants 101. The online conference screen 10 is an example of a screen displayed on the terminal of a participant 101 by an online conference application. Persons A to F on the online conference screen 10 are examples of participants 101. The intention expression area 110 displays the intentions of all participants 101 in response to a statement made by a certain participant 101 during the online conference.

[0014] The expression of intention is the participant's own thoughts or intentions expressed by the participant 101 in the online conference, and may be, for example, one of three types: (1) agreement or sympathy, (2) opposition or discomfort, or (3) no intention. For example, the participant 101 inputs his / her intention to the online conference system 100 by selecting a button corresponding to his / her intention from the participant's terminal. The button may be displayed on the screen of the participant's terminal and selected by clicking with a mouse 151 (described later with reference to FIG. 10) or by touching with a touch panel (not shown). The button may also be pre-assigned to any key on the keyboard 152 (described later with reference to FIG. 10) of the participant's terminal. The button may also be pre-assigned to a sub-key of a mouse connected to the participant's terminal. It is sufficient to provide two buttons, one corresponding to (1) agreement or sympathy and the other to (2) opposition or discomfort, respectively. If neither button is selected, the selection may be treated as (3) no intention. The participant 101's expression of intent may be displayed in the intent expression area 110, for example, as (1) "Like" for agreement or sympathy, (2) "Hmm" for opposition or discomfort, or (3) "zzz" for no intent.

[0015] In the intention expression area 110 illustrated in FIG. 1, A and C express their intentions with "Like," D with "Hmm," and B, E, and F with "zzz."

[0016] The online conference system 100 causes the terminal of each participant 101 to execute a program that transmits an expression of intention to an expression of intention database 103. Then, the online conference system 100 causes the result of the expression of intention stored in the expression of intention database 103 to be displayed as an expression of intention area 110 in a part of the online conference screen 10 viewed by each participant 101 on their terminal.

[0017] FIG. 2 is a block diagram schematically illustrating an example of the software configuration of the online conference system 100 shown in FIG.

[0018] The CPU (Central Processing Unit) 11 of the information processing device 1, which will be described later using Figure 10, functions as an intention expression pattern display unit 111, a statement section accumulation unit 112, a statement ratio calculation unit 113, an intention expression pattern determination unit 114, a prompt determination unit 115, a text generation unit 116, a text transmission unit 117, and a prompt success / failure determination unit 118, as shown in Figure 2.

[0019] The terminal of each participant 101 transmits an expression of intent (see dashed arrow) in response to comments made by other participants 101 during the conference to an expression of intent database 103 via a network 102. Examples of the terminal include a personal computer, a tablet terminal, and a smartphone. The expression of intent database 103 may be stored in a storage device 14 of an information processing device 1, which will be described later with reference to FIG. 10.

[0020] The intention expression pattern display unit 111 reads out the intention expression of each participant 101 from the intention expression database 103, and displays the intention expressions of the participants 101 in the intention expression area 110 of the online conference screen 10 on the terminals of all participants 101. The intention expressions displayed in the intention expression area 110 may be the intention expressions of all participants 101, or may be the intention expressions of some of the participants 101.

[0021] The speech section accumulation unit 112 acquires the conference audio stream (see dashed-dotted arrows) from the terminal of each participant 101 via the network 102, detects the speech section for each participant 101, and accumulates the speech time for each participant 101 in the storage device 14 (described later with reference to FIG. 10). As an example, the speech time is the time during which each participant 101 speaks from the start of the online conference until the timing at which the speech ratio is calculated. As another example, the speech time may be the time during which each participant 101 speaks from a predetermined time before the timing at which the speech ratio is calculated.

[0022] The speech ratio calculation unit 113 calculates the speech ratio for each participant 101 based on the speech time of each participant 101. As an example, the speech ratio is a value obtained by dividing the speech time of each participant 101 by the total speech time, which is the sum of the speech times of all participants 101. The speech ratio calculation unit 113 records the calculated speech ratio in prompt success / failure information, which will be described later with reference to FIG. 5.

[0023] The speech ratio calculation unit 113 may use an existing voice activity detection (VAD) technique to detect speech intervals from the conference audio stream, and may use the total length of these intervals as the speech time.

[0024] Assuming that the speech times of n participants 101 are v1, v2, . . . , vn, the speech ratio ri of participant i is given by the following equation.

number

[0025] The intention expression pattern determination unit 114 accepts the intention expression of each participant 101 by reading out the intention expression database 103. The intention expression pattern determination unit 114 determines the intention expression pattern for all participants 101 based on the intention of each participant 101 read out from the intention expression database 103 and the calculated speech ratio of each participant 101. The intention expression pattern is a combination pattern of the content of the intention expression shown by the participants 101. Specifically, the intention expression pattern determination unit 114 refers to the intention expression pattern conditions described later with reference to FIG. 3 and outputs the number of the intention expression pattern based on the intention expression and speech ratio of each participant 101 and the ID of the participant 101 to be prompted to speak.

[0026] In other words, the intention expression pattern determination unit 114 accepts an intention of a first person in an online conference selected by the first person from among multiple people participating in the online conference. The first person may be a person who makes a relatively small amount of comments among the multiple people. The first person is a person identified based on the comment status of each of the multiple people. The comment status is the status regarding comments made by each participant 101 in the online conference. As an example, the comment status is expressed as a comment volume, which indicates the amount of comments made by each participant 101. As an example, the comment volume is the amount of time each participant 101 spoke during a predetermined period of the online conference, the number of characters spoken, the number of words spoken, the frequency of speech, etc. The comment volume may be expressed as a ratio of the comment volume of each participant. The comment ratio is an example of the comment volume.

[0027] The intention expression pattern determination unit 114 may select the M people with the highest speech rate at a certain point in time as people with a high speech rate, and may select the N people with the lowest speech rate at a certain point in time as people with a low speech rate. For example, M and N may be 2 to 3. By selecting multiple people with a high speech rate, it is possible to prevent instruction texts encouraging a particular person to speak from being concentrated on one particular person. Furthermore, by selecting multiple people with a low speech rate, it is possible to prevent a particular person from being the target of encouragement to speak.

[0028] The prompt determination unit 115 determines the participant 101 (for example, the second person) to whom the instruction text for prompting the participant 101 to speak is to be notified, and the participant 101 to be prompted (for example, the first person) to be prompted to speak by the participant 101 to whom the instruction text is to be notified. The prompt determination unit 115 may determine the participant 101 to be notified from among the top M participants 101 in terms of speech ratio selected by the intention expression pattern determination unit 114, and may determine the participant 101 to be prompted from among the bottom N participants 101 in terms of speech ratio selected by the intention expression pattern determination unit 114.

[0029] The text generation unit 116 generates instruction text for encouraging the notified participant 101 to speak. Specifically, the text generation unit 116 generates instruction text corresponding to the intention expression pattern number determined by the intention expression pattern determination unit 114, with reference to the intention expression pattern conditions described later with reference to FIG.

[0030] In other words, if the received expression of intention satisfies a condition, the text generation unit 116 identifies the text that conforms to the condition and encourages the first person to speak. The text may be text that includes a phrase encouraging the first person to speak or information suggesting a phrase. The condition may be a condition based on a relationship between the expression of intention of the first person and the expressions of intention of each of multiple people other than the first person. If the received expression of intention satisfies the condition, the text generation unit 116 may identify the text and the timing to present the text.

[0031] The text sending unit 117 sends the generated instruction text to the participant 101 who is the second person to be notified.

[0032] In other words, the text sending unit 117 presents the identified text to a second person, who is different from the first person, among the plurality of people. The second person may be a person who speaks relatively more frequently among the plurality of people. The text sending unit 117 may present the identified text to the second person at the identified timing.

[0033] The prompting success / failure determination unit 118 determines whether the participant 101 who was prompted to speak by the participant 101 who was notified has spoken.

[0034] In this way, when the results of the intention expression of each participant 101 become a specific intention expression pattern, the online conference system 100 transmits instructions (text) to those with a high speaking rate to encourage those with a low speaking rate to speak. After transmitting the instruction to encourage speaking, the online conference system 100 also feeds back the result of whether the prompt was actually successful in the prompt as prompt success / failure information (described later using FIG. 5), and determines who to encourage from next time onwards, taking into account the result of the success / failure of the prompt.

[0035] FIG. 3 is a table illustrating intention expression pattern conditions in the online conference system 100 shown in FIG.

[0036] The intention expression pattern conditions illustrated in Fig. 3 include a category, a pattern No., an intention expression pattern, a prompt destination, and the contents of an instruction text. The intention expression pattern conditions may be stored in the storage device 14 of the information processing device 1, which will be described later with reference to Fig. 10.

[0037] The expressions of intention of the participants 101 are divided into several patterns based on the combination of the expressions of intention of each participant 101, the frequency of the expressions of intention of each participant 101, the speed of the expressions of intention, etc. As an example, patterns No. 001 to 005 are expression patterns based on the "combination of the expressions of intention of the conference participants", pattern No. 006 is an expression pattern based on the "frequency of the expressions of intention", and pattern No. 007 is an expression pattern based on the "speed of the expressions of intention".

[0038] Pattern No. 001 indicates the condition that when there is an expression pattern of "only one person saying 'zzz'" (even though everyone else is expressing their intention) and "the person who said 'zzz' has a low speaking rate," the person who expressed the intention of "zzz" will be determined to be the person to be prompted. When the conditions of Pattern No. 001 are met, the instruction text "Ask them why they didn't press it" is generated.

[0039] Pattern No. 002 indicates a condition in which, when the pattern is "a large number of 'Like's, a small number of 'Hmm's'" and "among those who displayed 'Hmm' there is a person with a low speaking rate," the person who displayed 'Hmm' is determined to be the person to be prompted. When the conditions of Pattern No. 002 are met, the instruction text "Ask why you don't agree" is generated.

[0040] Pattern No. 003 indicates a condition in which, when the intention expression pattern is "many 'hmm's, few 'like's'" and "among those who displayed 'like' there is a person with a low speech rate," the person who displayed the intention of "like" is determined to be the person to be prompted. When the conditions of Pattern No. 003 are met, the instruction text "Ask why you agree" is generated.

[0041] Pattern No. 004 indicates a condition in which, when the number of "Like"s and "Hmm"s is the same and "among those who have displayed "Like" there is a person with a low speech rate," the person who displayed "Like" is determined to be the person to be prompted. When the conditions of Pattern No. 004 are met, the instruction text "As a representative of the "Like" side, ask for their opinion" is generated.

[0042] Pattern No. 005 indicates a condition that if the number of "Like"s and "Hmm"s is the same and "among those who displayed "Hmm" there is a person with a low speaking rate," the person who displayed "Hmm" will be selected as the person to be prompted. If the conditions of Pattern No. 005 are met, the instruction text generated is "As a representative of the "Hmm" side, ask for their opinion."

[0043] Pattern No. 006 is an intention expression pattern where "the number of times a person displays 'Hmm' per minute exceeds a threshold" and "the person who displayed 'Hmm' has a low speaking rate" indicates a condition that the person who displayed 'Hmm' will be selected as the person to be prompted. If the conditions of Pattern No. 006 are met, the instruction text "Ask them why they don't agree" is generated.

[0044] Pattern No. 007 is an intention expression pattern for "the first to express his / her intention" and indicates the condition that if "the first to express his / her intention is a person with a low speaking rate", then "the person who expressed his / her intention first" will be determined to be the first to be prompted. If the conditions of pattern No. 007 are met, the instruction text "Ask why he / she expressed his / her intention first" is generated.

[0045] In the example shown in Figure 3, the content of the instruction text is information suggesting a phrase encouraging speech, but it is not limited to this. The content of the instruction text may be the phrase itself encouraging speech, for example, in the case of pattern No. 001, it may be "Why didn't you press the intention button?"

[0046] FIG. 4 is a diagram illustrating an example of a speech prompt notification screen in the online conference system 100 shown in FIG.

[0047] The text sending unit 117 may display the speech prompting notification screen shown in FIG. 4 in a pop-up format on the online conference screen 10 on the terminal of the participant 101 to whom the notification is to be sent.

[0048] In the example shown in Figure 4, "Mr. A" is specified as the prompt recipient, and "Ask him why he didn't press the button" of pattern No. 001 in the intention expression pattern conditions in Figure 3 is specified as the prompt content.

[0049] The notified participant 101 asks Mr. A why he did not press the statement button in accordance with the speech prompt notification screen shown in Fig. 4. The notified participant 101 may close the speech prompt notification screen by pressing the "OK" button displayed on the speech prompt notification screen shown in Fig. 4.

[0050] The speech prompt notification screen may also display a "notify later" button (not shown). This allows the speech prompt notification screen to be redisplayed after a predetermined time or after a time specified by the notified participant 101 in an online conference where the conversation should not be interrupted by the speech prompt, thereby enabling the speech prompt to be implemented at an effective timing.

[0051] The display of the prompt to speak notification screen is not limited to a pop-up format, and the prompt to speak notification may be displayed by various means, such as chat in the online conference app or chat software other than the online conference app.

[0052] FIG. 5 is a table illustrating prompt success / failure information in the online conference system 100 shown in FIG.

[0053] The speech ratio calculation unit 113 registers the speech ratio for each participant 101 in the prompt success / failure information shown in Fig. 5. In the example shown in Fig. 5, the speech ratios are 34% for Person A, 26% for Person B, 25% for Person C, 7% for Person D, 3% for Person E, and 5% for Person F. The prompt success / failure information may be stored in the storage device 14 of the information processing device 1, which will be described later with reference to Fig. 10.

[0054] The prompt success / failure determination unit 118 notifies the prompt determination unit 115 of the notification destination (second person), the prompt recipient (first person), and the success / failure result of the prompt to make a statement.

[0055] The prompt determination unit 115 calculates the prompt success rate for each combination of notification destination and prompt destination, and registers the calculated rate in the prompt success / failure information shown in Fig. 5. Furthermore, as shown in parentheses around the prompt success / failure information in Fig. 5, the prompt determination unit 115 may also register the number of times prompts have been performed for each combination of notification destination and prompt destination.

[0056] In the example shown in Figure 5, A prompts D three times with a success rate of 67%, A prompts E once with a success rate of 0%, A prompts F once with a success rate of 0%, and B prompts F three times with a success rate of 100%.

[0057] The prompt determination unit 115 may determine the notification destination and the prompt destination in consideration of the speech ratio and the success or failure and frequency of previous prompts, for example, according to the following example 1 or example 2. Note that, since the speech ratio changes in real time depending on prompts, etc., the order of the notification destination and the prompt destination will change each time.

[0058] Example 1: If the person being prompted is person E, and if prompting from person A has failed in the past, then the notification will be sent to person B, who has the next highest speaking rate.

[0059] Example 2: When the prompt recipient is F, the prompt from B is 100%, but since this combination of prompts has been implemented three times, the notification recipient will be C, who has the next highest speaking rate (A is not the notification recipient because he has already failed).

[0060] FIG. 6 is a diagram showing details of the intention display area 110 on the online conference screen 10 shown in FIG.

[0061] For example, when a PC (Personal Computer) is used as the terminal of participant 101, the means for transmitting the expression of intention of participant 101 may be to execute an executable file capable of transmitting each expression of intention. The executable file may be programmed to store the content of the expression of intention in a database associated with a specified IP address on the network.

[0062] 6, the intention expression pattern display unit 111 displays the intention expression patterns of all the participants 101 in real time. The intention expression pattern display unit 111 may also display the intention expression patterns for approximately 10 seconds.

[0063] As shown in the intention expression area 110 of Fig. 6, the intention expression pattern display unit 111 may display icons representing the intention expressions "Like," "Hmm," and "zzz" in addition to the display contents in the intention expression area 110 shown in Fig. 1. Furthermore, the intention expression pattern display unit 111 may display the intention expressions "Like," "Hmm," and "zzz" in different colors. This makes it easier to visually understand the intentions of each participant 101.

[0064] On the online conference screen 10 shown in FIG. 1, the intention expression area 110 is displayed alongside the video of each participant 101, but the present invention is not limited to this.

[0065] The intention expression area 110 may be displayed superimposed on the video of each participant 101. When the intention expression area 110 is displayed superimposed on the video of each participant 101, an intention expression such as "Like," "Hmm," or "zzz" may be displayed in the display area of ​​the video of the corresponding participant 101. The color of the display area of ​​the video of the corresponding participant 101 may be changed for each intention expression such as "Like," "Hmm," or "zzz." This eliminates the area on the online conference screen 10 that is allocated to the intention expression area 110, making it possible to display a larger image of each participant 101 or increase the number of videos of participants 101 that are displayed.

[0066] Furthermore, the intention expression area 110 may be displayed in an application other than the application that displays the online conference screen 10. This eliminates the need to incorporate the software shown in Fig. 2 into an existing online conference application, and allows the software shown in Fig. 2 to be applied to various online conference applications.

[0067] [A-2] Example of operation The process of determining an intention expression pattern in this embodiment will be described with reference to the flowchart shown in FIG.

[0068] The intention expression pattern determination unit 114 acquires time information (step S1).

[0069] The intention expression pattern determination unit 114 determines whether the time for checking the intention expression pattern (for example, about one second from the start of the conference or the previous confirmation of the intention expression pattern) has elapsed (step S2).

[0070] If the time to check the intention expression pattern has not elapsed (see the No route from step S2), the process returns to step S1.

[0071] On the other hand, if the time to check the intention expression pattern has passed (see the Yes route in step S2), the intention expression pattern determination unit 114 acquires the speech ratios of all participants 101 from the speech ratio calculation unit 113 (step S3).

[0072] The intention expression pattern determination unit 114 selects the bottom N users (N is a natural number) based on the comment ratio (step S4).

[0073] The intention expression pattern determination unit 114 determines whether all but one person has expressed an intention and whether that person is one of the N people with the lowest speech ratio (step S5).

[0074] If all but one person expresses their intention and that person is one of the N people with the lowest speech ratio (see the Yes route in step S5), the intention expression pattern determination unit 114 refers to the intention expression pattern conditions. The intention expression pattern determination unit 114 records pattern No. 001 from the intention expression pattern conditions and the IDs of the people who have not expressed their intentions in, for example, the storage device 14 (described below using FIG. 10) (step S6). Then, the intention expression pattern determination process ends.

[0075] On the other hand, if the condition of step S5 is not met (see the No route of step S5), the intention expression pattern determination unit 114 determines whether all members have expressed their intention and whether the minority who said "Hmm" include the bottom N members in terms of speech ratio (step S7).

[0076] If all members have expressed their intentions and the minority who said "Hmm" includes the N members with the lowest speech ratio (see the Yes route in step S7), the intention expression pattern determination unit 114 refers to the intention expression pattern conditions. The intention expression pattern determination unit 114 records pattern No. 002 from the intention expression pattern conditions and the IDs of the minority members with the lowest speech ratios in, for example, the storage device 14 (described later using FIG. 10) (step S8). Then, the intention expression pattern determination process ends.

[0077] On the other hand, if the condition of step S7 is not met (see the No route of step S7), the intention expression pattern determination unit 114 determines whether all members have expressed their intention and whether the minority of "likes" includes the bottom N members with the lowest comment ratio (step S9).

[0078] If all members have expressed their intentions and the minority of "Likes" includes the N members with the lowest comment ratios (see the Yes route in step S9), the intention expression pattern determination unit 114 refers to the intention expression pattern conditions. The intention expression pattern determination unit 114 records pattern No. 003 from the intention expression pattern conditions and the IDs of the minority members with the lowest comment ratios in, for example, the storage device 14 (described below using FIG. 10) (step S10). Then, the intention expression pattern determination process ends.

[0079] On the other hand, if the condition of step S9 is not met (see the No route of step S9), the intention expression pattern determination unit 114 determines whether all members have expressed their intention, and whether the person with the smallest comment ratio, who has the same number of "Like" and "Hmm", has expressed "Like" (step S11).

[0080] If all members have expressed their intentions, the number of "Like" and "Hmm" responses is the same, and the person with the smallest comment ratio has expressed "Like" (see step S11, Yes route), the intention expression pattern determination unit 114 refers to the intention expression pattern conditions. The intention expression pattern determination unit 114 records pattern No. 004 from the intention expression pattern conditions and the ID of the person with the smallest comment ratio in, for example, the storage device 14 (described later using FIG. 10) (step S12). Then, the intention expression pattern determination process ends.

[0081] On the other hand, if the condition of step S11 is not met (see the No route of step S11), the intention expression pattern determination unit 114 determines whether all members have expressed their intention, and whether the person with the smallest comment ratio, who has the same number of "Like" and "Hmm", has expressed "Hmm" (step S13).

[0082] If all members have expressed their intentions, the number of "Like" and "Hmm" are equal, and the person with the smallest comment ratio has expressed "Hmm" (see the Yes route in step S13), the intention expression pattern determination unit 114 refers to the intention expression pattern conditions. The intention expression pattern determination unit 114 records pattern No. 005 from the intention expression pattern conditions and the ID of the person with the smallest comment ratio in, for example, the storage device 14 (described below using FIG. 10) (step S14). Then, the intention expression pattern determination process ends.

[0083] On the other hand, if the condition of step S13 is not met (see the No route of step S13), the intention expression pattern determination unit 114 determines whether the number of times the person expressed "Hmm" within one minute was I (e.g., 3 times) or more and whether the person was one of the bottom N people with the lowest speech ratio (step S15).

[0084] If the number of times "Hmm" is expressed within one minute is N (e.g., 3) or more, and the person is one of the N lowest-ranked speech rate users (see the Yes route in step S15), the intention expression pattern determination unit 114 refers to the intention expression pattern conditions. The intention expression pattern determination unit 114 records pattern No. 006 from the intention expression pattern conditions and the ID of the person with the lowest speech rate, for example, in the storage device 14 (described later using FIG. 10) (step S16). The intention expression pattern determination process then ends.

[0085] On the other hand, if the condition of step S15 is not met (see the No route of step S15), the intention expression pattern determination unit 114 determines whether the person who first expressed their intention from a state where the intention expression was 0 is a person with a low speech ratio (step S17).

[0086] If the person who first expressed their intention when the number of intentions expressed was 0 is a person with a low speech ratio (see the Yes route in step S17), the intention expression pattern determination unit 114 refers to the intention expression pattern conditions. The intention expression pattern determination unit 114 records pattern No. 007 from the intention expression pattern conditions and the ID of the person with the low speech ratio in, for example, the storage device 14 (described below using FIG. 10) (step S18). Then, the intention expression pattern determination process ends.

[0087] On the other hand, if the condition of step S17 is not met (see the No route of step S17), there is no need to notify the user of the urge to speak, so the intention expression pattern determination unit 114 does not identify an intention expression pattern, and the intention expression pattern determination process ends.

[0088] Next, the process of determining notification destinations and prompt destinations in this embodiment will be described with reference to the flowchart shown in FIG.

[0089] The prompt determining unit 115 acquires the pattern number and the ID of the participant 101 to be prompted from the intention expression pattern determining unit 114 (step S21).

[0090] The prompt determination unit 115 sets the acquired ID as the prompt destination (step S22).

[0091] The prompt determining unit 115 selects the top M names (M is a natural number) with the highest comment ratio (step S23).

[0092] The prompt determination unit 115 selects a combination of a notification destination and a prompt destination (step S24).

[0093] The prompt determining unit 115 determines whether there are any combinations that have not been tried (step S25).

[0094] If there are no untried combinations (see the No route in step S25), the prompt determination unit 115 determines the prompt recipient and also determines the user with the highest speech ratio as the notification recipient (step S26). Then, the process of determining the notification recipient and the prompt recipient ends.

[0095] On the other hand, if there is a combination that has not been tried (see the Yes route in step S25), the prompt determining unit 115 determines whether the success rate of this combination is 0% (step S27).

[0096] If the success rate for this combination is 0% (see the Yes route from step S27), the process returns to step S24.

[0097] On the other hand, if the success rate for this combination is not 0% (see the No route in step S27), the prompt determining unit 115 determines whether instruction texts have been transmitted three or more times for this combination (step S28).

[0098] If instruction text transmission for this combination has occurred three or more times (see the Yes route in step S28), the process returns to step S24.

[0099] On the other hand, if the instruction text transmission for this combination is not three or more times (see the No route in step S28), the prompt determination unit 115 finalizes the combination of the notification destination and the prompt destination that has been tried (step S29), and the notification destination and prompt destination determination process ends.

[0100] In step S26, if the success rate is 0% for all combinations or the instruction text has been sent three or more times, the notification recipient cannot be determined. Therefore, if the notification recipient cannot be determined, the recipient with the highest speech ratio at that time may be determined as the notification recipient.

[0101] Next, the process of determining whether prompting is successful or not in this embodiment will be described with reference to the flowchart shown in FIG.

[0102] Prompt success / failure determination unit 118 acquires transmission data (for example, time, notification destination, and prompt destination) from text transmission unit 117 (step S31).

[0103] The prompt success / failure determination unit 118 determines whether the time elapsed since transmission is within three minutes (step S32).

[0104] If the time elapsed since transmission is not within 3 minutes (see No route in step S32), the data {notification destination, prompt destination, failure} is sent to prompt determination unit 115 (step S33). Then, the prompt success / failure determination process ends.

[0105] If the time that has elapsed since the transmission is within three minutes (see the Yes route in step S32), the prompt success / failure determination unit 118 acquires the sender information from the utterance section accumulation unit 112 after the transmission (step S34).

[0106] The prompt success / failure determination unit 118 determines whether or not the notification recipient has made a statement (step S35).

[0107] If there is no message from the notification recipient (see the No route from step S35), the process returns to step S32.

[0108] On the other hand, if the notification recipient has made a statement (see the Yes route in step S35), prompting success / failure determination unit 118 determines whether the notification recipient has made a statement followed by the prompt recipient's statement (step S36).

[0109] If the person to be prompted does not make a statement after the person to be notified has made a statement (see the No route in step S36), the process returns to step S32.

[0110] On the other hand, if the prompt recipient makes a statement after the notification recipient makes a statement (see the Yes route in step S36), prompt success / failure determination unit 118 sends the data {notification recipient, prompt recipient, success} to prompt determination unit 115 (step S37). Then, the prompt success / failure determination process ends.

[0111] [A-3] Hardware configuration example 10, the information processing device 1 includes a CPU 11, a memory 12, a display control device 13, a storage device 14, an input interface (IF) 15, an external recording medium processing device 16, and a communication IF 17. Note that the terminal of the participant 101 is a separate piece of hardware from the information processing device 1, but may have the same hardware configuration as the information processing device 1.

[0112] The memory 12 is an example of a storage unit, and is illustratively a read-only memory (ROM) or a random access memory (RAM). A program such as a basic input / output system (BIOS) may be written to the ROM of the memory 12. The software program in the memory 12 may be read and executed by the CPU 11 as appropriate. The RAM of the memory 12 may be used as a temporary storage memory or a working memory.

[0113] The display control device 13 is connected to and controls the display device 131. The display device 131 is a liquid crystal display, an organic light-emitting diode (OLED) display, a cathode ray tube (CRT), an electronic paper display, or the like, and displays various information to the operator of the information processing device 1. The display device 131 may be combined with an input device, and may be, for example, a touch panel. The display device 131 displays various information to the user of the information processing device 1.

[0114] The storage device 14 is a high-IO performance storage device, and may be, for example, a dynamic random access memory (DRAM), a solid state drive (SSD), a storage class memory (SCM), or a hard disk drive (HDD). The storage device 14 may store an expression of intention database 103.

[0115] The input IF 15 may be connected to input devices such as a mouse 151 and a keyboard 152, and may control the input devices such as the mouse 151 and the keyboard 152. The mouse 151 and the keyboard 152 are examples of input devices, and an operator performs various input operations via these input devices.

[0116] The external recording medium processing device 16 is configured so that a recording medium 160 can be attached thereto. The external recording medium processing device 16 is configured so that, when the recording medium 160 is attached, the information recorded on the recording medium 160 can be read. In this example, the recording medium 160 is portable. For example, the recording medium 160 is a non-transitory recording medium such as a flexible disk, an optical disk, a magnetic disk, a magneto-optical disk, or a semiconductor memory.

[0117] The communication IF 17 is an interface that enables communication with an external device.

[0118] The CPU 11 is an example of a processor, and is a processing device that performs various controls and calculations. The CPU 11 realizes various functions by executing an operating system (OS) and programs loaded into the memory 12. The CPU 11 may be a multiprocessor including multiple CPUs, a multi-core processor having multiple CPU cores, or a configuration having multiple multi-core processors.

[0119] The device for controlling the overall operation of the information processing device 1 is not limited to the CPU 11, and may be, for example, any one of an MPU, a DSP, an ASIC, a PLD, and an FPGA. The device for controlling the overall operation of the information processing device 1 may also be a combination of two or more of the CPU, MPU, DSP, ASIC, PLD, and FPGA. MPU is an abbreviation for Micro Processing Unit, DSP is an abbreviation for Digital Signal Processor, and ASIC is an abbreviation for Application Specific Integrated Circuit. PLD is an abbreviation for Programmable Logic Device, and FPGA is an abbreviation for Field Programmable Gate Array.

[0120] [B] Effect According to the information processing program, the information processing device, and the information processing method in the above-described embodiments, the following advantageous effects can be achieved, for example.

[0121] The intention expression pattern determination unit 114 accepts an intention of a first person in an online conference selected by a first person from among multiple people participating in the online conference. If the accepted intention expression satisfies a condition, the text generation unit 116 identifies text that meets the condition and encourages the first person to speak. The text transmission unit 117 presents the identified text to a second person, different from the first person, from among the multiple people.

[0122] The information processing device 1 identifies text that prompts the first person to speak based on the timing when the first person expressed their intention, the content of the first person's expression of intention, a combination of the expressions of intention of each participant 101, and the like. This makes it easier for the first person who is prompted to speak to speak compared to when they are uniformly selected. If the first person's expression of intention satisfies the conditions, it is predicted that the first person has some kind of opinion, and therefore it is possible to expect a speech from the first person who is the target of the prompt. Furthermore, the information processing device 1 can prompt a person to speak not because they "were selected because they did not speak much," but in a situation where opinions are divided and a speech is required, or at a timing when it is predicted that they will be able to speak naturally if they are requested to speak. In this way, the information processing device 1 can appropriately prompt people to speak in an online conference. The information processing device 1 can induce participants to speak, thereby revitalizing the online conference.

[0123] The text is text that includes a phrase that urges the first person to speak or information that suggests a phrase. This allows the information processing device 1 to enable the second person to appropriately urge the first person to speak.

[0124] The first person is a person who is identified based on the speech states of each of the multiple people. In this way, the information processing device 1 can identify a person to be encouraged to speak based on the speech states of each participant, thereby making the online conference more lively.

[0125] The first person is a person who speaks relatively little among the multiple people. The second person is a person who speaks relatively much among the multiple people. To activate work performed in a team, it is preferable that the members are able to work as evenly as possible, rather than only the proactive person being active. The information processing device 1 can prompt the first person who speaks less to speak appropriately from the second person who speaks more. In this way, the information processing device 1 can improve the imbalance in the amount of speech among each participant, thereby activating the meeting.

[0126] The condition is based on the relationship between the expression of intention of the first person and the expressions of intention of each of the multiple people other than the first person. This allows the information processing device 1 to prompt the first person to speak by using instruction text whose content corresponds to the relationship between the expressions of intention of the first person and the other participants.

[0127] If the accepted expression of intention satisfies the conditions, the text generation unit 116 identifies the text and the timing for presenting the text. The text transmission unit 117 presents the identified text to the second person at the identified timing. This allows the information processing device 1 to prompt the second person to make an appropriate statement at an appropriate timing.

[0128] [C] Other The disclosed technology is not limited to the above-described embodiment, and various modifications can be made without departing from the spirit of the present embodiment. The configurations and processes of the present embodiment can be selected or combined as needed.

[0129] In the above-described embodiment, an example has been described in which the software shown in Fig. 2 is applied to the online conference system 100, but the present invention is not limited to this. The software shown in Fig. 2 may also be applied to an offline conference system or a hybrid conference system (a conference in which online and offline participants are mixed). In an offline conference or an offline conference, by displaying the intention expression area 110 shown in Fig. 1 on a terminal operated by the participant 101 and acquiring the conference audio stream of the participant 101, it is possible to achieve the same effect as the online conference system 100 described in the above-described embodiment.

[0130] [D] Supplementary Note The following additional notes are provided regarding the above-described embodiments.

[0131] (Appendix 1) Accepting an expression of intent of a first person in an online conference selected by the first person from among a plurality of people participating in the online conference; If the received expression of intention satisfies a condition, identifying the text that complies with the condition and encourages the first person to speak; presenting the identified text to a second person, different from the first person, among the plurality of people; An information processing program that causes a computer to execute a process.

[0132] (Appendix 2) The text is a phrase that prompts the first person to speak or text that includes information that suggests the phrase. An information processing program as described in Appendix 1.

[0133] (Appendix 3) The first person is a person identified based on the speech states of each of the plurality of people. An information processing program according to appendix 1 or 2.

[0134] (Appendix 4) the first person is a person who makes relatively few comments among the plurality of people, The second person is a person who has a relatively large amount of comments among the plurality of people. An information processing program according to appendix 1 or 2.

[0135] (Appendix 5) The condition is based on a relationship between the expression of intention of the first person and the expression of intention of each of the plurality of people other than the first person. An information processing program according to appendix 1 or 2.

[0136] (Appendix 6) the specifying process is a process of specifying the text and a timing for presenting the text when the received expression of intention satisfies a condition; The presenting process is a process of presenting the specified text to the second person at the specified timing. An information processing program according to appendix 1 or 2.

[0137] (Appendix 7) Accepting an expression of intent of a first person in an online conference selected by the first person from among a plurality of people participating in the online conference; If the received expression of intention satisfies a condition, identifying the text that complies with the condition and encourages the first person to speak; presenting the identified text to a second person, different from the first person, among the plurality of people; An information processing device having a processor that executes processing.

[0138] (Appendix 8) The text is a phrase that prompts the first person to speak or text that includes information that suggests the phrase. 8. The information processing device according to claim 7.

[0139] (Appendix 9) The first person is a person identified based on the speech states of each of the plurality of people. 9. The information processing device according to claim 7 or 8.

[0140] (Appendix 10) the first person is a person who makes relatively few comments among the plurality of people, The second person is a person who has a relatively large amount of comments among the plurality of people. 9. The information processing device according to claim 7 or 8.

[0141] (Appendix 11) The condition is based on a relationship between the expression of intention of the first person and the expression of intention of each of the plurality of people other than the first person. 9. The information processing device according to claim 7 or 8.

[0142] (Appendix 12) the specifying process is a process of specifying the text and a timing for presenting the text when the received expression of intention satisfies a condition; The presenting process is a process of presenting the specified text to the second person at the specified timing. 9. The information processing device according to claim 7 or 8.

[0143] (Appendix 13) Accepting an expression of intent of a first person in an online conference selected by the first person from among a plurality of people participating in the online conference; If the received expression of intention satisfies a condition, identifying the text that complies with the condition and encourages the first person to speak; presenting the identified text to a second person, different from the first person, among the plurality of people; An information processing method in which processing is performed by a computer.

[0144] (Appendix 14) The text is a phrase that prompts the first person to speak or text that includes information that suggests the phrase. 14. The information processing method according to claim 13.

[0145] (Appendix 15) The first person is a person identified based on the speech states of each of the plurality of people. 15. The information processing method according to claim 13 or 14.

[0146] (Appendix 16) the first person is a person who makes relatively few comments among the plurality of people, The second person is a person who has a relatively large amount of comments among the plurality of people. 15. The information processing method according to claim 13 or 14.

[0147] (Appendix 17) The condition is based on a relationship between the expression of intention of the first person and the expression of intention of each of the plurality of people other than the first person. 15. The information processing method according to claim 13 or 14.

[0148] (Appendix 18) the specifying process is a process of specifying the text and a timing for presenting the text when the received expression of intention satisfies a condition; The presenting process is a process of presenting the specified text to the second person at the specified timing. 15. The information processing method according to claim 13 or 14. [Explanation of symbols]

[0149] 100: Online conference system 101:Participant 102: Network 103: Expression of Intention Database 10: Online meeting screen 110: Intention display area 111: Intention expression pattern display section 112: Speech section storage unit 113: Speech ratio calculation unit 114: Intention expression pattern determination unit 115: Prompt decision section 116: Text generation unit 117: Text sending section 118: Prompt success / failure determination section 1: Information processing equipment 11: CPU 12: Memory 13: Display control device 131:Display device 14:Storage device 15: Input IF 151: Mouse 152: Keyboard 16: External recording medium processing device 160: Recording media 17: Communication IF

Claims

1. receiving an expression of intent of a first person in an online conference selected by the first person from among a plurality of people participating in the online conference; If the received expression of intention satisfies a condition, identifying the text that complies with the condition and encourages the first person to speak; presenting the identified text to a second person, different from the first person, among the plurality of people; An information processing program that causes a computer to execute a process.

2. The text is a phrase that prompts the first person to speak or text that includes information that suggests the phrase. The information processing program according to claim 1 .

3. The first person is a person identified based on the speech states of each of the plurality of people.

3. The information processing program according to claim 1.

4. the first person is a person who makes relatively few comments among the plurality of people, The second person is a person who has a relatively large amount of comments among the plurality of people.

3. The information processing program according to claim 1.

5. The condition is a condition based on a relationship between the expression of intention of the first person and the expression of intention of each of the plurality of people other than the first person.

3. The information processing program according to claim 1.

6. the specifying process is a process of specifying the text and a timing for presenting the text when the received expression of intention satisfies a condition; The presenting process is a process of presenting the specified text to the second person at the specified timing.

3. The information processing program according to claim 1.

7. receiving an expression of intent of a first person in an online conference selected by the first person from among a plurality of people participating in the online conference; If the received expression of intention satisfies a condition, identifying the text that complies with the condition and encourages the first person to speak; presenting the identified text to a second person, different from the identified first person, among the plurality of people; An information processing device having a processor that executes processing.

8. receiving an expression of intent of a first person in an online conference selected by the first person from among a plurality of people participating in the online conference; If the received expression of intention satisfies a condition, identifying the text that complies with the condition and encourages the first person to speak; presenting the identified text to a second person, different from the identified first person, among the plurality of people; An information processing method in which processing is performed by a computer.

Images