JP6511192B2 - Discussion support system, discussion support method, and discussion support program - Google Patents

Description

  The present invention relates to a discussion support system, a discussion support method, and a discussion support program.

  In recent years, attempts have been made to create new ideas using a framework for market analysis and corporate strategy formulation. At the conference for creating new ideas, the moderator of the conference advances the proceedings through organizing the participants' opinions and asking questions, etc., and supports the creation of new ideas.

  One of the methods for conducting such meetings is to apply system dynamics. System dynamics specifies elements (nodes) that affect system fluctuation and models causality between the nodes. Then, by performing simulation based on that model, the characteristics that change with the passage of time of the system are clarified. In system dynamics, a causal loop diagram is used as a method of modeling causality between nodes. The causal loop diagram is composed of each node and an arrow representing a causal relationship. The arrows indicate positive correlation that one increases (or decreases) the other increases (or decreases), and one increases (or decreases) the other decreases (or increases). There is something that expresses a negative correlation. The causal loop diagram is suitable for modeling characteristics that change with the passage of time, because it can represent nodes that take time to appear.

  This causal loop diagram is applied to create a causal loop diagram with nodes constituting elements of the meeting agenda as nodes, and by visualizing the agenda content, promoting the understanding and discussion activation of the participants on the meeting agenda It is being tried to do. Patent documents 1 and patent documents 2 are this related art. Patent Document 1 discloses that information is presented according to a scene in a meeting. Further, Patent Document 2 discloses that the user is presented with a topic for which discussion is developed, such as a related topic that has not been discussed at a meeting.

JP, 2014-85916, A JP, 2015-156099, A

  In Patent Document 1, a conference state change condition and a conference state change action are utilized in order to present information at an appropriate timing according to a scene of a conference. The conference state change condition includes silent time, frequency of appearance of a specific word, frequency of appearance of a specific context, time when the same speaker continues speaking, time when a specific person does not continue speaking, a specific utterance It defines at least one selected from the group consisting of a person's statement or a specific statement content. In addition, the meeting status change action displays a message prompting rest, text display of speech, display of Internet search results of frequent keywords, display of search results in a document management system of frequent keywords, or text or image which brightens the atmosphere The display of etc. is defined. Then, when at least one of the conference status change conditions described above is satisfied, a conference status change action associated with the condition is executed. However, since the system of Patent Document 1 executes the conference state change actions one after another when the predetermined condition is satisfied, the participants of the conference individually input the respective requests, or If the participant specifies the state of the meeting and displays it on the screen, the presenter may not be able to control the meeting.

  In Patent Document 2, in order to present the topic of the conference to the user, first, the speech of the ongoing conference is converted into text and a keyword is extracted by morphological analysis. Then, the topic is extracted from the document collected in advance from the external public database and stored in the external information DB (Database). Thereafter, a topic having a high degree of similarity to the extracted keyword is extracted from the external information DB and presented on the monitor. However, in Patent Document 2, since the topic acquired from the external information DB is expressed by words (words) similar to the extracted keyword, it may be insufficient as a motive for creating a new idea. For example, it is difficult for the parties to create new viewpoints and create new ideas by combining unknown keywords.

  The present invention has been made in view of such circumstances, and an object thereof is to provide a discussion support system, a discussion support method, and a discussion support program capable of presenting a new development argument.

  In order to solve the above problems, one aspect of the present invention is a discussion support system for supporting a discussion on an agenda consisting of a plurality of elements, which is a statement for acquiring the content of the utterance made by the speaker for the agenda. An acquiring unit, an utterance analysis processing unit which decomposes the acquired utterance into a plurality of words, and the element corresponding to the acquired utterance based on the decomposed word, and having a causal relationship with the identified element Determining whether or not there is another element, and if it is determined that the other element is present, generating a question about the subject based on the other element, and generating the question Outputting a question output unit for outputting

  According to the present invention, new development arguments can be presented.

FIG. 1 is a diagram for explaining an example of the configuration of a discussion support system according to the present embodiment. FIG. 2 is a diagram for explaining an example of the hardware configuration of the discussion support device 100. FIG. 3 is a diagram for explaining the functions of the discussion support device 100. FIG. 4 is a diagram showing an example of the speech information 202. As shown in FIG. FIG. 5 is a diagram showing an example of the natural language classification dictionary 204. As shown in FIG. FIG. 6 is a diagram showing an example of the evaluation expression dictionary 205. As shown in FIG. FIG. 7 is a diagram showing an example of the utterance analysis result information 206. As shown in FIG. FIG. 8 is a diagram showing an example of the agenda element information 208. As shown in FIG. FIG. 9 is a diagram for explaining an example of a causal loop diagram. FIG. 10 is a diagram showing an example of the agenda related case information 209. As shown in FIG. FIG. 11 is a flowchart illustrating an outline of processing performed by the discussion support device 100. FIG. 12 is a flowchart for explaining the details of the question sentence generation process. FIG. 13 is a flowchart for explaining the details of the question sentence generation process. FIG. 14 is an example of the discussion screen.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

<< System Configuration >>
FIG. 1 is a diagram for explaining an example of the configuration of a discussion support system according to the present embodiment. As shown in the figure, the discussion support system 10 is introduced in a conference room, a hall or the like in which a plurality of participants 13 including a speaker 11 and a chairman 12 participate in a discussion.

  Each participant 13 discusses an agenda consisting of a plurality of elements (hereinafter also referred to as nodes). That is, this agenda is composed of a plurality of topics or themes, and each participant 13 discusses the respective topics or themes.

  The discussion support system 10 is provided with a screen 14 for displaying the contents of the agenda and the contents of the remarks of the participant 13 so that all the participants 13 can confirm the contents of the discussion.

  On the screen 14, a diagram (hereinafter referred to as a causal loop diagram) or the like indicating a causal relationship between elements (nodes) constituting an agenda is displayed. The details of the causal loop diagram will be described later.

  The screen 14 is, for example, a monitor such as a liquid crystal display. In this case, the display of the information on the screen 14 is performed, for example, by connecting an information processing apparatus (server, personal computer (Personal Computer) or the like) storing the information of the conference material to the screen 14. Also, the screen 14 may be a wall of a conference room or a whiteboard. In this case, the display of the information on the screen 14 is performed using, for example, a projector or the like to which the information processing apparatus is connected.

  As shown in FIG. 1, the discussion support system 10 is provided with a discussion support apparatus 100.

<< Hardware Configuration of Discussion Support Device 100 >>
FIG. 2 is a diagram for explaining an example of the hardware configuration of the discussion support device 100. As shown in the figure, the discussion support apparatus 100 is an information processing apparatus (computer), and includes, as hardware, a central processing unit 101 including a CPU (Central Processing Unit) or the like, a RAM (Random Access Memory), and a ROM (Random Access Memory). A storage device 102 such as Read Only Memory (NVR) or NVRAM (Non-Volatile RAM), a Hard Disk Drive (Hard Disk Drive), a Solid State Drive (SSD), a Compact Disc-Read Only Memory (CD-ROM) drive, etc. It comprises a next storage device 103, an input device 104 comprising a keyboard, a mouse, a touch panel and the like, an output device 105 comprising a monitor (display) and the like, and a communication device 106 such as a LAN (Local Area Network) card. These devices are communicably connected by a bus 107.

<< Functions of the Argument Support Device 100 >>
Next, the functions of the discussion support device 100 will be described.
FIG. 3 is a diagram for explaining the functions of the discussion support device 100. As shown in the figure, the discussion support device 100 includes the functions of a speech reception unit 201, a speech analysis processing unit 203, an idea creation support processing unit 207, a question sentence generation processing unit 210, and a display processing unit 211.

  In addition, the discussion support device 100 stores information of the speech information 202, the natural language classification dictionary 204, the evaluation expression dictionary 205, the speech analysis result information 206, the agenda element information 208, and the agenda related case information 209.

  The speech reception unit 201 (speech acquisition unit) acquires the contents of the speech uttered by the speaker with respect to the subject. Specifically, for example, the speech reception unit 201 digitizes the speech (voice) of each participant 13 acquired from the microphone device connected to the speech reception unit 201 or the device having the speech recognition function, The content that the participant 13 has said is acquired. Alternatively, the speech reception unit 201 acquires the speech input by the participant 13 by acquiring the speech input to the information processing apparatus (for example, an electronic tablet) used by the participant 13 via the communication device 106. You may The message reception unit 201 displays the contents of the obtained message on the screen 14 via the communication unit such as the communication device 106.

  The speech reception unit 201 stores the contents of the acquired speech in the speech information 202.

<Comments Information 202>
Here, the speech information 202 will be described.
FIG. 4 is a diagram showing an example of the speech information 202. As shown in FIG. As shown in the figure, the speech information 202 is a database storing the contents of speech, and includes items of a speech ID 301, a parent speech ID 302, a corresponding node ID 303, a speech 304, a speech date 305, and a speaker 306. It consists of at least one or more records.

  An identifier (hereinafter referred to as an utterance ID) for identifying the utterance of the participant 13 is stored in the utterance ID 301, and an utterance (hereinafter referred to as a parent utterance) causing the utterance of the utterance ID 301 is stored in the parent utterance ID 302. An identifier for identification (hereinafter referred to as a parent utterance ID) is stored. As the parent utterance ID, for example, the chairman 12 specifies the parent utterance of the utterance of the utterance ID 301 while listening to the utterance of the participant 13, and sets the identified utterance ID of the parent utterance as the parent utterance ID 302. Further, for example, the speech reception unit 201 analyzes the speech time and the speech content of each speech of the participant 13, and identifies the parent speech based on the context of each speech and the quotation status of each speech, and the specified parent speech The message ID of is set in the parent message ID 302.

  In the corresponding node ID 303, an identifier (hereinafter referred to as a node ID) for specifying a node corresponding to the utterance of the utterance ID 301 (hereinafter referred to as a corresponding node) is stored. In the utterance 304, the contents of the utterance of the utterance ID 301 are stored. The information on the date and time when the utterance of the utterance ID 301 is acquired is stored in the utterance date and time 305 (hereinafter referred to as the utterance date and time), and the information on the speaker 306 specifies the participant who made the utterance (for example, the name of the speaker And an identifier (hereinafter referred to as a speaker ID). In these items, for example, a character string or a numerical value is stored.

  In the corresponding node ID 303, for example, when the chairman 12 is in the middle of a conference using a causal loop diagram, the correspondent node ID 303 listens to the utterance ID of the utterance ID 301 (the utterance of the participant 13). Above, node ID corresponding to the statement is specified, specified node ID is set to corresponding node ID303.

  The discussion support device 100 may acquire the content of the utterance of the participant 13 by the function of the electronic sticky note by providing the function of the electronic sticky note. For example, the presenter 12 causes the speech of the participant 13 to be displayed as a telegraphic sticky note by the electronic tablet etc. of its own, and the displayed content is displayed on the screen of the electronic tablet etc. held by each participant 13 or the screen of the screen 14 The electronic sticky note may be displayed at a predetermined position. In this case, the discussion support device 100 may determine the correspondence between the utterance of the participant 13 and the corresponding node based on the output positional relationship, based on the function of the electronic sticky note. For example, when the chairman 12 places (outputs) the utterance of the participant 13 at an arbitrary node of the causal loop diagram on the screen or in the vicinity thereof, the discussion support device 100 recognizes the utterance and the arbitrary event. Correspond to the node.

  Next, the speech analysis processing unit 203 analyzes the contents of the speech acquired by the speech reception unit 201. For example, the speech analysis processing unit 203 refers to the natural language classification dictionary 204 and the evaluation expression dictionary 205 while referring to the speech acquired by the speech reception unit 201 for morphological analysis, syntactic analysis, semantic analysis, case grammar, emotion analysis, etc. Analyze by natural language processing technology of

  Specifically, the utterance analysis processing unit 203 decomposes the utterance acquired by the utterance receiving unit 201 into a plurality of words. In the present embodiment, the speech analysis processing unit 203 decomposes the acquired speech into at least one or more morphemes (words having a predetermined meaning).

  Further, the speech analysis processing unit 203 acquires the viewpoint of the word of the decomposed speech. That is, the utterance analysis processing unit 203 classifies the viewpoint indicated by the utterance into any one of a plurality of types of viewpoints. In the present embodiment, the viewpoint includes the viewpoint of the subject, the viewpoint of the target, the viewpoint of the time, the viewpoint of the place, the viewpoint of the reason, and the viewpoint of the method. That is, it is assumed that the viewpoints are six types of so-called 5W1H (Who, What, When, Where, Why, How).

  Further, the speech analysis processing unit 203 acquires evaluation information of the acquired speech. Specifically, the speech analysis processing unit 203 analyzes the evaluation information of the acquired speech, and stores the analyzed evaluation information in association with the acquired speech. In the present embodiment, the evaluation information includes emotional polarity information indicating the degree of positive meaning or negative degree of meaning of the element.

  Note that the speech analysis processing unit 203 stores the speech analysis result in the speech analysis result information 206 described later.

  Here, the natural language classification dictionary 204 and the evaluation expression dictionary 205 to which the speech analysis processing unit 203 refers will be described.

<Natural language classification dictionary 204>
FIG. 5 is a diagram showing an example of the natural language classification dictionary 204. As shown in FIG. As shown in the figure, the natural language classification dictionary 204 is a database storing morpheme information, and includes a morpheme ID 401, a morpheme 402, an original 403, a part of speech 404, a synonym ID 405, a broad term ID 406, a narrow term ID 407, and a relation. It is configured by at least one or more records including each item of the word ID 408. In each of these items, for example, a character string or a numerical value is stored.

  The morpheme ID 401 stores an identifier for identifying the morpheme (hereinafter referred to as a morpheme ID), the morpheme 402 stores the content of the morpheme of the morpheme ID 401, and the prototype 403 stores the prototype of the morpheme . A prototype of a morpheme is a morpheme representing the common semantic content in the case where the semantic content is common among a plurality of different types of morphemes (for example, in the case where there are a plurality of inflection forms in the morpheme) It is.

  In the part of speech 404, types of morphemes of the morpheme ID 401 (for example, nouns, verbs, adjectives, adverbs, adverbs, conjunctions, particles, auxiliary verbs, exclamations, and adjectives, etc.) The type of the morpheme is stored, and the synonym ID 405 is a morpheme having a different word (for example, a different word form) from the morpheme of the morpheme ID 401 but having a similar semantic content (for example, a morpheme that can be replaced depending on the situation) An identifier (hereinafter referred to as synonym ID) for identifying the word is stored, and in the broad term ID 406, an identifier (hereinafter referred to as a broad term ID) identifying the morpheme of the upper concept of the morpheme of the morpheme ID 401 is stored. Stores an identifier (hereinafter referred to as narrow term ID) identifying the morpheme of the lower concept of the morpheme of the morpheme ID 401. The word ID 408 is an identifier (hereinafter referred to as a synonym, a term similar to, for example, a synonym, a co-occurrence word, an associative word, or an associative word). , Related word ID) is stored.

  By referring to the natural language classification dictionary 204 described above, the utterance analysis processing unit 203 can acquire the designated morpheme's prototype, part of speech, synonyms, broad terms, narrow terms, and related terms. Although not shown, the natural language classification dictionary 204 also stores antonyms for each morpheme.

  In the present embodiment, a common identifier is given to each of the synonym ID and the morpheme ID, and when searching a synonym for a morpheme of a certain morpheme ID, the record of the morpheme ID is stored. Information of the synonym can be acquired by acquiring the synonym ID and acquiring the record of the morpheme ID having the same identifier as the acquired synonym ID.

  Further, in the present embodiment, a common identifier is given to each of the broad-word ID and the morpheme ID, and when searching a broad-word for a morpheme of a certain morpheme ID, the record of the morpheme ID is stored. By acquiring a broad-word ID and referring to a record of morpheme ID having the same identifier as the acquired broad-word ID, information of the broad-word can be acquired.

  Further, in the present embodiment, a common identifier is given to each of the narrow term ID and the morpheme ID, and when searching a narrow term for a morpheme of a certain morpheme ID, a record in which the morpheme ID is stored By acquiring the narrow term ID and referring to the morpheme ID record having the same identifier as the acquired narrow term ID, it is possible to obtain information on the narrow term.

  Further, in the present embodiment, a common identifier is given to each of the related word ID and the morpheme ID, and when searching for a related word to a morpheme of a certain morpheme ID, the record in which the morpheme ID is stored By acquiring the related term ID and referring to the record of the morpheme ID having the same identifier as the acquired related term ID, it is possible to obtain information on the related term.

<Evaluation Expression Dictionary 205>
Next, the evaluation expression dictionary 205 will be described.
FIG. 6 is a diagram showing an example of the evaluation expression dictionary 205. As shown in FIG. As shown in the figure, the evaluation expression dictionary 205 is a database storing information of evaluation information (emotional polarity) of morphemes, and includes a main word ID 501, a main word 502, a dependent word ID 503, a dependent word 504, and an evaluation polarity value. It consists of at least one or more records including each item 505. In each of these items, for example, a character string or a numerical value is stored.

  A morpheme ID is stored in the main word ID 501. The morpheme ID stored in the main word ID 501 is a morpheme (hereinafter referred to as a main word, for example, a noun) in which the morpheme indicated by the morpheme ID can be a subject (for example, a subject) of a sentence.

  The main word 502 stores the content of the morpheme of the main word ID 501, and the dependent word ID 503 corresponds to the morpheme of the sentence corresponding to the morpheme of the main word ID 501 (hereinafter referred to as a dependent word. An identifier (hereinafter referred to as a dependent word ID) for identifying an adjective and an adjective verb is stored, and in the dependent word 504, a dependent word of a dependent word ID 503 is stored.

  The evaluation polarity value 505 stores information (hereinafter, referred to as a polarity value) representing the emotional polarity of a word obtained by combining the main word of the main word ID 501 and the dependent word of the dependent word ID 503 in a numerical value. For example, “1” is stored if the meaning of the word is positive, “−1” if the meaning of the word is negative, and “0” if the meaning of the word is neutral. For example, in the word "fruit is sweet" where the main word is "fruit" and the subordinate word is "sweet", the meaning of the word is positive, so "1" is included in the evaluation polarity value 505. Stored. On the other hand, in the word "check" is a main word "check" and the subordinate word "sweet", the meaning of the word is negative, so "-1" is included in the evaluation polarity value 505. Stored. In addition, in the words "the umbrella is the umbrella" and the subordinate words "is", and the word "the umbrella is in the umbrella", the meaning of the word is neither positive nor negative. Stores "0".

  By referring to the evaluation expression dictionary 205 described above, the utterance analysis processing unit 203 can acquire the polarity value of the designated morpheme in consideration of the relationship with the corresponding dependent word.

  The contents of the evaluation expression dictionary 205 may be input in advance by the user, or the discussion support apparatus 100 may automatically create the contents based on natural language processing technology or the like. Further, the content of the evaluation polarity value 505 may be based on a polarity value (for example, a real number in the range of −1 or more and 1 or less) acquired from a predetermined or manually created emotion dictionary.

  As shown in FIG. 3, the speech analysis processing unit 203 stores the result of speech analysis performed based on the natural language classification dictionary 204 and the evaluation expression dictionary 205 in the speech analysis result information 206.

<Sentence analysis result information 206>
FIG. 7 is a diagram showing an example of the utterance analysis result information 206. As shown in FIG. As shown in the figure, the speech analysis result information 206 includes a speech ID 601, a speech morpheme ID 602, a speech morpheme 603, a sentence evaluation polarity value 604, subject information 605, target information 606, state information 607, time information 608, position information 609. And at least one record including each item of reason information 610. For example, a character string or a numerical value is stored in each of these items.

  The speech ID 601 is similar to the speech ID 301 of the speech information 202. The utterance morpheme ID 602 stores the morpheme ID of the morpheme that constitutes the utterance of the utterance ID 601, and the utterance morpheme 603 stores the content of the morpheme of the utterance morpheme ID 602.

  In the sentence evaluation polarity value 604, the polarity value of the message of the message ID 601 is stored. For example, when the utterance of the utterance ID 601 is a positive expression, “1” is stored in the sentence evaluation polarity value 604, and when the utterance of the utterance ID 601 is negative, the sentence evaluation polarity value 604 is stored. When “−1” is stored and the utterance of the utterance ID 601 is neither a positive expression nor a negative expression, “0” is stored in the sentence evaluation polarity value 604. In the case where a real number of −1 or more and 1 or less is stored in the evaluation polarity value 505 of the evaluation expression dictionary 205, that value may be used.

  In the subject information 605, the object information 606, the state information 607, the time information 608, the position information 609, and the reason information 610, information of a morpheme viewpoint is stored.

  The subject information 605 stores information indicating whether or not the morpheme of the utterance morpheme ID 602 represents a subject. For example, when the morpheme of the utterance morpheme ID 602 represents the subject, “1” is stored in the subject information 605, and when the morpheme of the utterance morpheme ID 602 does not represent the subject, “0” is stored in the subject information 605. Is stored. Here, to represent a subject means, for example, corresponding to a so-called 5W1H Who (who is it?).

  The target information 606 stores information indicating whether the morpheme of the utterance morpheme ID 602 represents a target (for example, an object to be an operation target). For example, when the morpheme of the utterance morpheme ID 602 represents a target, “1” is stored in the target information 606, and when the morpheme of the utterance morpheme ID 602 does not represent a target, “0” is displayed in the target information 606. Is stored. In addition, expressing an object is, for example, corresponding to what is called 5W1H What.

  The state information 607 stores information indicating whether the morpheme of the utterance morpheme ID 602 represents a method. For example, when the morpheme of the utterance morpheme ID 602 represents a method, “1” is stored in the state information 607, and when the morpheme of the utterance morpheme ID 602 does not represent a method, “0” is displayed in the state information 607. Is stored. Note that expressing a method means, for example, corresponding to the so-called How of 5W1H.

  The time information 608 stores information indicating whether the morpheme of the utterance morpheme ID 602 represents time. For example, when the morpheme of the utterance morpheme ID 602 represents time, “1” is stored in the time information 608, and when the morpheme of the utterance morpheme ID 602 does not represent time, “0” is displayed in the time information 608. Is stored. In addition, expressing time is, for example, corresponding to what is called 5W1H When.

  The position information 609 stores information indicating whether the morpheme of the utterance morpheme ID 602 represents a place. For example, when the morpheme of the utterance morpheme ID 602 represents a place, “1” is stored in the position information 609, and when the morpheme of the utterance morpheme ID 602 does not represent a place, “0” is stored in the position information 609. Is stored. In addition, expressing a place is, for example, corresponding to the so-called 5W1H Where (where?).

  The reason information 610 stores information indicating whether the morpheme of the utterance morpheme ID 602 represents a reason. For example, if the morpheme of the utterance morpheme ID 602 indicates the reason, “1” is stored in the reason information 610, and if the morpheme of the utterance morpheme ID 602 does not indicate the reason, “0” is indicated in the reason information 610. Is stored. In addition, expressing a reason is, for example, corresponding to so-called 5W1H Why (why?).

  With reference to the statement analysis result information 206 described above, the statement analysis processing unit 203 determines, for the statement of the designated participant 13, a morpheme constituting the statement, a polarity value of the statement, and each statement constituting the statement. You can get morpheme perspectives.

  As shown in FIG. 3, the idea creation support processing unit 207 controls the speech analysis processing unit 203, the question sentence generation processing unit 210, and the display processing unit 211.

<Question Sentence Generation Processing Unit 210>
Next, the question sentence generation processing unit 210 (question generation unit) identifies the element corresponding to the utterance acquired by the utterance reception unit 201 based on the word decomposed by the utterance analysis processing unit 203, and identifies the element It is determined whether or not there is another element having a causal relationship with an element, and when it is determined that the other element is present, the other element is identified as the subject of the argument, and the identified element is identified. Based on the question about the object is generated.

  In addition, when it is determined that the question generation unit does not have the other element, the question generation unit selects at least one or more of the plurality of the points among the plurality of points of the specified element, and the point of the selected element And generate questions about the agenda.

  Further, the question generation unit determines whether or not there are a plurality of elements that are the cause of the specified element as the other element, and when it is determined that there are a plurality of elements that are the cause, the plurality If a question about the subject is generated based on a selected one of the elements of the element, and it is determined that there are not a plurality of cause elements, the question about the subject is generated based on the element that is the result of the specified element Generate a question.

  In addition, the question generation unit acquires evaluation information of the element specified by the utterance reception unit 201, and determines whether the evaluation information of the acquired utterance corresponds to the evaluation information of the acquired element. When it is determined that the two do not correspond, the word having the evaluation information different from the evaluation information of the element is extracted from the decomposed words, and the word different from the extracted word, and Generate questions about the subject based on other factors.

  The question generation unit determines whether the element corresponding to the utterance is an initial element in the argument, and determines that the acquired element is not an initial element. It is determined whether the evaluation information corresponds to the evaluation information of the specified element.

  Further, the question generation unit may determine whether the other element having a causal relationship with the element corresponding to the utterance is important based on the information indicating the importance in the argument set for each of the elements. If it is determined that the other element is important, a question about the agenda is generated based on the other element, and if it is determined that the other element is not important, Based on the decomposed words, a question on the subject is generated.

  In addition, the question generation unit determines whether or not the specified element is an element within the authority of the person making the discussion, and determines that the element is an element within the authority. , Generate questions about the agenda.

  The question generation unit stores an element used to generate a question and a viewpoint of the element.

<Agenda element information 208>
Here, the agenda element information 208 will be described.
FIG. 8 is a diagram showing an example of the agenda element information 208. As shown in FIG. As shown in the figure, the agenda element information 208 is a database storing information on causality between elements (nodes), and node ID 801, node name 802, node morpheme ID 803, node morpheme 804, viewpoint attribute 805. , Node evaluation polarity 806, control availability 807, cause node ID 808, result node ID 809, time series label 810, loop ID 811, and important node label 812 are constituted by at least one or more records. In each of these items, for example, a character string or a numerical value is stored.

  The node ID 801 stores the node ID, the node name 802 stores the name of the node of the node ID 801, and the node morpheme ID 803 stores the morpheme ID of the morpheme forming the node of the node ID 801. The content of the morpheme of the node morpheme ID 803 is stored in 804, and the viewpoint of the morpheme of the node morpheme 804 is stored in the viewpoint attribute 805. If there is no morpheme viewpoint of the node morpheme 804, nothing is stored in the viewpoint attribute 805.

  The node evaluation polarity 806 stores the polarity value of the node of the node ID 801. For example, “1” is stored if the event represented by the node of the node ID 801 is preferable, and “−1” is stored if the event is not desirable. For example, "1" is stored if the event is "yield", and "-1" is stored if the event is "number of traffic accidents". The content of the node evaluation polarity 806 may be input (set) by the user in advance, or data regarding an event indicated by the node of the node ID 801 by the discussion support apparatus 100 (for example, disclosed information such as news) ) From another device or network, analyze the acquired data (eg, analyze positive / negative evaluation for the event), convert the analyzed result into a polarity value, and store it in the node evaluation polarity 806. You may do so.

  In the control availability 807, information indicating whether the participant 13 has the authority for the event indicated by the node of the node ID 801 is stored. For example, if the event indicated by the node with the node ID 801 is an event within the authority (for example, within the business authority) of the participant 13 in the conference, “1” is stored, and the event indicated by the node with the node ID 801 is the participant in the conference 13 If the event is out of the authority (e.g., out of the business authority), "-1" is stored. For example, in the case where the participant 13 is engaged in the production of an object, if the event indicated by the node of the node ID 801 is “production amount”, the event is within the authority of the participant 13 and therefore controllability 807 If “1” is stored in, but the event indicated by the node with the node ID 801 is “low birthrate and aging,” “1” is stored in the control availability 807 because the event is out of the authority of the participant 13 Be done. The content of the control availability 807 may be set in advance, or may be set as needed during the meeting based on the utterance of the participant 13. Note that, for example, the participant 13 having the authority means that the participant 13 has the authority to be directly involved in the promotion or suppression of the event indicated by the node. For example, when the participant 13 belongs to a private enterprise but the event indicated by the node is a government policy, a natural phenomenon or the like, the participant 13 has no right.

  The cause node ID 808 stores the node ID of the node that is the cause of the node of the node ID 801 (that is, the node indicating the cause in the causal relationship; hereinafter, referred to as the cause node). If no cause node exists, “0” is stored.

  The result node ID 809 stores the node ID of the node that is the result of the node of the node ID 801 (that is, the node representing the result in the causal relationship; hereinafter, referred to as a result node). If no result node exists, “0” is stored.

  The time-series label 810 stores time-series information assumed by the agenda indicated by the node of the node ID 801. Specifically, information is stored in the time-series label 810 when a plurality of nodes including the node of the node ID 801 form a circulation of a causal relationship, and these plurality of circulating nodes (hereinafter referred to as a circulation node) The time series information (hereinafter referred to as a node time series) in a series of arguments indicated by) is stored. For example, in the time-series label 810, information such as "initial", "transition", "mature", "present", "5 years later", "10 years later" and the like are stored. Even if values are stored in the time-series label 810, such as “1” for “initial”, “2” for “transient period”, “3” for “mature period”, etc. Good. As a result, it becomes possible to grasp which stage the participants 13 discuss in chronological order.

  The loop ID 811 stores an identifier of a circulating node to which the node of the node ID 801 belongs (hereinafter referred to as a loop ID).

  The important node label 812 stores information indicating the importance of the node of the node ID 801 (hereinafter referred to as the important node label). Specifically, when the event indicated by the node with the node ID 801 is an event to be deepened in the discussion, “1” is stored in the important node label 812 and the event indicated by the node with the node ID 801 is the argument The important node label 812 stores “0” when it is an event that should not be deepened at. The contents of the important node label 812 may be set by the user (the moderator 12 or the like), or may be set based on a predetermined rule. For example, when the node with the node ID 801 is a node constituting two different cyclic nodes, or when the node time series of the node with the node ID 801 is a node time series different from its causal node or its resultant node The node label 812 may be set to “1”.

  By referring to the above-mentioned agenda element information 208, the message analysis processing unit 203 designates the morpheme that constitutes the designated node, the viewpoint of each morpheme that constitutes the designated node, the polarity value of the designated node, It is possible to acquire the authority of the specified node, the cause node or the result node of the specified node, the time series of the specified node, the importance of the specified node, and the circulating node etc. configured by the specified node. .

  Here, the causal loop diagram output to the discussion support system 10 based on the agenda element information 208 will be described.

<Causal loop diagram 700>
FIG. 9 is a diagram for explaining an example of a causal loop diagram. As shown in the figure, the causal loop diagram 700 includes a plurality of nodes 701 (701 (1) to (7)) indicating nodes, and a link 702 connecting two nodes 701. Ru.

  A link 702 indicates that there is a causal relationship between the two nodes 701. In the present embodiment, the links 702 are indicated by arrows. That is, the node 701 connected to the end point of the arrow of the link 702 is a result node, and the node 701 connected to the start point of the arrow indicated by the link 702 is a cause node. Each link 702 is represented by a solid or broken arrow. If the arrow on link 702 is a solid line, the relationship between the two nodes 701 linked to link 702 is positively correlated, and if the arrow on link 702 is a dotted line, the link 702 is linked to 2 The relationship between two nodes 701 is negatively correlated.

  Also, the causal loop diagram 700 indicates this by means of a loop 703 when causality is circulating among a plurality of nodes. In the example of the figure, the node 701 (2) (node A) is the cause node of the node 701 (3) (node B), and the node 701 (3) (node B) is the node 701 (4) (node C) Node 701 (4) (node C) is the cause node of node 701 (5) (node D), and node 701 (5) (node D) is the node 701 (2) (node A). Is the cause node of

  In the agenda element information 208 of FIG. 8 corresponding to these, the cause node of the node 701 (5) (node D) is the node 701 (4) (node C) and the node 701 (5) (node D). Since the result node is the node 701 (2) (node A), “1” is stored in the loop ID 811. Also, since the cause node of the node 701 (5) (node D) is the node 701 (7) (node F) and the result node is the node 701 (2) (node A), the loop ID 811 is “2”. Is stored.

  The causal loop diagram 700 may be output to, for example, the output device 105 of the discussion support device 100 or may be output to the screen 14.

  For each element shown in the causal loop diagram 700 or the like, information on a case related to each element (hereinafter referred to as a related case) is stored in the agenda related case information 209.

<Agenda related case information 209>
FIG. 10 is a diagram showing an example of the agenda related case information 209. As shown in FIG. As shown in the figure, the agenda related case information 209 is a database storing related agendas, and includes a node ID 901, a node configuration case ID 902, a node configuration case name 903, a node configuration case morpheme ID 904, a node configuration case morpheme 905, and It is composed of at least one or more records including each item of the viewpoint attribute 906. In each of these items, for example, a character string or a numerical value is stored.

  The same information as the node ID 801 is stored in the node ID 901, the identifier of the related case of the node of the node ID 901 (hereinafter referred to as the related case ID) is stored in the node configuration case ID 902, and the node configuration case name 903 is stored. The contents of the related case of the node configuration case ID 902 are stored. For example, when the node ID 901 stores the phrase "price of domestic vegetables", the node configuration example name 903 includes "weather of the production area" or "example of weather required for discussing prices of domestic vegetables". The information of the phrase "import quantity from foreign countries" is stored.

  The node configuration case morpheme ID 904 stores an identifier (hereinafter, referred to as a related case morpheme ID) of a morpheme (hereinafter, referred to as a related case morpheme) constituting a related case of the node configuration case ID 902.

  The content of the related case morpheme is stored in the node configuration case morpheme 905, and the information of the related case morpheme of the node configuration case morpheme 905 is stored in the viewpoint attribute 906. If there is no corresponding viewpoint, nothing is stored in the node configuration case morpheme 905.

  The above-mentioned agenda related case information 209 acquires the contents of the related case of the designated node, the morphemes constituting the related case of the node, and the viewpoints of the morphemes constituting the related case of the node.

  Returning to FIG. 3, the display processing unit 211 includes a question output unit 212 and a viewpoint output unit 213.

  The question output unit 212 outputs the question generated by the question generation processing unit.

  The viewpoint output unit 213 outputs the viewpoint included in the element used to generate the question and the viewpoint included in the acquired word.

  The functions of the discussion support apparatus 100 described above can be realized by the hardware of the discussion support apparatus 100 or the central processing unit 101 of the discussion support apparatus 100 stores programs stored in the storage device 102 or the secondary storage device 103. It is realized by reading out and executing. Note that this program may be recorded on a recording medium such as an IC card, an SD card, or a DVD.

<< Process Performed by Discussion Support System 10 >>
Next, the process performed in the discussion support system 10 will be described.

<Overall processing>
FIG. 11 is a flowchart illustrating an outline of processing performed by the discussion support device 100. Note that this process (hereinafter referred to as the entire process) is performed, for example, when the discussion support apparatus 100 is activated or when a predetermined timing set in the discussion support apparatus 100 arrives (for example, a predetermined time interval). ) Is done.

  As shown in the figure, first, the idea creation support processing unit 207 selects one node (S1001). Specifically, for example, the idea creation support processing unit 207 receives from the presenter 12 an input of one of the node IDs stored in the agenda element information 208, or a node stored in the agenda element information 208. Among IDs, a node ID which has not been selected so far and whose value is the largest is selected. Hereinafter, the node of the selected node ID is referred to as a selected node.

  The speech reception unit 201 waits for acquisition of the speech of the participant 13 (speaker 11 or presenter 12) (S1002: NO).

  When the message is acquired (S1002: YES), the message analysis processing unit 203 analyzes the message acquired in S1002 (S1003). Specifically, the speech analysis processing unit 203 utilizes natural language processing technology of morphological analysis, syntactic analysis, semantic analysis, case grammar, emotion analysis, and the natural language classification dictionary 204 and evaluation expression dictionary. Based on 205, morphemes are extracted from the utterances of the participants or the presenter, a viewpoint for the extracted morphemes is added, and the utterances are polarized, and these results are stored in the utterance analysis result information 206.

  The question statement generation processing unit 210 generates a question statement based on the contents of the message acquired in S1002, the morpheme of the selection node, the importance of the selection node, the circulation node to which the selection node belongs, etc. (hereinafter, question statement generation processing ) Is performed (S1004). Details of the question sentence generation process will be described later.

  Next, the display processing unit 211 outputs the question sentence created in S1004 (S1005).

  The speech reception unit 201 determines whether the participant 13 has made a speech in response to the question sentence created in S1005 (S1006). Specifically, the speech reception unit 201 monitors whether or not a new speech has been acquired from the participant 13 for a predetermined time.

  When an utterance is newly acquired from the participant 13 (S1006: YES), the process returns to S1003, and when a new utterance is not acquired from the participant 13 (S1006: NO), the process proceeds to S1007. move on.

  In step S1007, the idea creation support processing unit 207 determines whether to end the discussion on the selected node selected in step S1001. Specifically, for example, the idea creation support processing unit 207 receives, from the participant 13 (for example, the presenter 12), an input as to whether or not to end the discussion on the selected node, and determines the content of the received input. .

  If the discussion on the selected node is ended (S1007: YES), the process proceeds to S1008. If the discussion on the selected node is not ended (S1007: NO), the process returns to S1004.

  In S1008, the idea creation support processing unit 207 determines whether there is a node for which a question sentence has not been generated. If there is a node for which a question sentence has not been generated (S1008: YES), the idea creation support processing unit 207 sets the node as a selected node and repeats the process of S1001. On the other hand, when there is no node for which the question sentence has not been generated (S1008: NO), the whole process ends (S1009).

<Question sentence generation process>
The details of the question sentence generation process will be described.
12 and 13 are flowcharts for explaining the details of the question sentence generation process (the drawings are divided into two for convenience of the paper).

  As shown in FIG. 12, the question sentence generation processing unit 210 determines whether the selected node is an initial element of the discussion (S1101). Specifically, the question sentence generation processing unit 210 refers to the agenda element information 208 and determines whether or not the time-series label of the selected node is “1”.

  If the selected node is an initial element of the discussion (S1101: YES), the processing proceeds to S1102, and if the selected node is not an initial element of the discussion (S1101: NO), the processing is S1112 (FIG. 13) Go to

  In S1102, the query sentence generation processing unit 210 determines whether the selected node is important in the discussion. Specifically, the question sentence generation processing unit 210 refers to the agenda element information 208 and determines whether the important node label of the record of the selected node is “1”.

  If the selected node is important in the discussion (S1102: YES), the process proceeds to S1104. If the selected node is not important in the discussion (S1102: NO), the process proceeds to S1103.

  In S1104, the question sentence generation processing unit 210 determines whether the question sentence has been generated based on the morphemes of all the viewpoints of the selected node. When the question sentence is generated based on the morphemes of all the viewpoints of the selected node (S1104: YES), the question sentence generation process is ended (S1130), and the question sentence based on the morphemes of all the viewpoints of the selected node is generated If not (S1104: NO), the process proceeds to S1109.

  In S1109, the question sentence creation processing unit 210 determines whether or not the cause node of the selected node or the result node of the selected node (hereinafter referred to as the front and rear nodes) is important. Specifically, for example, the question sentence generation processing unit 210 obtains the cause node of the selected node and the result node of the selected node by referring to the agenda element information 208, and then, again, the agenda element information 208 By referring to it, it is determined whether the important node label of the cause node or the important node label of the result node is “1”.

  If the cause node of the selection node or the result node of the selection node is important, the process proceeds to S1110 (S1109: YES), if none of the cause node of the selection node and the result node of the selection node is important (S1109: NO), the process proceeds to S1111.

  In S1110, the question sentence generation processing unit 210 generates a question sentence about the subject based on the important cause node or result node (hereinafter, referred to as a front / rear important node).

  Specifically, the question sentence generation processing unit 210 refers to the agenda element information 208 and the agenda related case information 209 to select one of the viewpoints of the question sentences generated so far, which is not used in the selected node. select. Next, the question sentence generation processing unit 210 acquires each morpheme of the front and back important nodes and each morpheme of the related case of the front and back important nodes (hereinafter, referred to as unused viewpoint morpheme in this paragraph) having the selected viewpoint. Then, the question sentence generation processing unit 210 generates a question sentence asking about the unused viewpoint morpheme. Thus, the question sentence generation process ends (S1130).

  In S1111, the question sentence generation processing unit 210 selects, from among the plurality of viewpoints of the selection node, the viewpoint of the selected node which has not been used in the generation of the question sentence, and selects each of the selected nodes having the selected viewpoint. Generate questions about the agenda based on morphemes.

  Specifically, by referring to the agenda element information 208, the question sentence generation processing unit 210 acquires the viewpoints of the selected nodes not used in the question sentences generated so far among all the viewpoints of the selected nodes. . Then, the question sentence generation processing unit 210 acquires each morpheme of the selected node having the acquired viewpoint, and generates a question sentence asking about each acquired morpheme. Thus, the question sentence generation process ends (S1130).

  On the other hand, in S1103, the question sentence creation processing unit 210 determines whether or not the selected node is an element within the authority of the participant 13. Specifically, the question sentence creation processing unit 210 determines whether the selected node is an element within the authority of the participant 13 by referring to the agenda element information 208.

  If the selected node is an element within the authority of the participant 13 (S1103: YES), the process proceeds to S1105, and if the selected node is not an element within the authority of the participant 13 (S1103: NO) , And the question sentence generation process ends.

  In S1105, by referring to the statement information 202 and the statement analysis result information 206, the question sentence generation processing unit 210 makes a statement in terms of the utterances of the participants 13 up to now among the plurality of viewpoints of the selected node. Identify the many points of view. Then, the question sentence generation processing unit 210 determines whether or not the question sentence based on the selected node having the identified viewpoint has been generated so far. Note that “a viewpoint with a large number of utterances” may be, for example, a viewpoint with the largest number of utterances among the viewpoints of participants 13 mentioned above, or may be a predetermined one among the viewpoints of participants 13 It may be all viewpoints in which more than the number of statements have been made.

  If the question sentence is generated (S1105: YES), the question sentence generation process ends (S1130), and if the question sentence is not generated (S1105: NO), the process proceeds to S1106.

  In S1106, the question sentence creation processing unit 210 determines whether the preceding and succeeding nodes are important as in S1109. If the front and back nodes are important (S1106: YES), the processing proceeds to S1107, and if the front and back nodes are not important (S1106: NO), the processing proceeds to S1108.

  In S1107, the question sentence generation processing unit 210 generates a question sentence about the agenda based on the front and back nodes.

  Specifically, for example, the question sentence generation processing unit 210 first acquires the viewpoint identified in S1105 and in which there are many utterances. In addition, the question sentence generation processing unit 210 refers to the agenda element information 208 and the agenda related case information 209 to find each morpheme of the front and back important nodes and each morpheme of the related case of the front and back important nodes (hereinafter referred to as front and back important in this paragraph). Get a morpheme). Next, the question sentence generation processing unit 210 acquires morphemes having the acquired many viewpoints among the important morphemes before and after. Then, the question sentence generation processing unit 210 generates a question sentence asking about each acquired morpheme. Thus, the question sentence generation process ends (S1130).

  In S1108, the question sentence generation processing unit 210 generates a question sentence about the subject based on the remarks of the participant 13.

  Specifically, for example, the question sentence generation processing unit 210 first acquires the viewpoint specified in S1105. In addition, the question sentence generation processing unit 210 acquires the morpheme of the utterance acquired in S1003. Next, the question sentence generation processing unit 210 acquires the related words of the acquired morphemes by referring to the natural language classification dictionary 203. Then, the question sentence generation processing unit 210 generates a question sentence asking about the acquired related word. Thus, the question sentence generation process ends (S1130).

  As shown in FIG. 13, in step S1112, the question sentence generation processing unit 210 determines whether the selected node is important in the discussion, as in step S1102. If the selected node is important in the discussion (S1112: YES), the process proceeds to S1113. If the selected node is not important in the discussion (S1112: NO), the process proceeds to S1114.

  In S1113, as in S1104, the question statement generation processing unit 210 determines whether the question statement has been generated based on the morphemes of all the viewpoints of the selected node. If the question sentence is generated based on the morphemes of all the viewpoints of the selected node (S1113: YES), the process proceeds to S1116, and the question sentence is not generated based on the morphemes of all the viewpoints of the selected node. (S1113: NO), the process proceeds to S1115.

  In S1116, the question message generation processing unit 210 determines whether or not the evaluation information of the utterance of the participant 13 corresponds to the evaluation information of the selected node. Specifically, for example, the question sentence generation processing unit 210 acquires the polarity value of the utterance acquired in S1002 by referring to the utterance analysis result information 206, and refers to the agenda element information 208, thereby selecting the polarity of the selected node. A value is acquired, and it is determined whether or not the acquired two polarity values match (or whether or not the polarity of the two polarity values match).

  If the evaluation information of the two does not correspond (S1116: NO), the process proceeds to S1119, and if the evaluation information of the two correspond (S1116: YES), the question sentence generation process ends (S1130).

  In S1119, the question sentence creation processing unit 210 determines whether there is a plurality of cause nodes of the selected node as nodes having a causal relationship with the selected node. Specifically, the question sentence creation processing unit 210 determines whether there is a plurality of cause nodes of the selected node by referring to the agenda element information 208.

  If there are multiple cause nodes of the selected node (S1119: YES), the process proceeds to S1121, and if there are not multiple cause nodes of the selected node (one or no cause nodes of the selected node) (S1119: NO), The processing proceeds to step S1120.

  In S1121, the question sentence creation processing unit 210 selects one of the plurality of cause nodes, and generates a question on the subject based on the selected cause nodes.

  Specifically, for example, the question sentence generation processing unit 210 first acquires the viewpoint of each morpheme of the utterance of the selected node by referring to the utterance information 202 and the utterance analysis result information 206. Next, the question sentence generation processing unit 210 selects one of the plurality of cause nodes which has not been selected so far (or the cause node of which the number of times of selection is smaller). And each morpheme of the related case of its cause node (hereinafter referred to as the same-view morpheme in the present paragraph) is acquired by referring to the agenda element information 208 and the agenda related case information 209. Next, the question sentence generation processing unit 210 identifies a morpheme having a polarity value that is different (or different) from the polarity value of the selected node among the morphemes of the utterance acquired in S1003 and identifies an antonym of the identified morpheme Get an antinym that reverses the polarity. Then, the question sentence generation processing unit 210 generates a question asking about the acquired same-viewpoint morpheme and the acquired opposite word. Thus, the question sentence generation process ends (S1130).

  On the other hand, in S1120, the question sentence creation processing unit 210 creates a question about the agenda based on the result node of the selected node.

  Specifically, for example, the question sentence generation processing unit 210 first acquires the viewpoint of the morpheme of the utterance acquired in S1003. In addition, the question sentence generation processing unit 210 generates agenda element information 208 and agenda related case information 209 for each morpheme of the result node of the selected node and each morpheme of the related case of the result node (hereinafter referred to as result morpheme in this paragraph). Acquired by referring to. Then, the question sentence generation processing unit 210 acquires each morpheme having the acquired viewpoint among the resultant morphemes. In addition, the question sentence generation processing unit 210 identifies a morpheme having a polarity value that is different (or different) from the polarity value of the selected node among the morphemes of the utterance acquired in S1003 and identifies an antonym of the identified morpheme Get an antinym that reverses the polarity. Then, the question sentence generation processing unit 210 generates a question asking about the acquired opposite word and each acquired morpheme in the resultant morpheme. Thus, the question sentence generation process ends (S1130).

  In S1114, the question message generation processing unit 210 determines whether the selected node is within the authority of the participant 13 as in S1103.

  If the selected node is within the authority of the participant 13 (S1114: YES), the process proceeds to S1122, and if the selected node is not within the authority of the participant 13 (S1114: NO), question sentence generation The process ends (S1130).

  In S1122, the question statement generation processing unit 210 refers to the statement information 202 and the statement analysis result information 206 in the same manner as the step S1105 in the question statement generation processing unit 210, among the plurality of viewpoints of the selected node. The viewpoint in which many utterances were made in the viewpoint of the participant 13 until now is specified. Then, the question sentence generation processing unit 210 determines whether or not the question sentence based on the selected node having the identified viewpoint has been generated so far.

  If the question sentence is generated (S1122: YES), the process proceeds to S1124. If the question sentence is not generated (S1122: NO), the process proceeds to S1123.

  In S1123, the question statement generation processing unit 210 generates a question statement on the agenda based on the remarks of the participant 13.

  Specifically, for example, the question sentence generation processing unit 210 acquires the viewpoint identified in S1122 in which there are many utterances. Next, the question sentence generation processing unit 210 acquires the morphemes of the utterance acquired in S1003, and acquires the morphemes having the many viewpoints among the acquired morphemes. Then, the question sentence generation processing unit 210 generates a question sentence asking about each acquired morpheme. Thus, the question sentence generation process ends (S1130).

  On the other hand, in S1124, as in S1116, the question sentence generation processing unit 210 determines whether the evaluation information of the utterance of the participant 13 corresponds to the evaluation information of the selected node.

  If the two pieces of evaluation information correspond to each other (S1124: YES), the question sentence generation process ends (S1130). If the two pieces of evaluation information do not correspond to each other (S1124: NO), the process proceeds to S1125.

  In S1125, as in S1106, the query statement generation processing unit 210 determines whether the cause node of the selected node or the result node (pre- and post-nodes) of the selected node is important. If the cause node of the selection node or the result node of the selection node is important (S1125: YES), the process proceeds to S1127, and if the cause node of the selection node and the result node of the selection node are not important ( S1125: NO), the process proceeds to S1126.

  In S1126, the question sentence generation processing unit 210 extracts a morpheme having evaluation information different from the evaluation information of the selected node from the morphemes of the utterance of the participant 13 associated with the selected node, and extracts the extracted morpheme Generate questions about the agenda based on different morphemes.

  Specifically, for example, the question sentence generation processing unit 210 first acquires the viewpoint of each morpheme of the utterance acquired in S1003. Next, the question sentence generation processing unit 210 determines that each morpheme of the front and back nodes and each morpheme of the related case of the front and back nodes (hereinafter referred to as the same viewpoint morpheme in this paragraph) having the same viewpoint as the acquired viewpoints It acquires by referring to 208 and the agenda related case information 209. In addition, the question sentence generation processing unit 210 acquires morphemes having polarity values that are different (or different in polarity) from the polarity value of the selected node among the morphemes of the utterance acquired in S1003 and An antinym that inverts the polarity is obtained by referring to the natural language classification dictionary 204. Then, the question sentence generation processing unit 210 generates a question sentence that asks about the acquired same-point morpheme and the acquired opposite word. Thus, the question sentence generation process ends (S1130).

  In S1127, the question sentence generation processing unit 210 generates a question sentence based on the selected node (S1127).

  Specifically, for example, the question sentence generation processing unit 210 first acquires a morpheme having a polarity value different (or different in value) from the polarity value of the selected node among the morphemes of the utterance acquired in S1003. The antinym of the acquired morpheme (antinym that reverses the polarity) is acquired by referring to the evaluation expression dictionary 205. Next, the question sentence generation processing unit 210 acquires the morpheme having a viewpoint with a large number of utterances specified in S1122, and acquires the related term of the acquired morpheme by referring to the natural language classification dictionary 204. Then, the question sentence generation processing unit 210 generates a question sentence asking about the acquired opposite word and the acquired related word. Thus, the question sentence generation process ends (S1130).

  In S1115, as in S1106, the query statement generation processing unit 210 determines whether the cause node of the selected node or the result node of the selected node is important. If the cause node of the selection node or the result node of the selection node is important, the processing proceeds to S1118, and if neither the selection node's cause node nor the selection node result node is important, the processing is S1117 Go to

  In S1118, as in S1107, the question statement generation processing unit 210 generates a question statement asking questions about the agenda based on the front and rear important nodes. Thus, the question sentence generation process ends (S1130).

  On the other hand, in step S1117, the question statement generation processing unit 210 generates a question statement on the subject based on the remarks of the participant 13 as in step S1108. Thus, the question sentence generation process ends (S1130).

  As described above, according to the discussion support system 10 of the present embodiment, the content of the utterance made by the speaker is acquired and decomposed into a plurality of words, and the element corresponding to the utterance is divided based on the decomposed words. If it is determined that there is another element that has been identified and has a causal relationship with the identified element, and if it is determined that there is another element, a question about the agenda is generated based on the other elements and generated Since the question is output, it is possible to present a new development of the discussion to the discussion participants 13. In this way, each participant 13 of the discussion can effectively create a new idea based on the speaking condition of the participant 13. For example, according to the discussion support system 10 of the present embodiment, the participant 13 can make an argument by combining creative keywords necessary for creating a new idea, or make an idea from a viewpoint different from the conventional one. it can.

  Further, according to the discussion support system 10 of the present embodiment, when there is no other element having a causal relationship, the question about the agenda is selected based on the element corresponding to the utterance having the viewpoints selected from a plurality of viewpoints. Since there is no topic having a causal relationship with the remark, and it is not appropriate to widely discuss the remark, the participant 13 of the discussion can discuss the remarks in detail based on each viewpoint. You can dig deeper into the debate.

  Further, according to the discussion support system 10 of the present embodiment, when there are a plurality of causal elements as other elements having a causal relationship, a question on the agenda is made based on the selected element among the plurality of elements. If there is more than one causative element, the question about the agenda is generated based on the element that is the result, so if there is more than one topic that is the cause of the statement, The discussion can be guided to one of the topics (the topic that is causing the remark), otherwise the participants can be guided to the topic that results in the remark. Thereby, the awareness of the participant 13 in the discussion can be guided to an appropriate topic in the vicinity, and the participant 13 can effectively discuss the topic related to the agenda. Thereby, for example, it is possible to present to the presenter 12 a question sentence that utilizes a point of view that has not been discussed yet, and this makes it possible to realize an argument without omission or omission.

  Further, according to the discussion support system 10 of the present embodiment, when the evaluation information of the utterance does not correspond to the evaluation information of the element, it has the evaluation information different from the evaluation information of the element among the words of the utterance. Since a word is extracted, and a question about an agenda is generated based on the extracted word and a different word, and the other elements, if there is a conflict between the evaluation of the node and the evaluation of the participant 13, the node By presenting a question sentence that utilizes the content assumed by the user (for example, the content assumed by the presenter 12), intensive discussion can be conducted that incorporates a different viewpoint from the content of the speech of the participants 13 so far it can.

  Further, according to the discussion support system 10 of the present embodiment, it is determined whether the element corresponding to the utterance is an initial element in the argument, and the evaluation of the utterance is performed only when it is determined that the element is not an initial element. Since it is judged whether the information corresponds to the evaluation information of the element, for example, in the initial stage of the discussion, the speech of the participant 13 is prioritized, and in the stage where the discussion is advanced, the speech of the participant 13 of the discussion A discussion can be made by adding the viewpoint of the content assumed by the node (for example, the content assumed by the chairman 12) to the content. Thus, depending on the degree of progress of the discussion of the participant 13, the discussion can be flexibly guided in an appropriate direction.

  Further, according to the discussion support system 10 of the present embodiment, when another element having a causal relationship with the element corresponding to the utterance is important, a question about the agenda is generated based on the other elements, and the other If the elements of are not important, they will generate questions about the agenda based on the words of the statement, so the participants 13 of the discussion focus on the topics to be discussed, depending on the importance of the topics shown by each node Can be discussed.

  Further, according to the discussion support system 10 of the present embodiment, since the question about the agenda is generated only when the element is an element within the authority of the speaker, the participants 13 of the discussion are the results of the discussion, You can exercise your own authority to solve the problem. Thus, the participant 13 can perform practical discussions.

Finally, the screen output by the discussion support system 10 will be described.
<Discussion progress screen>
FIG. 14 is an example of a screen (hereinafter, referred to as a discussion progress screen) output by the viewpoint output unit 213 to the screen 14. As shown in the figure, the discussion screen 1201 is a diagram showing the degree of progress of the discussion, and a causal loop display unit 1202, a notable node viewpoint display unit 1203, an important node viewpoint display unit 1204, and a question message presentation management unit 1205. Of each output item. Further, the question sentence presentation management unit 1205 has output items of the question sentence display unit 1206 and the question sentence display result operation unit 1207.

  A causal loop diagram is output to the causal loop display unit 1202. In this case, a node having a causal relationship with the selected node may be additionally output to the causal loop display unit 1202. In addition, only selected nodes may be emphasized and output (for example, display with a bold frame or enlarged display), or important nodes may be emphasized and output (for example, display by double lines) And enlarged view). As a result, the participant 13 can easily identify the node currently being discussed from the nodes set as the agenda.

  The notable node viewpoint display unit 1203 outputs each morpheme of the utterance issued by the participant 13 and the viewpoint of the morpheme. As a result, the participant 13 can check the viewpoint (5W1H) of many utterances and the viewpoint that has not been spoken yet regarding the selected node.

  The important node viewpoint display unit 1204 outputs each morpheme of the outputted question sentence and the viewpoint of the morpheme. This allows the participant 13 to confirm the viewpoints that have been discussed a lot, and the viewpoints that have not been discussed yet.

  The question sentence presentation management unit 1205 outputs the question sentence generated for the selected node. The question text to be output may be a sentence such as “What is xxx (subject) of □□□ (place)?” Or the like, such as “□□□ (place), xxx (subject)” It may be a combination of different words.

  In addition, the question statement display result operation unit 1207 has input fields of a display 1208, a correction 1209, and a cancel 1210.

  When the display 1208 is pressed, the question sentence outputted to the question sentence display unit 1206 is outputted to another information processing apparatus (for example, an information processing apparatus possessed by each participant 13).

  When the correction 1209 is pressed, input (correction) of the question sentence output to the question sentence display unit 1206 is accepted.

  When the cancel 1210 is pressed, the question sentence output to the question sentence display unit 1206 is not displayed or another question sentence is output.

  Note that the display 1208, the correction 1209, or the cancellation 1210 may be output only to the information processing apparatus that the presenter 12 has.

  As described above, since the viewpoint output unit 213 outputs the viewpoints of the elements used for generating the question and the viewpoints of the speech morpheme, the participant 13 can speak or discuss any viewpoints. You can easily know if you are

  The above description of the embodiments is intended to facilitate understanding of the present invention, and is not intended to limit the present invention. The present invention can be modified and improved without departing from the gist thereof, and the present invention includes the equivalents thereof.

DESCRIPTION OF REFERENCE NUMERALS 10 discussion support system, 13 participants, 100 discussion support apparatus, 201 statement reception unit, 203 statement analysis processing unit, 210 question sentence generation processing unit, 213 viewpoint output unit

Claims (15)

A discussion support system comprising a processor and a memory and supporting discussions on a multi-element agenda, comprising:
A speech acquisition unit for acquiring the contents of the speech issued by the speaker on the subject,
An utterance analysis processing unit that decomposes the acquired utterance into a plurality of words;
Based on the decomposed words, the element corresponding to the acquired utterance is identified, and whether or not there is another important element in the agenda having a causal relationship with the identified element, between the elements in the agenda Judging on the basis of the information defining the causal relationship between the information and the information indicating the importance in the argument set for each of the elements, and judging that the other element is present, the other elements A question generation unit generating questions about the agenda based on questions about morphemes of the other elements and morphemes of related cases associated with the other elements ;
A question output unit that outputs the generated question;
, A discussion support system. If the question generation unit determines that the other element is not present, the question generation unit selects and selects at least one or more of the plurality of points of the specified element that have not been selected so far. Generating a question about the agenda questioning the morpheme having the selected view in the identified element based on the view of the selected element ,
The discussion support system according to claim 1. The question generation unit determines, as the other element, whether or not there are a plurality of elements that are the cause of the specified element, and when it is determined that there are a plurality of the elements that are the cause, the plurality of elements If the question about the subject is generated based on the selected element among the above, and it is determined that there is not more than one factor causing the problem, the question about the subject is selected based on the element that is the result of the identified element Generate,
The discussion support system according to claim 1. The utterance analysis processing unit acquires evaluation information of the acquired utterance,
The question generation unit acquires evaluation information of the identified element, determines whether the evaluation information of the acquired utterance and the evaluation information of the acquired element correspond, and both correspond. If it is determined that there is not, the word having the evaluation information different from the evaluation information of the element is extracted from the decomposed words, and the word different from the extracted word and the other element are extracted, Generating a question on the agenda asking the morpheme of the other element and the morphemes of related cases of the other element and the different words ,
The discussion support system according to claim 1. The question generation unit determines whether the element corresponding to the utterance is an initial element in the argument, and the evaluation information of the acquired utterance is determined only when it is determined that the element is not an initial element. To determine whether the evaluation information of the identified element corresponds to
The discussion support system according to claim 4. The question generation unit determines whether or not the other element having a causal relationship with the element corresponding to the utterance is important, based on the information indicating the importance in the argument set for each of the elements. And, if it is determined that the other element is important, ask about the morpheme of the other element and the morpheme of the related case corresponding to the other element based on the other element, Generating a question about the subject, asking about related words of the decomposed word based on the decomposed word, if the other element is determined to be unimportant,
The discussion support system according to claim 1. The question generation unit determines whether or not the specified element is an element within the authority of the person making the discussion, and determines that the element is an element within the authority. Generate questions about the agenda,
The discussion support system according to claim 1. The utterance analysis processing unit acquires a viewpoint of the decomposed word.
The discussion support system further includes a viewpoint output unit that outputs a viewpoint of the element used to generate the question and a viewpoint of the acquired word.
The discussion support system according to claim 2. If the question generation unit determines that the other element is not present, the question generation unit selects and selects at least one or more of the plurality of points of the specified element that have not been selected so far. Generating a question about the agenda questioning the morpheme having the selected viewpoint in the identified element based on the viewpoint of the selected element ;
The question generation unit determines, as the other element, whether or not there are a plurality of elements that are the cause of the specified element, and when it is determined that there are a plurality of the elements that are the cause, the plurality of elements If the question about the subject is generated based on the selected element among the above, and it is determined that there is not more than one factor causing the problem, the question about the subject is selected based on the element that is the result of the identified element Generate
The utterance analysis processing unit acquires evaluation information of the acquired utterance,
The question generation unit acquires evaluation information of the identified element, determines whether the evaluation information of the acquired utterance and the evaluation information of the acquired element correspond, and both correspond. If it is determined that there is not, the word having the evaluation information different from the evaluation information of the element is extracted from the decomposed words, and the word different from the extracted word and the other element are extracted, Generating a question on the agenda asking the morpheme of the other element and the morphemes of related cases of the other element and the different words ;
The question generation unit determines whether the element corresponding to the utterance is an initial element in the argument, and the evaluation information of the acquired utterance is determined only when it is determined that the element is not an initial element. And whether or not the evaluation information of the specified element corresponds to each other,
The question generation unit determines whether or not the other element having a causal relationship with the element corresponding to the utterance is important, based on the information indicating the importance in the argument set for each of the elements. And, if it is determined that the other element is important, ask about the morpheme of the other element and the morpheme of the related case corresponding to the other element based on the other element, Generating a question about the subject, asking about related words of the decomposed word based on the decomposed word, if the other element is determined to be unimportant,
The question generation unit determines whether or not the specified element is an element within the authority of the person making the discussion, and determines that the element is an element within the authority. Generate questions about the agenda,
The utterance analysis processing unit acquires a viewpoint of the decomposed word.
The discussion support system further includes a viewpoint output unit that outputs a viewpoint of the element used to generate the question and a viewpoint of the acquired word.
The discussion support system according to claim 1. A discussion support method for supporting a discussion on a multi-element agenda by a computer having a processor and a memory, comprising:
The computer is
Acquire the content of the utterance made by the speaker on the above-mentioned agenda,
Decompose the acquired statement into a plurality of words,
Based on the decomposed words, the element corresponding to the acquired utterance is identified, and whether or not there is another important element in the agenda having a causal relationship with the identified element, between the elements in the agenda Judging on the basis of the information defining the causal relationship between the information and the information indicating the importance in the argument set for each of the elements, and judging that the other element is present, the other elements Generating questions about the agenda based on questions about morphemes of the other elements and morphemes of related cases associated with the other elements ;
Output the generated question,
Discussion support method. When the computer determines that the other element is not present, the computer selects and selects at least one or more of the plurality of aspects that the identified element has not been selected so far. Generating a question about the agenda questioning the morpheme having the selected view in the identified element based on the view of the element ;
A discussion support method according to claim 10. The computer is
The evaluation information of the acquired statement is acquired,
Obtain evaluation information of the specified element,
It is determined whether the evaluation information of the acquired utterance and the evaluation information of the acquired element correspond to each other, and when it is determined that the both do not correspond, the word among the decomposed words The word having evaluation information different from the evaluation information of the element is extracted, the morpheme of the other element and the morpheme of the related case of the other element are extracted based on the extracted word and the different word and the other element Ask about the different words , generate questions about the agenda,
A discussion support method according to claim 10. A discussion support program for supporting discussions on a multi-element agenda, comprising: a computer having a processor and a memory;
A speech acquisition process for acquiring the contents of the speech issued by the speaker on the above-mentioned agenda,
An utterance analysis process that decomposes the acquired utterance into a plurality of words;
Based on the decomposed words, the element corresponding to the acquired utterance is identified, and whether or not there is another important element in the agenda having a causal relationship with the identified element, between the elements in the agenda Judging on the basis of the information defining the causal relationship between the information and the information indicating the importance in the argument set for each of the elements, and judging that the other element is present, the other elements On the basis of the morpheme of the other element and the morpheme of the related case corresponding to the other element, a question generation process for generating a question about the subject,
Question output processing for outputting the generated question;
A discussion support program that will When it is determined that the question generation process does not have the other element, the question generation process selects and selects at least one or more of the plurality of points of the identified element that have not been selected so far. Processing of generating a question about the subject questioning the morpheme having the selected viewpoint in the specified element based on the viewpoint of the selected element ,
The discussion support program according to claim 13. The statement analysis process is a process of obtaining evaluation information of the acquired statement,
The question generation process acquires evaluation information of the specified element, determines whether the evaluation information of the acquired utterance and the evaluation information of the acquired element correspond, and both correspond. If it is determined that there is not, the word having the evaluation information different from the evaluation information of the element is extracted from the decomposed words, and the word different from the extracted word and the other element are extracted, A process of generating a question about the subject questioning the morpheme of the other element and the morphemes of related cases of the other element, and the different words ;
The discussion support program according to claim 13.

Images