JP2017215943A - Information sharing support system, information sharing support device, information sharing support method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To improve efficiency of information sharing in a conference.SOLUTION: An information sharing support system receives an input of sentences indicating the details of utterance uttered in a conference, the details of description described in electronic mail, electronic file, or chat data, or combinations of these, determines the types of the sentences input through the input, and outputs a list of specific sentences having a type to be set, of the types, on the basis of a result of determination through the determination.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an information sharing support system, an information sharing support device, an information sharing support method, and a program.

  2. Description of the Related Art Heretofore, a method has been known in which a meeting support system reduces the burden of complicated work such as time adjustment in a meeting, and manages progress so that the chair can concentrate on the contents of proceedings properly. In this method, the meeting support system displays the progress of the meeting and controls the display according to the proceedings of the meeting. Specifically, the meeting support system first sets, in advance, scheduled proceeding times required for the proceedings of a plurality of meeting agenda items, and creates a timetable for the entire meeting. Next, the meeting support system displays an index indicating the elapsed time of the meeting subject as needed. Furthermore, the meeting support system detects the end of the proceedings of the meeting proceedings and shifts the index to the next meeting agenda. Then, the meeting support system reallocates the remaining scheduled proceeding time to each remaining meeting agenda when the meeting agenda is finished. In this manner, since the meeting support system automatically adjusts the time so that the meeting is completed within the scheduled meeting time, the load of the time adjustment work is reduced. Therefore, the chairperson can concentrate on the content of the proceedings and appropriately manage the progress of proceedings (for example, Patent Document 1 etc.).

  However, in the conventional method, only time management of each topic in the meeting is performed. On the other hand, there has been a demand for efficiently sharing information such as a meeting by visualizing the contents of the meeting.

  One aspect of the present invention aims to provide an information sharing support system capable of efficiently sharing information such as a meeting.

An information sharing support system having one or more information processing devices and supporting information sharing according to one aspect is:
An input unit for inputting one or a plurality of sentences indicating the contents of an utterance said at a meeting, an electronic mail, an electronic file, or written contents described in chat data, or a combination thereof;
A determination unit that determines the type of the sentence input by the input unit;
And an output unit configured to output, as a list, specific sentences to be set among the types based on the determination result by the determination unit.

  It is possible to streamline information sharing such as meetings.

BRIEF DESCRIPTION OF THE DRAWINGS It is a conceptual diagram explaining an example of the whole structure of the meeting assistance system which concerns on one Embodiment of 1st Embodiment of this invention. It is a block diagram showing an example of the hardware constitutions of the information processor concerning one embodiment of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS It is a functional block diagram explaining an example of a function structure of the meeting assistance system which concerns on one Embodiment of 1st Embodiment of this invention. It is a figure which shows an example of the screen displayed by the meeting assistance system which concerns on one Embodiment of 1st Embodiment of this invention. It is a figure which shows an example of the setting screen for setting an agenda, a goal, etc. in the meeting assistance system which concerns on one Embodiment of 1st Embodiment of this invention. It is a figure which shows the example by which an alert and remaining time are displayed on the screen displayed by the meeting assistance system which concerns on one Embodiment of 1st Embodiment of this invention. It is a flowchart which shows an example of the process which judges the kind of the content of a statement by the meeting assistance system which concerns on one Embodiment of 1st Embodiment of this invention. It is a figure which shows an example of the screen for switching the summary and the whole text by the meeting assistance system which concerns on one Embodiment of 1st Embodiment of this invention. It is a flowchart which shows an example of the process which switches the summary and the whole text by the meeting assistance system which concerns on one Embodiment of 1st Embodiment of this invention. It is a figure which shows an example of the screen which shows the summary displayed by the meeting assistance system which concerns on one Embodiment of 1st Embodiment of this invention. It is a figure which shows an example of a display of the topic produced | generated by the meeting assistance system which concerns on one Embodiment of 1st Embodiment of this invention. It is a flowchart which shows the example of a production | generation of the topic by the meeting assistance system which concerns on one Embodiment of 1st Embodiment of this invention. It is a figure which shows an example of a display of an alert etc. by the meeting assistance system which concerns on one Embodiment of 1st Embodiment of this invention. It is a figure which shows an example to which the specific sentence listed by the meeting assistance system which concerns on one Embodiment of 1st Embodiment of this invention was output. It is a figure which shows the example of a display of the process by the meeting assistance system which concerns on one Embodiment of 1st Embodiment of this invention. It is a figure which shows an example of the communication diagram displayed by the meeting assistance system which concerns on one Embodiment of 1st Embodiment of this invention. It is a figure which shows the example of a display of the log in the communication diagram displayed by the meeting assistance system which concerns on one Embodiment of 1st Embodiment of this invention. It is a functional block diagram explaining an example of a function structure of the meeting assistance system which concerns on one Embodiment of 2nd Embodiment of this invention. It is a figure which shows an example of the summary screen displayed by the meeting assistance system which concerns on one Embodiment of 2nd Embodiment of this invention. It is a figure which shows an example of the evaluation screen displayed by the meeting assistance system which concerns on one Embodiment of 2nd Embodiment of this invention. It is a figure which shows an example of the screen for inputting the subjective evaluation displayed by the meeting assistance system which concerns on one Embodiment of 2nd Embodiment of this invention. It is a flowchart which shows an example of the process which evaluates based on the time when the meeting by the meeting assistance system which concerns on one Embodiment of 2nd Embodiment of this invention was held. It is a conceptual diagram which shows an example of the natural language processing using the machine learning by the meeting assistance system which concerns on one Embodiment of 3rd Embodiment of this invention. It is a conceptual diagram explaining an example of the whole structure of the information sharing assistance system which concerns on one Embodiment of 4th Embodiment of this invention. It is a figure explaining an example of the output by the information sharing assistance system which concerns on one Embodiment of 4th Embodiment of this invention. It is a flowchart which shows the process example by the information sharing assistance system which concerns on one Embodiment of 4th Embodiment of this invention. It is a conceptual diagram explaining an example of the whole structure of the information sharing assistance system which concerns on another embodiment of 4th Embodiment of this invention.

Hereinafter, embodiments of the present invention will be described. In the following description, it is assumed that information sharing is performed in a meeting, and an example in which a meeting support system, which is an example of an information sharing support system, is used for the meeting. Therefore, in the following example, one or a plurality of sentences (hereinafter, simply referred to as "sentences") input to the meeting support system will be described as an example in which only the contents of the speech in the meeting. A sentence is a minimum unit indicating a complete content when expressing a thought or an emotion in words.

First Embodiment
(Example of overall configuration)
FIG. 1 is a conceptual diagram for explaining an example of the entire configuration of a conference support system according to an embodiment of the first embodiment of the present invention. For example, as illustrated, the meeting support system 1 is configured to include a server 10 which is an example of an information sharing support device, and one or more terminals 11. Also, the server 10 and each terminal 11 are connected via the network 12. The server 10 and the terminal 11 are information processing apparatuses such as a PC (Personal Computer), and have, for example, the following hardware configuration.

(Hardware configuration example)
FIG. 2 is a block diagram showing an example of the hardware configuration of the information processing apparatus according to the embodiment of the present invention. For example, the server 10 and the terminal 11 include a central processing unit (CPU) 10H1, an I / F (interface) 10H2, and an output device 10H3. The server 10 and the terminal 11 have an input device 10H4, an HD (Hard Disk) 10H5, and a storage device 10H6. Further, each piece of hardware is connected via a bus 10H7. The server 10 and the plurality of terminals 11 may have the same hardware configuration or different hardware configurations. Hereinafter, the server 10 and the plurality of terminals 11 are assumed to have the same hardware configuration, and the server 10 will be described as an example.

  The CPU 10H1 is an arithmetic device that performs arithmetic processing to realize various processes and processing of various data, and a control device that controls each hardware and the like. The server 10 may have a plurality of arithmetic devices or control devices.

  The I / F 10H2 is, for example, a connector and a processing IC (Integrated Circuit). For example, the I / F 10H2 transmits and receives data to and from an external device via a network or the like.

  The output device 10H3 is a display or the like that displays a display screen, a graphical user interface (GUI), and the like.

  The input device 10H4 is a touch panel for inputting an operation or the like by the user, a keyboard, a mouse, a microphone, a combination thereof, or the like. It is more preferable that the microphone be a so-called directional microphone in which the direction of the sound source can be known.

  The HD 10H5 is an example of an auxiliary storage device. That is, the HD 10H 5 stores data such as programs, files, and various settings used for processing.

  The storage device 10H6 is a so-called memory or the like. That is, a program or data stored in the HD 10H5 is read out to the storage device 10H6.

(Example of functional configuration)
FIG. 3 is a functional block diagram for explaining an example of a functional configuration of a conference support system according to an embodiment of the first embodiment of the present invention. For example, the meeting support system 1 includes an input unit 1F1, a control unit 1F2, a storage unit 1F3, and an output unit 1F4.

  For example, in the meeting support system 1, the input unit 1F1 and the output unit 1F4 are respectively included in the terminal 11 (FIG. 1). The control unit 1F2 and the storage unit 1F3 are included in the server 10 (FIG. 1). Note that each unit illustrated may be included in either the terminal 11 or the server 10.

  The input unit 1F1 inputs the content of the utterance made in the conference. For example, the input unit 1F1 is realized by the input device 10H4 (FIG. 2) or the like.

  The control unit 1F2 performs control to realize each process. Specifically, control unit 1F2 includes determination unit 1F21. Further, as illustrated, the control unit 1F2 may include a decoration unit 1F22, a time management unit 1F23, and a speaker determination unit 1F24. For example, the control unit 1F2 is realized by the CPU 10H1 (FIG. 2) or the like.

  The storage unit 1F3 stores data and the like input in advance. The storage unit 1F3 implements a database and the like. In addition, the storage unit 1F3 stores the contents of the statement. For example, the storage unit 1F3 is realized by the HD 10H5 (FIG. 2), the storage device 10H6 (FIG. 2), and the like.

  The output unit 1F4 displays or prints the contents of the meeting, and outputs the contents of the meeting such as the minutes, the evaluation result, the summary, the contents of the utterance, the judgment result, or the combination thereof to the participants of the meeting. For example, the output unit 1F4 is realized by the output device 10H3 (FIG. 2) or the like.

  First, in the meeting support system 1, a person who made a speech content during a meeting (hereinafter referred to as a "speaker"), a person in charge of the minutes, or the like inputs the speech content made into the conference through the input unit 1F1. Specifically, the statement content is input in a text format, for example, by a keyboard or the like. Note that the content of the statement may be the content that the participant verbally described later is input using a keyboard or the like. In addition, in the case of using a keyboard to enter the content that the participant wants to speak in an online meeting or the like between remote locations using chat or the like, the content of the speech may be the content input in the chat or the like. That is, the content of the speech is not limited to the content spoken orally. That is, the content of the statement may not be verbally described, but may be content input using a keyboard or the like.

  Besides, the contents of the statement may be input by voice by a microphone or the like. That is, when the content of speech is input by voice, the conference support system 1 may perform speech recognition of the input voice to generate text data and the like.

  Furthermore, the statement content may be input by handwriting, for example, by an electronic blackboard or a tablet terminal. That is, the conference support system 1 may convert and input characters written in handwriting on an electronic blackboard or the like into text data or the like by means of optical character recognition (OCR).

  The contents of the statement are an example of a sentence, and other contents described in the e-mail are input to the meeting support system in the information sharing by the e-mail etc. May be In this case, the description content is input, for example, by text data or the like in which the content of the electronic mail is described. The sentence is not limited to the input by text data, and may be input by other document data or the like.

  Besides, for example, data indicating a daily report or a report may be input to the input unit 1F1. For example, the data such as the daily report input to the input unit 1F1 is text data indicating the content of the daily report, data created on a Web application, data generated by reading a handwritten document by OCR (etc.), and the like.

  When the speaker determination section 1F24 identifies from the participant who the speaker is, the speaker determination section 1F24 has a voice generation source using a plurality of directional microphones or the like. The speaker may be identified from the participants by linking the direction in which it can be determined with the speaker. Alternatively, the speaker determination unit 1F24 may perform voice authentication on input voice data, and specify the speaker based on the authentication result. In addition, the speaker determination unit 1F24 identifies the speaker by photographing the speaker with a camera or the like connected to the network 12 (FIG. 1) and performing face authentication using the photographed image. May be

  Moreover, the information which can specify who is the speech content may be input by the input unit 1F1 or the like. Specifically, for example, first, speaker information is assigned in advance to a plurality of function keys (“F1” to “F12”) of the keyboard. Then, when the content of the statement is input, when the function key is pressed at the time of the input, the speaker support information may be added to the content of the statement by the conference support system 1. In this way, the contents of the statement and the speaker may be linked.

  In the information sharing by electronic mail, the speaker information is added based on the data of the sender and the receiver contained in the header of the electronic mail.

  Next, the meeting support system 1 determines the type of the input speech by the determination unit 1F21. Specifically, types of remarks are, for example, "suggestion", "question", "answer", "positive opinion", "negative opinion", "neutral opinion", "information", "request", These include "tasks", "action items" (hereinafter sometimes referred to as "AI"), and "decisions". Hereinafter, the case where the contents of the message are classified into such types of messages will be described as an example.

  First, in the meeting support system 1, in order to determine the type of utterance, an expression defined in advance for each type of utterance is stored in the storage unit 1F3. Further, the expression is a sentence, a phrase, an expression or the like, and the storage unit 1F3 stores the type of the utterance and the expression specific to the type of the utterance. Then, when the speech content is input by the input unit 1F1, the determination unit 1F21 determines whether the speech content includes an expression stored in the storage unit 1F3. Subsequently, when the utterance content includes the expression stored in the storage unit 1F3, the determination unit 1F21 identifies a corresponding type from among the utterance types. In this way, the meeting support system 1 can determine the type of the utterance content of the utterance content in the conference.

  Further, the output unit 1F4 outputs a list of meeting contents and the like in a list. In addition, the output unit 1F4 may decorate and display the content of the statement based on the type of the statement determined by the determination unit 1F21. Details such as the listing will be described later.

(Example of input and output)
In the conference support system, for example, each terminal displays the following screen and performs each process.

  FIG. 4 is a view showing an example of a screen displayed by the conference support system according to the first embodiment of the present invention. For example, the screen displayed on the screen of each terminal has a display, a graphical user interface (GUI) as illustrated, and the like. Hereinafter, the illustrated screen will be described as an example.

  In this example, the output unit displays an agenda 301 and the purpose of the conference, that is, the goal 302. In addition, when the agenda 301 and the goal 302 are displayed during the meeting, it is possible to match the vectors of recognition and discussion of the participants. Therefore, the meeting support system can reduce derailment of the meeting and the like. Further, the agenda 301 and the goal 302 are set in advance, for example, before the meeting is held or at the beginning of the meeting as follows.

  FIG. 5 is a view showing an example of a setting screen for setting an agenda, a goal, and the like in the conference support system according to the embodiment of the first embodiment of the present invention. For example, a setting screen as illustrated is displayed by the meeting support system at the beginning of the meeting. In addition, after each setting shown below is performed by the setting screen, if the start button 505 is pressed down, a setting will be completed. That is, after the start button 505 is pressed, the screen shown in FIG. 4 or the like is displayed by the conference support system.

  As illustrated, the participant inputs an agenda in the agenda setting text box 501. Furthermore, each goal is set by the participant for each agenda input in the agenda setting text box 501. The goal is input to, for example, a goal setting text box 502. As described above, the agenda and goals input to the agenda setting text box 501 and the goal setting text box 502 are displayed as the agenda 301 and the goal 302 by the conference support system, as shown in FIG. 4.

  In addition, prior to holding a meeting, a notice may be prepared in advance. In such a case, the agenda and the goals described in the holding notification may be displayed as an agenda 301 and a goal 302 by the conference support system, as shown in FIG. 4. As described above, when participants in a meeting are notified in advance of a notice of holding etc., the participants can prepare in advance, so that the meeting can be made more efficient. In addition, when notification of holding or the like is notified in advance to the participants of the meeting, the participants can determine whether or not to participate, so it is possible to avoid unnecessary participation in the meeting.

  Referring back to FIG. 4, on the screen, the current time 306, the time allocation 307, the progress 308, and the like are displayed by the meeting support system. The current time 306 is displayed based on data set in advance or data indicating the time acquired via a network or the like. Furthermore, the time allocation 307 is displayed based on the scheduled time for each agenda set in advance. For example, each scheduled time for each subject is input in the scheduled time setting text box 503 shown in FIG. Further, the progress status 308 is displayed by a display indicating the percentage of the elapsed time or the like as shown in the figure based on the time elapsed from the conference start time to the current time 306, a so-called progress bar or the like.

  Also, the following display may be performed by the time management unit 1F23 (FIG. 3) and the output unit 1F4 (FIG. 3). For example, the meeting support system may display the remaining time or display an alert prompting a meeting summary when the scheduled end time of the entire meeting or each subject approaches. For example, in the example using the screen shown in FIG. 4, the following display is performed by the conference support system.

  FIG. 6 is a view showing an example in which an alert and remaining time are displayed on a screen displayed by the conference support system according to the embodiment of the first embodiment of the present invention. As shown, the remaining time 401 and the alert 402 may be displayed by the conference support system. In the illustrated example, the remaining time 401 is an example of a display indicating that the time from the current time to the scheduled end time of the entire conference has become “10 minutes or less”. Also, the alert 402 is an example of a display for notifying the participants to summarize the conclusion of the conference, etc., because the remaining time of the conference has decreased. When such a display is given, it is easy for the participants to secure time to organize the discussion. As a result, the meeting support system is less likely to become obsessed with discussions and become overdue, and to be less vague about the conclusions or action items of the meeting.

  Note that the alert and the remaining time are not limited to being output in the illustrated form. For example, the output may use voice or the like.

  Referring back to FIG. 4, the message content 303 is displayed on the screen. In addition, decoration is performed to the statement content 303 based on the determination result by the determination unit 1F 21 (FIG. 3). For example, as shown in the figure, in each comment content, "Q:", "A:", "Proposal:", "Opinion (P):", "Opinion (N):", "Information:", " The display indicating the type of each statement is added to the beginning or end of the sentence, and the like, and the content of the statement is displayed, such as the agenda: "" and "A. I. candidate:". In addition, the decoration should just be able to distinguish the type of each statement. For example, the decoration is color-coding, character decoration such as italics and bold, font type, addition of characters at the end or end of the sentence, or a combination thereof. Note that how to decorate can be set in advance in the conference support system. Specifically, for example, the statement contents judged to be “positive opinion” are displayed in blue and set so that the display of “opinion (P)” is added to the beginning of the sentence. In addition, remarks that are judged as "negative opinion" and "task" are displayed in red, and the display of "opinion (N)" and "task" is added to each sentence head It is set. In this manner, when the type of speech is indicated by decoration, the participant can intuitively grasp the important parts in the meeting, the contents of the discussion, the tendency of the meeting, and the like. The decoration may be processed by the server 10 (FIG. 1) or may be processed by a browser installed on the terminal 11 (FIG. 1).

  Further, when a speaker is identified, the speaker may be displayed by the conference support system as illustrated. In the illustrated example, the speaker's name is displayed in parentheses. The speaker may be displayed in a format other than that illustrated. Also, a person who is a candidate of a speaker, that is, a participant is set in advance in the participant setting text box 504, for example, on the setting screen shown in FIG. Further, as shown in FIG. 4, the participant set in the participant setting text box 504 is displayed as shown by the participant display 305 by the conference support system.

  The illustrated example is an example in which function keys are set to be associated with each participant displayed in the participant display 305. For example, in the illustrated example, when “Sato”, one of the participants, makes a statement, the function content “F2” is input when the content of the statement made by “Sato” is input to the content input text box 304. When is pressed, the input statement content is linked with "Sato" which is speaker information. That is, in the example shown in the figure, when the function key "F2" is pressed when inputting the speech content in the speech content input text box 304, the conference support system adds "(Sato)" to the inputted speech content. To display.

  Also, the type of message is determined, for example, by the following process. Hereinafter, an example in which the type of the utterance is “Question”, “Answer”, “Proposal”, “Issue” and “Opinion” will be described.

  FIG. 7 is a flowchart showing an example of a process of determining the type of speech contents by the conference support system according to the first embodiment of the present invention. In addition to the statement content, when the description content is input, the description content is processed in the same manner.

  In step S01, the meeting support system initializes a question flag. Specifically, the meeting support system sets the question flag to “FALSE”. The question flag is an example of data indicating whether or not the type of the statement of the statement content inputted immediately before is “a question”. Hereinafter, when the question flag is “FALSE”, it is assumed that the type of the statement of the statement content inputted immediately before is the type of the statement other than “a question”. On the other hand, when the question flag is "TRUE", it is assumed that the type of the statement of the statement content inputted immediately before is the type of the statement of "a question".

  In step S02, the meeting support system inputs the contents of the statement. Specifically, the meeting support system inputs the contents of the statement by the input unit 1F1 (FIG. 3). That is, in the example shown in FIG. 4, the content of the statement is input as text or the like in the statement content input text box 304.

  In step S03, the meeting support system determines whether the question flag is "TRUE". Next, if the question flag is "TRUE" (YES in step S03), the conference support system proceeds to step S04. On the other hand, when the question flag is not "TRUE", that is, "FALSE" (NO in step S03), the conference support system proceeds to step S05.

  In step S04, the meeting support system determines that the type of the statement of the statement content is "answer". The “answer” is the content of the statement returned to the content of the statement corresponding to the type of the statement of the “question”. Therefore, "answer" is allowed free expression. That is, in some cases, an expression that can be determined as an "answer" can not be set in advance for the "answer". Therefore, as in step S03 shown in the figure, the meeting support system determines whether or not the content of the immediately preceding message is a "question", that is, whether or not the type of the message of the content is "answer" by the question flag. To judge. That is, when the content of the immediately preceding message is a "question", the conference support system determines that the type of the message of the next content of the message is "answer". On the other hand, when the content of the immediately preceding utterance is other than the “question”, the conference support system determines that the type of the next utterance content is other than “answer”. In this manner, the meeting support system classifies the contents of the "answer". In step S04, the meeting support system sets the question flag to "FALSE".

  In step S05, the meeting support system determines whether the content of the statement includes the expression of "question". For example, the conference support system determines the type of the utterance content by the auxiliary verb part of the utterance content and the like. Specifically, first, expressions such as, for example, "?", "? ~?" Or "? ~?" Are stored in advance in the storage unit 1F3 (Fig. 3). Next, the conference support system determines whether all or a part of the contents of the utterance input by the input unit 1F1 (FIG. 3) matches the stored expression by the determination unit 1F21 (FIG. 3) . That is, the determination is realized by so-called pattern matching or the like.

  Next, when it is determined in step S05 that the message content includes the expression of “a question” (YES in step S05), the conference support system proceeds to step S06. On the other hand, if it is determined in step S05 that the message content does not include the expression of "question" (NO in step S05), the conference support system proceeds to step S08.

  In step S06, the meeting support system determines that the type of the statement of the statement content is "a question".

  In step S07, the meeting support system sets “TRUE” in the question flag.

  In step S08, it is determined whether the content of the statement includes an expression of "proposal". For example, the conference support system determines the type of the utterance content according to the auxiliary verb part of the utterance content and the like, as in the case of the “question”. Specifically, first, for example, expressions such as “To be done” or “It is better to do” are stored in advance in the storage unit 1F3 (FIG. 3). Next, the conference support system determines whether all or a part of the contents of the utterance input by the input unit 1F1 (FIG. 3) matches the stored expression by the determination unit 1F21 (FIG. 3) .

  Next, when it is determined in step S08 that the message content includes the expression of “proposal” (YES in step S08), the conference support system proceeds to step S09. On the other hand, if it is determined in step S08 that the content of the statement does not include the expression of "proposal" (NO in step S08), the conference support system proceeds to step S10.

  In step S09, the meeting support system determines that the type of the statement of the statement content is "suggestion".

  In step S10, it is determined whether the content of the statement includes the expression of "task". For example, the conference support system determines the type of the utterance content according to the auxiliary verb part of the utterance content and the like, as in the case of the “question”. Specifically, first, for example, expressions such as “must do” or “must do” are stored in advance in the storage unit 1F3 (FIG. 3). Next, the conference support system determines whether all or a part of the contents of the utterance input by the input unit 1F1 (FIG. 3) matches the stored expression by the determination unit 1F21 (FIG. 3) .

  Next, when it is determined in step S10 that the message content includes the expression of “task” (YES in step S10), the conference support system proceeds to step S11. On the other hand, when it is determined in step S10 that the message content does not include the expression of "task" (NO in step S10), the conference support system proceeds to step S12.

  In step S11, the meeting support system determines that the type of the utterance content is “task”.

  In step S12, the meeting support system determines that the type of the statement of the statement content is "opinion".

  As described above, steps S02 to S12 are repeated for each message content. By performing such processing, the meeting support system can determine the type of the statement of the statement content.

  The meeting support system may also display the summary. For example, when the operation is performed as follows, the conference support system switches the summary and the full text.

  FIG. 8 is a view showing an example of a screen for switching abstracts and full texts by the conference support system according to the embodiment of the first embodiment of the present invention. The illustrated screen is an example of a screen displayed during a meeting. When the summary instruction button BN1 displayed as “important sentence extraction display” illustrated is pressed, the conference support system switches the screen to display the summary.

  FIG. 9 is a flowchart showing an example of a process of switching abstracts and full texts by the conference support system according to the first embodiment of the present invention. The conference support system performs processing as illustrated to generate a summary. The following types of remarks are: "Suggestion", "Question", "Answer", "Positive Opinion", "Negative Opinion", "Neutral Opinion", "Information", "Request", "Issue", " The action items are "decision items" and the like.

  In step S21, the meeting support system initializes a summary flag. Specifically, the meeting support system sets the summary flag to “FALSE”. The summary flag is a flag that switches whether to extract an important part of the input statement content and display a summary or to display a full text indicating all statement content. Hereinafter, when the summary flag is “FALSE”, it is assumed that the conference support system is set to display the full text. On the other hand, when the summary flag is "TRUE", the conference support system is set to display a summary.

  In step S22, the conference support system accepts that the summary instruction button BN1 (FIG. 8) is pressed. Every time the summary instruction button BN1 is pressed, the full text and the summary are switched.

  In step S23, the meeting support system determines whether the summary flag is "TRUE". Next, when it is determined that the summary flag is “TRUE” (YES in step S23), the conference support system proceeds to step S24. On the other hand, when it is determined that the summary flag is not "TRUE", that is, "FALSE" (NO in step S23), the conference assistance system proceeds to step S26.

  In step S24, the meeting support system displays the full text. Specifically, for example, the screen shown in FIG. 8 is displayed by the meeting support system. That is, in the full text, the conference support system displays all types of the statement content among the statement content input.

  In step S25, the conference assistance system sets the summary flag to "FALSE".

  In step S26, the meeting support system displays a summary. Specifically, for example, a screen as shown below is displayed by the conference support system.

  FIG. 10 is a view showing an example of a screen showing a summary displayed by the conference support system according to the embodiment of the first embodiment of the present invention. Compared with the screen shown in FIG. 8, the screen shown in FIG. 10 is different in that the summary display ABS is displayed.

  The summary is the result of extracting important comment content out of the input statement contents. Whether or not an utterance content is an important utterance content is determined based on whether or not it is a type of important utterance content set in advance. For example, the summary is a result of extraction of the utterance content of the type of utterance judged as “proposal”, “task”, and “action item” among all types of input utterance content. That is, the summary is a minutes which is generated by the conference support system extracting an utterance content of a predetermined utterance type among the input utterance contents. Note that the illustrated example is an example in which the contents of the type of the speech judged as the “task” and the “action item” are extracted from the full text shown in FIG. 8 by the conference support system, and the summary is generated. As shown in the figure, the conference support system displays the utterance content of the target utterance type, and hides the utterance content of other utterance types. That is, when the abstract shown in FIG. 10 is displayed, the participant can easily make an action item. Thus, when the summary is displayed, participants can review the points of the conference. Therefore, the meeting support system can cause participants to arrange tasks, action items, decisions, and the like without omission. Thus, the meeting support system can streamline the meeting.

  Returning to FIG. 9, in step S27, the conference support system sets the summary flag to "TRUE".

  As described above, steps S22 to S27 are repeatedly performed by the meeting support system. By performing such processing, the meeting support system can switch and display the full text and the summary.

  In addition, the meeting support system may generate topics such as the contents of an utterance. The topic is a word indicating the subject, topic or topic of a plurality of sentences. For example, the meeting support system displays the topic generated as follows.

  FIG. 11 is a view showing an example of display of a topic generated by the conference support system according to the embodiment of the first embodiment of the present invention. In the illustrated example, the meeting support system generates topics 1101 and arranges and displays corresponding utterance content 1102 for each topic 1101.

  The contents of a statement etc. in a meeting are often composed of a plurality of topics 1101. Note that the content of the speech in the meeting may be the same as the topic 1101 or the topic 1101.

  As shown in the figure, the speech contents 1102 are grouped by topic 1101. And, the speech contents 1102 grouped by topic are decorated according to the type of each speech contents 1102. Further, in the example shown in the figure, among the utterance contents 1102, the utterance contents 1102 of "positive opinion" are disposed on the left side, while the utterance contents 1102 of "negative opinion" and "task" are disposed on the right side. It is an example. As described above, when a sentence is placed depending on the type of sentence, the conference support system can display the contents of the discussion intuitively and easily by the user.

  In addition, when the speech content 1102 is a long speech content, the conference support system may make the sentence of the speech content 1102 shorter. For example, the meeting support system performs so-called sentence compression and the like. That is, the conference support system may convert each utterance content into a simple form by sentence compression or the like.

  Specifically, the conference support system first parses the speech content by a syntactic analysis tool or the like. And, the syntactic analysis divides the speech contents into a plurality of elements. Next, the meeting support system assigns each element a degree of importance. Subsequently, the meeting support system deletes elements of low importance based on the importance. In this way, the conference support system can reduce the elements of the sentence and shorten the contents of the statement without destroying the structure of the sentence.

  Also, the importance is determined, for example, as follows.

  ・ Nouns, proper nouns, nominative cases or purpose cases have high importance.

  -An element, an adverb or an adjective modification clause that includes an "etc." or a particle of "Y", which shows an example, has a low degree of importance.

  Therefore, the conference support system compresses the sentence by deleting the adjunctive modification clause, the embedded sentence, the dependent clause, and the like, and shortens the utterance content. In addition, sentence compression is, for example, the method disclosed in "Basics of Natural Language Processing", by Okumura Manabu, Corona Press.

  In this way, when the topic is displayed by the meeting support system, the user can easily review the meeting. That is, the user can efficiently perform information sharing such as a meeting by displaying the “task”, the “action item” and the “decision item” associated with each topic by the meeting support system.

  Note that the conference system is not limited to being used at the end of the conference. For example, after the meeting is over, minutes may be input and used. Also, the distance between topics may be, for example, "http://ryotakatoh.hatenablog.com/entry/2015/10/29/015502" and "http://tech-sketch.jp/2015/09/topic-model It is desirable to be generated to reduce leakage and duplication, such as by the methods disclosed in ".html".

  The topic 1101 is generated, for example, as follows.

  FIG. 12 is a flowchart showing an example of topic generation by the conference support system according to the embodiment of the first embodiment of the present invention. For example, when a process as illustrated is performed, a screen as illustrated in FIG. 11 can be displayed by the meeting support system.

  In step S31, the meeting support system inputs a sentence. For example, after the meeting in which the meeting support system is used is performed, the meeting support system is in a state in which the content of the speech spoken in the meeting is input.

  In step S32, the meeting support system estimates topic boundaries. Specifically, since the topic is generated for each group of the contents of the speech, the meeting support system first divides the contents of the speech into groups. Therefore, the meeting support system estimates topic boundaries which are divisions into groups. For example, the meeting support system estimates the topic boundaries such that the utterance content that is common content or the utterance content that can be estimated to be highly relevant utterance content is in the same group.

  The topic boundaries are estimated, for example, by the following four methods.

  First, a first estimation method is an estimation method of estimating a topic boundary as "a keyword that can be estimated that a topic is transitioning is detected". Specifically, the keywords that can be estimated that the topic is transitioning are “if you say so” and “by the way”. Further, such a keyword is, for example, a sentence set by the user or the like in the conference support system in advance before the conference or the like.

  Further, a second estimation method is an estimation method of estimating a topic boundary as "a word indicating a change in dialogue initiative is detected". Specifically, the second estimation method is an estimation method of estimating a topic boundary when a word such as "preceding", "preceding", or "preceding" appears. Further, such a word is, for example, a sentence set by the user or the like in the conference support system in advance before the conference or the like.

  The first and second estimation methods may be, for example, “topic transition detection in information search chat”, “http://www.cl.cs.titech.ac.jp/_media/publication/632.pdf” It is the method etc. which are disclosed.

  Furthermore, the third estimation method is an estimation method of estimating a topic boundary when a sentence of type "question" appears. That is, if there is a sentence judged to be a "question", the meeting support system estimates it as a topic boundary.

  Furthermore, the fourth estimation method is an estimation method of estimating topic boundaries using “lexical cohesion”. In the fourth estimation method, for example, “lexical cohesion” is calculated using a thesaurus or the like. Specifically, a chain consisting of a set of sentences in a "lexical cohesion" relationship, a so-called "lexical chain" is first detected. Then, in the fourth estimation method, it is assumed that “lexical cohesion” indicates that the sentence has a meaningful grouping, and it is estimated that the start and end points of the “lexical chain” are the topic boundaries. is there. For example, the fourth estimation method is “text segmentation based on lexical cohesion”, “https://ipsj.ixsq.nii.ac.jp/ej/index.php?action=pages_view_main&active_action=repository_action_common_download&item_id=49265&item_no= 1 & attribute_id = 1 & file_no = 1 & page_id = 13 & block_id = 8 "and" Basics of Natural Language Processing ", by Okumura Manabu, and the method disclosed in Corona, Inc., etc.

  In step S33, the meeting support system generates a topic. That is, in step S33, the meeting support system generates each topic for each topic boundary estimated in step S32. Therefore, step S33 is repeated for the number of groups divided by topic boundaries.

  The topic is estimated, for example, by the following three methods.

  The first generation method is a generation method of extracting a so-called unknown word, a sentence not registered in a proper noun or a dictionary, out of sentences grouped by topic boundaries, and setting it as a topic.

  In the second generation method, first, nouns, verbs or adjectives are extracted from the sentences grouped by the topic boundaries. Next, in the second generation method, utilization of the extracted sentence is returned to the original form. Then, sentences that appear many times are considered as topics. Thus, the meeting support system can display topics and the like.

  Besides, in the third generation method, the topic may be, for example, an important word included in a group separated by topic boundaries. For example, the important words can be identified by the TF-IDF (Term Frequency-Inverse Document Frequency) method or the like.

  Then, the conference support system lists and outputs types of sentences (hereinafter referred to as “specific sentences”), which are set in advance, out of the contents of the speech. First, it is assumed that the meeting support system is used to hold a meeting. Next, in the conference system, when there is a specific sentence classified in advance as “problem”, “action item” or “decision item”, the following processing is set as an example.

  FIG. 13 is a view showing an example of display of an alert or the like by the conference support system according to the embodiment of the first embodiment of the present invention. First, it is assumed that a meeting is held using the meeting support system, and the contents of a statement or the like which is the type of the “task” is made at the meeting. That is, an example in which a specific sentence classified as "problem" is input will be described below. Then, for example, when the conference ends, the conference system outputs a screen as illustrated. When the described content of the e-mail is input to the conference support system, the conference system outputs a screen as illustrated when e-mail is received.

  Specifically, as illustrated, the meeting support system displays an alert 1201. In the example illustrated, the alert 1201 indicates a message for displaying the content of the statement that becomes the “task” among the statement content that has been said at the conference. That is, with the alert 1201, it is possible to specify, from among the speech contents, the speech contents tagged to the “task”, that is, a specific sentence.

  The alert 1201 may be a link that, when pressed, displays the minutes and the like corresponding to the content of the displayed utterance. When the user presses the alert 1201 serving as the link, the minutes and the like are displayed, so that it is possible to know the background of the contents of the message displayed in the alert 1201 or the process leading to the determination. In this way, for example, when the manager is a user, the manager can quickly grasp a newly generated “problem” or the like before the periodic report or the like is sent. Therefore, the manager can detect the problem early and follow the problem promptly.

  Next, in the illustrated example, when the list button 1202 is pressed, the conference support system lists and outputs, for example, sentences of the type of “task”, “action item” or “decision item” as follows. .

  FIG. 14 is a diagram showing an example in which the listed specific sentences are output by the conference support system according to the embodiment of the first embodiment of the present invention. In the illustrated example, the meeting support system is an example of extracting the speech contents of the types to be the “task” and the “action item” from the speech contents etc., that is, the specific sentences and displaying them as a list 1301. For example, the screen shown in FIG. 14 is a screen displayed by the conference support system when the list button 1202 is pressed on the screen shown in FIG.

  As shown in the figure, in the list 1301, among the utterance contents spoken in the conference, the utterance contents of types such as “task”, “action item” and “decision item” are listed in order and displayed. In addition, the types of sentences to be listed, such as “task”, “action item” and “decision item” in this example, are set in advance in the meeting support system.

  As described above, when each specific sentence is listed and displayed, for example, when the user is a manager, the manager can centrally manage tasks etc. related to his / her department by looking at the list 1301. .

  Also, as shown, a link 1302 may be provided for the list 1301. Specifically, when the link 1302 is pressed, for example, details such as a scene where the “task”, the “action item” and the “decision item” indicated by the list 1301 occur, that is, the minutes of the specific sentence are displayed. Ru. By this, the user can grasp details such as the background and the background in which the “task”, the “action item” and the “decision item” are determined.

  The sentence displayed as the list 1301 may be, for example, a result limited to sentences related to the own department. For example, in the case where the participant includes a person who belongs to the own department among the minutes and the like to be input, the conference support system determines that the sentence described in the meeting is related to the own department. Further, in the electronic mail, when the sender or receiver of the electronic mail includes a person who belongs to the own department, the conference support system determines that the text described in the electronic mail is related to the own department. Furthermore, when sending an e-mail, it is assumed that the conference support system can be set to one of the destinations, and when it becomes the e-mail destination, the conference support system sends the text described in the sent e-mail to its own department. I judge that it is related.

  In addition, the meeting support system may display the history of the meeting and the e-mail as follows.

  FIG. 15 is a view showing a display example of the process of the conference support system according to the first embodiment of the present invention. The screen illustrated is an example of a screen displayed when the button 1303 is pressed in the screen illustrated in FIG. 14, for example. The user performs an operation of pressing the corresponding button 1303 when there is an utterance content that the user wants to refer to the process among the utterance content listed.

  When the button 1303 is pressed, the conference support system extracts the statement contents related to the listed statement contents and arranges and displays them in chronological order. The extraction may be, for example, for each topic. Further, as shown in the figure, “action item” and “decision item” etc. related to the extracted statement content etc. may be displayed. It is assumed that items to be displayed such as “action item” and “decision item” shown in the figure are set in advance in the conference support system.

  It is specified at which position in time-series order the message content 1501 is displayed according to the date and time etc. described in the minutes. In addition, it is specified at which position in chronological order the description 1502 etc. described in the e-mail etc. is displayed according to the transmission date and time etc. inputted in the header etc. of the SMTP.

  As described above, when the statements 1501 and 1502 are displayed in chronological order, the user can grasp the details of the past decision making and the like. For example, it is possible to easily take over when a new manager is assigned by relocation or the like, or to easily look back or analyze causes when a problem occurs.

  Furthermore, the meeting support system may display a screen visualizing communication as follows. Hereinafter, a diagram that visualizes communication is called a "communication diagram."

  FIG. 16 is a view showing an example of a communication diagram displayed by the conference support system according to the embodiment of the first embodiment of the present invention. The illustrated communication diagram is an example in which the amount of communication between each user is represented by the thickness of a line connecting each user. The communication diagram is a diagram displayed by the conference support system, for example, when the visualization button 1203 is pressed on the screen shown in FIG.

  First, the meeting support system extracts participants and the meeting time from the input minutes and the like. Then, the meeting support system calculates the strength of communication between the respective users (hereinafter referred to as “communication strength”) based on the participants and the meeting time and the like.

  For example, the communication strength is a value calculated by summing up the meeting times of the meetings in which the respective users participated together. Alternatively, the meeting support system may calculate the communication strength by weighting the meeting time based on, for example, the number of participants. Specifically, in a meeting with a small number of participants, for example, in a one-to-one meeting in which two participants are involved, close communication is likely to be taken. Therefore, the meeting support system calculates the communication strength by multiplying the meeting time of the meeting with a small number of participants by the weighting factor which becomes a large value. In this way, it is calculated that the communication strength is strong among users who have a long meeting time of the meeting with a small number of participants.

  In the case of e-mail, the communication strength is calculated based on the number of times e-mails are transmitted and received, and the weighting of "destination" or "CC (Carbon Copy, broadcast)". .

  Then, the meeting support system changes the thickness of the line connecting each user based on the calculated communication strength. For example, in the illustrated example, when the communication strength between “user B” and “user A” is strong, as illustrated, “user B” UB and “user A” UA are , It is tied by thick line LN1.

  On the other hand, when the communication strength between the “user D” UD and the “user E” UE is weaker as compared with the “user B” UB and the “user A” UA, as illustrated, The “user D” UD and the “user E” UE are connected by a line LN2 thinner than the thick line LN1. That is, like the thick line LN1 and the thin line LN2, the conference support system changes the thickness of the line connecting the users based on the communication strength.

  In this way, the meeting support system can visualize the density of communication between users. Also, with such a communication diagram, the user can grasp the strength of the connection between users at work. This allows the user to understand who is the key user of the organization and to understand important users connecting departments.

  In the communication diagram, as illustrated, the conference support system may use a plurality of users as a “team”, such as “team A” TA and “team B” TB. As in the illustrated example, the meeting support system may connect and display lines between users and teams and between teams and teams based on communication strength, such as between each user.

  In addition, in the communication diagram, when a line is pressed, the conference support system may display the following screen or the like.

  FIG. 17 is a diagram showing a display example of a log in a communication diagram displayed by the conference support system according to the embodiment of the first embodiment of the present invention. For example, when the thick line LN1 or the thin line LN2 in FIG. 16 is pressed, the conference support system records a communication, such as minutes, performed between users, as shown in FIG. The "log 1601" is displayed. For example, as illustrated, the log 1601 shows a list of minutes of a meeting in which each user connected by a line is present. Further, when the link indicated by the log 1601 is pressed, the conference support system displays details of the minutes, etc., as in the case where the link 1302 shown in FIG. 14 is pressed.

  Thus, when the details of each communication are displayed by the log 1601 or the like, the user can grasp the contents of each communication. Specifically, the log 1601 or the like allows the user to understand what kind of report is being made or what kind of decision is being made by the user who is the window with other departments.

Second Embodiment
The second embodiment is, for example, an embodiment realized by the same overall configuration and hardware configuration as the first embodiment. Therefore, the description of the overall configuration and the hardware configuration is omitted, and different points will be mainly described below. The second embodiment is different in functional configuration from the first embodiment.

  FIG. 18 is a functional block diagram for explaining an example of a functional configuration of a conference support system according to an embodiment of the second embodiment of the present invention. Compared with FIG. 3, the functional configuration shown in FIG. 18 is different in that the control unit 1F2 includes a cost calculation unit 1F31 and an evaluation unit 1F32.

  The cost calculator 1F31 calculates the cost generated by the conference held on the basis of the labor cost of the participant.

  The evaluation unit 1F32 evaluates the conference based on the time when the conference was held, the number of utterance contents, the type of utterance, the ratio of the type of utterance, and the like.

  The cost calculation by the cost calculation unit 1F31 and the evaluation by the evaluation unit 1F32 may be performed, for example, when the summary button 309, which is a button of "to a screen for summary / storage" shown in FIG. It is performed when 402 is displayed. For example, the conference system displays the following summary screen.

  FIG. 19 is a diagram showing an example of a summary screen displayed by the conference support system according to the second embodiment of the present invention. In the illustrated example of the screen, the agenda display 801 displays the agenda set by the agenda setting text box 501 (FIG. 5) or the like at the beginning of the held notification or the conference by the conference support system. Furthermore, in the example of the screen illustrated, the meeting display system displays, on the goal display 802, the meeting notification or a goal set by the goal setting text box 502 (FIG. 5) or the like at the beginning of the meeting by the conference support system.

  Based on the contents displayed in the agenda display 801 and the goal display 802, the conclusion for the discussion is input in the conclusion input text box 803. Also, based on the contents displayed on the agenda display 801 and the goal display 802, the action item determined in the meeting is input to the action item input text box 804. A date, that is, a time limit may be set for the action item. Besides, a person in charge may be set for the action item. In addition, in the action item input text box 804, the meeting support system may display the statement contents determined to be "action items" as action item candidates.

  In addition, the conference support system displays the calculation of the cost by the cost calculation unit 1F31 (FIG. 18) and the evaluation by the evaluation unit 1F32 (FIG. 18), for example, in the following evaluation screen.

  FIG. 20 is a diagram showing an example of an evaluation screen displayed by the conference support system according to the second embodiment of the present invention. For example, the meeting support system displays the cost and the evaluation result in the meeting as a score and an amount as illustrated.

  The conference score 901 is an overall score obtained by summing up each score of the achievement grade score 902, the meeting time grade score 903, the activity grade score 904, and the forward grade score 905.

  The achievement degree evaluation point 902 is an evaluation result as to whether or not a conclusion has been input with respect to a preset goal for each agenda set by the agenda setting text box 501 (FIG. 5) and the like. For example, in the case where four agendas are set by the agenda setting text box 501 (FIG. 5) and the like, and there are two conclusions input for the four agendas, the meeting support system evaluates the achievement level The point 902 is half the full point.

  The meeting time evaluation point 903 is an evaluation result obtained by comparing the scheduled time set by the holding notification or the scheduled time setting text box 503 (FIG. 5) or the like with the time when the conference was held. For example, if the time when the meeting was held is shorter than the scheduled time, the meeting time score 903 will be high. On the other hand, if the time when the meeting was held is longer than the scheduled time, the meeting time evaluation point 903 is lowered.

  The activity evaluation score 904 is an evaluation result evaluated based on the number of utterance contents, the number of utterance contents per unit time, or the like. For example, when the number of utterance contents or the number of utterance contents per unit time is large, the activity evaluation score 904 becomes high. On the other hand, when the number of utterance contents or the number of utterance contents per unit time is small, the activity evaluation score 904 is lowered. For this reason, when the activity evaluation score 904 is low, so-called inside work is performed by the possibility of being a place of information sharing where a meeting is unnecessary or gathering of people unrelated to the agenda. there is a possibility. Therefore, the conference support system can improve the operation of the conference by feeding back these possibilities.

  The degree-of-forward evaluation score 905 is an evaluation result evaluated based on the type of the speech and the ratio of the type of the speech judged by the determination unit 1F 21 (FIG. 18). For example, when the proportion of types of utterance content that are evaluated as "proposal" is high, the positive evaluation score 905 is high. On the other hand, when the proportion of the types of utterance contents that are evaluated as “proposals” is low, the positive evaluation score 905 is low. For this reason, when the positive evaluation score 905 is low, the meeting may be a meeting which is high in criticism and comments and does not approach the conclusion. Therefore, the conference support system can suggest this possibility and urge a constructive opinion towards the goal.

  The conference support system performs the above evaluation by the evaluation unit 1F 32 (FIG. 18). Next, the meeting support system can feed back the evaluation result of the objective meeting to the participants by outputting the evaluation result on a screen or the like by the output unit 1F4 (FIG. 18). In this way, when feedback is given, the meeting support system suggests to the participants where in the meeting the problem is likely to occur, and the participants are made aware of the time at which the meeting was held. Can. Thus, the meeting support system can cause the participants to reconsider the members or the manner of proceeding to the meeting.

  Note that each evaluation result, the number of utterance contents, the type of utterance, and the like may be displayed by the meeting support system during the meeting. For example, in the example illustrated in FIG. 4, the evaluation result or the like may be displayed as the evaluation display 310. That is, the evaluation result may be displayed in real time during the meeting. In this way, the conference support system can, for example, urge a person who has a small amount of speech to speak.

  In addition, the meeting support system may perform weighting on the statement contents that are determined to be “problem”, “suggestion”, and the like in the evaluation. In this manner, the conference support system can urge the participants to make a large number of speech contents that are the types of speech such as “task” and “proposal”. Thus, the conference support system can facilitate more useful discussions.

  Besides, in the evaluation screen, the meeting support system may display the calculation result of the cost and the like. For example, the cost is calculated by the cost calculator 1F31 (FIG. 18) based on the meeting time 906 and the labor cost of each participant. The calculated cost is displayed, for example, as a cost display 907 or the like.

  In order to calculate the cost, first, the meeting support system is input with the labor cost per unit time of the participant. The personnel expenses may be fixed uniformly for all the participants or may be set for each post. In addition, the labor cost may be set based on the actual salary and the like.

  Next, the meeting support system measures the time elapsed from the meeting start time until the end of the meeting, and displays the measurement result in the meeting time 906. Then, the meeting support system multiplies the meeting time 906 by the labor cost per unit time of each participant to calculate the cost of each participant. Next, the conference support system sums up the respective costs of each participant, and displays the calculation result on a cost display 907.

  Further, on the evaluation screen, the evaluation result may be displayed by the conference support system for each participant. For example, the evaluation result for each participant is displayed as a contribution degree display 908 or the like.

  The contribution degree display 908 indicates each evaluation result for each participant based on, for example, the type of utterance and the number of utterance contents determined by the determination unit 1F21 (FIG. 18). Note that the contents of the statement are linked to the participant who has made a statement of each statement by the speaker determination unit 1F 24 or the like shown in FIG.

  The contribution degree indication 908 is calculated by the conference support system, for example, as follows. First of all, participants are considered to be important according to the purpose of the meeting, such as “1 point” for “neutral opinion” and “5 points” for “problem” and “proposal”. Set weight to type. In the conference support system, it is desirable that the weight of constructive opinions such as "problem" and "proposal" be set to be large. When set in this manner, the meeting support system can facilitate useful discussions for problem solving.

  Next, the conference support system evaluates each participant based on the product of the determination result by the determination unit 1F 21 (FIG. 18) and the number of utterance contents. The values calculated by this evaluation are the "contribution" and "acquisition point" illustrated in the contribution display 908. As described above, when the "degree of contribution" or the like is fed back to the participant by the conference support system, the participant can use the "degree of contribution" or the like to review the members who are to participate in the conference. Thus, the conference support system can facilitate more useful discussions. In addition, since the number of unnecessary members can be reduced, the meeting support system can reduce the cost of the meeting.

  In addition, each screen shown above may be shared in real time by each terminal 11 connected to the network 12 shown in FIG. In this way, even if the conference is held in a place without a display, if the participants bring the terminal 11 such as a notebook PC, each participant can view the above-mentioned screens and conduct a conference.

  Further, the contents of the statement may be edited jointly from each terminal 11. For example, the server 10 transmits the contents to be displayed on the screen to the respective terminals 11 as, for example, an HTML (Hyper Text Markup Language) file or the like. Next, when the content of the statement is input and data indicating the content of the statement is transmitted to the server 10, the server 10 transmits an HTML file in which the content of the new statement is reflected to the respective terminals 11.

  The words displayed on the screen may be subjected to translation processing. For example, when the content of a statement is input and data indicating the content of a statement is transmitted to the server 10, the server 10 translates the content of the statement and HTML indicating the content of the statement before translation and the content of the statement after translation Generate a file Subsequently, the server 10 transmits, to each of the terminals 11, an HTML file indicating the content of the statement before translation and the content of the statement after translation. In this way, the conference support system can make it possible to reduce miscommunication, even for foreign language participants.

  Each terminal 11 may perform user authentication. For example, user authentication is performed by inputting the user name in the input text box of the user name displayed on the screen. Besides, user authentication may be performed using an IC card or an RFID. In this manner, as in the case of assignment of function keys shown in FIG. 4, the speaker and the content of the utterance may be linked based on the authentication result of the user authentication described above and the terminal to which the content of the utterance is input. . The information on the speaker may be added by coloring, displaying the beginning of a sentence, displaying the end of a sentence, or the like, as in the first embodiment.

  Furthermore, a subjective evaluation may be input with respect to the content of an utterance, and a meeting assistance system may perform evaluation based on the input subjective evaluation. For example, the subjective evaluation is input as follows.

  FIG. 21: is a figure which shows an example of the screen for inputting the subjective evaluation displayed by the meeting assistance system which concerns on one Embodiment of 2nd Embodiment of this invention. Compared with FIG. 6, the example of the illustrated screen is different in that the subjective evaluation button 1001 is added to each of the displayed utterance contents.

  As illustrated, the subjective evaluation button 1001 is displayed for each message content. And each participant pushes the subjective evaluation button 1001 displayed with respect to the statement content of the content to support, when it is judged that it is the statement content which each one supports. The subjective evaluation button 1001 may be pressed by a participant in charge of input, or may be pressed by each participant based on their respective judgments. In addition, the subjective evaluation button 1001 may be a button that is pressed when not supported. As described above, when the subjective evaluation is input, the conference support system can evaluate whether or not each utterance content is a good utterance based on each participant's subjectivity. Then, the meeting support system can display the evaluation result by the subjective evaluation to urge the participant to make a good speech for achieving the purpose of the meeting.

  In addition, the conference support system may decorate and display the speech content based on the input by the subjective evaluation button 1001. For example, in the illustrated screen, the conference support system displays the message content for which the subjective evaluation button 1001 is pressed in the large display 1002. The large display 1002 is an example decorated so that the font size of the character indicating the content of the message is larger than that of the other content of the message as illustrated. As described above, when the decoration is performed and the content of the statement is output, the participant can intuitively know whether the content of the statement is supported among the content of the statement. In addition, the meeting support system may use the user information to display the status of approval or disapproval of the statement content, such as who agrees with who disagrees with the specific opinion.

  Note that the decoration is realized by changing the description of Cascading Style Sheets (CSS) using a language such as Javascript (registered trademark), for example, using information that is supported and not supported.

  Further, when displaying the summary, the conference support system may display, in addition to the display based on the type of the speech, the speech content that can be judged as the important speech based on the input subjective evaluation. In this way, participants can better understand the background of the discussion leading up to the conclusion. That is, this enables the meeting support system to generate minutes that are effective as meeting reflection and information sharing.

  Furthermore, the evaluation unit 1F32 (FIG. 18) may evaluate the meeting based on the time when the meeting was held. For example, the evaluation unit 1F32 (FIG. 18) performs the evaluation as follows.

  FIG. 22 is a flow chart showing an example of a process of performing evaluation based on the time when the meeting was held by the meeting support system according to the second embodiment of the present invention.

  In step S31, the meeting support system receives the pressing of the evaluation button. For example, when an evaluation button such as “evaluate this meeting” shown in FIG. 10 is pressed, the meeting support system starts the evaluation. In addition, it is assumed that the time when the conference was held is the time from the time when the conference was started to the time when the conference was ended (hereinafter referred to as "elapsed time"). Furthermore, it is assumed that the scheduled time for the conference to be held (hereinafter simply referred to as “scheduled time”) is input to the conference support system in advance before the evaluation button is pressed, for example.

  In step S32, the meeting support system determines whether the elapsed time has exceeded the planned time by 10% or more. Next, when it is determined by the conference support system that the elapsed time has exceeded the planned time by 10% or more (YES in step S32), the conference support system proceeds to step S33. On the other hand, if it is determined by the conference support system that the elapsed time has not exceeded the planned time by 10% or more (NO in step S32), the conference support system proceeds to step S34.

  In step S33, the meeting support system sets the evaluation point to "0".

  In step S34, the meeting support system determines whether the elapsed time has exceeded the scheduled time by less than 10%. Next, when it is determined by the meeting support system that the elapsed time has exceeded the scheduled time by less than 10% (YES in step S34), the meeting support system proceeds to step S35. On the other hand, when it is determined by the meeting support system that the elapsed time has not exceeded the scheduled time by less than 10% (NO in step S34), the meeting support system proceeds to step S36.

  In step S35, the meeting support system sets the evaluation point to "5".

  In step S36, the meeting support system determines whether the elapsed time has exceeded the scheduled time by less than 5%. Next, when it is determined by the conference support system that the elapsed time has exceeded the scheduled time by less than 5% (YES in step S36), the conference support system proceeds to step S37. On the other hand, if it is determined by the meeting support system that the elapsed time has not exceeded the scheduled time by less than 5% (NO in step S36), the meeting support system proceeds to step S38.

  In step S37, the meeting support system sets the evaluation point to "10".

  In step S38, the meeting support system determines whether the elapsed time is 10% or more shorter than the scheduled time. Next, when it is determined by the meeting support system that the elapsed time is 10% or more shorter than the scheduled time (YES in step S38), the meeting support system proceeds to step S39. On the other hand, if it is determined by the meeting support system that the elapsed time is not 10% or more shorter than the scheduled time (NO in step S38), the meeting support system proceeds to step S40.

  In step S39, the meeting support system sets the evaluation point to "25".

  In step S40, the meeting support system determines whether the elapsed time is 5% or more shorter than the scheduled time. Next, if it is determined by the meeting support system that the elapsed time is 5% or more shorter than the scheduled time (YES in step S40), the meeting support system proceeds to step S41. On the other hand, if it is determined by the meeting support system that the elapsed time is not 5% or more shorter than the scheduled time (NO in step S40), the meeting support system proceeds to step S42.

  In step S41, the meeting support system sets the evaluation point to "20".

  In step S42, the meeting support system sets the evaluation point to "15".

  For example, as illustrated, the conference support system evaluates cases where the elapsed time is shorter than the scheduled time so that the score is high. On the other hand, the meeting support system evaluates when the elapsed time exceeds the scheduled time so that the evaluation point becomes low. The numerical values of the evaluation points and the judgment criteria are not limited to the illustrated values and the judgment, and may be changed by setting or the like. As shown, the evaluated scores are displayed by the conference support system.

  Further, as shown in FIG. 20, the meeting support system may display the evaluation result by using a star or the like. Furthermore, as shown in FIG. 20, the meeting support system may also display a comment or the like prompting a change in behavior. Furthermore, as shown in FIG. 20, the meeting support system may display the evaluation result concerning time together with other evaluation results. Thus, when the evaluation result which evaluated the meeting based on the time when the meeting was held is displayed, the meeting support system can make the participants aware of the time concerning the meeting, and the purpose in time is Encourage them to achieve In this way, the meeting support system can streamline the meeting.

Third Embodiment
The third embodiment is, for example, an embodiment realized by the same overall configuration, hardware configuration, and functional configuration as the first embodiment. Hereinafter, differences will be mainly described below. The third embodiment is different from the first embodiment in the determination method by the determination unit 1F21 (FIG. 3).

  In the third embodiment, the conference support system uses a tagged corpus as so-called training data. Then, the conference support system learns a classifier that performs natural language processing by performing so-called supervised learning, which is a method of machine learning. The following tags indicate the types of comments: "Suggest", "Question", "Answer", "Positive Opinion", "Negative Opinion", "Neutral Opinion", "Information", "Request", "Issue An example of “action item” and “decision matter” will be described.

  The machine learning method is, for example, a support vector machine (SVM), a naive Bayes classifier, decision tree learning, a conditional establishment field (CRF), or the like. The machine learning method is preferably a support vector machine. If it is a support vector machine, so-called real-time performance etc. will be improved since judgment can be made sequentially.

  The classifier determines the type of utterance based on the feature of the utterance content (hereinafter referred to as "feature"). Specifically, the feature uses BoW (Bag of Words) of speech, an auxiliary verb included in the speech content, an adverb, an adjective, a part of speech such as a noun or an auxiliary verb, who the speaker is, and the like. For example, an adjective may indicate a positive or negative expression or the like. In addition to a positive expression or a negative expression, a noun may be an expression indicating "action item" and "task" such as "requirement required" and "answer required". Furthermore, an auxiliary verb etc. may be an expression showing hope, duty, necessity, request, suggestion, assertion, guess, hearing, evaluation, etc. at the end of a sentence. Therefore, when the classifier determines the type of utterance based on the feature, the conference support system can accurately determine the type of utterance.

  The conference support system performs natural language processing using machine learning, for example, according to the method described in "Basics of Natural Language Processing", Okumura Gaku, Corona Press.

  FIG. 23 is a conceptual diagram showing an example of natural language processing using machine learning by the conference support system according to the third embodiment of the present invention. As illustrated, the meeting support system learns the classifier CLF by supervised learning. First, a feature and data represented as a set of value pairs are input to the classifier CLF, and the classifier outputs a class to which the input test data TSD belongs. The class is indicated by the class label CLB. That is, the class label CLB indicates the result of determining the type of the statement of the statement content indicated by the test data TSD.

  In order to learn the classifier CLF by a machine learning algorithm, as shown in the figure, the conference support system inputs data and a set of sets of classes to which the data belongs as training data TRD. Next, when the training data TRD is input, the conference support system learns the classifier CLF by a machine learning algorithm. Thus, when the test data TSD is input after learning the classifier CLF, the conference support system can output the class to which the test data TSD belongs by the classifier CLF.

  In the method of determining the type of utterance using the classifier CLF, the conference support system can accurately determine the type of utterance as compared with the method of using pattern matching or the like. Further, the method of determining the type of utterance using the classifier CLF can reduce the time and effort for updating the pattern matching rule, etc., as compared with the method using pattern matching and the like. That is, when the method of determining the type of utterance using the classifier CLF is used, so-called maintainability can be improved.

  Also, the configuration may be such that the participant can change the class label. In this way, when the class label CLB of the result determined by the classifier CLF indicates a class different from the class intended by the participant, the participant can change the class. For example, even if the content of the commented statement is judged as "opinion" by the meeting support system, if the participant thinks that it is a "question", the participant is considered to be a class that is considered as "opinion" Do the operation to change the label to "Question".

  In this manner, when the change operation is performed and feedback is performed, the conference support system can learn the classifier CLF as in the case where the training data TRD in machine learning is input. Therefore, it is possible to cause the conference support system to learn the classifier CLF with little effort for updating data. Therefore, the meeting support system can accurately determine the type of speech.

  In addition, information on a person who has made a statement of the specified utterance may be used as a feature to make the classifier CLF learn. In this way, the conference support system can determine the type of the speech in consideration of the tendency of the person who made the speech content. Therefore, the meeting support system can accurately determine the type of speech.

  Furthermore, the meeting support system may determine the type of utterance based on the role in the conference of the person who spoke the utterance content. For example, in a meeting such as a briefing session, if the person who has made a statement is a "decision maker", the information of the "decision maker" may be used as an identity to determine the type of the statement. . In this way, the conference support system can determine the type of the speech in consideration of the tendency of the person who made the speech content. Therefore, the meeting support system can accurately determine the type of speech. In particular, the meeting support system can accurately determine the type of utterance such as "action item" and "decision item".

  Also, as the types of remarks, i.e., labels, increase in accuracy, the accuracy often decreases. Therefore, the meeting support system may divide the types of speech into groups. For example, types of remarks are "suggestion", "question", "answer", "positive opinion", "negative opinion", "neutral opinion", "information", "request", "problem", "action" An example will be described in which the item is an item and the item to be determined.

  For example, the groups are referred to as "first group" and "second group" shown below.

First group: "Proposal", "Question", "Answer", "Positive opinion", "Negative opinion", "Neutral opinion", "Information" and "Request"
Second group: "action items" and "decision items"
Then, the conference support system determines which of the types of utterances of the “first group” the utterance contents are. Next, the conference support system determines which of the types of utterances of the “second group” the utterance contents are. In the configuration shown in FIG. 23, a classifier CLF is prepared for each group.

  For example, it is assumed that there is a comment content saying "I want something to be done among a plurality of persons in charge" in a meeting. The content of the statement is determined by the conference support system to be the type of the "answer" of the first group and the type of the "action item" of the second group.

  For example, it is assumed that the statement contents of the "action item" and the "decision item" statement types are important in the meeting. In such a case, when the important utterance types are selected and grouped as in the second group, the conference support system can accurately determine the utterance contents of the important utterance types. Further, since the types of utterances in each group are smaller than in the case where they are not grouped, the conference support system can accurately determine the types of utterances.

Fourth Embodiment
Also, the information sharing support system 20 may have, for example, the following overall configuration.

  FIG. 24 is a conceptual diagram for explaining an example of the entire configuration of an information sharing support system according to an embodiment of the fourth embodiment of the present invention. For example, the information sharing support system 20 is an entire configuration including the meeting support system 1 and the information sharing server 21. As illustrated, there may be a plurality of meeting support systems 1. Further, in the information sharing support system 20, as illustrated, the meeting support system 1, the information sharing server 21, and the terminal 11 may not be separate devices. For example, the conference support system 1 and the information sharing server 21 may be shared by one information processing apparatus. Hereinafter, the entire configuration shown in the drawings will be described as an example.

  Communication logs such as electronic mail data DEM, chat data DCH and electronic file data DEF are input to the information sharing server 21 from an external device such as each terminal 11 or the like.

  As described above, the information sharing support system 20 is not limited to the speech contents in the conference, and sentences may be input in various data formats. Note that data such as the electronic mail data DEM, the chat data DCH, and the electronic file data DEF may be input through the meeting support system 1 or the like.

  Then, when a certain person such as a manager accesses the information sharing server 21 when a certain amount of data is collected, for example, a screen as shown in FIG. 14 is displayed. Next, when the button 1303 is pressed, for example, the information sharing support system 20 outputs the sentence input in each data format as follows.

  FIG. 25 is a view for explaining an example of an output of the information sharing support system according to the fourth embodiment of the present invention. The information sharing server 21 displays, for example, a screen as illustrated to the user via the display device or the terminal 11 or the like.

  Note that the screen as illustrated is not limited to being displayed based on the operation of the button 1303 or the like. For example, when an utterance of a specific type such as "task" is generated from an input communication log, first, a predetermined person such as a manager is notified of the occurrence of "task" or the like. The type is assumed to be set in advance. Then, when accessed from a link (a URL (Uniform Resource Locator) or the like described in an e-mail) included in the push notification, a screen as illustrated may be displayed.

  For example, the information sharing server 21 generates a screen as illustrated in the following process.

  FIG. 26 is a flow chart showing an example of processing by the information sharing support system according to the fourth embodiment of the present invention. In the figure, the same processes as in FIG. 12 will be assigned the same reference numerals, and duplicate explanations will be omitted hereinafter.

  In step S51, the information sharing support system 20 sorts sentences. First, in the illustrated example, when the processing up to step S33 is performed, the information sharing support system 20 can extract a sentence related to a specific content. Next, the information sharing support system 20 sorts the extracted sentences, for example, in chronological order.

  The example shown in FIG. 25 shows the result of sorting by the information sharing support system 20 from the bottom to the top of the figure so that new sentences are arranged from old sentences. As described above, when the sorted result is output, the user can view the screen as illustrated to grasp how and when a certain agenda led to the conclusion.

  The sentence to be output may be selected. For example, the information sharing support system 20 selects a sentence as follows.

  In step S52, the information sharing support system 20 selects a sentence. For example, the information sharing support system 20 selects a sentence to be output based on the form in which the sentence is input. Specifically, in the example shown in FIG. 24, a sentence is input from the meeting support system 1 to the information sharing support system 20 in the form of minutes data. Similarly, a sentence is input from the terminal 11 to the information sharing support system 20 in the form of e-mail data DEM, the form of chat data DCH, and the form of electronic file data DEF. Hereinafter, as described above, it is assumed that sentences are input to the information sharing support system 20 in four types of formats.

  Then, the screen shown in FIG. 25 indicates that the meeting icon ICM is a sentence based on the minutes data. Similarly, it indicates that the chat icon ICC is a sentence based on the chat data DCH. Further, it indicates that the email icon ICE is a sentence based on the email data DEM. As illustrated, the information sharing support system 20 can indicate where each sentence is spoken by, for example, outputting the sentence together with each icon.

  In the output, for example, as shown in FIG. 25, attached data FL may be associated with each sentence. The attached data FL is, for example, meeting material used in a meeting, or an attached file attached to an e-mail. In this manner, when the attached data FL is linked to a sentence and output, it is easy to view the used material when viewing the process, etc., and the user can understand the process etc. in detail. In addition, for example, in the working method such as telework (telewprk), even if there is no person in charge, the user can quickly identify and access the attached data FL.

  When, for example, the user wants to focus on a sentence input in a specific format, the user can select an operation to be output using the check boxes CB1, CB2, CB3 and CB4 shown in FIG. input. Specifically, in the example illustrated in FIG. 25, when the check box CB1 is set, the information sharing support system 20 outputs a sentence based on the minutes data. Similarly, when the check box CB2 is set, the information sharing support system 20 outputs a sentence based on the chat data DCH. Furthermore, when the check box CB3 is set, the information sharing support system 20 outputs a sentence based on the email data DEM. Furthermore, when the check box CB4 is set, the information sharing support system 20 outputs a sentence based on the electronic file data DEF.

  In the example shown, since the check box CB1, the check box CB2 and the check box CB3 are set, the information sharing support system 20 is based on the minutes data among the input sentences as shown in FIG. A sentence, a sentence based on chat data DCH and a sentence based on e-mail data DEM are selected and output.

  The selection by the information sharing support system 20 is not limited to being performed based on the form in which the sentence is input. For example, when the e-mail data DEM is input, there are many cases where there is affiliation data DAF indicating the affiliation of the person who sent the e-mail data DEM. For example, the affiliation data DAF is a mail address or the like indicating the sender of the electronic mail.

  Then, the user first sets a specific organization name or the like in the information sharing support system 20. Next, the information sharing support system 20 selects, based on the affiliation data DAF, the e-mail data DEM sent by a person who belongs to the set organization. In this way, the information sharing support system 20 can narrow down and output sentences spoken by a person who belongs to a predetermined organization. Therefore, for example, the user can view a screen as shown in FIG.

(Another embodiment)
FIG. 27 is a conceptual diagram for explaining an example of the entire configuration of an information sharing support system according to another embodiment of the fourth embodiment of the present invention. For example, the information sharing support system 20 may have the following overall configuration. Compared to FIG. 24, the overall configuration shown is different in that the conference support system 1 is not provided.

  As described above, the information sharing support system 20 may receive the electronic mail data DEM, the chat data DCH, the electronic file data DEF, or a combination of these as input. That is, holding of a meeting is not essential, and a sentence may be input to the information sharing support system 20 in any format as long as it is data indicating exchange of words, that is, a so-called communication log.

  Note that all or part of each process according to the present invention can be implemented using a programming language such as assembler, C, C ++, C #, Java (registered trademark), Javascript (registered trademark), Python (registered trademark), Ruby, PHP, or the like The present invention may be realized by a program for causing a computer described in an object oriented programming language or the like to execute each procedure according to the conference support method. That is, the program is a computer program for causing a computer such as an information processing apparatus or an information sharing support system having one or more information processing apparatuses to execute each procedure.

  Also, the program can be stored and distributed in a computer readable recording medium such as a ROM or an EEPROM (Electrically Erasable Programmable ROM). Furthermore, the recording medium may be an EPROM (Erasable Programmable ROM), a flash memory, a flexible disc, a CD-ROM, a CD-RW, a DVD-ROM, a DVD-RAM, a DVD-RW, a Blu-ray disc, an SD (registered trademark) card, or MO etc. may be sufficient. Furthermore, the program can be distributed via telecommunication lines.

  Furthermore, the information sharing support system may have two or more information processing apparatuses mutually connected by a network or the like. That is, even if all or part of various processes are distributed, performed in parallel as in a duplex system, etc., or redundantly performed as in a dual system, etc., by the information sharing support system. Good.

  Although the preferred embodiments of the present invention have been described in detail, the present invention is not limited to the specific embodiments, and various modifications may be made within the scope of the present invention as set forth in the claims. Or change is possible.

REFERENCE SIGNS LIST 1 conference support system 10 server 11 terminal 1 F 1 input unit 1 F 2 control unit 1 F 21 determination unit 1 F 22 decoration unit 1 F 23 time management unit 1 F 24 speaker determination unit 1 F 31 cost calculation unit 1 F 32 evaluation unit 1 F 3 storage unit 1 F 4 output unit CLF classifier

Unexamined-Japanese-Patent No. 2007-43493 gazette

Claims (12)

An information sharing support system having one or more information processing apparatuses for supporting information sharing,
An input unit for inputting a sentence indicating any one or a combination of description contents stated in a meeting, an electronic mail, an electronic file, or chat data;
A determination unit that determines the type of the sentence input by the input unit;
An information sharing support system, comprising: an output unit configured to output, as a list, specific sentences to be set among the types based on a determination result by the determination unit.   The information sharing support system according to claim 1, wherein when the specific sentence is input, an alert indicating the content of the specific sentence is displayed. Estimate the topic boundaries that separate the groups of sentences,
The information sharing support system according to claim 1, wherein a topic is generated for each of the groups separated by the topic boundary.   The information sharing support system according to claim 3, wherein the topic indicates a subject of a plurality of sentences belonging to the group, a topic, a topic, or a sentence compressed sentence.   The information sharing support system according to any one of claims 1 to 4, wherein the output unit lists the utterance content or the description content in time series and outputs the list.   The information sharing support system according to any one of claims 1 to 5, which outputs a communication diagram indicating communication strength indicating the strength of communication by the meeting or the electronic mail. The communication diagram shows communication in a line,
The information sharing support system according to claim 6, wherein when the line is pressed, a log of the communication is shown.   The information sharing support system according to any one of claims 1 to 7, wherein the sentence input by the input unit is sorted and output.   9. The information sharing support system according to claim 8, wherein the sentence to be output is selected based on the affiliation of the person who sent the sentence, the form in which the sentence is input, or a combination thereof. An information sharing support method performed by an information sharing support system having one or more information processing apparatuses for supporting information sharing,
An input procedure in which the information sharing support system inputs a sentence indicating any one or a combination of the contents of a statement made at a meeting, an electronic mail, an electronic file, or chat data;
A determination procedure in which the information sharing support system determines the type of the sentence input by the input procedure;
An information sharing support method, including: an output procedure in which the information sharing support system outputs, as a list, specific sentences to be set among the types based on a determination result by the determination procedure. A program that causes a computer to execute an information sharing support method for supporting information sharing, the information sharing support method comprising:
An input procedure in which the computer inputs a sentence indicating any one or a combination of the contents of a statement spoken in a meeting, an electronic mail, an electronic file, or chat data;
A determination procedure in which the computer determines the type of the sentence input by the input procedure;
A program including: an output procedure of outputting, as a list, specific sentences to be set among the types based on a determination result by the determination procedure. An information sharing support device for supporting information sharing, comprising:
An input unit for inputting a sentence indicating any one or a combination of description contents stated in a meeting, an electronic mail, an electronic file, or chat data;
A determination unit that determines the type of the sentence input by the input unit;
An information sharing support device, comprising: an output unit configured to output, as a list, specific sentences to be set among the types based on a determination result by the determination unit.

Images