JP6179226B2 - Minutes generating device, minutes generating method, minutes generating program and communication conference system - Google Patents

Description

  The present invention relates to a minutes generation device, a minutes generation method, a minutes generation program, and a communication conference system.

  In recent years, communication conference systems that can hold a conference in real time between geographically distant bases are becoming increasingly popular. The communication conference system mainly includes an audio conference system that performs a conference by communicating only audio and a video conference system that performs a conference by communicating audio and video. Conference attendees have the advantage of using the communication conference system to reduce travel time to the conference location, business travel expenses, and the like.

  The teleconference system converts spoken voice data into text data, identifies the person who spoke and displays the text data of the speech content on the monitor along with the speaker information, and discusses all or a significant part of the speech content. A technique for storing recorded data is known.

  In particular, as a method for creating minutes in the teleconference system, select the technology for creating minutes without human intervention using voice recognition technology, and the important details that the minutes creators want to keep in the minutes from character data Thus, a technique for creating the minutes is disclosed.

  For example, in Patent Document 1, it is possible to know the content of a speech that was missed during a communication conference and the speaker, and it is possible to leave only important content in the minutes data by selecting the speech to be left in the minutes. A teleconferencing device is described. The communication conference apparatus described in Patent Document 1 includes voice-character data conversion means, character data display means, and marking retroactive means for performing minutes adoption processing.

  However, the method of creating minutes without human intervention using conventional speech recognition technology, especially when the meeting takes several hours, the amount of data in the created minutes increases, making it difficult to understand the main points of the meeting. There was a problem.

  Also, in the method of creating a minutes by selecting the important contents that the person in charge of the minutes described in Patent Document 1 wants to keep in the minutes from the character data, the minutes are created at the discretion of the person in charge of the minutes. There was a problem that. That is, there has been a problem that contents that have not been agreed between the attendees of the meeting are recorded as minutes in the minutes, or important matters are treated as mere discussion statements and not recorded in the minutes.

  The present invention has been made in view of the above, and provides a minutes generation device, a minutes generation method, a minutes generation program, and a teleconference system that create minutes for the contents agreed between the attendees of the meeting The purpose is to do.

  In order to solve the above-described problems and achieve the object, the minutes generation apparatus according to the present invention includes a speech data acquisition unit that acquires speech data of conference attendees, and the conference attendees with respect to the speech data. Each agenda level acquisition unit for acquiring each selected agenda level, a determination condition acquisition unit for acquiring a general agenda level determination condition set by the attendee, and each agenda level for the speech data Based on the agenda level based on the agenda level determined by the agenda level, and the agenda level determined by the agenda level determination unit, A minutes generation unit that determines whether or not to write the minutes and generates a minutes.

  According to the present invention, there is an advantageous effect that minutes can be created for the contents agreed between the attendees.

FIG. 1 is a diagram illustrating a configuration example of a communication conference system according to the present embodiment. FIG. 2 is a diagram illustrating a hardware configuration example of the communication conference terminal device according to the present embodiment. FIG. 3 is a block diagram showing a functional configuration of the communication conference apparatus according to the present embodiment. FIG. 4 is a diagram showing an example of a display display image of the communication conference terminal device according to the present embodiment. FIG. 5 is a diagram illustrating an example of a display display image of the communication conference terminal device according to the present embodiment. FIG. 6 is a diagram illustrating a hardware configuration example of the minutes generation device according to the present embodiment. FIG. 7 is a block diagram showing a functional configuration of the minutes generation apparatus according to the present embodiment. FIG. 8 is a diagram illustrating an example of a comprehensive agenda level determination method based on determination conditions. FIG. 9 is a diagram illustrating an example of a comprehensive agenda level determination method based on determination conditions. FIG. 10 is a diagram illustrating an example of a comprehensive agenda level determination method based on determination conditions. FIG. 11 is a diagram illustrating an example of a comprehensive agenda level determination method based on determination conditions. FIG. 12 is a diagram illustrating an example of a comprehensive agenda level determination method based on determination conditions. FIG. 13 is a diagram illustrating an example of a comprehensive agenda level determination method based on determination conditions. FIG. 14 is a diagram showing an example of a description format of the minutes generated by the minutes generation device according to the present embodiment. FIG. 15 is a block diagram showing a functional configuration of the multipoint connection apparatus according to the present embodiment. FIG. 16 is a flowchart illustrating an example of a procedure for generating minutes in the communication conference system according to the present embodiment. FIG. 17 is a flowchart showing an example of details of a procedure for generating minutes in the communication conference system according to the present embodiment. FIG. 18 is a flowchart showing an example of the processing operation of the communication conference terminal device according to the present embodiment. FIG. 19 is a flowchart showing an example of the processing operation of the multipoint connection apparatus according to the present embodiment. FIG. 20 is a flowchart showing an example of the processing operation of the minutes generating device according to the present embodiment.

  Hereinafter, an embodiment of a minutes generation device, a minutes generation method, a minutes generation program, and a communication conference system according to the present invention will be described in detail with reference to the accompanying drawings.

  The minutes generation apparatus of the present embodiment performs comprehensive discussion on the basis of each agenda level (importance) selected and input by each conference attendant with respect to the speech data obtained by converting the speech data of the conference attendee to text. Determine the level. The minutes generating device determines whether or not to write the statement data in the minutes based on the determined overall agenda level and generates the minutes. Thereby, it is possible to create a minutes that makes it easy to understand the main points of the conference based on the respective agenda levels selected and input by the conference attendees regarding the contents agreed upon by the conference attendees.

  Below, the example which implement | achieves the minutes production | generation apparatus of this Embodiment as a one part apparatus of the communication conference system which communicates and communicates an audio | voice and an image | video is demonstrated. A system to which the minutes generation apparatus of the present embodiment is applicable is not limited to such a communication conference system.

  FIG. 1 is a diagram illustrating a configuration example of a communication conference system according to the present embodiment. As shown in FIG. 1, the communication conference system 100 according to the present embodiment includes a plurality of communication conference terminal devices 11A to 11C used by conference attendees, a minutes generation device 21, and communication conference terminal devices 11A to 11C. And a multipoint control unit (MCU) 31 that relays data between them. Hereinafter, when it is not necessary to distinguish the plurality of communication conference terminal devices 11A to 11C, they are referred to as communication conference terminal devices 11. Similarly, when there is no need to distinguish between the communication conference apparatuses 12A to 12C, the microphones 13A to 13C, the cameras 14A to 14C, the speakers 15A to 15C, and the displays 16A to 16C, the communication conference apparatus 12, the microphone 13, and the camera 14 are used. , Speaker 15 and display 16. In addition, although the communication conference terminal device 11 of this Embodiment demonstrates by the example of 3 units | sets, the number of the communication conference terminal devices 11 is not restricted to this.

  The plurality of communication conference terminal devices 11 </ b> A to 11 </ b> C, the minutes generation device 21, and the multipoint connection device 31 are connected via a network 41 so that they can communicate with each other, for example. The network 41 is a network such as the Internet or an intranet.

  The teleconference terminal device 11 inputs the voice spoken by the conference attendee from the microphone 13, converts the voice into a digital voice signal, acquires voice data, converts the voice data into character information, and generates the voice data. To do. The communication conference terminal device 11 captures the conference attendees with the camera 14 and acquires video data of the conference attendees. The communication conference terminal device 11 transmits and receives voice data, speech data, video data, and the like to and from the multipoint connection device 31. In addition, the communication conference terminal device 11 transmits the utterance data and the utterer information corresponding to the utterance data (hereinafter also referred to as the utterer of the utterance data) to the minutes generation device 21 and the multipoint connection device 31. The communication conference terminal device 11 outputs the synthesized audio data received from the multipoint connection device 31 by synthesizing each audio data, and displays synthesized video data obtained by synthesizing each video data.

  The minutes generating device 21 acquires the utterance data and the utterer information corresponding to the utterance data (the utterer of the utterance data) from the communication conference terminal device 11. The minutes generation device 21 acquires the agenda level selected by the conference attendant with respect to the utterance data in the communication conference terminal device 11 from the communication conference terminal device 11. The minutes generation device 21 uses the communication conference terminal to determine the judgment condition of the overall agenda level (hereinafter, the overall agenda level is also referred to as “total agenda level”) input by the conference attendee in the communication conference terminal device 11. Obtained from the device 11. The minutes generation device 21 acquires from the communication conference terminal device 11 the basic conference information input by the conference attendee at the communication conference terminal device 11. The minutes generation device 21 determines the total agenda level based on each agenda level selected by the conference attendees with respect to the utterance data acquired from the communication conference terminal device 11 and the overall agenda level determination conditions. And decide. The minutes generating device 21 determines whether or not to write the statement data in the minutes based on the determined general agenda level. In addition, the minutes generating device 21 determines a format for describing the statement data in the minutes based on the determined general agenda level. The minutes generating device 21 refers to the acquired statement data, speaker information, and basic information on the agenda, and generates a minutes based on the determined general agenda level.

  The multipoint connection device 31 distributes the synthesized voice data obtained by synthesizing each voice data received from each communication conference terminal device 11 to each communication conference terminal device 11. Further, the multipoint connection device 31 combines the composite video data obtained by synthesizing the speech data, the speaker information, the video data, the information of the conference material acquired in advance, and the like received from each communication conference terminal device 11. Deliver to. That is, the multipoint connection device 31 relays data between the plurality of communication conference terminal devices 11 via the network.

  Next, the communication conference terminal device 11 of the present embodiment will be described. FIG. 2 is a diagram illustrating a hardware configuration example of the communication conference terminal device according to the present embodiment. As shown in FIG. 2, the communication conference terminal device 11 according to the present embodiment includes a communication conference device 12, a microphone 13, a camera 14, a speaker 15, and a display 16.

  The teleconference device 12 includes a CPU 101, ROM 102, RAM 103, flash memory 104, SSD 105, media 106, media drive 107, operation buttons 108, bus line 109, network I / F 110, and voice input. An output I / F 111, an image sensor I / F 112, and a display I / F 113 are provided.

  A CPU (Central Processing Unit) 101 controls the operation of the entire communication conference apparatus 12. In addition, when compression processing of audio data or video data is performed, compression (encoding) and expansion (decoding) processing is performed. A ROM (Read Only Memory) 102 stores a program for the communication conference terminal device 11. A RAM (Random Access Memory) 103 is used as a work area of the CPU 101.

  The flash memory 104 stores various data such as video data and audio data. An SSD (Solid State Drive) 105 controls reading or writing of various data with respect to the flash memory 104 under the control of the CPU 101. The media drive 107 controls reading or writing (storage) of data with respect to a medium such as a flash memory (hereinafter also referred to as a recording medium) 106.

  The operation button 108 operates the communication conference device 12. The network I / F 110 performs data transmission using the network. The audio input / output I / F 111 processes input / output of audio signals between the microphone 13 and the speaker 15 under the control of the CPU 101. The image sensor I / F 112 captures a subject with the camera 14 under the control of the CPU 101, acquires video data, and controls transmission of the video data. The display I / F 113 transmits video data to the display 16 under the control of the CPU 101.

  The microphone 13 inputs sound. The speaker 15 outputs sound. The bus line 109 electrically connects the above-described components as shown in FIG. The bus line 109 is, for example, an address bus or a data bus.

  The medium 106 is configured to be detachable from the communication conference device 12. Further, as long as it is a non-volatile memory that reads or writes data under the control of the CPU 101, not only the flash memory 104 but also an EEPROM (Electrically Erasable and Programmable ROM) or the like may be used. In addition, as the camera 14, a CMOS (Complementary Metal-Oxide Semiconductor) is used as an example. A CMOS is a solid-state imaging device that converts light into electric charges and digitizes an image (video) of a subject. In addition, as long as the subject is imaged, not only the CMOS but also a CCD (Charge Coupled Device) may be used. Further, the display 16 is constituted by, for example, a liquid crystal or an organic EL that displays a subject image, an operation icon, and the like.

  Note that the above-described program for the teleconference terminal device 11 is a file in an installable or executable format, and may be recorded on a computer-readable recording medium such as the recording medium 106 and distributed. .

  FIG. 3 is a block diagram showing a functional configuration of the communication conference apparatus according to the present embodiment. As shown in FIG. 3, the communication conference apparatus 12 according to the present embodiment includes an A / D converter 201, an audio CODEC control unit 202, a D / A converter 203, a video control unit 204, and an input control unit. 205, a communication control unit 206, a storage unit 207, a voice data character conversion unit 208, and a control unit 209.

  The A / D converter 201 inputs a conference attendee's voice as an analog voice signal from the microphone 13 and converts it into a digital voice signal.

  The audio CODEC control unit 202 transmits the audio data converted into the digital audio signal by the A / D converter 201 to the multipoint connection device 31 connected to the network 41 in real time via the communication control unit 206. The audio CODEC control unit 202 temporarily stores the audio data converted into the digital audio signal in the storage unit 207. In general, audio data is often communicated as compressed audio data after being subjected to data compression processing, but in this embodiment, compression processing may or may not be performed. The audio CODEC control unit 202 includes an audio encoder for encoding (encoding) audio data and an audio decoder for decoding and outputting the audio data to the speaker 15 when performing audio data compression processing. Examples of compression methods include G.I. 711 and AAC (Advanced Audio Coding). Also, the voice CODEC control unit 202 acquires synthesized voice data obtained by synthesizing voice data received from the multipoint connection device 31 via the communication control unit 206 and outputs the synthesized voice data to the D / A converter 203.

  The D / A converter 203 converts the synthesized voice data obtained by synthesizing the voice data input from the voice CODEC control unit 202 into an analog voice signal, and outputs the voice signal from the speaker 15 in real time.

  The video control unit 204 transmits the video data of the conference attendee photographed by the camera 14 to the multipoint connection device 31 connected to the network 41 via the communication control unit 206 in real time. In general, video data is often communicated as compressed video data after being subjected to data compression processing, but in this embodiment, compression processing may or may not be performed. The video control unit 204 includes a video encoder for encoding (encoding) video data and a video decoder for decoding and displaying the video data on the display 16 when performing video data compression processing. Examples of compression methods include H.264. H.264 and MPEG-4. Further, the video encoder changes the compression parameters according to the compression parameters (compression method, resolution, frame rate, bit rate, etc.) instructed from the video control unit 204. In addition, when the compression method is changed, the video encoder adds data indicating the compression method to the encoded data. For example, the video encoder includes data indicating the compression method in the encoded header, or adds it to the head of the encoded data as data that can be uniquely identified. In addition, the video control unit 204 acquires synthesized video data obtained by synthesizing the video data received from the multipoint connection device 31 via the communication control unit 206 and displays the synthesized video data on the display 16.

  The input control unit 205 acquires data input from the display (touch panel display) 16 and transmits the data to the minutes generation device 21 and the multipoint connection device 31 connected to the network 41 via the communication control unit 206. The data includes, for example, agenda basic information, general agenda level determination conditions, names of attendees using the communication conference terminal device 11, agenda levels selected by conference attendees for speech data, and the like.

  The communication control unit 206 controls data transmission / reception with the minutes generation device 21 and the multipoint connection device 31 connected to the network 41.

  The storage unit 207 acquires the attendee name (speaker information) input from the display 16 by the conference attendee under the control of the control unit 209 via the input control unit 205 and stores it. The storage unit 207 stores audio data converted into a digital audio signal. Further, the storage unit 207 stores the speech data converted by the voice data character conversion unit 208 in association with the above-described speaker information (name of attendee).

  The voice data character conversion unit 208 converts the voice data stored in the storage unit 207 into character information (hereinafter referred to as speech data). The voice data / character conversion unit 208 stores the utterance data and the utterer information (the utterer of the utterance data) stored in advance in the storage unit 207 in association with each other. The voice data / character conversion unit 208 transmits the utterance data and the speaker information corresponding to the utterance data to the minutes generation device 21 and the multipoint connection device 31 via the communication control unit 206. Note that, for example, a speech recognition technology can be used as a technology for converting speech data into speech data that is character information (character data).

  The control unit 209 controls the operation of the entire communication conference device 12.

  4 and 5 are diagrams showing examples of display display images of the communication conference terminal device according to the present embodiment. As shown in FIG. 4, the display image 301 on the display of the communication conference terminal device 11 is mainly divided into, for example, three display areas 302 to 304.

  The display area 302 is an area for displaying conference materials, for example. As a result, the meeting attendees can discuss while viewing the meeting material displayed in the display area 302. The display area 303 is an area for displaying, for example, videos of conference attendees using the communication conference terminal devices 11A to 11C. Thereby, the attendees of the meeting can discuss while looking at the facial expressions of other attendees.

  The display area 304 is an area for displaying, for example, the content of a conference attendee. The display area 304 displays the utterance time, the utterer information (the utterer of the utterance data), the agenda level (importance), and the like, in addition to the utterance data obtained by converting the voice data of the conference attendees into character information. As a result, even if the conference attendee misses the speech content of another conference attendee, the content of the speech and the speaker can be known by referring to the speech data and the speaker information.

  FIG. 5 is an example of a display image of the display area 304 in FIG. 4 and is a diagram illustrating a display image of the display 16C of Mr. Z using the communication conference terminal device 11C. As shown in FIG. 5, the display area 304 of the display 16C of the communication conference terminal device 11C is mainly divided into, for example, four display areas 401 to 404.

  The display area 401 is an area for displaying the utterance time of the utterance data. A display area 402 is an area for displaying speech data obtained by converting voice data of conference attendees into character information. The display area 403 is an area for displaying a speaker who is a person who has made a statement of the statement data. A display area 404 is an area in which each meeting attendee can select and input the agenda level for the speech data, and is an area for displaying the agenda level selected and input by each meeting attendee. Here, the agenda level is the degree of importance for the speech data. The minutes generating device 21 to be described later determines the total agenda level of the statement data based on the importance (agenda level) with respect to the statement data, and determines whether or not to describe the statement data in the minutes.

  In FIG. 5, for example, the agenda level is set to four stages of “A, B, C, and deletion”. In this example, the agenda level “A” indicates that the level of importance is high. The agenda level “B” indicates that the importance level is medium. The agenda level “C” indicates that the level of importance is low. The agenda level “deletion” indicates that the importance level is the lowest level, and it is not recorded in the minutes. As an example, the agenda level is divided into four stages of “A, B, C, and deletion”, but the present invention is not limited to this, and the agenda level stage and type can be arbitrarily set.

  The agenda level is selected and input for each utterance data by the utterer of the utterance data and other conference attendees. As for the input of the agenda level, the part indicated by the display area 412 in FIG. 5 is, for example, a touch panel type, and the conference attendee touches an arbitrary agenda level to select and input the agenda level for each message data. it can.

  Line 405 of the display area 412 shows an example in which Mr. Z selects and inputs the agenda level “A” with respect to the remark data that Mr. X remarks that “the development policy has no problem”. In line 406, Mr. Z selects and inputs the agenda level “B” in response to the remark data that Mr. X remarks, “Can the labor cost of development cost be further reduced?” . Similarly, line 407 shows an example in which Mr. Z selects and inputs the agenda level “C” with respect to the remark data that Mr. Y remarks that “there is no more personnel reduction to keep the development schedule.” In this way, the conference attendee can select and input each agenda level for each message data. In addition, although the example of the selection input by a touch panel type was shown as the agenda level input method, you may use other methods, such as a mouse | mouth and a keyboard (not shown in FIG. 3).

  The agenda levels selected by the attendees of the conference for the message data are the minutes generation device 21 connected to the network 41 via the input control unit 205 and the communication control unit 206 of the communication conference device 12 described above, and It is transmitted to the multipoint connection device 31. The minutes generating device 21 determines and determines the overall agenda level of each message data based on each agenda level selected and input by each attendee of the conference, and transmits it to the multipoint connection device 31. In the multipoint connection device 31, composite video data obtained by synthesizing the agenda level selected by each attendee of the conference and the general agenda level determined by the minutes generation device 21 based on the determination conditions together with other video data. Is distributed to each communication conference terminal device 11. Through the above processing, as shown in the display area 413 of FIG. 5, the display 16 of each communication conference terminal device 11 displays the agenda level and the agenda selected by each conference attendee for each message data. The general agenda level determined by the record generation device 21 based on the determination condition is displayed.

  Next, the minutes generation apparatus 21 of this embodiment will be described. FIG. 6 is an explanatory diagram showing a hardware configuration example of the minutes generating device according to the present embodiment. As shown in FIG. 6, the minutes generating device 21 of the present embodiment includes a CPU 501, ROM 502, RAM 503, HD 504, HDD 505, media 506, media drive 507, display 508, network I / O. F509, bus line 510, keyboard 511, mouse 512, CD-ROM 513, and CD-ROM drive 514 are provided.

  The CPU 501 controls the overall operation of the minutes generating device 21. The ROM 502 stores a program for the minutes generation device 21 for controlling the minutes generation device 21. The RAM 503 is used as a work area for the CPU 501. An HD (Hard Disk) 504 stores various data. An HDD (Hard Disk Drive) 505 controls reading or writing of data with respect to the HD 504 under the control of the CPU 501.

  The media drive 507 controls reading or writing (storage) of data with respect to a medium such as a flash memory (hereinafter also referred to as a recording medium) 506. The display 508 displays various information such as a cursor, menu, window, character, or image.

  A network I / F 509 transmits data using the network 41. The keyboard 511 includes a plurality of keys for inputting characters, numerical values, various instructions, and the like. The mouse 512 performs selection and execution of various instructions, selection of a processing target, movement of a cursor, and the like. The CD-ROM drive 514 controls reading or writing of data with respect to a CD-ROM (Compact Disc Read Only Memory) 513 as an example of a removable recording medium.

  The bus line 510 electrically connects the above-described components as shown in FIG. The bus line 510 is, for example, an address bus or a data bus.

  The program for the minutes generating apparatus 21 is a file in an installable or executable format, and is recorded and distributed on a computer-readable recording medium such as the recording medium 506 or CD-ROM 513. It may be.

  FIG. 7 is a block diagram showing a functional configuration of the minutes generation apparatus according to the present embodiment. As shown in FIG. 7, the minutes generating device 21 of the present embodiment includes a speech data acquisition unit 601, a speaker information acquisition unit 602, a conference level acquisition unit 603, a determination condition acquisition unit 604, and a conference basics. Information acquisition unit 605, general proceeding level determination unit 606, minutes generation unit 607, general proceeding level output unit 608, storage unit 609, minutes data output unit 610, communication control unit 611, control unit 612.

  The utterance data acquisition unit 601 acquires each utterance data received from each communication conference terminal device 11 via the communication control unit 611. The utterance data acquisition unit 601 transmits the acquired utterance data to the general agenda level determination unit 606 and the minutes generation unit 607.

  The speaker information acquisition unit 602 acquires the speaker information corresponding to each piece of speech data acquired by the speech data acquisition unit 601 from the communication conference terminal device 11 via the communication control unit 611. The speaker information acquisition unit 602 transmits the speaker information associated with each of the above-described speech data to the general agenda level determination unit 606 and the minutes generation unit 607. That is, the speech data acquisition unit 601 and the speaker information acquisition unit 602 cooperate to combine the respective speech data and the speaker information associated with the speech data, and the general proceeding level determination unit 606 and the minutes generation unit. To 607.

  The agenda level acquisition unit 603 selects and inputs each agenda level (importance) of each conference attendant for one message data in the communication conference terminal device 11 via the communication control unit 611. Get from. The agenda level acquisition unit 603 transmits each agenda level for one piece of acquired speech data to the general agenda level determination unit 606. That is, the utterance data acquisition unit 601, the speaker information acquisition unit 602, and the agenda level acquisition unit 603 cooperate with each other to provide one piece of speech data, speaker information associated with the piece of speech data, and one piece of speech data. The total agenda level is sent to the general agenda level determination unit 606.

  The determination condition acquisition unit 604 acquires the determination condition set by the conference attendee in the communication conference terminal device 11 from the communication conference terminal device 11 via the communication control unit 611. The determination condition acquisition unit 604 transmits the acquired determination condition to the general agenda level determination unit 606. Here, the determination condition is a condition for determining a comprehensive agenda level.

As the determination conditions for determining the overall agenda level, for example, the following determination conditions (1) to (4) can be set.
(1) Judgment condition is to average each agenda level selected and input by each attendee for one statement data, and if the average agenda level exceeds a certain threshold value, the overall agenda level When the average value of the agenda level is within the first threshold range, the overall agenda level is set to the medium level, and when the average value of the agenda level is within the second threshold range, the overall agenda If the average level of the agenda level is below a certain threshold, the overall agenda level is deleted.
(2) The determination condition is that the number of agenda levels selected for each agenda level type is determined based on each agenda level selected and input by each attendee for one statement data, and the most selected number The agenda level where there are many agendas will be the overall agenda level.
(3) Judgment conditions are selected for each type of agenda based on the weight assigned in advance to each conference attendee and each agenda level selected and input by each conference attendee for one statement data. The number of selected agenda levels is determined, and the agenda level with the most selected number is set as the overall agenda level.
(4) When the agenda level selected and input by the speaker with respect to the speech data is the highest level or the lowest level, the determination condition is that the agenda level selected and input by the speaker is the overall agenda level.
Note that the determination condition is not limited to these, and an arbitrary determination condition can be set.

  The agenda basic information acquisition unit 605 acquires the agenda basic information input by the conference attendee in the communication conference terminal device 11 from the communication conference terminal device 11 via the communication control unit 611. The agenda basic information acquisition unit 605 transmits the acquired agenda basic information to the minutes generation unit 607. Here, the agenda basic information is basic information described in the minutes such as the meeting name, meeting date, meeting place, meeting attendees, meeting materials.

  The overall agenda level determination unit 606 determines and determines the overall agenda level for the speech data according to the acquired determination condition based on each agenda level selected and input by each attendee for the speech data. To do. The general agenda level determination unit 606 transmits the overall agenda level determined for the statement data to the minutes generation unit 607 and the general agenda level output unit 608. That is, in the general agenda level determination unit 606, for example, if there are 10 pieces of speech data, the general proceedings level for each of the 10 pieces of speech data is determined.

  The minutes generation unit 607 determines whether or not to write the statement data in the minutes based on the overall level of the statement data determined by the general meeting level determination unit 606. In addition, the minutes generation unit 607 determines a format for describing the statement data in the minutes based on the overall agenda level for the statement data determined by the general agenda level determination unit 606. The minutes generating unit 607 generates the minutes based on the acquired statement data, the speaker information corresponding to the statement data, and the basic minutes information. The minutes generation unit 607 stores the generated minutes in the storage unit 609 and transmits the minutes to the minutes data output unit 610.

  The general agenda level output unit 608 transmits the overall agenda level for the speech data determined by the general agenda level determination unit 606 to the multipoint connection device 31 via the communication control unit 611.

  The storage unit 609 stores the generated minutes.

  The minutes data output unit 610 transmits the minutes generated by the minutes generation unit as data to the multipoint connection device 31 via the communication control unit 611.

  The communication control unit 611 controls data transmission / reception with the minutes generation device 21 and the multipoint connection device 31 connected to the network 41.

  The control unit 612 controls the overall operation of the minutes generating device 21.

  Next, an example of a comprehensive agenda level determination method based on the determination conditions (1) to (4) will be described. 8 to 13 are diagrams illustrating an example of a comprehensive agenda level determination method based on the determination conditions (1) to (4). The agenda level and the general agenda level are described in four stages, “A, B, C, and deletion”, as an example, as described above, but the stage and type of the agenda level and the general agenda level can be set arbitrarily. can do.

[In the case of judgment condition (1)]
FIGS. 8 to 10 are diagrams for explaining an example of averaging the agenda levels selected and input by the attendees of each conference and determining the overall agenda level based on the average value. FIG. 8 shows numerical values corresponding to the agenda level. As shown in FIG. 8, for example, numerical values of agenda level A = 3, agenda level B = 2, agenda level C = 1, and agenda level deletion = 0 are assigned.

  FIG. 9 shows the general agenda level corresponding to the average value of the agenda level. As shown in FIG. 9, when the average value of the agenda level is, for example, a certain threshold value of 2.5 and 3.0 or less, the general agenda level is determined as A (high importance level). For example, when the average value of the agenda level is 1.5 to 2.5, which is the first threshold range, the overall agenda level is determined to be B (medium level of importance). For example, if the average value of the agenda level is 0.5 to 1.5 or less, which is the range of the second threshold, the overall agenda level is determined as C (low importance level). For example, when the average value of the agenda level is 0.5 or less which is a certain threshold value, it is determined that the general agenda level is deleted (the importance level is the lowest level).

  FIG. 10 shows an example of determining the general agenda level based on the average value of each agenda level of each attendee. For example, since the average value of the row 701 is 2.6, the general agenda level is determined as A. In rows 702 to 704, the average value is 1.6 to 2.3, so the general proceedings level is determined to be B. In row 705, since the average value is 1.3, it is determined that the general agenda level is C. In row 706, since the average value is 0.3, it is determined that the general proceedings level is deleted.

  In addition, rows 405, 406, 408, and 409 illustrated in FIG. 5 are examples of determination based on the determination condition (1). Thus, by applying the determination condition (1), it is possible to accurately determine the general agenda level.

[In the case of judgment condition (2)]
FIG. 11 is a determination example in which the agenda level having the largest selected number among the agenda levels selected and input by each conference attendant for one message data is determined as the general agenda level. As shown in FIG. 11, for example, in row 801, Mr. X and Mr. Y are at the agenda level A and the agenda level having the largest number of selections is determined, so the general agenda level is determined as A.

  More specifically, Mr. X's agenda level is A, Mr. Y's agenda level is A, and Mr. Z's agenda level is B. The general agenda level is determined as A, which is the agenda level with the largest number selected among the three agenda levels A, A, and B. That is, the general agenda level is determined from the three agenda levels A, A, and B to the agenda level A by majority vote.

  Similarly, in row 802, since Mr. Y and Mr. Z are at the agenda level B and the agenda level has the most selected number, the overall agenda level is determined as B. In row 803, since Mr. X and Mr. Y are at the agenda level B and the agenda level has the largest number of selections, the overall agenda level is determined as B.

  In rows 804 and 805, Mr. Y and Mr. Z are at the agenda level C and the agenda level having the largest number of selections is selected, so the total agenda level is determined as C. In row 806, since Mr. Y and Mr. Z are the agenda level deletion and the agenda level with the most selected number is the agenda level, it is determined that the general agenda level is deletion. As described above, the general agenda level is determined by a majority vote with the agenda level having the largest number selected among the agenda levels.

  In addition, a row 407 illustrated in FIG. 5 is an example in which determination is performed based on the determination condition (2). Thus, by applying the determination condition (2), it is possible to determine a fair general agenda level.

[In the case of judgment condition (3)]
FIG. 12 shows the agenda level selected for each type of agenda based on the weight assigned in advance to each attendee and each agenda level selected and input by each attendee for one message data. This is a determination example in which the agenda level having the most selected number is determined as the overall agenda level. As shown in FIG. 12, for example, when the agenda levels of the attendees are all different, the row 901 assigns the weight of the speaker Mr. X twice in advance, so that the agenda level A is two. Become. Therefore, since the agenda level with the most selected number among the agenda levels is A, the overall agenda level is determined as A.

  More specifically, the agenda level of the speaker X is A, the agenda level of Mr Y is B, and the agenda level of Mr Z is C. Here, it is assumed that the speaker Mr. X is assigned a double weighting in advance, and the Mr. Y and Mr. Z weights are assigned a single weight. For example, since the speaker Mr. X is assigned twice as much weight in advance, the number of agenda levels A selected by Mr. X is doubled to two. Since Mr. Y and Mr. Z are assigned a weight of 1 times, the number of agenda level B selected by Mr. Y and the number of agenda levels C selected by Mr. Z do not change. That is, the number of agenda levels selected for each agenda level type is 2 for A, 1 for B, and 1 for C. Therefore, the general agenda level is determined as A, which is the agenda level with the largest number selected among the agenda levels selected and input by each attendee. That is, the general agenda level is determined from the four agenda levels A, A, B, and C to the agenda level A by majority vote.

  Line 902 is an example of assigning twice the weight to the speaker Mr. Y in advance, and the number of agenda level B selected by Mr. Y is twice, which is the most selected among the agenda levels. The total agenda level is determined as B because the agenda level is large. Line 903 is an example in which a weight of twice is assigned to the speaker Mr. Z in advance, and the number of agenda levels C selected by Mr. Y is doubled, which is the most selected among the agenda levels. The total agenda level is determined as C because the agenda level is large. In this way, by applying the judgment condition (3), it is possible to determine the general agenda level to the agenda level with the largest number selected among the agenda levels, taking the intention of the speaker heavily. it can. It should be noted that the weight assigned in advance to each conference attendee is not limited to double and can be arbitrarily set.

[In the case of judgment condition (4)]
FIG. 13 shows a determination example in which, when the speaker's agenda level is the highest or lowest level, the overall agenda level is set as the agenda level selected and input by the speaker. As illustrated in FIG. 13, for example, when the speaker is Mr. X, the row 1001 determines that the total agenda level is A because the agenda level of the speaker Mr. X is the highest level of A. The row 1002 determines that the general agenda level is A selected by Mr. Y and Mr. Z because the agenda level of Mr. X is the middle level of B. In row 1003, since the agenda level of the speaker Mr. X is a low level of C, the general agenda level is determined to be B selected by Mr. Y and Mr. Z. In row 1004, since the agenda level of the speaker Mr. X is the lowest level of deletion, it is determined that the general agenda level is deletion.

  Further, a row 410 illustrated in FIG. 5 is an example in which determination is performed based on the determination condition (4). As described above, by applying the determination condition (4), the agenda level of the speaker can be set to the general agenda level while capturing the intention of the speaker more heavily.

  In this manner, the minutes generating device 21 is based on each agenda level selected and input by each attendee for one message data in accordance with a comprehensive agenda level determination condition set by the attendee. To determine the general agenda level. In the present embodiment, the general proceedings level is, for example, 4 (A (high importance), B (medium importance), C (low importance), and deletion (low importance)). It is a stage. In the present embodiment, the minutes generating device 21 determines that the statement data is to be described in the minutes if the overall minutes determined for the statement data is A to C, and the general minutes level is deleted. If there is, the decision is made not to include the statement data in the minutes. In addition, the general agenda level within the range described in the minutes can be set arbitrarily.

  Next, an example of the minutes generated by the minutes generation device 21 will be described with reference to FIGS. 5 and 14. FIG. 14 is a diagram showing an example of a description format of the minutes generated by the minutes generation device according to the present embodiment.

  As shown in FIG. 14, in the first row 1101 to 1105 of the minutes as the description format of the minutes, the meeting name 1101, date and time 1102, place 1103, attendee 1104, meeting material 1105 are displayed based on the acquired basic information on the minutes. Is described.

  The minutes content includes, for example, speech data 1106 and speaker information 1107 based on the general agenda level. As the description format, for example, the statement data “development policy has no problem” in line 405 shown in FIG. 5 and “we know the necessity of development cost is known,” adopt this method. The statement data is determined to be general agenda level A. Therefore, as shown in Fig. 14, “Development policy is no problem. 1106” and “I understand the necessity of development cost, so I will adopt this method. 1110” is the main item of the minutes (direct proceedings) And

  In addition, the remark data “Can the labor cost of development cost be further reduced?” In line 406 shown in FIG. 5 and “No more personnel reduction is possible to keep the development schedule” in line 407. Is determined to be the general agenda level B. Therefore, as shown in Fig. 14, “Is it possible to further reduce the labor cost of development costs? 1108” and “No more personnel reduction is possible to keep the development schedule. 1109” The subordinate items (detailed discussion). If the speech data is determined to be general proceeding level C, the item is further subordinated.

  In addition, the statement data “Wow, is it? Is it affected on the schedule?” In row 408 and the statement data “Thank you.” In row 410 shown in FIG. It has been determined. Therefore, it is not described in the minutes as shown in FIG.

  In this way, the minutes generating device 21 describes the main item (direct agenda) of the minutes if the statement data is the general agenda level A for each general agenda level. If it is general agenda level C, it will be described as a lower item. If the general agenda level is deleted, it will not be recorded in the minutes.

  In addition, the description format of the minutes can be described so that the appearance of the text of the speech data is changed for each general proceeding level. For example, the character color of the utterance data may be changed for each general agenda level, or the character size may be changed. For example, it may be written in red for the general agenda level A, and may be described with a character size smaller than the general agenda level A for the general agenda level B.

  In addition, the format of the minutes can be changed for each general meeting level, for example, if it is a general meeting level C, it is not included in the body text of the minutes as an attachment to the minutes. The description format based on the general agenda level is not limited to this and can be set arbitrarily.

  As described above, the minutes generation device 21 according to the present embodiment generates the minutes by assigning item rankings to the remark data for each general meeting level based on the general meeting level. It is possible to generate a minutes that makes it easy to understand the details and details of the decision.

  In addition, the minutes generating device 21 of the present embodiment generates the minutes that are easy to understand visually in order to change the appearance of the text of the speech data for each general agenda level based on the general agenda level. Can do.

  Next, the multipoint connection apparatus according to the present embodiment will be described. Since the hardware configuration example of the multipoint connection device 31 of the present embodiment has the same configuration as the minutes generation device 21 described above, detailed description thereof is omitted.

  FIG. 15 is a block diagram showing a functional configuration of the multipoint connection apparatus according to the present embodiment. The multipoint connection apparatus 31 of this Embodiment is provided with the communication control part 1201 and the information processing part 1202, as shown in FIG.

  The communication control unit 1201 controls data transmission / reception with the communication conference terminal device 11 and the minutes generation device 21 connected to the network 41.

  The information processing unit 1202 includes a reception control unit 1203, a video synthesis unit 1204, a voice synthesis unit 1205, and a transmission control unit 1206.

  The reception control unit 1203 distributes video data and audio data of all communication conference terminal devices 11 received from the network 41 via the communication control unit 1201 to the video synthesis unit 1204 and the voice synthesis unit 1205.

  The video synthesizing unit 1204 lays out all video data acquired from each communication conference terminal device 11 and the minutes generating device 21 and synthesizes them into one video data, and synthesizes the video data (hereinafter also referred to as synthesized video data). Is output to the transmission control unit 1206. As all the video data, for example, the video data acquired from each communication conference terminal device 11 and the minutes generating device 21, speech data, speaker information corresponding to the speech data, the agenda level for the speech data, and the comprehensive for the speech data The agenda level, basic information on the agenda (information on meeting materials, etc.).

  The video synthesizing unit 1204 lays out each video data in an arbitrary format, and synthesizes it into one video data to generate synthesized video data. At this time, the video compositing unit 1204 may be highlighted according to, for example, character attributes (color, bold, etc.) or line attributes (shading, etc.) of the speech data to be displayed according to the general agenda level. . For example, in FIG. 5, the speech data rows 405 and 409 determined to be general proceeding level A are displayed in red characters, and the speech data rows 408 and 410 determined to be general proceeding level deletion are displayed in blue characters. Thus, by highlighting the utterance data, the general agenda level can be easily understood visually.

  The voice synthesis unit 1205 synthesizes all voice data acquired from each communication conference terminal device 11 and outputs the synthesized voice data (hereinafter also referred to as synthesized voice data) to the transmission control unit 1206.

  The transmission control unit 1206 distributes the synthesized video data and synthesized audio data acquired from the video synthesis unit 1204 and the voice synthesis unit 1205 to all the communication conference terminal devices 11 via the communication control unit 1201. Since the video synthesis process takes more time than the voice synthesis process, the transmission control unit 1206 delays and synchronizes the synthesized voice data with the synthesized video data and distributes the synthesized voice data to all the communication conference terminal devices 11.

  As described above, the multipoint connection device 31 synthesizes the audio data and the video data received from each communication conference terminal device 11 and the minutes generation device 21 and distributes them to all the communication conference terminal devices 11. That is, the multipoint connection device 31 relays various data between the plurality of communication conference terminal devices 11 via the network. Thereby, the conference attendees can discuss each other while watching the video of the other party's face, the conference material, and the like between the plurality of communication conference terminal devices 11 to perform the communication conference.

  Next, a flow of a procedure for generating minutes in the communication conference system according to the present embodiment will be described. FIG. 16 is a flowchart showing an example of a procedure for generating minutes in the communication conference system according to the present embodiment.

  With reference to FIG. 16, the flow of the procedure of the communication conference terminal device 11 will be mainly described. The communication conference terminal device 11 acquires the agenda basic information input from the communication conference terminal device 11 by the conference manager or the conference organizer among the conference attendees (step S101). The communication conference terminal device 11 transmits the acquired basic meeting information to the minutes generation device 21 and the multipoint connection device 31 (step S102). Next, the communication conference terminal device 11 acquires the general agenda level determination condition set by the conference manager or the conference organizer (step S103). The communication conference terminal device 11 transmits the acquired comprehensive proceeding level determination condition to the minutes generating device 21 (step S104). Next, the communication conference terminal device 11 acquires the name of the attendee who uses the communication conference terminal device 11 input from the communication conference terminal device 11 by the conference attendee (step S105). The communication conference terminal device 11 associates the acquired attendee name with each communication conference terminal device 11 (step S106). Thereby, in each communication conference terminal device 11, the speech data acquired by the communication conference terminal device 11 and speaker information are matched. When the communication conference terminal device 11 generates the message data, the communication conference terminal device 11 transmits the message data and the speaker information to the minutes generation device 21 and the multipoint connection device 31 together.

  Next, the communication conference terminal device 11 acquires audio data and video data when the communication conference is started (step S107). The communication conference terminal device 11 generates speech data from the voice data (step S108). The communication conference terminal device 11 transmits the voice data, the generated utterance data, the speaker information, and the video data to the minutes generation device 21 and the multipoint connection device 31 (step S109). The communication conference terminal device 11 acquires the synthesized voice data and the synthesized video data from the multipoint connection device 31 (step S110). The communication conference terminal device 11 outputs the synthesized voice data and displays the synthesized video data (step S111). The communication conference terminal device 11 acquires the agenda level selected and input by the conference attendee for the utterance data, and transmits it to the minutes generation device 21 and the multipoint connection device 31 (step S112). The communication conference terminal device 11 acquires the comprehensive proceeding level from the minutes generating device 21 and displays it (step S113). The minutes generation device 21 generates minutes according to the progress of the minutes (step S114). The communication conference terminal device 11 acquires the minutes data from the minutes generation device 21, displays it on the display 16 (step S115), and ends the process.

  In step S115, the communication conference terminal device 11 displays and outputs the minutes data acquired from the minutes generation device 21 on the display 16 and prints the minutes data with a printer (not shown in FIGS. 1 to 3). You may make it output. As the printer, a printer directly connected to the communication conference terminal device 11 or a printer connected to the network 41 may be used.

  Next, details of the flow of the procedure for generating the minutes in step S114 of FIG. 16 will be described. FIG. 17 is a flowchart showing an example of details of a procedure for generating minutes in the communication conference system according to the present embodiment.

  With reference to FIG. 17, the flow of the procedure of the minutes generation apparatus 21 and the multipoint connection apparatus 31 will be mainly described. The minutes generation device 21 and the multipoint connection device 31 acquire the speech data and the speaker information from the communication conference terminal device 11 (step S201). The multipoint connection device 31 transmits and displays the speech data and the speaker information to each communication conference terminal device 11 (step S202).

  Next, the minutes generating device 21 determines whether or not to modify the message data displayed on the communication conference terminal device 11 (step S203). When correcting the utterance data (step S203: YES), the minutes generating device 21 acquires the corrected utterance data (step S204). The speech data can be corrected, for example, by the speaker using the communication conference terminal device 11. Returning to step S202, the multipoint connection device 31 acquires the corrected message data and speaker information from the communication conference terminal device 11, transmits them to the communication conference terminal device 11, and displays them.

  When the utterance data is not modified (step S203: NO), the multipoint connection device 31 acquires each agenda level selected and input from the display 16 of each communication conference terminal device 11 by each conference attendee (step S205). Next, the multipoint connection device 31 transmits each agenda level for the speech data selected and input by each conference attendee to each communication conference terminal device 11 for display (step S206).

  The minutes generating device 21 determines whether or not all meeting attendees have entered the meeting level (step S207). If all meeting attendees have not entered the proceeding level (step S207: NO), the process returns to step S205, and the minutes generating apparatus 21 waits until each meeting attendee enters the proceeding level. If all meeting attendees have already entered the proceeding level (step S207: YES), the minutes generating device 21 acquires the respective proceeding levels selected and input by each meeting attendant for the speech data (step S208).

  Next, the minutes generating device 21 determines whether or not to change the general meeting level determination condition (step S209). When changing the general agenda level determination condition (step S209: YES), the minutes generation device 21 acquires the changed determination condition (step S210). The judgment condition can be changed by, for example, a conference attendee using each communication conference terminal device 11.

  Next, when the general agenda level determination condition is not changed (step S209: NO), the minutes generating device 21 determines the general agenda level based on the general agenda level determination condition (step S211). The minutes generating device 21 transmits and displays the determined general meeting level to each communication conference terminal device 11 via the multipoint connection device 31 (step S212).

  Next, the minutes generation device 21 determines whether or not the communication conference has ended (step S213). If the communication conference has not ended (step S213: NO), the minutes generation device 21 deletes one row of the oldest message data display (step S214). Next, the minutes generating device 21 shifts and displays the display position of the message data display displayed on the display 16 of each communication conference terminal device 11 via the multipoint connection device 31 (step S215). Next, the process returns to step S201, and the acquisition process of the utterance data and the speaker information is continued.

  When the communication conference is completed (step S213: YES), the minutes generating device 21 determines whether or not to describe each piece of statement data in the minutes based on the total level of each piece of statement data (step S216). . Next, the minutes generation device 21 determines a format for writing each statement data in the minutes according to the total agenda level of each statement data (step S217). Next, the minutes generating device 21 generates the minutes, stores the generated minutes data in the storage unit 609 (step S218), and stores the minutes data through the multipoint connection device 31 to each communication conference terminal. The data is transmitted to the apparatus 11 (step S219), displayed on the display 16, and the process is terminated.

  According to the flow of the procedure as described above, in the communication conference system 100 according to the present embodiment, the general agenda is based on each agenda level (importance) selected and input by the conference attendees regarding the contents agreed upon by the conference attendees. The level can be determined, and the minutes of the conference that are easy to understand based on the determined overall level can be created.

  Next, with reference to FIGS. 18-20, the processing operation in each apparatus of the teleconference system 100 according to the present embodiment will be described. FIG. 18 is a flowchart showing an example of the processing operation of the communication conference terminal device according to the present embodiment.

  The communication conference terminal device 11 acquires the proceeding basic information and transmits it to the minutes generating device 21 and the multipoint connection device 31 (step S301). The agenda basic information can be acquired from the agenda basic information input from the communication conference terminal device 11 by the conference attendee. The communication conference terminal device 11 acquires the general conference level determination condition and transmits it to the minutes generation device 21 (step S302). The general proceeding level determination condition can be acquired from the general proceeding level determination condition set by the conference attendee from the communication conference terminal device 11. The communication conference terminal device 11 acquires the attendee name (speaker information) (step S303). The attendee name (speaker information) can be acquired from the attendee name input by the conference attendee from the communication conference terminal device 11.

  Next, the communication conference terminal device 11 associates the attendee name (speaker information) with the communication conference terminal device 11 (step S304). Thereby, the speech data acquired by each communication conference terminal device 11 and the speaker information are associated with each other. Next, the communication conference terminal device 11 acquires audio data (step S305). The communication conference terminal device 11 converts the acquired voice data into speech data that is character information (step S306). The communication conference terminal device 11 acquires video data (step S307).

  Next, the communication conference terminal device 11 transmits voice data, speech data, speaker information corresponding to the speech data, and video data to the minutes generation device 21 and the multipoint connection device 31 (step S308). Next, the communication conference terminal device 11 acquires the synthesized voice data from the multipoint connection device 31 and outputs it to the speaker 15 (step S309). The communication conference terminal device 11 acquires the composite video data from the multipoint connection device 31 and displays it on the display 16 (step S310).

  Next, the communication conference terminal device 11 acquires each agenda level corresponding to the statement data and transmits it to the minutes generation device 21 and the multipoint connection device 31 (step S311). The agenda level can be acquired from each agenda level selected and input from the communication conference terminal device 11 by the conference attendee. Next, the communication conference terminal device 11 acquires the composite video data including each agenda level and the general agenda level from the multipoint connection device 31 and displays them on the display 16 (step S312).

  Next, the communication conference terminal device 11 determines whether or not the communication conference has ended (step S313). If the communication conference has not ended (step S313: NO), the communication conference terminal apparatus 11 returns to step S305 and continues the process. When the communication conference is completed (step S313: YES), the communication conference terminal device 11 acquires the minutes data from the minutes generation device 21 via the multipoint connection device 31, and outputs the minutes data to the display 16 (step). S314), the process is terminated.

  FIG. 19 is a flowchart showing an example of the processing operation of the multipoint connection apparatus according to the present embodiment.

  The multipoint connection device 31 acquires the agenda basic information from the communication conference terminal device 11 (step S401). The multipoint connection device 31 acquires voice data, speech data, and speaker information and video data corresponding to the speech data from each communication conference terminal device 11 (step S402). Next, the multipoint connection device 31 synthesizes each acquired voice data to generate synthesized voice data (step S403). The multipoint connection device 31 synthesizes the agenda basic information, the utterance data, the utterer information corresponding to the utterance data, and the video data to generate synthesized video data (step S404).

  Next, the multipoint connection device 31 distributes the synthesized voice data and the synthesized video data to each communication conference terminal device 11 (step S405). The multipoint connection device 31 acquires each agenda level corresponding to the message data from the communication conference terminal device 11 (step S406). The multipoint connection device 31 acquires a comprehensive proceeding level corresponding to the utterance data from the minutes generating device 21 (step S407). Next, the multipoint connection device 31 generates composite video data including each agenda level and general agenda level, and distributes them to each communication conference terminal device 11 (step S408).

  Next, the multipoint connection device 31 determines whether or not the communication conference has ended (step S409). If the communication conference has not ended (step S409: NO), the multipoint connection device 31 returns to step S402 and continues the process. When the communication conference is ended (step S409: YES), the multipoint connection device 31 acquires the minutes data from the minutes generation device 21 (step S410). Next, the multipoint connection device 31 distributes the minutes data to each communication conference terminal device 11 (step S411), and ends the process.

  FIG. 20 is a flowchart showing an example of the processing operation of the minutes generating device according to the present embodiment.

  The minutes generating device 21 acquires the basic information of the minutes from the communication conference terminal device 11 (step S501). The minutes generation device 21 acquires a general meeting level determination condition from the communication conference terminal device 11 (step S502). Next, the minutes generation device 21 determines whether or not the communication conference has been started (step S503). When the communication conference has not been started (step S503: NO), the minutes generation device 21 continues to determine whether or not the communication conference has started. When the communication conference is started (step S503: YES), the minutes generating device 21 acquires the utterance data and the speaker information corresponding to the utterance data from the communication conference terminal device 11 (step S504).

  Next, the minutes generating device 21 determines whether or not the message data is to be corrected (step S505). When correcting the utterance data (step S505: YES), the minutes generating device 21 acquires the corrected utterance data (step S506). When the message data is not modified (step S505: NO), the minutes generating device 21 proceeds to step S507.

  Next, the minutes generating device 21 acquires the respective minutes levels corresponding to the message data from the communication conference terminal device 11 (step S507). The minutes generation device 21 determines whether or not the agenda levels of all attendees have been acquired (step S508). When the agenda levels of all the attendees have not been acquired (step S508: NO), the minutes generation device 21 returns to step S507 and continues to acquire the agenda level. When the agenda levels of all attendees have been acquired (step S508: YES), the minutes generation device 21 determines whether or not to change the general agenda level determination condition (step S509). When the general agenda level determination condition is changed (step S509: YES), the minutes generation device 21 acquires the changed general agenda level determination condition (step S510). When the general agenda level determination condition is not changed (step S509: NO), the minutes generation device 21 proceeds to step S511.

  Next, the minutes generating device 21 determines the general agenda level based on the general agenda level determination condition (step S511). The minutes generation device 21 transmits the determined comprehensive proceedings level to the multipoint connection device 31 (step S512). Next, the minutes generating device 21 determines whether or not the communication conference has ended (step S513). If the communication conference has not ended (step S513: NO), the minutes generating device 21 returns to step S504, and continues the acquisition processing of the utterance data and the speaker information corresponding to the utterance data. When the communication conference is completed (step S513: YES), the minutes generation device 21 determines whether or not to describe each piece of comment data in the minutes based on the total level of each piece of comment data (step S514). ).

  Next, the minutes generation device 21 determines a format for writing each statement data in the minutes according to the total agenda level of each statement data (step S515). Next, the minutes generating device 21 generates the minutes and stores the generated minutes data in the storage unit 609 (step S516). Thereafter, the minutes generating device 21 transmits the minutes data to each communication conference terminal device 11 via the multipoint connection device 31 (step S517), and ends the process.

  As described above, the above-described processing operation is executed in cooperation with the communication conference terminal device 11, the minutes generation device 21, and the multipoint connection device 31 that constitute the communication conference system 100 of the present embodiment. Thereby, the minutes generation apparatus 21 of this Embodiment can produce the minutes about the content agreed between the meeting attendees.

  In addition, the minutes generating device 21 according to the present embodiment determines the general agenda level based on each agenda level (importance) selected and input by the conference attendees for the contents agreed upon by the attendees. Based on the total agenda level, the minutes of the meeting can be created.

  In addition, since the minutes generating device 21 of the present embodiment generates minutes for the contents agreed between the meeting attendees, it is possible to suppress an increase in the amount of minutes, and as the minutes. Can prevent the description of inappropriate content.

  Further, the minutes generation device 21 of the present embodiment has agreed that the minutes are generated based on the agenda level (importance) selected and input by the meeting attendees for the contents agreed upon among the attendees. It is possible to prevent the description of unexplained contents and the omission of description of important voting matters.

  As mentioned above, although embodiment of this invention was described, each above-mentioned embodiment is shown as an example and is not intending limiting the range of invention. The present invention is not limited to the above-described embodiments as they are, and can be embodied by modifying the components without departing from the scope of the invention in the implementation stage. Further, various inventions can be formed by appropriately combining a plurality of constituent elements disclosed in the above-described embodiments. For example, some components may be deleted from all the components shown in the embodiment. Further, the above embodiments and modifications can be arbitrarily combined.

  The control program executed by the communication conference terminal device 11, the minutes generation device 21, and the multipoint connection device 31 of each of the above-described embodiments is an installable format or an executable format file, a CD-ROM, You may comprise so that it may record and provide on computer-readable recording media, such as a flexible disk (FD), CD-R, and DVD (Digital Versatile Disk).

  Furthermore, the control program executed by the communication conference terminal device 11, the minutes generation device 21, and the multipoint connection device 31 of each of the above-described embodiments is stored on a computer connected to a network such as the Internet, and is transmitted via the network. You may comprise so that it may provide by making it download. In addition, the control program executed by the communication conference terminal device 11, the minutes generation device 21, and the multipoint connection device 31 of each embodiment described above may be provided or distributed via a network such as the Internet. .

11, 11A, 11B, 11C Communication conference terminal devices 12A, 12B, 12C Communication conference devices 13A, 13B, 13C Microphones 14A, 14B, 14C Cameras 15A, 15B, 15C Speakers 16A, 16B, 16C Display 21 Minutes generation device 31 Multi Point connection device 41 Network 101 CPU
102 ROM
103 RAM
104 Flash memory 105 SSD
106 Media (Recording media)
107 Media drive 108 Operation button 109 Bus line 110 Network I / F
111 Voice input / output I / F
112 Image sensor I / F
113 Display I / F
201 A / D converter 202 Audio CODEC control unit 203 D / A converter 204 Video control unit 205 Input control unit 206 Communication control unit 207 Storage unit 208 Audio data character conversion unit 209 Control unit 301 Display video 302, 303, 304 Display Area 401, 402, 403, 404, 412, 413 Display area 405, 406, 407, 408, 409, 410 Line 501 CPU
502 ROM
503 RAM
504 HD
505 HDD
506 Media (Recording media)
507 Media drive 508 Display 509 Network I / F
510 Bus line 511 Keyboard 512 Mouse 513 CD-ROM
514 CD-ROM drive 601 Speech data acquisition unit 602 Speaker information acquisition unit 603 Agenda level acquisition unit 604 Judgment condition acquisition unit 605 Agenda basic information acquisition unit 606 General agenda level determination unit 607 Minutes generation unit 608 General agenda level output unit 609 Storage unit 610 Minutes data output unit 611 Communication control unit 612 Control unit 701 to 706 Line 801 to 806 Line 901 to 903 Line 1001 to 1004 Line 1101 to 1105 Agenda basic information 1106, 1110 Main items (direct proceedings)
1107 Speaker information (speaker of speech data)
1108, 1109 Subordinate items of main items (detailed discussion)
1201 Communication control unit 1202 Information processing unit 1203 Reception control unit 1204 Video synthesis unit 1205 Voice synthesis unit 1206 Transmission control unit

JP 2008-160667 A

Claims (13)

A speech data acquisition unit that acquires speech data of conference attendees,
An agenda level acquisition unit for acquiring each agenda level selected and input by the attendees of the conference data;
A determination condition acquisition unit that acquires a determination condition of a comprehensive agenda level set by the attendees;
Based on the respective agenda levels for the statement data, a comprehensive agenda level determination unit for determining an overall agenda level for the statement data according to the determination condition;
A minutes generation unit for determining whether to write the statement data in the minutes based on the overall agenda level determined by the overall agenda level determination unit;
A minutes generating device characterized by comprising:   The judgment condition is that the average agenda level selected by each attendee for each conference data is averaged, and if the average agenda level exceeds a certain threshold, the overall agenda level is set to a high level. And when the average value is in the first threshold range, the overall agenda level is the medium level, and when the average value is in the second threshold range, the overall agenda level is the low level, 2. The minutes generation apparatus according to claim 1, wherein when the average value is equal to or less than a certain threshold value, the overall agenda level is deleted.   Based on the agenda levels selected and input by each attendee for one conference data, the determination condition is the number of agenda levels selected for each agenda level type, and the most selected number is 2. The minutes generation apparatus according to claim 1, wherein the agenda level is a comprehensive agenda level.   The judgment condition is based on the weight assigned in advance to each conference attendee and each agenda level selected and input by each conference attendee for one message data. 2. The minutes generation apparatus according to claim 1, wherein the number of levels is obtained, and the agenda level having the most selected number is set as a comprehensive agenda level.   The judgment condition is characterized in that, when the agenda level selected and input by the speaker with respect to the speech data is the highest level or the lowest level, the agenda level selected and input by the speaker is set as a comprehensive agenda level. The minutes generating apparatus according to claim 1.   The agenda according to claim 1, wherein the minutes generation unit determines a format in which the statement data is described in the minutes based on the overall agenda level determined by the overall agenda level determination unit. Record generator.   7. The minutes generation apparatus according to claim 6, wherein the format uses the statement data as a main item of the minutes or a subordinate item of the main item for each comprehensive agenda level.   7. The minutes generation apparatus according to claim 6, wherein the format changes the appearance of the character of the comment data for each overall agenda level. A speaker information acquisition unit that acquires speaker information corresponding to the speech data;
Agenda basic information acquisition unit for acquiring agenda basic information input by the attendees;
A storage unit for storing the minutes generated by the minutes generation unit;
A minutes data output unit for outputting the minutes generated by the minutes generation unit as data;
The minutes generating apparatus according to claim 1, further comprising: A speech data acquisition step for acquiring speech data of meeting attendees;
An agenda level acquisition step of acquiring each agenda level selected and input by the attendees of the conference data;
A determination condition acquisition step of acquiring a determination condition of a general agenda level set by the meeting attendee;
Based on the respective agenda levels for the statement data, a comprehensive agenda level determination step for determining a comprehensive agenda level for the statement data according to the determination condition;
Based on the overall agenda level determined in the overall agenda level determination step, it is determined whether or not to describe the statement data in the minutes, and a minutes generation step for generating the minutes;
A method for generating minutes, comprising: In the minutes generator,
A speech data acquisition step for acquiring speech data of meeting attendees;
An agenda level acquisition step of acquiring each agenda level selected and input by the attendees of the conference data;
A determination condition acquisition step of acquiring a determination condition of a general agenda level set by the meeting attendee;
Based on the respective agenda levels for the statement data, a comprehensive agenda level determination step for determining a comprehensive agenda level for the statement data according to the determination condition;
Based on the overall agenda level determined in the overall agenda level determination step, it is determined whether or not to describe the statement data in the minutes, and a minutes generation step for generating the minutes;
Minutes generation program to execute A plurality of communication conference terminal devices that transmit and receive data, a minutes generation device that is connected to the communication conference terminal device via a network, and relay data between the plurality of communication conference terminal devices via the network A teleconferencing system comprising a multipoint connection device,
The communication conference terminal device
A microphone that captures audio data spoken by the attendees,
A speaker for outputting the audio data;
A camera for acquiring video data of the attendees;
The voice data is converted into character information to be utterance data, the utterance data, speaker information corresponding to the utterance data, the video data, and the communication conference device that transmits the audio data to the multipoint connection device;
A display for displaying the composite video data received from the multipoint connection device,
The minutes generating device is:
A speech data acquisition unit that acquires speech data of conference attendees,
An agenda level acquisition unit for acquiring each agenda level selected and input by the attendees of the conference data;
A determination condition acquisition unit that acquires a determination condition of a comprehensive agenda level set by the attendees;
Based on the respective agenda levels for the statement data, a comprehensive agenda level determination unit for determining an overall agenda level for the statement data according to the determination condition;
A minutes generation unit for determining whether to describe the statement data in the minutes based on the overall agenda level determined by the overall agenda level determination unit, and a minutes generation unit,
The multipoint connection device is:
Synthesizing video data obtained by synthesizing the speech data, the speaker information, the video data, and pre-obtained agenda basic information received from each communication conference terminal device, and synthesized voice data obtained by synthesizing the audio data An information processing unit for transmitting to the conference terminal device;
A teleconferencing system comprising:   13. The respective agenda levels selected and input by conference attendees and a total agenda level for the statement data determined by the general agenda level determination unit are displayed on a display of the communication conference terminal device. The teleconference system described in 1.

Images