JP2019102060A - Information presentation system, information presentation method, program, and recording medium - Google Patents

Abstract

To improve adequacy of information to be presented.SOLUTION: An information presentation system 1 creates a query on the basis of a common word common to a plurality of pieces of text data included in at least two pieces of data from among voice data of a voice acquired in an arbitrary period, image data displayed on a predetermined display or prepared for printing purpose, and keyword data indicating registered keywords, acquires a result of searching with a query from a predetermined database, and outputs the search result or part of the search result to a predetermined output device.SELECTED DRAWING: Figure 3

Description

  The present invention relates to an information presentation system, an information presentation method, a program, and a recording medium.

  A system is used that presents meeting participants with relevant information related to the meeting. In such a system, for example, it is required to be able to simply and appropriately present to a participant a document (related information) related to a voice emitted during a meeting, an image displayed on a display device, etc. Be

  For example, an idea extraction support system is disclosed that extracts character information from an image of a character string acquired by an imaging unit and voice acquired by a microphone and generates support information based on the extracted character information (Patent Document 1).

  By using the system as described above, it is possible to present the participants with information relating to the sound emitted during the meeting and the displayed image. However, in speech recognition processing performed when converting speech into text and image recognition processing performed when converting into text, it is inevitable that false recognition occurs with a certain degree of probability. When such misrecognition occurs, information unrelated to the content of the meeting may be presented. Since conventional systems can not cope with such problems, there is much room for improvement in terms of the appropriateness of the presented information. For example, even if a participant does not perform a search operation, it is desirable that related information be presented to the participant voluntarily from the system based on many types of acquired information. It is important to improve the appropriateness of the information presented at this time.

  The present invention has been made in view of the above, and its object is to improve the appropriateness of presented information.

  In order to solve the problems described above and achieve an object, an aspect of the present invention is an information presentation system that presents related information related to information presented or acquired at any time within any period. At least one of voice data of voice obtained within the given period, image data to be displayed on a predetermined display device or prepared for printing on a medium, and keyword data indicating a registered keyword A query is generated based on a common word common to a plurality of text data included in two data, and an information acquisition unit for acquiring a search result by the query from a predetermined database, the search result or a part of the search result And an output unit for outputting the signal to a predetermined output device.

  According to the present invention, it is possible to improve the appropriateness of presented information.

FIG. 1 is a diagram showing an example of a system configuration of the information presentation system according to the first embodiment. FIG. 2 is a block diagram showing an example of the hardware configuration of the management server and the database server according to the first embodiment. FIG. 3 is a block diagram showing an example of a functional configuration of the information presentation system according to the first embodiment. FIG. 4 is a block diagram showing an example of a functional configuration of the external search unit according to the first embodiment. FIG. 5 is a diagram showing an example data structure of index information according to the first embodiment. FIG. 6 is a block diagram showing an example of the functional configuration of the text conversion unit according to the first embodiment. FIG. 7 is a diagram showing an example data structure of recognition data information according to the first embodiment. FIG. 8 is a block diagram showing an example of a functional configuration of the information acquisition unit according to the first embodiment. FIG. 9 is a sequence diagram showing an example of processing in the information presentation system according to the first embodiment. FIG. 10 is a flowchart showing an example of processing when generating a query according to the first embodiment. FIG. 11 is a diagram showing an example of a setting screen according to the first embodiment. FIG. 12 is a diagram showing an example of a search result display screen according to the first embodiment. FIG. 13 is a block diagram showing an example of a functional configuration of the information presentation system according to the second embodiment. FIG. 14 is a block diagram showing an example of the functional configuration of a keyword acquisition unit according to the second embodiment. FIG. 15 is a block diagram showing an example of a functional configuration of the external search unit according to the second embodiment. FIG. 16 is a sequence diagram showing an example of processing in the information presentation system according to the second embodiment. FIG. 17 is a diagram illustrating an example of the SNS screen according to the second embodiment. FIG. 18 is a block diagram showing an example of a functional configuration of the information presentation system according to the third embodiment. FIG. 19 is a block diagram showing an example of a functional configuration of a similar sentence extraction unit according to the third embodiment. FIG. 20 is a sequence diagram showing an example of processing in the similar sentence extraction unit according to the third embodiment. FIG. 21 is a block diagram showing an example of a functional configuration of a key phrase creation unit according to the third embodiment. FIG. 22 is a flowchart showing an example of processing in the key phrase creation unit according to the third embodiment. FIG. 23 is a block diagram showing an example of a functional configuration of an information acquisition unit according to the third embodiment. FIG. 24 is a flowchart illustrating an example of processing in the information acquisition unit according to the third embodiment. FIG. 25 is a block diagram showing an example of a functional configuration of the information presentation system according to the fourth embodiment. FIG. 26 is a block diagram showing an example of a functional configuration of a similar information extraction unit according to the fourth embodiment. FIG. 27 is a sequence diagram showing an example of processing in the similar information extraction unit according to the fourth embodiment. FIG. 28 is a block diagram showing an example of a functional configuration of an information presentation system according to the fifth embodiment. FIG. 29 is a block diagram showing an example of a functional configuration of an acquisition information clustering unit according to the fifth embodiment. FIG. 30 is a sequence diagram showing an example of processing in an acquisition information clustering unit according to the fifth embodiment.

  Hereinafter, embodiments of an information presentation system, an information presentation method, a program, and a recording medium will be described in detail with reference to the attached drawings. The present invention is not limited by the following embodiments, and the constituent elements in the following embodiments include those which can be easily conceived by those skilled in the art, substantially the same ones, and so-called equivalent ranges. . Various omissions, substitutions, changes, and combinations of the constituent elements can be made without departing from the scope of the following embodiments.

First Embodiment
FIG. 1 is a diagram showing an example of a system configuration of the information presentation system 1 according to the first embodiment. The information presentation system 1 is a system that presents related information related to the conference to the participants of the conference. The "related information" is not limited to the information related to the "meeting", and may be information related to the information presented or acquired at any time within any period. The information presentation system 1 according to the present example includes a management server 11, a database server 12, a microphone 13, a projector 14 (display device), a display 15 (display device), a client terminal 16 (terminal), and a network 19.

  The microphone 13 collects the voices of the participants in the conference and generates voice data. The voice data is transmitted to the management server 11 via the network 19. The projector 14 projects an image (still or moving image) on a predetermined screen. The display 15 displays an image. The projector 14 and the display 15 operate in accordance with image data, control signals and the like transmitted from the management server 11 via the network 19. The client terminal 16 is a personal computer operated by a participant of the conference, etc., and is connected to the management server 11 via the network 19. The database server 12 is a computer system including a processor, a storage device and the like that manages (writes, reads, searches, etc.) various data including related information, and is connected to the management server 11 via the network 19. The management server 11 is a computer system including a processor, a storage device, and the like that performs processing for presenting related information to participants, and the database server 12, the microphone 13, the projector 14, the display 15, and the client via the network 19. It is connected to the terminal 16 and other appropriate devices.

  The projector 14 and the display 15 do not always have to be used at the same time, but only one of them may be used. In addition, the display 15 may operate based on not only the control signal from the management server 11 but also the control signal from the client terminal 16. Although the projector 14 and the display 15 are illustrated as display devices in FIG. 1, for example, a device having both a display (projection) function and an input function (electronic blackboard (interactive white board), electronic information board, etc. ) May be used. Further, related information may be displayed on a predetermined display device under the control of the management server 11 based on the acquired display content. Further, when using a search engine having a database function, the database server 12 may not be included in the information presentation system 1. The management server 11 may be a specific computer, but may be configured to delegate the function of the management server 11 to the cloud.

  FIG. 2 is a block diagram showing an example of the hardware configuration of the management server 11 and the database server 12 according to the first embodiment. The management server 11 and the database server 12 include a central processing unit (CPU) 21, a random access memory (RAM) 22, a read only memory (ROM) 23, a storage 24, an input device 25, an output device 26, and a communication I / F 27. Including. The CPU 21 performs predetermined control arithmetic processing with the RAM 22 as a working area in accordance with a program stored in the ROM 23. The storage 24 is a non-volatile memory and stores various data. The input device 25 is a device for receiving an operation of a user (a system administrator or the like) and inputting information from the outside, and is, for example, a keyboard, a mouse, a touch panel or the like. The output device 26 is a device for outputting the internally generated information to the outside, and is, for example, a display, a printer or the like. The communication I / F 27 is a device that enables transmission and reception of information with an external device via the network 19. The input device 25 and / or the output device 26 may be unnecessary.

  The system configuration and the hardware configuration shown in FIGS. 1 and 2 are merely examples, and the information presentation system 1 should be constructed using appropriate hardware and software according to the use situation.

  FIG. 3 is a block diagram showing an example of a functional configuration of the information presentation system 1 according to the first embodiment. The information presentation system 1 according to this example includes an audio data acquisition unit 101, an image data acquisition unit 102, a keyword acquisition unit 103, an input unit 104, a textification unit 105, an information acquisition unit 106, an external search unit 107, an output unit 108. And an external output unit 109.

  The audio data acquisition unit 101 acquires audio data of audio emitted during a meeting. The audio data is acquired, for example, by the microphone 13 installed in the conference room.

  The image data acquisition unit 102 acquires image data of an image displayed on a display device (projector 14, display 15 or the like) installed in a conference room or the like. The image data may be data obtained by capturing an image actually displayed on the display device, or may be content data indicating the display content.

  The keyword acquisition unit 103 acquires keyword data indicating a keyword registered in advance by a participant or the like. The registration of the keyword is performed, for example, by the participant operating the client terminal 16 or the like. The keywords in this case are information that is effective for acquiring appropriate related information, and are, for example, texts and the like that are related to the contents of the meeting and that indicate that the participants are interested. It is preferable to register, as a keyword, a wording that is not spoken during the meeting or is not displayed as an image despite the relevance of the contents of the meeting and the participants are interested.

  The input unit 104 inputs the audio data acquired by the audio data acquisition unit 101, the image data acquired by the image data acquisition unit 102, and the keyword data acquired by the keyword acquisition unit 103. Input and retention of voice data, image data, and keyword data are performed using, for example, the storage 24 of the management server 11 or the like.

  The text conversion unit 105 converts the voice data, the image data, and the keyword data input by the input unit 104 into text. By converting voice data into text, voice text data is generated. Image text data is generated by converting the image data into text. Keyword text data is generated by converting the keyword data into text. Textification of keyword data is, for example, a process of converting keyword data input by means such as handwriting into a normalized character string. Textification can be performed using known speech recognition processing (ASR (Automatic Speech Recognition) processing), image recognition processing (OCR (Optical Character Recognition) processing), etc., and mainly the processing capability of the management server 11 is It can be done using.

  The information acquisition unit 106 acquires related information from the external search unit 107 based on the text data (voice text data, image text data, and keyword text data) generated by the textification unit 105. The information acquisition unit 106 generates a query based on text data, transmits the query to the external search unit 107, and acquires related information matching the query from the external search unit 107. The “query” in this embodiment is a clear information request in information search. Queries are mainly expressed by linking keywords with logical operators and other modifiers. The information acquisition unit 106 is realized, for example, using the processing capability of the management server 11.

  The external search unit 107 searches and extracts related information conforming to the query received from the information acquisition unit 106 from the database storing the related information, and transmits the extracted related information to the information acquisition unit 106. The external search unit 107 is realized, for example, using the processing capability of the database server 12.

  The output unit 108 outputs the related information acquired by the information acquisition unit 106 to the external output unit 109. The output unit 108 has a function of converting the acquired related information into a format according to the specification of each external output unit 109, and is realized, for example, using the function of the management server 11.

  The external output unit 109 presents related information to the participant, and may be, for example, the client terminal 16, the display 15, the projector 14 or the like.

  FIG. 4 is a block diagram showing an example of a functional configuration of the external search unit 107 according to the first embodiment. The external search unit 107 according to this example includes an external source 121 (database), an external source cooperation unit 122, a crawl control unit 123, a document collection unit 124, an index storage unit 125, and a document search unit 126.

  The external source cooperation unit 122 performs processing for reading out related information such as a document stored in the external source 121. The external source cooperation unit 122 accesses the external source 121 by a predetermined access process. The access process may include an authentication process in addition to the transmission and reception of data.

  The crawl control unit 123 performs a crawl operation on the related information read by the external source cooperation unit 122 within a range set according to the restriction of the external source 121 or the like.

  The document collection unit 124 collects related information via the crawl control unit 123. The document collection unit 124 formats the related information received from the crawl control unit 123 into an appropriate format, generates index information corresponding to the formatted related information, and stores the index information in the index storage unit 125.

  The document search unit 126 searches for index information that matches the query received from the information acquisition unit 106 (management server 11), and acquires related information corresponding to the searched index information from the document collection unit 124.

  In addition, since the function of the external search unit 107 can be realized by an existing search engine, the information presentation system 1 may not be provided with the external search unit 107 when using such a search engine. .

  FIG. 5 is a view showing an example of the data structure of the index information 130 according to the first embodiment. In the index information 130 according to this example, as columns, a “creator” indicating the creator of the document, a “class” indicating the type of the document, a “creation date” indicating the date and time when the document was created, and the document are stored "Source" to identify the source (external source 121), "text" indicating the content of text, "title" indicating the title of the document, "document ID" which is an identification number uniquely assigned to each document, and the document Contains an "update date and time" indicating the date and time when was updated. All documents can be identified by "document ID" and "source". When the document is updated, the "updated date" is updated. A plurality of documents having the same “title” may be divided into a plurality of items (rows) and registered due to the restriction of the external source 121. "Text" and "Title" are search targets.

  FIG. 6 is a block diagram showing an example of a functional configuration of the textification unit 105 according to the first embodiment. The textification unit 105 according to this example includes an input data reception unit 131, an input data processing unit 132, a text transmission unit 133, and a recognition data storage unit 134.

  The input data receiving unit 131 receives the audio data, the image data, and the keyword data received from the input unit 104, stores the data as a cache, and then transmits these data to the input data processing unit 132.

  The input data processing unit 132 converts voice data into text and generates voice text data. The input data processing unit 132 converts image data into text and generates image text data. The keyword data is converted into text and keyword text. It includes a keyword processing unit 143 that generates data. The input data processing unit 132 transmits the generated voice text data, image text data, and keyword text data to the text transmission unit 133. The input data processing unit 132 generates recognition data information based on voice text data, image text data, and keyword text data, and causes the recognition data storage unit 134 to store recognition data information. The recognition data information is used for subsequent verification, learning and the like.

  The text transmission unit 133 transmits the received voice text data, image text data, and keyword text data to the information acquisition unit 106.

  FIG. 7 is a view showing an example data structure of the recognition data information 150 according to the first embodiment. The recognition data information 150 according to the present example specifies, as a column, a “meeting ID” (which is an identification number uniquely assigned to each meeting) that identifies a meeting from which the original data targeted for the texting is acquired. "Recognition date" which indicates the date and time when the event was performed, "language" which indicates the type of language of the text, "recognition type" which indicates the type of recognition processing used for text conversion (in this example, OCR or ASR), and Includes "text" to indicate content. In this example, the partition key of each item is "meeting ID" and the sort key is "recognition date".

  FIG. 8 is a block diagram showing an example of a functional configuration of the information acquisition unit 106 according to the first embodiment. The information acquisition unit 106 according to this example includes a text reception unit 151, a text selection unit 152, a query generation unit 153, a search call unit 154, and a search result transmission unit 155.

  The text reception unit 151 receives voice text data, image text data, and keyword text data from the text conversion unit 105 (text transmission unit 133).

The text selection unit 152 selects two or more text data from the plurality of text data received by the text reception unit 151. In the present embodiment, the following four selection patterns (1) to (4) exist.
(1) voice text data + image text data (2) voice text data + keyword text data (3) image text data + keyword text data (4) voice text data + image text data + keyword text data

  The query generation unit 153 generates a query based on the text data selected by the text selection unit 152. For example, if the selection pattern is (2), the query generation unit 153 compares voice text data with keyword text data, and extracts a “common word” common to both. By extracting the common word, it is possible to avoid the erroneous recognition portion occurring in the audio text data or the keyword text data as a result. Thereafter, the query generation unit 153 generates a query by connecting the common word and the common word with an appropriate logical operator. In this example, the following four types of queries (first to fourth queries) can be generated.

  The first query corresponds to the selection pattern (1) and is a query generated by combining speech text data and image text data. By using the first query, for example, it becomes possible to obtain related information reflecting the contents of both the sound emitted during the meeting and the displayed image. As described above, by combining the voice text data and the image text data to generate a query, it is possible to reduce the effects of false recognition in voice recognition processing and false recognition in image recognition processing. Although misrecognition may occur with a certain probability in the speech recognition process and the image recognition process, the possibility of misrecognition of the same object in both the speech recognition process and the image recognition process is extremely low. This can improve the appropriateness of the search results. Further, in the first query, flexible search results can be obtained because there is no influence of the registered keywords.

  The second query corresponds to the selection pattern (2) and is a query generated by combining speech text data and keyword text data. By using keyword text data, it is possible to define a search direction in the search process of related information. By using the second query, for example, related information corresponding to voices having a high degree of association with a pre-registered keyword is preferentially acquired, or related information corresponding to voices having a low degree of association with a keyword It is possible to eliminate This can improve the appropriateness of the search results.

  The third query corresponds to the selection pattern (3), and is a query generated by combining the image text data and the keyword text data. By using keyword text data, it is possible to define a search direction in the search process of related information. By using the third query, for example, related information corresponding to an image having a high degree of association with a pre-registered keyword is preferentially acquired, or related information corresponding to an image having a low degree of association with a keyword It is possible to eliminate This can improve the appropriateness of the search results.

  The fourth query corresponds to the selection pattern (4), and is a query generated by combining speech text data, image text data, and keyword text data. By using keyword text data, it is possible to define a search direction in the search process of related information. By using the fourth query, it is possible to reduce the influence of misrecognition in speech recognition processing and misrecognition in image recognition processing, and, for example, to speech and / or speech that have a high degree of association with pre-registered keywords. It is possible to preferentially obtain related information corresponding to an image, or to exclude related information corresponding to voice and / or an image having a low degree of association with a keyword. This can improve the appropriateness of the search results.

The corresponding method in the case of “misrecognized” is exemplified below.
(1) Correct to the correct term.
(2) Do not use terms that may be misrecognized (do not include in queries).

  The “common language” may be extracted after performing the above-mentioned correspondence method (1) for a pair of commonly used terms, synonyms, synonyms, homonyms, and the like. Further, the correspondence method (2) is not limited to “do not use”, and is, for example, correspondence such as “weighting terms according to the number of times of appearance when comparing a plurality of texts”. It is also good. Specifically, it may be a response such as “increase weighting of common words and decrease weighting of other terms”.

  For adjustment of search directionality using keyword text data, it is desirable to operate keywords in a filtering manner. For example, when a keyword is designated, a process of excluding search results not including the keyword may be used. For example, when there are voice text data, image text data, and keyword text data as in selection pattern (4), a query such as {(voice text) OR (image text)} AND (keyword) is generated, Keywords can be used as filters. That is, those that do not include keywords (and their synonyms) may not be included in the search results. Note that not only the form in which the keyword is used in AND, for example, the keyword may be “weighted” to perform concept search based on the keyword.

  The search calling unit 154 transmits the query generated by the query generation unit 153 to the external search unit 107, and receives a search result (related information conforming to the query) as a response to the query.

  The search result transmitting unit 155 transmits the search result received by the search calling unit 154 to the output unit 108.

  FIG. 9 is a sequence diagram showing an example of processing in the information presentation system 1 according to the first embodiment. When the information acquisition unit 106 requests capture of the image projected by the projector 14 installed in the conference room (S101), the textification unit 105 (image processing unit 142) converts the characters present in the projected image into text. The generated image text data is generated, and the image text data is transmitted to the information acquisition unit 106 (S102).

  When the information acquisition unit 106 requests speech data (S103), the textification unit 105 (voice processing unit 141) generates voice text data in which the voice emitted in the conference room is converted to text, and the voice text data is acquired as an information acquisition unit It transmits to 106 (S104).

  When the information acquisition unit 106 requests a keyword registered by a participant or the like (S105), the textification unit 105 (keyword processing unit 143) requests the keyword acquisition unit 103 for a keyword (S106). When receiving the request from the textification unit 105, the keyword acquisition unit 103 transmits normalized data obtained by normalizing the keyword data to the textification unit 105 (keyword processing unit 143) (S107). Here, normalization refers to the conversion of the format of keyword data indicating a keyword registered by the client terminal 16 or the like into text processing by the text conversion unit 105, query generation processing by the information acquisition unit 106, and search by the external search unit 107. In order to facilitate processing, etc., it is necessary to change, for example, the keyword data may be changed to a format suitable for searching a relational database or a format suitable for Internet searching. The text conversion unit 105 (keyword processing unit 143) generates keyword text data based on the received normalized data, and transmits the keyword text data to the information acquisition unit 106 (S108).

  The information acquisition unit 106 generates a query by combining two or more of the received image text data, voice text data, and keyword text data (S109). Thereafter, the information acquisition unit 106 transmits a query to the external search unit 107 (document search unit 126) to request a search (S110). Based on the received query, the document search unit 126 searches and extracts a document (related information) having a high degree of association with the content of the meeting using the index information 130 stored in the index storage unit 125 (S111 , S112). The document search unit 126 transmits a search result including the extracted document as a query response to the information acquisition unit 106 (S113).

  The information acquisition unit 106 processes the received search result so as to be data that can be displayed on the external output unit 109 (such as the client terminal 16) (S114). The information acquisition unit 106 transmits the processed search result to the output unit 108 (S115), and the output unit 108 outputs the processed search result to the external output unit 109 (such as the client terminal 16) (S116).

  FIG. 10 is a flowchart showing an example of processing when generating a query according to the first embodiment. First, the input data processing unit 132 determines whether there is image data or audio data (S1001). When there is no image data or audio data (S1001: No), the information acquisition unit 106 determines whether the meeting is over (S1008). When the meeting is over (S1008: Yes), this routine is ended, and when the meeting is not over (S1008: No), the process returns to step S1001.

  If there is image data or voice data (S1001: Yes), the image processing unit 142 performs OCR processing on the image data (S1002), and the voice processing unit 141 performs ASR processing on the voice data (S1003).

  Thereafter, the input data processing unit 132 determines whether a keyword is necessary (S1004). Although the method of determining whether or not a keyword is necessary should not be particularly limited, for example, it can be determined based on the presence or absence of a keyword registration request from a participant. When the keyword is not necessary (S1004: No), the query generation unit 153 generates a query based on the image text data generated by the OCR processing and the voice text data generated by the ASR processing (S1006). If no keyword is required (S1004: No) and only one of image text data and voice text data exists, the text data can not be nulled, or a preset default value is set. It is conceivable to use On the other hand, when a keyword is required (S1004: Yes), the keyword acquisition unit 103 acquires a keyword (keyword data) (S1005), and the query generation unit 153 generates image text data generated by the OCR process and the ASR process A query is generated based on the generated voice text data and the keyword text data obtained by converting the acquired keyword data into text (S1006).

  Thereafter, the external search unit 107 performs a search process for searching and extracting a document (related information) having a high degree of association with the content of the meeting based on the query generated as described above (S1007). Thereafter, the information acquisition unit 106 determines whether the meeting is over (S1008), and when the meeting is over (S1008: Yes), this routine is finished, and when the meeting is not over (S1008: No), the step is It returns to S1001.

  FIG. 11 is a view showing an example of the setting screen 201 according to the first embodiment. The setting screen 201 according to the present example is a screen for registering a keyword and the like, and is an example of a screen displayed on a display or the like of the client terminal 16. In the setting screen 201 according to this example, a keyword input unit 202 for inputting a keyword, a database selection unit 203 for selecting a database to be searched (external source 121), and a search engine selection unit for selecting a search method 204 and the like are provided. By using such a screen, it becomes possible for participants and the like to easily register keywords, select a database to be searched, and select a search method to be used.

  FIG. 12 is a diagram showing an example of the search result display screen 211 according to the first embodiment. The search result display screen 211 according to the present example is a screen for displaying related information, and is an example of a screen displayed on a display or the like of the client terminal 16. The search result display screen 211 according to this example is provided with a related information display unit 212 for displaying the title and content of the related information (document), a relation degree display unit 213 for showing the relation between the discussion and the related information, and the like. There is. By using such a screen, it becomes possible for participants etc. to browse various information related to the discussion during a meeting or the like.

  The program for realizing the functions of the information presentation system 1 described above is a file in an installable format or an executable format, and a computer readable information such as a CD-ROM, a memory card, a CD-R and a DVD (Digital Versatile Disk). It is stored in a storage medium and provided as a computer program product. Also, a method of reading a web service provided via a browser may be used.

  Alternatively, the program may be stored on a computer connected to a network such as the Internet, and may be provided by being downloaded via the network. Alternatively, the program may be provided via a network such as the Internet without downloading the program. Also, the program may be configured to be provided by being incorporated in advance in a suitable storage device such as a ROM. Further, the program may have a module configuration including functions that can be realized by the program among the plurality of functions. The functions implemented by the program are loaded to a main storage device such as a RAM by reading and executing the program from the recording medium. That is, the functions implemented by the program are generated on the main storage device.

  As described above, according to the information presentation system 1 according to the present embodiment, data obtained by converting voices emitted during a meeting into text, data obtained by converting an image displayed during a meeting into text, and registration by participants or the like A query is generated based on two or more of the selected keywords, and relevant information matching such a query is obtained. As a result, the influence of false recognition in voice recognition processing and false recognition in image recognition processing is reduced, and it becomes possible to obtain highly relevant information along the search direction indicated by the keyword.

  Hereinafter, other embodiments will be described with reference to the drawings, but portions having the same or similar effects as the first embodiment may be denoted by the same reference numerals and description thereof may be omitted.

Second Embodiment
FIG. 13 is a block diagram showing an example of a functional configuration of the information presentation system 301 according to the second embodiment. The information presentation system 301 according to the present embodiment is characterized in that it has a configuration that can perform keyword registration using an external social networking service (SNS) system 302, and includes an SNS communication unit 311.

  The SNS system 302 is a known communication support system built using the Internet or the like. The existing SNS system 302 can be used as long as the participants of the meeting can access.

  The SNS communication unit 311 is connected to the SNS system 302, and receives keyword data indicating a keyword input from a terminal (such as the client terminal 16) accessing the SNS system 302. The SNS communication unit 311 is realized, for example, using the processing capacity of the management server 11.

  FIG. 14 is a block diagram showing an example of a functional configuration of the keyword acquisition unit 312 according to the second embodiment. The keyword acquisition unit 312 according to the present embodiment includes a keyword data acquisition unit 321 and a normalization unit 322.

  The keyword data acquisition unit 321 acquires keyword data from the SNS communication unit 311.

  The normalization unit 322 normalizes the keyword data acquired by the keyword data acquisition unit 321. Here, normalization means that the format of the keyword data received from the SNS system 302 can be easily converted into text by the text conversion unit 105, query generation by the information acquisition unit 106, and search processing by the external search unit 313. Change the received keyword data into a format suitable for Internet search (for example, connect keywords with words such as OR, AND, NOT, etc. and convert them into a search query) Etc. The keyword data normalized by the normalization unit 322 is input to the input unit 104. As in the first embodiment, the query generation unit 153 of the information acquisition unit 106 according to the present embodiment includes two of speech text data, image text data, and keyword text data generated by the textification unit 105. Generate a query based on the above.

  FIG. 15 is a block diagram showing an example of a functional configuration of the external search unit 313 according to the second embodiment. The external search unit 313 according to the present embodiment has a function of extracting related information from information published on the Internet 335, and includes a document search unit 331 and an external network cooperation unit 332.

  The document search unit 331 receives the query transmitted from the information acquisition unit 106 and transmits the query to the external network cooperation unit 332. The external network cooperation unit 332 collects information (related information) conforming to the query transmitted from the document search unit 331 from among the information disclosed on the Internet 335. Collection of related information by the external network cooperation unit 332 may be performed using an existing Internet search engine. The related information collected by the external network cooperation unit 332 is transmitted to the information acquisition unit 106 via the document search unit 331. The related information collected in this manner is preferably transmitted to the terminal that has accessed the SNS system 302 and registered the keyword.

  FIG. 16 is a sequence diagram showing an example of processing in the information presentation system 301 according to the second embodiment. When the information acquisition unit 106 requests capture of the image projected by the projector 14 installed in the conference room (S201), the textification unit 105 (image processing unit 142) converts the characters present in the projected image into text The generated image text data is generated, and the image text data is transmitted to the information acquisition unit 106 (S202).

  When the information acquisition unit 106 requests speech data (S203), the textification unit 105 (voice processing unit 141) generates voice text data in which the voice emitted in the conference room is converted to text, and the voice text data is acquired as an information acquisition unit It transmits to 106 (S204).

  When the information acquisition unit 106 requests a keyword registered by a participant or the like (S205), the text conversion unit 105 (keyword processing unit 143) requests the keyword acquisition unit 312 for a keyword (S206). When the keyword acquisition unit 312 receives a keyword request, the keyword acquisition unit 312 acquires keyword data from the SNS system 302 via the SNS communication unit 311, and normalizes the keyword data to the text conversion unit 105 (keyword processing unit 143). It transmits (S207). The text conversion unit 105 (keyword processing unit 143) generates keyword text data based on the received normalized data, and transmits the keyword text data to the information acquisition unit 106 (S208).

  The information acquiring unit 106 generates a query by combining two or more of the received image text data, voice text data, and keyword text data (S209). Thereafter, the information acquisition unit 106 transmits a query to the external search unit 313 (document search unit 331) to request a search (S210). Based on the received query, the document search unit 331 searches and extracts a document (related information) having a high degree of association with the contents of the conference from the information disclosed on the Internet 335 via the external network cooperation unit 332. The search result including the extracted document is transmitted to the information acquisition unit 106 as a response to the query (S211).

  The information acquisition unit 106 processes the received search result so that the terminal (client terminal 16 or the like) that has accessed the SNS system 302 can display data (S212). The information acquisition unit 106 transmits the processed search result to the output unit 108 (S213), and the output unit 108 outputs the processed search result to the terminal (client terminal 16 or the like) that has accessed the SNS system 302 (S214) .

  FIG. 17 is a diagram showing an example of the SNS screen 351 according to the second embodiment. The SNS screen 351 according to this example is a screen for registering a keyword using the SNS system 302, displaying related information, and the like, and is a screen displayed on a display of a terminal accessing the SNS system 302 or the like. An example of In the SNS screen 351 according to the present embodiment, a keyword input unit 352 for inputting a keyword, a keyword display unit 353 for displaying a registered keyword (in the present embodiment, "security"), and a related information A related information display unit 354 and the like are provided. By using such a screen, it becomes possible for participants and the like to easily register keywords and view related information.

  As described above, according to the information presentation system 301 according to the present embodiment, in addition to the same effects as the information presentation system 1 according to the first embodiment, using the SNS system 302 for keyword registration and related information It becomes possible to do browsing easily.

Third Embodiment
FIG. 18 is a block diagram showing an example of a functional configuration of an information presentation system 401 according to the third embodiment. The information presentation system 401 according to the present embodiment extracts similar sentences whose meanings are similar from utterance contents and projection contents having different expressions, and a key phrase used when acquiring related information based on the similar sentences. It has the composition which creates. An information presentation system 401 according to the present embodiment includes an internal storage unit 411, a similar sentence extraction unit 412, and a key phrase creation unit 413.

  The internal storage unit 411 stores all text data (speech text data, image text data, and keyword text data) generated by the textification unit 105 within an arbitrary period. The internal storage unit 411 is realized, for example, using the processing function (storage 24 or the like) of the management server 11.

  The similar sentence extraction unit 412 is similar to the latest text data based on the latest text data acquired from the textification unit 105 at an arbitrary time within an arbitrary period and all the text data stored in the internal storage unit 411. Similar sentences are extracted from all text data. The similar sentence extraction unit 412 is realized, for example, using the processing capability of the management server 11 or the like.

  The key phrase creation unit 413 creates, based on the similar sentences extracted by the similar sentence extraction unit 412, a key phrase (a search keyword or the like) used when acquiring the related information from the external search unit 107. The key phrase creation unit 413 is realized using the processing capability of the management server 11 and the like.

  FIG. 19 is a block diagram showing an example of a functional configuration of the similar sentence extraction unit 412 according to the third embodiment. The similar sentence extraction unit 412 according to the present embodiment includes a data acquisition unit 421, a data storage unit 422, an implication recognition unit 423, a similar sentence storage unit 424, and a transmission unit 425.

  The data acquisition unit 421 acquires data that has been textified by the textification unit 105. The data acquisition unit 421 includes a latest text acquisition unit 430 that acquires latest text data from the textification unit 105, and a stored information acquisition unit 434 that acquires all text data from the internal storage unit 411. The latest text acquisition unit 430 acquires keyword text data from the keyword processing unit 143 of the text conversion unit 105, and the voice text acquisition unit 432 acquires voice text data from the audio processing unit 141 of the text conversion unit 105. And an image text acquisition unit 433 for acquiring image text data from the image processing unit 142 of the textification unit 105.

  The data storage unit 422 stores the data acquired by the data acquisition unit 421, and includes a determination source temporary storage unit 441 and an extraction target temporary storage unit 442. The determination source temporary storage unit 441 is the latest text data acquired by the data acquisition unit 421, that is, the keyword text data acquired by the keyword text acquisition unit 431 at an arbitrary time, the voice text acquired by the voice text acquisition unit 432 The data and the image text data acquired by the image text acquisition unit 433 are temporarily stored as a determination source. The extraction target temporary storage unit 442 temporarily stores all text data acquired by the stored information acquisition unit 434 in an arbitrary period as an extraction target.

  Note that, when voice text data and image text data are obtained at an arbitrary time, the data storage unit 422 extracts information having the same meaning as the voice text data from the image text data, and only the extracted information is extracted. It may be stored as a determination source. In this way, it is possible to treat only the information that is the subject as text data that is the determination source.

  The implication recognition unit 423 determines whether a plurality of sentences (including phrases) have the same meaning, and extracts similar sentences having the same meaning as the determination source (the latest text data) (all text data) Perform processing to extract from. The implication recognition unit 423 may be realized, for example, using a suitable system that performs implication recognition processing using synonym / synonym dictionary data or the like. The implication recognition unit 423 may be realized using an external service (for example, a system using the technology disclosed in Japanese Patent No. 5696555 or Japanese Patent Application Laid-Open No. 2016-045652), or the management server 11 or the like. It may be realized using the processing function of the database server 12.

  The similar sentence storage unit 424 stores the similar sentence extracted by the implication recognition unit 423 (a sentence having the same meaning as the sentence indicated by the latest text data stored as the determination source).

  The transmission unit 425 transmits the similar sentence stored in the similar sentence storage unit 424 to the key phrase generation unit 413.

  FIG. 20 is a sequence diagram showing an example of processing in the similar sentence extraction unit 412 according to the third embodiment. First, the latest text acquisition unit 430 of the data acquisition unit 421 acquires latest text data (S301), and the stored information acquisition unit 434 of the data acquisition unit 421 acquires all text data (S302). Thereafter, the data acquisition unit 421 transmits the acquired latest text data and all text data to the data storage unit 422 (S303).

  The determination source temporary storage unit 441 of the data storage unit 422 temporarily stores the received latest text data as a determination source (S304), and the extraction target temporary storage unit 442 of the data storage unit 422 processes all the received text data. It temporarily stores as an extraction target (S305). The data storage unit 422 transmits the stored immediate text data and all text data to the implication recognition unit 423 (S306).

  The implication recognition unit 423 extracts similar sentences having the same meaning as the received latest text data from all text data (S307), and transmits the extracted similar sentences to the similar sentence storage unit 424 (S308). The similar sentence storage unit 424 temporarily stores the received similar sentence (S309), and transmits the stored similar sentence to the transmission unit 425 (S310).

  The transmitting unit 425 transmits the received similar sentence to the key phrase creating unit 413 (S311). Then, the key phrase generation unit 413 generates a key phrase for generating a query for acquiring the related document from the external search unit 107 based on the received similar sentence (S312).

  FIG. 21 is a block diagram showing an example of a functional configuration of the key phrase creation unit 413 according to the third embodiment. The key phrase creation unit 413 according to the present embodiment includes a similar sentence acquisition unit 451, a clustering unit 452, a key phrase storage unit 453, and a transmission unit 454.

  The similar sentence acquisition unit 451 acquires the similar sentence transmitted from the similar sentence extraction unit 412.

  The clustering unit 452 performs clustering to generate a group consisting of one or more similar sentences having a common meaning from a plurality of similar sentences acquired by the similar sentence acquisition unit 451, and one or more having the common meanings. Perform processing to create a key phrase representing a similar sentence of The clustering unit 452 may be realized using an appropriate external service, or may be realized using the processing function of the management server 11 or the database server 12.

  The key phrase storage unit 453 stores the key phrase created by the clustering unit 452.

  The transmission unit 454 transmits the key phrase stored in the key phrase storage unit 453 to the information acquisition unit 106.

  FIG. 22 is a flowchart showing an example of processing in the key phrase creation unit 413 according to the third embodiment. First, the similar sentence acquisition unit 451 acquires all similar sentences from the similar sentence extraction unit 412 (S321). The clustering unit 452 performs clustering on all the acquired similar sentences, and creates a key phrase for each group of one or more similar sentences having a common meaning (S322). The key phrase storage unit 453 temporarily stores the created key phrase (S323). The transmission unit 454 transmits the key phrase stored in the key phrase storage unit 453 to the information acquisition unit 106 (S324).

  FIG. 23 is a block diagram showing an example of a functional configuration of the information acquisition unit 106 according to the third embodiment. The information acquisition unit 106 according to the present embodiment includes a key phrase acquisition unit 461, a search result acquisition unit 462, a search result storage unit 463, and a transmission unit 464.

  The key phrase acquisition unit 461 acquires the key phrase transmitted from the key phrase generation unit 413.

  The search result acquisition unit 462 generates a query using the key phrase acquired by the key phrase acquisition unit 461, and acquires a search result including the related document from the external search unit 107 using the query.

  The search result storage unit 463 stores the search result including the related document acquired by the search result acquisition unit 462.

  The transmitting unit 464 transmits the search result stored in the search result storage unit 463 to the output unit 108.

  FIG. 24 is a flowchart showing an example of processing in the information acquisition unit 106 according to the third embodiment. First, the key phrase acquisition unit 461 acquires a key phrase from the key phrase creation unit 413 (S331). The search result acquisition unit 462 acquires the related document (search result) from the external search unit 107 (using the query generated from the key phrase) using the acquired key phrase (S332). The search result storage unit 463 temporarily stores the acquired related document (S333), and transmits the stored related document to the output unit 108 (S334).

  As described above, according to the information presentation system 401 according to the present embodiment, similar sentences having a common meaning are extracted from text data acquired during a meeting, and a plurality of similar sentences having a common meaning are extracted. A key phrase representing is automatically created. Then, the related document acquired using the key phrase is presented to the meeting participant or the like. This makes it possible to simply and accurately present information that is semantically related even if there is a difference in expression.

Fourth Embodiment
FIG. 25 is a block diagram showing an example of a functional configuration of an information presentation system 501 according to the fourth embodiment. The information presentation system 501 according to the present embodiment has the same meaning as the key phrase among the information (related documents) acquired from the external search unit 107 using the key phrase created as in the third embodiment. And the similar information is extracted and output. An information presentation system 501 according to the present embodiment includes a similar information extraction unit 511.

  FIG. 26 is a block diagram showing an example of a functional configuration of the similar information extraction unit 511 according to the fourth embodiment. The similar information extraction unit 511 according to the present embodiment includes a data acquisition unit 521, a data storage unit 522, an implication recognition unit 523, a similar information storage unit 524, and a transmission unit 525.

  The data acquisition unit 521 includes a key phrase acquisition unit 531 for acquiring the key phrase transmitted from the key phrase generation unit 413, and a search result acquisition unit 532 for acquiring the search result transmitted from the information acquisition unit 106.

  The data storage unit 522 temporarily stores the key phrase acquired by the key phrase acquisition unit 531 as a determination source, a determination source temporary storage unit 541, and the search result acquired by the search result acquisition unit 532 (using the key phrase It includes an extraction target temporary storage unit 542 that temporarily stores information including the related document acquired from the external search unit 107 as an extraction target.

  Similar to the implication recognition unit 423 according to the second embodiment, the implication recognition unit 523 determines whether a plurality of sentences (including phrases) have a common meaning, and is common to the determination source (key phrase). The key phrase sentence having the meaning of is extracted from the extraction target (related document). The implication recognition unit 523 may be realized, for example, using a suitable system that performs implication recognition processing using synonym / synonym dictionary data or the like. The implication recognition unit 523 may be realized using an external service (for example, a system using the technology disclosed in Japanese Patent No. 5696555 or Japanese Patent Application Laid-Open No. 2016-045652), or the management server 11 or the like. It may be realized using the processing function of the database server 12.

  The similar information storage unit 524 stores the similar information extracted by the implication recognition unit 523.

  The transmission unit 525 outputs the similarity information stored in the similarity information storage unit 524 to the output unit 108.

  FIG. 27 is a sequence diagram showing a process example of the similar information extraction unit 511 according to the fourth embodiment. First, the key phrase acquisition unit 531 of the data acquisition unit 521 acquires a key phrase from the key phrase generation unit 413 (S401), and the search result acquisition unit 532 of the data acquisition unit 521 acquires a search result (information including related documents) (S402). Thereafter, the data acquisition unit 521 transmits the acquired key phrase and the search result to the data storage unit 522 (S403).

  The determination source temporary storage unit 541 of the data storage unit 522 temporarily stores the received key phrase as a determination source (S404), and the extraction target temporary storage unit 542 of the data storage unit 422 extracts the received search result. It temporarily stores as (S405). The data storage unit 522 transmits the stored key phrase and the search result to the implication recognition unit 523 (S406).

  The implication recognition unit 523 extracts, from the search result (related document), similar information having the same meaning as the received key phrase, and the title of the related document as the extraction source (S407), and the extracted similar information and title Are transmitted to the similar information storage unit 524 (S408). The similarity information storage unit 524 temporarily stores the received similarity information and title (S409), and transmits the stored similarity information and title to the transmission unit 525 (S410).

  The transmitting unit 525 transmits the received similar information and title to the output unit 108 (S411). Then, the output unit 108 outputs the received similar information and title to a predetermined display device (S412).

  As described above, according to the information presentation system 501 according to the present embodiment, among the related documents acquired from the external search unit 107 using the key phrase automatically generated as in the third embodiment, It becomes possible to extract similar information having a common meaning with the key phrase and present the similar information to the conference participants and the like.

Fifth Embodiment
FIG. 28 is a block diagram showing an example of a functional configuration of an information presentation system 601 according to the fifth embodiment. The information presentation system 601 according to the present embodiment is characterized by having a configuration for clustering and outputting related documents acquired from the external search unit 107 using the key phrase created as in the third embodiment. . An information presentation system 601 according to the present embodiment includes an acquired information clustering unit 611.

  FIG. 29 is a block diagram showing an example of a functional configuration of the acquired information clustering unit 611 according to the fifth embodiment. The acquired information clustering unit 611 according to the present embodiment includes a search result acquisition unit 621, a clustering unit 622, a clustering result storage unit 623, and a transmission unit 624.

  The search result acquisition unit 621 acquires information including the related document acquired from the external search unit 107 using the search result acquired from the information acquisition unit 106, that is, the key phrase generated by the key phrase generation unit 413. .

  The clustering unit 622 classifies one or more sentences included in the related document (related information) acquired by the search result acquisition unit 621 into a group consisting of one or more sentences having the same meaning as the key phrase, and for each group Create a representative sentence that represents one or more sentences. The clustering unit 622 may be realized using an appropriate external service, or may be realized using the processing function of the management server 11 or the database server 12.

  The clustering result storage unit 623 stores the clustering result including the representative sentence created by the clustering unit 622.

  The transmission unit 624 transmits the clustering result stored in the clustering result storage unit 623 to the output unit 108.

  FIG. 30 is a sequence diagram showing a process example of the acquired information clustering unit 611 according to the fifth embodiment. First, the search result acquisition unit 621 acquires a search result (information including related documents) from the information acquisition unit 106 (S501). Thereafter, the search result acquisition unit 621 transmits the acquired search to the clustering unit 622 (S502).

  The clustering unit 622 classifies one or more sentences included in the related documents included in the search result into a group consisting of one or more sentences having the same meaning as the key phrase, and represents one or more sentences in each group. A representative sentence is created (S 503), and the clustering result including the representative sentence is transmitted to the clustering result storage unit 623 (S 504).

  The clustering result storage unit 623 temporarily stores the received clustering result (S505), and transmits the stored clustering result to the transmitting unit 624 (S506).

  The transmitting unit 624 transmits the received clustering result to the output unit 108 (S507). Then, the output unit 108 outputs the received clustering result to a predetermined display device (S508).

  As described above, according to the information presentation system 601 according to the present embodiment, at least one of the related documents acquired from the external search unit 107 using the key phrase automatically generated as in the third embodiment is used. Are classified into a group consisting of one or more sentences having the same meaning as the key phrase, a representative sentence representing one or more sentences is prepared for each group, and the clustering result including the representative Can be presented to

(Modification)
Textification in the above-described embodiment can be realized by various methods. For example, regarding conversion of image data into text, text data directly from an electronic file for display and projection (data file for display and projection), not from an image displayed and projected on a display device (projector 14, display 15, etc.) You may get For example, upload a display / projection data file (or a plurality of files) in advance to the management server 11, and construct a system capable of accessing the display / projection data file via the management server 11. It is also good. In such a system, normally, a display image signal indicating display content (screen configuration) is transmitted from the management server 11 to the display device.

  With the above configuration, text data can be directly extracted from a display image signal or the like. Thereby, for example, even when the image is not displayed on a part of the plurality of display devices, the image text data can be properly acquired. Such a configuration is effective, for example, when materials for presentation can be viewed by some participants through the display device, but can be viewed only by printed matter by other participants. It becomes.

  In addition, when using a display device (for example, an electronic blackboard, IWB (Interactive Whiteboard), etc.) having a function of performing text conversion processing, the display device directly reads a display data file from a USB memory or the like to display an image. The text data may be obtained directly from the display data file (or not displayed). In such a case, the image text data can be acquired without the management server 11.

  Also, when the display / projection data file is stored in another storage device, a device (management server 11, display device, etc.) having access to the display / projection data file is Image text data can be acquired by acquiring a display / projection data file.

  In addition, in the case of using materials of a plurality of pages, it is preferable to perform processing of estimating which page the speech is about based on voice data of the speech indicating the progress status, the number of pages, and the like.

  While the embodiments of the present invention have been described above, the above embodiments are presented as examples, and are not intended to limit the scope of the invention. This novel embodiment can be implemented in various other forms, and various omissions, substitutions, changes, and combinations can be made without departing from the scope of the invention. While this embodiment and its modification are included in the range and subject matter of an invention, they are included in the invention indicated to the claim, and the equivalent range.

1,301,401 Information Presentation System 11 Management Server 12 Database Server 13 Microphone 14 Projector 15 Display 16 Client Terminal 19 Network 21 CPU
22 RAM
23 ROM
24 storage 25 input device 26 output device 27 communication I / F
101 voice data acquisition unit 102 image data acquisition unit 103, 312 keyword acquisition unit 104 input unit 105 text conversion unit 106 information acquisition unit 107, 313 external search unit 108 output unit 109 external output unit 121 external source 122 external source cooperation unit 123 crawl Control unit 124 Document collection unit 125 Index storage unit 126, 331 Document search unit 130 Index information 131 Input data reception unit 132 Input data processing unit 133 Text transmission unit 134 Recognition data storage unit 141 Speech processing unit 142 Image processing unit 143 Keyword processing unit 150 recognition data information 151 text reception unit 152 text selection unit 153 query generation unit 154 search call unit 155 search result transmission unit 201 setting screen 202 keyword input unit 203 database Selection unit 204 Search engine selection unit 211 Search result display screen 212 Related information display unit 213 Relevance display unit 302 SNS system 311 SNS communication unit 321 Keyword data acquisition unit 322 Normalization unit 332 External network cooperation unit 335 Internet 351 SNS screen 352 Keyword Input part 353 Keyword display part 354 Related information display part 412 Similar sentence extraction part 413 Key phrase creation part 511 Similar information extraction part 611 Acquisition information clustering part

Unexamined-Japanese-Patent No. 2017-111678

Claims (14)

An information presentation system for presenting related information related to information presented or acquired at any time within any period of time, comprising:
At least two of voice data of voice acquired within the arbitrary period, image data displayed on a predetermined display device or prepared for printing on a medium, and keyword data indicating a registered keyword An information acquisition unit that generates a query based on a common word common to a plurality of text data included in one data and acquires a search result by the query from a predetermined database;
An output unit that outputs the search result or a part of the search result to a predetermined output device;
An information presentation system comprising: The text data is text data in an electronic file for generating the image data, instead of the image data.
The information presentation system according to claim 1. When the information acquisition unit generates the query using voice text data based on the voice data and image text data based on the image data, the information recognition unit executes voice recognition processing when the voice data is converted into text. The query is generated so as to reduce the effects of false recognition and false recognition in image recognition processing performed when converting the image data into text.
The information presentation system according to claim 1 or 2. The information acquisition unit generates the query so that a search direction when searching the database conforms to the keyword when the query is generated using text data based on the keyword data. ,
The information presentation system according to any one of claims 1 to 3. A keyword acquisition unit that enables registration of the keyword using a predetermined terminal;
The information presentation system according to any one of claims 1 to 4, further comprising: The keyword acquisition unit acquires the keyword using an SNS system accessible by the terminal.
The information presentation system according to claim 5. The related information is transmitted to the terminal that has registered the keyword using the SNS system.
The information presentation system according to claim 6. An internal storage unit for storing the text data acquired during the arbitrary period;
A similar sentence extraction unit which extracts similar sentences having the same meaning as the latest text data which is the text data acquired at the arbitrary time, from the text data stored in the internal storage unit;
A key phrase creation unit that creates a key phrase based on the similar sentence;
And further
The information acquisition unit acquires the related information from the database using a query generated based on the key phrase.
The information presentation system according to any one of claims 1 to 7. A key phrase sentence extraction unit for extracting a key phrase sentence having a common meaning with the key phrase from the related information acquired using the query generated based on the key phrase;
And further
The output unit outputs the key phrase sentence to a predetermined output device.
The information presentation system according to claim 8. The one or more sentences included in the related information acquired using the query generated based on the key phrase are classified into a group consisting of one or more sentences having the same meaning as the key phrase, and the group Acquisition information clustering unit which creates representative sentences representing one or more sentences each time
And further
The output unit outputs a clustering result including the representative sentence to a predetermined output device.
The information presentation system according to claim 8. When similar text extraction unit acquires voice text data based on the voice data and image text data based on the image data at the arbitrary time, the similar text extraction unit makes a meaning in common with the voice text data from the picture text data. Extract information that you have,
The information presentation system according to any one of claims 8 to 10. What is claimed is: 1. A method for presenting information related to information presented or obtained at an arbitrary time within an arbitrary period, comprising:
At least two of voice data of voice acquired within the arbitrary period, image data displayed on a predetermined display device or prepared for printing on a medium, and keyword data indicating a registered keyword Generating a query based on a common word common to a plurality of text data included in one data;
Acquiring a search result by the query from a predetermined database;
Outputting the search result or a part of the search result to a predetermined output device;
Information presentation method including A computer performing processing for presenting related information related to information presented or acquired at any time within any period of time;
At least two of voice data of voice acquired within the arbitrary period, image data displayed on a predetermined display device or prepared for printing on a medium, and keyword data indicating a registered keyword A process of generating a query based on a common word common to a plurality of text data included in one data;
A process of acquiring a search result by the query from a predetermined database;
A process of outputting the search result or a part of the search result to a predetermined output device;
A program that runs   A recording medium storing the program according to claim 13.

Images