JP5109571B2 - Information processing system and information processing program - Google Patents

Description

  The present invention relates to an information processing system and an information processing program.

At meetings, there may be a case where the number of statements is reduced and the discussion is stagnant. Depending on the meeting, the stagnation may occur frequently. In this situation, in order to stimulate the discussion, there are many parts that depend on the human facilitator (the organizer, facilitator, moderator, etc., or their abilities, or something related to them depending on the context), and anyone can , Can't activate the discussion well. On the other hand, there is almost no system support.
As a conventional system for facilitator support, there is a voice system that can reliably transmit the voices of facilitators to all members, and a system that uses fuzzy technology to prioritize the voices so that the voices can be fair. Exists.

  As a technology related to this, for example, Patent Document 1 aims to provide an audio conference system that can reliably convey the remarks of a specific conference participant such as a chairman to all conference participants, A specific speaker detection circuit for detecting a voice signal of a specific speaker, a switch circuit for inputting a voice signal output from each conference terminal, and selecting a voice signal to be output from the input, and a specific speaker detection circuit Switch control circuit for controlling the switch circuit to output only the voice signal of the specific speaker so that only the voice signal of the specific speaker is sent to each conference terminal when the voice signal of the specific speaker is detected in Is disclosed.

  In addition, for example, Patent Document 2 aims to enable a fair and effective transfer of the right to speak among electronic conference participants, and to facilitate smooth conference progress and sufficient opinion collection. Participant evaluation means for evaluating factors related to the priority of the right to speak, inference rules for fuzzy inference of the priority of the right to speak for each participant, evaluation results by the participant evaluation means and the inference rules A reasoning means for fuzzy inference of the priority of the right to speak based on each participant, and a priority presentation means for presenting the priority of the right to speak as a result of inference by the reasoning means on a display device, etc. Supporting the transfer of floor is disclosed.

In addition, for example, in Patent Document 3, in order to display the number of times that each conference room has spoken on a received image monitor during a video conference, the multipoint video conference controller is added to the audio level detection circuit. The counter control unit is provided with a counter corresponding to each conference room, the conference level is selected by the voice level detection circuit, and the counter control unit increments the counter each time, thereby statistically displaying the number of utterances. It is disclosed.
Japanese Patent Laid-Open No. 06-237304 Japanese Patent Laid-Open No. 06-189002 Japanese Patent Laid-Open No. 05-207456

By the way, these techniques are intended to provide efficient conference support, that is, smooth the progress of the conference, and do not focus on improving the quality of discussion.
The present invention was made in the background of such background art, and when searching for a document related to a conference, information related to the document and outputting information generated in the conference is output. An object of the present invention is to provide a processing system and an information processing program.

The gist of the present invention for achieving the object lies in the inventions of the following items.
The information processing system according to claim 1 stores a document used in a conference between remote areas, information generated in association with the document in the conference, and information on participants of the conference in association with each other. A meeting record storage means, a comment text storage means for storing text information of a comment in the meeting and a document associated with the comment, a detection means for detecting an active state in the meeting for each region, and the detection means A search instruction display means for displaying a prompt for a search instruction to the operator according to the detected active state, a search target limited by the operation of the operator based on the display by the search instruction display means, and a search by a keyword a receiving unit configured to receive an instruction, according to the accepted search instruction by said receiving means, a document stored in the proceedings storage means, said conference A search unit to search for the keyword to be limited to the conference participants are often the most common and participants of the conference on the basis of the information of the participants, the conference proceedings storage means corresponding to the documents retrieved by said retrieval means and an output means for outputting the information stored, the searching means searches the text information is further stored in the speech text storage means by the keyword search result documents associated with the text information characterized by a.

The information processing program according to claim 2 , wherein the computer corresponds to a document used in a conference held between remote areas, information generated in association with the document in the conference, and information of participants in the conference. A conference record storage means for storing, a speech text storage means for storing text information of a speech in the conference and a document related to the speech, a detection means for detecting an active state in the conference for each region, A search instruction display means for performing a display for prompting a search instruction to the operator according to an active state detected by the detection means; and a search target limitation by an operation of the operator based on the display by the search instruction display means; a receiving means for receiving search instruction by keyword, according to the accepted search instruction by said receiving means, are stored in the proceedings storage means A document, a search unit to search for the keyword is limited to the most common participants often conference and conference participants on the basis of the participants in the meeting information, corresponding to the documents retrieved by said retrieval means It functions as an output means for outputting information stored in the conference record storage means, and the search means further searches the text information stored in the remark text storage means with the keyword, and relates to the text information. The retrieved document is used as a search result .

According to the information processing system of the first aspect, when a document related to a conference is searched, information related to the document and generated in the conference can be output. When a speech is searched for in a conference, information related to the document related to the speech and generated in the conference can be output. A search instruction can be prompted in accordance with the active state of the conference. When a conference is held in a plurality of regions, a search instruction can be prompted according to the active state in the region.

According to the information processing program of the second aspect , when a document related to a conference is searched, information related to the document and generated in the conference can be output. When a speech is searched for in a conference, information related to the document related to the speech and generated in the conference can be output. A search instruction can be prompted in accordance with the active state of the conference. When a conference is held in a plurality of regions, a search instruction can be prompted according to the active state in the region.

Hereinafter, an example of a preferred embodiment for realizing the present invention will be described with reference to the drawings.
FIG. 1 shows a conceptual module configuration diagram of a configuration example of the present embodiment.
The module generally refers to components such as software (computer program) and hardware that can be logically separated. Therefore, the module in the present embodiment indicates not only a module in a computer program but also a module in a hardware configuration. Therefore, the present embodiment also serves as an explanation of a computer program, a system, and a method. However, for the sake of explanation, the words “store”, “store”, and equivalents thereof are used, but these words are stored in a storage device when the embodiment is a computer program, or It means to control to be stored in the storage device. In addition, the modules correspond almost one-to-one with the functions. However, in mounting, one module may be composed of one program, or a plurality of modules may be composed of one program. A plurality of programs may be used. The plurality of modules may be executed by one computer, or one module may be executed by a plurality of computers in a distributed or parallel environment. Note that one module may include other modules. In the following, “connection” includes not only physical connection but also logical connection (data exchange, instruction, reference relationship between data, etc.).
In addition, the system or device is configured by connecting a plurality of computers, hardware, devices, and the like by communication means such as a network (including one-to-one correspondence communication connection), etc., and one computer, hardware, device. The case where it implement | achieves by etc. is also included.

Hereinafter, as information generated in connection with the document, information added to the document displayed at the conference by the operation of the conference participant, for example, information written on the document used for the conference (Annotation data, hereinafter also simply referred to as annotation), information written on a merge page added to a document used in a meeting, and the like. Annotation data is electronic data such as an underline to be written, a surrounding line, a note to be pasted, a comment, or a document including the page (including a page of the document). As the form of the annotation data, there are electronic data such as text, freehand, figure, bitmap, marker, sticky note, a document including them, a page of the document, and the like.
The stimulus information is information that is output as a search result in response to an operator search instruction or the like, and the content of the information is annotation data. For example, a search is performed when the meeting is stagnant.
The meeting includes meetings and discussions held by multiple people. Moreover, although the meeting performed in a remote place is illustrated, the meeting performed in one place may be sufficient. Here, the remote place means an area dispersed in a plurality of locations, and does not necessarily have to be far away.
Further, although explanation will be given mainly using a facilitator as an operator, there may be a conference participant or the like depending on the context of the explanation. Further, there may be a plurality of operators, and the operator who performs the first operation and the operator who performs the second operation need not be the same person.

This embodiment is used in a conference room in a remote place.
There is an idea creation method in which some information is presented when an idea is boiled down at a meeting, and the idea is generated by getting a stimulus from the information.
However, this information is not necessarily anything. The way to present a stimulus that says anything is too inefficient. It is necessary to effectively present information related to the conference for stimulus information that activates the discussion.
In the present embodiment, information generated in association with a document that is history information is used as stimulus information. The information includes information such as annotations on meeting documents and handwritten notes on blank page inserts, which are not simply displayed information but full of ideas created during the meeting. This is because it is a collection of information.

As shown in FIG. 1, this embodiment has a conference system 100, a remote conference system 120, a conference meta DB server 130, and a history archive server 140, which are connected via a communication line 199. ing. In FIG. 1, connections in main data exchange are indicated by arrows, but connections between modules and the like are not limited to arrow connections. There may be a plurality of conference systems 100 and remote conference systems 120. For example, a conference system 100 and a remote conference system 120 are installed in a conference room at a remote location, and one conference is performed using the conference system 100 and the remote conference system 120.
The conference system 100 includes an inactive state detection module 101, an utterance keyword extraction module 102, a search condition input module 103, a search condition storage area 104, a communication module (reception module) 105, a speech status data storage module 106, and a facilitator screen management module 107. , A speech state visualization processing module 108, a stimulus information search module 109, a stimulus information storage module 110, and a shared screen management module 111.

The inactive state detection module 101 is connected to the speech state data storage module 106, extracts the speech state from the speech state data storage module 106, and detects the active state in the conference. The active state may be detected for each region (also referred to as a site, specifically, for each conference system 100 and remote conference system 120). In order to detect for each region, it is possible to detect a speech for each participant and total the number of speeches of the participant in that region.
The utterance keyword extraction module 102 is connected to the utterance situation data storage module 106, and extracts a keyword for retrieving stimulus information from the text information of the voice data stored in the utterance situation data storage module 106. The keyword is passed to the stimulus information search module 109.
The search condition input module 103 is connected to the facilitator screen management module 107, and receives a search instruction (including a search keyword and the like) by an operator's operation based on the display on the facilitator screen 113 by the facilitator screen management module 107. And received via the facilitator screen management module 107. Information related to the search instruction is stored in the search condition storage area 104.
The search condition storage area 104 is connected to the facilitator screen management module 107, receives a search instruction by an operation of the operator from the search condition input module 103 and the facilitator screen management module 107, and stores information related to the search instruction. Accessed from the stimulus information search module 109, information about the search instruction is passed.
The communication module (reception module) 105 is connected to the communication module 124, the conference body meta DB server 130, and the history archive server 140 of the remote conference system 120 via the communication line 199, and communicates therewith. .

The speech status data storage module 106 is connected to the inactive state detection module 101, the speech keyword extraction module 102, and the speech status visualization processing module 108, and stores the speech status in the conference. For example, the speech situation in the conference using the remote conference system 120 in the remote place and the speech situation in the conference using the conference system 100 are stored. The speech situation includes voice data, text information of the voice data, statistical information thereof, and the like.
The facilitator screen management module 107 is connected to the search condition input module 103, the search condition storage area 104, the speech status visualization processing module 108, and the facilitator screen 113, and based on display instructions from the speech status visualization processing module 108 and the like. Display on the facilitator screen 113. Further, an operator's instruction is given to the search condition input module 103 or the like according to the operation of the operator.
The speech status visualization processing module 108 is connected to the speech status data storage module 106 and the facilitator screen management module 107, and provides an operator of the conference system 100 with the active state detected by the inactive state detection module 101. The facilitator screen management module 107 is instructed to perform a display prompting a search instruction.

The stimulus information search module 109 accesses the conference body metadata 131 of the conference body metadata DB server 130 and the history archive 141 of the history archive server 140, and extracts information or search keyword that is stored in the search condition storage area 104 regarding the search instruction. Based on the keyword passed from the module 102, the document stored in the history archive 141 is searched. Further, text information stored in the history archive 141 may be searched, and a document related to the text information may be used as a search result. Further, a search may be performed according to a search instruction received by the search condition input module 103. Further, the conference entity metadata 700 in the conference entity metadata 131 is searched to manage the conference.
The stimulus information storage module 110 is connected to the shared screen management module 111 and the history archive 141 of the history archive server 140, and stores information stored in the history archive 141 corresponding to the document searched by the stimulus information search module 109. Store as stimulus information.
The shared screen management module 111 is connected to the stimulus information storage module 110 and the share screen 112 and gives priority to the stimulus information stored in the stimulus information storage module 110 and outputs it to the share screen 112.
The shared screen 112 is a display screen in a conference room in which the conference system 100 is installed, and is presented to participants other than the facilitator, and is connected to the shared screen management module 111 of the conference system 100. The content displayed by the shared screen management module 111 is controlled. For example, a document used for a meeting is displayed.
The facilitator screen 113 is connected to the facilitator screen management module 107 of the conference system 100 and is a screen presented to the facilitator. The content displayed by the facilitator screen management module 107 is controlled. For example, an active state of the conference, a stimulus information search screen, and the like are displayed.
The conference system 100 further includes an equivalent of the microphone 125, the voice input module 121, the speech recognition module 122, and the speech information storage area 123 of the remote site conference system 120. Then, the statistical information of the voice data related to the speech in the conference room where the conference system 100 is installed is stored in the speech status data storage module 106.

The remote conference system 120 includes a voice input module 121, a speech recognition module 122, a speech information storage area 123, and a communication module 124, and is connected to a microphone 125 and a shared screen 126.
The microphone 125 is connected to the audio input module 121 of the remote conference system 120, collects the participant's utterance as audio data, and passes it to the audio input module 121.
The voice input module 121 is connected to the microphone 125, receives the participant's speech as speech data, and passes it to the speech recognition module 122 and the speech information storage area 123.

The speech recognition module 122 recognizes who the speech is from the speech data passed from the speech input module 121 and converts it into text information by speech recognition.
The speech information storage area 123 stores voice data delivered from the speech input module 121 and information delivered from the speech recognition module 122 corresponding to the speech data (information about who is the speech, text information). .
The communication module 124 is connected to the communication module (reception module) 105 of the conference system 100 via the communication line 199, and transmits information stored in the speech information storage area 123 to the communication module (reception module) 105. To do. Further, the communication module (reception module) 105 receives the content displayed on the shared screen 112 connected to the conference system 100 and displays the content on the shared screen 126.
The shared screen 126 is a display screen in the conference room where the remote conference system 120 is installed, and displays the content displayed on the shared screen 112 connected to the conference system 100 received by the communication module 124. . That is, what is displayed on the shared screen 112 and the shared screen 126 is the same.

The conference body meta DB server 130 includes the conference body metadata 131 and is connected to the conference system 100 and the like via the communication line 199.
The conference body metadata 131 is accessed from the stimulus information search module 109 of the conference system 100 and stores the conference body metadata 700 and the like. The conference body metadata 700 is a data group having the conference name, participants, and the like for each conference, and details will be described later with reference to FIG.

The history archive server 140 has a history archive 141 and is connected to the conference system 100 and the like via a communication line 199.
The history archive 141 is accessed from the stimulus information search module 109 and the stimulus information storage module 110 of the conference system 100, and stores the document used for the conference and the annotation data added to the document in the conference in association with each other. To do. Further, the text information of the speech in the meeting and the document related to the speech may be stored. The speech data related to the speech and the text information that is the recognition result of the speech data may be stored in other storage means, but are related to the document in the history archive 141 by a link or the like.

The embodiment shown in FIG. 1 operates, for example, as shown in the following (1) to (7).
(1) The speech situation in the conference is always detected by the inactive state detection module 101, the detected content is stored in the speech status data storage module 106, and the content is visualized by the speech status visualization processing module 108, and the facilitator screen 113 is displayed.
(2) When the inactive state detection module 101 detects the inactive state from the speech state, it performs an idea emergence stimulus presentation process described later.
(3) The speech status visualization processing module 108 displays a stimulus information search screen on the facilitator screen 113 via the facilitator screen management module 107, and a search range, a keyword, and the like are input by the search condition input module 103.
(4) The keyword accepted by the search condition input module 103 may be extracted from text information of audio data, which is a conference log, in addition to the above (3).
(5) The stimulus information search module 109 specifies the search target range based on the information received by the search condition input module 103.
(6) The stimulus information search module 109 searches the search target range for stimulus information from the history archive 141 in the history archive server 140 based on the keyword.
(7) The stimulus information storage module 110 stores the searched stimulus information, and the shared screen management module 111 displays it on the shared screen 112.

The basic processing example according to the present embodiment recognizes the inactive state (including the case where the site or the speaker is biased) from the state of speech at each site, and relates to the discussion at that time as necessary. The information is presented as a stimulus for idea creation (idea emergence stimulus presentation process), and the discussion is activated.
In the present embodiment, there are two modes for performing the idea emergence stimulus presentation process. The first is a facilitator mode in which the processing is started in response to the operation of the facilitator in the conference, and the second is an automatic mode in which the inactive state detection module 101 detects the active state. When it is determined that it is inactive, the process is started.

A basic processing example according to the present embodiment in the facilitator mode will be described using the flowchart shown in FIG.
In step S <b> 202, the speech status visualization processing module 108 displays on the facilitator screen 113 based on the speech status stored in the speech status data storage module 106. The contents to be displayed will be described later with reference to FIG.
In step S204, the facilitator looks at the screen and determines whether or not to perform the idea emergence stimulus presentation process. That is, the search condition input module 103 receives the operation of the facilitator. If it is a search instruction, that is, an instruction for an idea emergence stimulus presentation process, the process proceeds to step S206, and otherwise the process ends (step S208).
In step S206, the stimulus information search module 109 searches the history archive 141 and displays the search result as stimulus information on the shared screen 112 via the stimulus information storage module 110 and the shared screen management module 111.

A basic processing example according to the present embodiment in the automatic mode will be described using the flowchart shown in FIG.
In step S <b> 302, the inactive state detection module 101 determines the active state from the speech status stored in the speech status data storage module 106. Specifically, this is performed by comparing the speech status with a predetermined value. Here, the predetermined value uses a predetermined value, a value that changes according to the conference status (for example, the time from the start of the conference, the number of conference participants, the number of utterances so far, the average value of utterances, etc. Calculated value). The comparison means the above, below, less than, coincidence, etc., and when it is satisfied or not satisfied, the inactive state is detected. In addition, the speech situation includes a time when participants other than the facilitator do not speak.
In step S304, when an inactive state is detected by the inactive state detection module 101, an idea emergence stimulus presentation process is performed. Then, a plurality of retrieved stimulus information may be displayed at regular intervals.

FIG. 4 is an explanatory diagram showing a screen example of the individual speech total time display screen 400.
In the speech status visualization performed by the speech status visualization processing module 108, the facilitator determines whether there is no bias in speech for each site or for each participant, or whether the conference status is inactive. In order to do this, information is provided visually in various forms.
A speech refers to a case where the volume input through a microphone exceeds a certain amount and continues for a certain time. Therefore, there is a possibility that voices uttered by laughter or the like may be included, but here, these errors are not important. Rather, since laughter is considered one of the activation situations, it may be counted including this.
The information displayed on the facilitator screen 113 by the speech status visualization processing module 108 is as follows.
(1) Time series information of speech (2) Speech time (3) Number of speeches

The individual speech total time display screen 400 is information that presents the total amount of individual speech time in a graph for each of the sites 401 to 404. A site (site 401) marked with “★” indicates that the operated facilitator exists.
The facilitator refers to such a graph and grasps the activation status of the discussion. For example, active remarks are made at the site 401 and the site 403, but the site 404 is considerably inactive, and it is determined that it is necessary to prompt some remark.
The facilitator can perform facilitation that activates the discussion of the inactive site by referring to the graph and performing an action to ask the participant of the site 404 to speak.
The inactive state detection module 101 may detect that all sites are inactive. If the entire meeting is inactive (all sites are inactive), in other words, when the idea is boiled and no new remarks come out, it ’s not enough for the facilitator to encourage it, Information that is a stimulus for creating some ideas is needed.

FIG. 5 is an explanatory diagram showing a screen example of the individual speech total time display screen 400 and the stimulus information search screen 510.
When the stimulus presentation button 501 in the individual message total time display screen 400 is pressed by the facilitator, the search condition input module 103 displays the stimulus information search screen 510. When the inactive state detection module 101 detects an inactive state, the search condition input module 103 may display the stimulus information search screen 510.
In the stimulus information search screen 510, a search range and a keyword to be searched can be designated as search conditions by operating a facilitator.
That is, the stimulus information search screen 510 displays a search range selection field 511 and a keyword selection field 514. Under the search range selection column 511, there are a same conference selection column 512 and a related conference selection column 513. Below the same conference selection column 512, today's conference column 5121, the last five times. Within the column 5122, the 6th to 10th column 5123, and the 11th previous column 5124. Below the related conference selection column 513, an explicit link column 5131, a participant column 5132, and a document similarity column 5133 are provided. , A similar theme column 5134 is provided. Below the keyword selection column 514, an automatic selection column 515 and an input selection column 516 are provided.
These designations are stored in the search condition storage area 104 by the search condition input module 103.

An example of a stimulus information presentation process will be described using the flowchart shown in FIG.
In step S <b> 602, the stimulus information search module 109 specifies a search range in accordance with designation by the search range selection field 511 in the stimulus information search screen 510. Since a large amount of documents are stored in the history archive 141, it is determined which range is to be searched.
In step S604, the stimulus information search module 109 determines a keyword for search according to the keyword specified by the keyword selection field 514 in the stimulus information search screen 510 or the keyword extracted by the utterance keyword extraction module 102.
In step S606, the stimulus information search module 109 searches the conference entity metadata 700 in the conference entity metadata 131 based on the search range, retrieves the document corresponding to the conference entity metadata 700 from the history archive 141, and Search for keywords in the document. Then, the document in which the keyword exists and information generated in association with the document are extracted from the history archive 141 and stored in the stimulus information storage module 110.
In step S <b> 608, the shared screen management module 111 gives priority to the information generated in association with the document from the information stored in the stimulus information storage module 110 and displays the information on the shared screen 112. That is, for example, the information generated in relation to the document as the stimulus information candidate group is displayed in the order of the document.
In step S610, the selected stimulus information candidate group is displayed on the shared screen 112 as stimulus information in accordance with the participant's selection operation.

FIG. 7 is an explanatory diagram showing the relationship among the history archive 141, the conference body metadata 700, and the voice DB 720.
The conference entity metadata 700 is stored in the conference entity metadata 131. The conference entity metadata 700 includes a conference entity name column 701, a member column 702, a history folder column 703, and a related conference entity name column 704. is doing.
The history archive 141 stores a folder-log 711 having a hierarchical structure. The folder-log 711 stores history data in the “XYZ conference” in the history folder column 703 in the conference body metadata 700. For example, specifically, as history data, folder-log 711 includes presentation document A 712, NNN research report 713, AAA data analysis 714, handwritten memo-01 715, handwritten memo-02 716, handwritten memo-nn 717, It has a link 718 to audio data. The link 718 to the audio data is linked to the audio DB 720.
Note that notes such as annotation data are stored as image information for handwriting. Further, the folder-log 711 stores metadata relating to which document page is the information added to the annotation added to the document. That is, an annotation corresponding to a document (or a page of the document) can be extracted by the metadata.
Further, a link 718 to audio data under folder-log 711 makes it possible to take out a document corresponding to the text information of the audio data.

Next, the search range will be described using the stimulus information search screen 510 shown in FIG. That is, the search condition input module 103 receives a range searched by the stimulus information search module 109 as a search instruction by an operator's operation, and the stimulus information search module 109 performs a search within the search range.
The basic search target (search range) is in the conference history folder.
Information appropriate as a stimulus is information that is referred to or generated during the meeting. Therefore, in the history folder, the original document used in the meeting and the annotation (memo writing etc.) written there are stored. Such annotation is one of the most creative information in the conference, and it is more effective and effective as stimulating information to stimulate discussions and create ideas than simply presenting document information. Information.
However, the number of organizations in a company or the like is enormous, and it is very inefficient to search for documents related to all meetings. Therefore, here, the range in which the stimulus information is searched is specified.

To limit the search target,
There are two options: (1) Selection within the same meeting (2) Selection of related meeting.
When the same conference selection column 512 is selected, the search period (today conference column 5121 to 11th previous column 5124) is further limited, and the range is set as a search target. In addition to this, the method for limiting the period may be the number of times or time (within months).

For the related conference selection field 513, information in the conference body metadata 700 is used. For example, the limited information includes an explicit link column 5131, a participant column 5132, a document similarity column 5133, a similar theme column 5134, and the like.
A case where the explicit link field 5131 is selected will be described. In the explicit link, a relationship with a conference is defined in advance and stored as conference body metadata 700. When an explicit link is instructed, the history folder in the history folder column 703 of the conference entity metadata 700 in addition to the related conference entity name column 704 defined in the conference entity metadata 700 is searched.

A case where the participant field 5132 is selected will be described. Participants are defined in the member column 702 of the conference body metadata 700. The higher the degree of duplication of participants in the conference body, the higher the relevance of the conference.
For example, FIG. 8 shows an example of the relevance of the conference. The AAA conference body set 810 and the CCC conference body set 830 have five members (D, E, F, G, H) overlapping, and the degree of association between the conference bodies is high. On the other hand, the BBB conference body set 820 has only one member (D) overlapping with the AAA conference body set 810 and the CCC conference body set 830, and the relevance is low. When the participant field 5132 is selected, a highly relevant conference (a conference highly relevant to the AAA conference entity set 810 is CCC conference entity set 830 in FIG. 8) is extracted. Here, the high relevance is specifically performed by comparing the number of the most common participants in the related conference name column 704 or comparing the common participants with a predetermined value. Here, the predetermined value includes a predetermined value, a value that changes according to the number of participants in the conference, a theme, and the like (for example, a value that is calculated using 60% of the number of participants in the conference).

A case where the document similarity column 5133 is selected will be described. When the document similarity column 5133 is selected, the document group stored in the history folder is analyzed using a natural language processing technique or the like to search for similar documents. Here, it is assumed that the agenda theme is similar for a meeting in which similar documents exist, and the documents in the history folder of the meeting in which similar documents are stored are searched to extract stimulus information.
When the selection column in the document similarity column 5133 and the same conference selection column 512 (today's conference column 5121 to 11th previous column 5124) is selected, the document within the specified target range in the same conference is selected. Search for something similar to the document used in the current meeting.
FIG. 9 shows an example of document similarity.
The history folder of the AAA conference body 910 has a history 911 and a history 912. The history 911 includes a document 913 and a document 914, and the history 912 includes a document 915 and a document 916. Similarly, the history folder of the BBB conference body 920 has a history 921 and a history 922. The history 921 has a document 923 and a document 924, and the history 922 has a document 925 and a document 926. Furthermore, the history folder of the CCC conference body 930 has a history 931 and a history 932. The history 931 includes a document 933 and a document 934, and the history 932 includes a document 935 and a document 936.
If the current meeting is the AAA meeting body 910, the history in the meeting is the history 911, the document similar to the document 913 is the document 933, and the documents similar to the document 914 are the document 934 and the document 923 The documents that are the ranges are the document 923 and the document 924 in the history 921 of the BBB conference body 920, and the document 933 and the document 934 in the history 931 of the CCC conference body 930.

A case where the similar theme column 5134 is selected will be described. The speech data of the discussion accumulated in the history folder is converted into text by speech recognition and subjected to syntax analysis. When the similar theme column 5134 is selected, the degree of similarity is determined by natural language processing technology for the text data of these discussions in the same manner as the document similarity determination. As a result, a similar conference is selected as a search target using the content actually spoken.
FIG. 10 shows an example of discussion similarity.
The voice DB 720 linked to the history folder of the AAA conference body 1010 has a history 1011 and a history 1012. The history 1011 includes discussion speech data 1013 and speech text analysis data 1014, and the history 1012 includes discussion speech data 1015 and speech text analysis data 1016. Similarly, the voice DB 720 linked to the history folder of the BBB conference body 1020 has a history 1021 and a history 1022. The history 1021 includes discussion speech data 1023 and speech text analysis data 1024, and the history 1022 includes discussion speech data 1025 and speech text analysis data 1026. Further, the voice DB 720 linked to the history folder of the CCC conference body 1030 has a history 1031 and a history 1032. The history 1031 includes discussion speech data 1033 and speech text analysis data 1034, and the history 1032 includes discussion speech data 1035 and speech text analysis data 1036.
When the current conference is the AAA conference body 1010, the history of the speech data in the conference is the history 1011, and the text data similar to the speech text analysis data 1014 is the speech text analysis data 1024 and the speech text analysis data 1036. The text data used as the search range is the speech text analysis data 1024 in the history 1021 of the BBB conference body 1020 and the speech text analysis data 1036 in the history 1032 of the CCC conference body 1030.

A case where the keyword selection field 514 is selected will be described. This keyword selection field 514 is for selecting a keyword for searching for stimulus information. There are two types of selection methods, automatic and manual.
When the automatic selection field 515 is selected, the present embodiment automatically selects a keyword. For example, the utterance keyword extraction module 102 analyzes the text data of the voice of the discussion, and extracts the vocabulary being spoken. By natural language processing, general terms and the like are excluded from the vocabulary, and frequently used terms are selected as keywords from the remaining words. Then, the keyword is searched for the document within the specified range. As another method, keywords are extracted by performing natural language processing similar to that described above on the text content of the document used in the meeting.
When the input selection field 516 is selected, the search condition input module 103 accepts a keyword that is explicitly input by an operation of the facilitator.

An example of a stimulus information search process performed by the stimulus information search module 109 and the shared screen management module 111 will be described using the flowchart shown in FIG.
In step S1102, the stimulus information search module 109 searches for the keyword in the contents in the document in the search target range folder using the search target (search range) and the keyword.
In step S1104, the stimulus information search module 109 determines whether the keyword exists. When it exists (Y), it progresses to step S1122, and when it does not exist (N), it progresses to step S1106.

In step S1106, the stimulus information search module 109 searches for the keyword in the text data contents of the voice data linked in the search target range folder using the search target (search range) and the keyword.
In step S1108, the stimulus information search module 109 determines whether the keyword exists. If it exists (Y), the process proceeds to step S1110, and if it does not exist (N), the process ends (step S1122).
In step S1110, the stimulus information search module 109 extracts the document that was displayed when the keyword was spoken. In other words, the text data in the speech DB 720 includes the time when the speech was made, and the keyword was spoken based on the history information in the history folder (including the history of which document was displayed when). Extract the document that was displayed at times.

In step S1112, the stimulus information search module 109 determines whether there is an annotation derived from the page including the keyword in the document searched in step S1102 or the document extracted in step S1110. If there is an annotation (Y), the process proceeds to step S1114. Otherwise (N), the process proceeds to step S1116.
In step S1114, the shared screen management module 111 extracts the derived annotation as stimulus information.

In step S1116, the stimulus information search module 109 determines whether there is an insertion page derived from the page including the keyword in the document searched in step S1102 or the document extracted in step S1110. If there is an insertion page (Y), the process proceeds to step S1118; otherwise (N), the process proceeds to step S1120.
In step S1118, the shared screen management module 111 extracts the derived insertion page as stimulus information.
In step S1120, the shared screen management module 111 extracts a page including a keyword as stimulus information in the document searched in step S1102 or the document extracted in step S1110.

Next, a process in which the shared screen management module 111 displays stimulus information on the shared screen 112 will be described.
The shared screen management module 111 displays a list of stimulus information searched by the stimulus information search module 109 on the shared screen 112.
Further, before the display on the shared screen 112 by the shared screen management module 111, the facilitator screen management module 107 displays the stimulus information stored in the stimulus information storage module 110 on the facilitator screen 113, so that the facilitator Any information can be selected from these information groups, and only the selected stimulus information can be referred to by all the participants in the conference. Display). As a result, the members' thoughts can be stimulated.
This function does not necessarily have to be used only to show and stimulate the participants. For example, depending on how it is used, the facilitator displays it only on the screen at hand, and the content is used by the facilitator itself as a material to examine the direction of the discussion and how to stimulate the idea. Such information may be used for facilitation.

  FIG. 12 is an explanatory diagram illustrating an example of a relationship between a meeting and a document. In FIG. 12, the conference is proceeding from left to right. That is, the first page 1201, the second page 1202, and the third page 1203 are displayed in order on the shared screen 112. The history is saved only when an annotation (append) or insertion page occurs in the document.

In the display of the cover of the first page 1201, there is no history since nothing was added.
When the second page 1202 is displayed, the annotation 1251 is added by the operation of the operator and stored as the history 1 1206 in the history folder.
In the display of the third page 1203, nothing is added, so there is no history.
Next, when the fourth page 1204 is displayed, an annotation 1252 is added by the operator and stored as history 2 1207 in the history folder.
After the fourth page 1204 is displayed, blank page insertion 1208 is performed, and the page is drawn on the insertion page by the operation of the operator, and stored as history 3 1209 in the history folder.
In the display of the fifth page 1205, nothing is added, so there is no history.
Then, after the fifth page 1205 is displayed, the history 2 1207 is displayed again by the operation of the operator. Here, an annotation 1253 and an annotation 1254 are further added and stored as the history 4 1211 in the history folder.
After the history 1210 is displayed, blank page insertion 1212 is performed, and the operator inserts the blank page 1212 and draws it on the insertion page. The history 51212 is stored in the history folder.

FIG. 13 is an explanatory diagram showing a data structure example of the history table 1300 in the conference shown in FIG. The history table 1300 is stored in the history archive 141.
The history table 1300 has a NO column 1301, a file name column 1302, a derivation source column 1303, and an insertion page column 1304.
The NO column 1301 stores a number that can uniquely identify the stored history.
A file name column 1302 is a file name of a display page of a document stored as a history. That is, in the example shown in FIG. 12, the file names of the histories 1206, 1207, 1209, 1211, and 1213 are used.
The derivation source column 1303 is a derivation source document (including pages). That is, it is possible to detect from which document the history is generated. Note that the derivation source document in the case of blank sheet insertion is a page before insertion. In the example of FIG. 12, the document from which history 3 1209 is derived is the fourth page 1204. If the derivation source document is a history, the document name stored in the file name column 1302 is stored in the derivation source column 1303. For example, the document from which the history 4 1211 is derived is the history 2 1207.
The insertion page column 1304 stores a code indicating whether or not the page is an insertion page. In the example of FIG. 12, the histories 1209 and 1213 are insertion pages.

  The stimulus information search module 109 uses the history table 1300 to extract annotations and insertion pages generated in relation to a document (including pages). In other words, it is only necessary to extract a history from the retrieved document (the page where the keyword exists) as a derivation source. More specifically, the retrieved document is extracted from the derivation source column 1303, and the file that is the history of the corresponding file name column 1302 is extracted.

  As shown in FIG. 14, the hardware configuration of a computer on which the program according to the present embodiment is executed is a general computer, specifically a personal computer, a computer that can be a server, or the like. A CPU 1401 that executes programs such as an inactive state detection module 101, a speech keyword extraction module 102, a facilitator screen management module 107, a speech status visualization processing module 108, a stimulus information search module 109, a shared screen management module 111, and a speech recognition module 122; A RAM 1402 for storing the program and data, a ROM 1403 for storing a program for starting the computer, an HD 1404 (for example, a hard disk can be used) as an auxiliary storage device, a keyboard, a mouse, and the like An input device 1406 for inputting data, an output device 1405 such as a CRT or a liquid crystal display, and a communication line interface 1407 (for example, a network interface) for connecting to a communication network It can be used face card), and, and a bus 1408 for exchanging data by connecting them. A plurality of these computers may be connected to each other via a network. Note that there may be a plurality of configurations, and in particular, the conference system 100 includes two output devices 1405 as the shared screen 112 and the facilitator screen 113.

Among the above-described embodiments, the computer program is a computer program that reads the computer program, which is software, in the hardware configuration system, and the software and hardware resources cooperate with each other. Is realized.
Note that the hardware configuration illustrated in FIG. 14 illustrates one configuration example, and the present embodiment is not limited to the configuration illustrated in FIG. 14, and is a configuration capable of executing the modules described in the present embodiment. I just need it. For example, some modules may be configured by dedicated hardware (for example, ASIC), and some modules may be in an external system and connected via a communication line. A plurality of systems shown in FIG. 5 may be connected to each other via communication lines so as to cooperate with each other. In particular, in addition to personal computers, information appliances, copiers, fax machines, scanners, printers, and multifunction machines (image processing apparatuses having two or more functions of scanners, printers, copiers, fax machines, etc.) Etc. may be incorporated.

  In the above embodiment, the data structures shown in FIGS. 7 and 13 are not limited to these data structures, and may be other data structures. For example, the table structure may be a link structure or the like. Further, the data items are not limited to those shown in the drawings, and may have other data items.

The program described above may be provided by being stored in a recording medium, or the program may be provided by communication means. In that case, for example, the above-described program may be regarded as an invention of a “computer-readable recording medium recording the program”.
The “computer-readable recording medium on which a program is recorded” refers to a computer-readable recording medium on which a program is recorded, which is used for program installation, execution, program distribution, and the like.
The recording medium is, for example, a digital versatile disc (DVD), which is a standard established by the DVD Forum, such as “DVD-R, DVD-RW, DVD-RAM,” and DVD + RW. Standards such as “DVD + R, DVD + RW, etc.”, compact discs (CDs), read-only memory (CD-ROM), CD recordable (CD-R), CD rewritable (CD-RW), etc. MO), flexible disk (FD), magnetic tape, hard disk, read only memory (ROM), electrically erasable and rewritable read only memory (EEPROM), flash memory, random access memory (RAM), etc. It is.
The program or a part of the program may be recorded on the recording medium for storage or distribution. Also, by communication, for example, a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a wired network used for the Internet, an intranet, an extranet, etc., or wireless communication It may be transmitted using a transmission medium such as a network or a combination of these, or may be carried on a carrier wave.
Furthermore, the program may be a part of another program, or may be recorded on a recording medium together with a separate program. Moreover, it may be divided and recorded on a plurality of recording media. Further, it may be recorded in any manner as long as it can be restored, such as compression or encryption.

It is a conceptual module block diagram about the structural example of this Embodiment. It is a flowchart which shows the example of a basic process by this Embodiment in a facilitator mode. It is a flowchart which shows the basic processing example by this Embodiment in automatic mode. It is explanatory drawing which shows the example of a screen of an individual speech total time display screen. It is explanatory drawing which shows the example of a screen of an individual speech total time display screen and a stimulus information search screen. It is a flowchart which shows the presentation process example of stimulus information. It is explanatory drawing which shows the relationship between a history archive, meeting body metadata, and audio | voice DB. It is explanatory drawing which shows the example of the association degree of a meeting. It is explanatory drawing which shows the example of the similarity of a document. It is explanatory drawing which shows the example of the similarity of discussion. It is a flowchart which shows the search process example of stimulus information. It is explanatory drawing which shows the example of the relationship between a meeting and a document. It is explanatory drawing which shows the data structure example of a log | history table. It is a block diagram which shows the hardware structural example of the computer which implement | achieves this Embodiment.

Explanation of symbols

DESCRIPTION OF SYMBOLS 100 ... Conference system 101 ... Inactive state detection module 102 ... Utterance keyword extraction module 103 ... Search condition input module 104 ... Search condition storage area 105 ... Communication module (reception module)
DESCRIPTION OF SYMBOLS 106 ... Statement situation data storage module 107 ... Facilitator screen management module 108 ... Statement situation visualization processing module 109 ... Stimulus information search module 110 ... Stimulus information storage module 111 ... Shared screen management module 112 ... Shared screen 113 ... Facilitator screen 120 ... Remote place Conference system 121 ... Voice input module 122 ... Speech recognition module 123 ... Speech information storage area 124 ... Communication module 125 ... Microphone 126 ... Shared screen 130 ... Conference body metadata DB server 131 ... Conference body metadata 140 ... History archive server 141 ... History archive 199 ... communication line

Claims (2)

A conference record storage means for storing a document used in a conference between remote regions, information generated in association with the document in the conference, and information on participants of the conference in association with each other;
Remark text storage means for storing remark text information in the conference and a document related to the replay;
Detecting means for detecting an active state in the conference for each region;
Search instruction display means for performing a display prompting the operator to search according to the active state detected by the detection means;
Accepting means for receiving a search instruction based on a limitation of a search target and a keyword by an operation of an operator based on a display by the search instruction display means;
In response to the search instruction received by the reception unit, the document stored in the conference record storage unit is converted into a conference having the most common participants with the conference participants based on the information of the conference participants. A search means for searching by the keyword limitedly ;
And an output means for outputting the information stored in the Proceedings storage means corresponding to the documents retrieved by said retrieval means,
The information processing system , wherein the search means further searches the text information stored in the remark text storage means with the keyword, and uses a document related to the text information as a search result . Computer
A conference record storage means for storing a document used in a conference between remote regions, information generated in association with the document in the conference, and information on participants of the conference in association with each other;
Remark text storage means for storing remark text information in the conference and a document related to the replay;
Detecting means for detecting an active state in the conference for each region;
Search instruction display means for performing a display prompting the operator to search according to the active state detected by the detection means;
Accepting means for receiving a search instruction based on a limitation of a search target and a keyword by an operation of an operator based on a display by the search instruction display means;
In response to the search instruction received by the reception unit, the document stored in the conference record storage unit is converted into a conference having the most common participants with the conference participants based on the information of the conference participants. A search means for searching by the keyword limitedly ;
To function as output means for outputting the information stored in the Proceedings storage means corresponding to the documents retrieved by said retrieval means,
The information processing program characterized in that the search means further searches text information stored in the remark text storage means with the keyword, and uses a document related to the text information as a search result .

Images