KR102283134B1 - METHOD AND APPARATUS FOR GENERATING READING DOCUMENT Of MINUTES - Google Patents

Abstract

A method and apparatus for generating a meeting minutes reading document are provided. The method for generating a meeting minutes reading document according to an embodiment of the present invention includes the steps of dividing draft meeting minutes data for a meeting to generate a plurality of speech unit data, the speech included in each of the plurality of speech unit data according to a preset condition Conducting a suitability assessment of the content, selecting non-conforming speech unit data according to the result of the conformity assessment, and reading the meeting minutes using the remaining speech unit data excluding the selected non-conforming speech unit data among the plurality of speech unit data generating a document.

Description

Method and device for generating meeting minutes reading documents

The present invention relates to a method for generating a meeting minutes reading document and an apparatus therefor. In more detail, by filtering the remarks that are not suitable for the agenda of the meeting from among the remarks included in the minutes, a method for creating a reading document for meeting minutes that can generate a meeting minutes reading document containing only the contents of remarks suitable for the agenda of the meeting, and a method thereof It's about the device.

The progress of meetings held in the National Assembly, regional councils, or basic local councils, and the contents of speeches, etc. are recorded by the secretary. In addition, the minutes recorded in this way are generally open to the public.

In the case of the conventional method for managing minutes, each of the minutes is stored as a unit. At this time, in order not to distort the speaker's intention to speak, it is managed without any changes to the oral style of the minutes.

However, in the case of the conventional meeting minutes management method, since it includes all remarks that are out of the agenda of the meeting, remarks that do not fit the gist of the question, or sudden remarks that do not fit the situation, users who read the minutes There is a problem in that it is inconvenient to accurately grasp the contents of the meeting based on the remarks on the agenda of the meeting.

In addition, in the case of the conventional meeting minutes management method, it provides only information on who made the remarks with respect to a specific remark or what type of remarks the specific remarks are, and intuitively checks whether the remarks are related to the agenda. Since it is difficult to grasp the utterance, there is a problem that users have to read and confirm the contents of the remarks to the end.

Korean Patent Publication No. 2014-0077514

The technical problem to be solved by the present invention is to generate a plurality of speech unit data by dividing the draft meeting minutes data for a meeting, and by selecting inappropriate speech unit data through suitability evaluation for each of the plurality of speech data, the agenda of the meeting It is to provide a method and device for generating meeting minutes reading documents that can filter out remarks that are not suitable for

Another technical problem to be solved by the present invention is a method of generating a meeting minutes reading document that allows users to intuitively check whether or not it is suitable for a topic by displaying the result of the suitability evaluation for each remark in the meeting minutes reading document and its to provide the device.

The technical problems of the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the following description.

In order to solve the above technical problem, the method of generating a meeting minutes reading document according to an embodiment of the present invention, in a method performed by a computing device, dividing the draft meeting minutes data for the meeting to generate a plurality of speech unit data step, performing a suitability evaluation on the remarks included in each of the plurality of speech unit data according to a preset condition, and selecting inappropriate speech unit data according to a result of the relevance evaluation, and among the plurality of speech unit data The method may include generating a meeting minutes reading document by using the remaining speech unit data except for the selected non-conforming speech unit data.

In some embodiments, the selecting of the inappropriate utterance unit data according to the result of the suitability evaluation includes extracting a keyword from each of the plurality of utterance unit data and determining the similarity between the keywords by comparing the extracted keywords and selecting speech unit data having the determined similarity equal to or less than a preset reference value as unsuitable speech unit data.

In some embodiments, the plurality of speech unit data includes first speech unit data including remarks of the first speaker and second speech unit data including remarks of the second speaker, and The step of selecting inappropriate speech unit data according to the result may include: when the speech content included in the first speech unit data includes information on the second speaker and a keyword for selecting the inappropriate speech unit data, the second The method may include selecting 2 speech unit data as the inappropriate speech unit data.

In some embodiments, the selecting of the inappropriate speech unit data according to the result of the suitability evaluation includes determining whether the microphones of the first speaker and the second speaker are activated using log data for the microphone used for the speech in the meeting. and when it is determined that the microphone of the second speaker is activated while the microphone of the first speaker is activated, the speech unit data including the contents of speech input through the microphone of the second speaker is said It may include the step of selecting the inappropriate speech unit data.

In some embodiments, the method of generating the meeting minutes reading document further comprises the step of obtaining image data for a plurality of speakers participating in the meeting from a photographing device, and selecting inappropriate speech unit data according to the result of the suitability evaluation The step is to analyze the expression change amount and behavior pattern of other speakers at the point in time when a specific speaker speaks by using the image data, and use the analysis result of the expression change amount and the behavior pattern to determine the content of the speech of the specific speaker It may include the step of evaluating suitability for the included speech unit data.

In some embodiments, the selecting of the inappropriate speech unit data according to the result of the suitability evaluation includes: determining whether a plurality of speakers participating in the conference are subject to speech by using the progress scenario information for the conference; and selecting, as the inappropriate speech unit data, speech unit data including speech contents of the speaker determined not to be the speech target among the plurality of speech unit data.

In some embodiments, the generating of the meeting minutes reading document includes only the remaining statement unit data except for the inappropriate statement unit data among the first meeting minutes reading document including all of the plurality of statement unit data and the plurality of statement unit data. When receiving a request for a reading of the meeting minutes reading document and generating a second meeting minutes reading document comprising: one of the first meeting minutes reading document or the second meeting minutes reading document according to the reading request It may optionally include the step of providing.

In some embodiments, the generating of the meeting minutes reading document may include, when a reading request for the meeting minutes reading document is received, remarks of the plurality of speech unit data and suitability evaluation results for each of the plurality of speech unit data may include the step of outputting together.

In order to solve the above technical problem, an apparatus for generating meeting minutes reading documents according to another embodiment of the present invention includes a communication interface for receiving draft meeting minutes data for a meeting, storage for storing software for generating and providing meeting minutes reading documents, A memory into which a plurality of instructions are loaded according to the execution of the software and a processor for executing the plurality of instructions, wherein the plurality of instructions divide the draft meeting minutes data to generate a plurality of speech unit data Instruction, an instruction for performing a suitability evaluation of the speech content included in each of the plurality of speech unit data according to a preset condition, and selecting unsuitable speech unit data according to a result of the suitability evaluation, and among the plurality of speech unit data It may include an instruction for generating a meeting minutes reading document by using the remaining speech unit data except for the selected non-conforming speech unit data.

1 is a diagram illustrating a system for generating and providing a meeting minutes reading document according to an embodiment of the present invention.
2 is a flowchart illustrating a method of generating a meeting minutes reading document according to another embodiment of the present invention.
3 is a diagram exemplarily illustrating a form in which a plurality of speech unit data is generated from draft meeting minutes data according to some embodiments.
4 is a flowchart for explaining a method of selecting inappropriate speech unit data through a similarity comparison between keywords, according to an embodiment.
FIG. 5 is a diagram illustrating a process of selecting inappropriate speech unit data according to the method of selecting inappropriate speech unit data through a similarity comparison between keywords described with reference to FIG. 4 .
6 is a flowchart illustrating a method of selecting inappropriate speech unit data using microphone activation information according to another embodiment.
FIG. 7 is a diagram illustrating a process of selecting inappropriate speech unit data according to a method of selecting inappropriate speech unit data using the microphone activation information described with reference to FIG. 6 .
8 is a flowchart for explaining a method of selecting inappropriate speech unit data according to the existence of a keyword, according to another embodiment.
9 is a diagram illustrating a process of selecting inappropriate speech unit data according to the method of selecting inappropriate speech unit data according to the existence of keywords described with reference to FIG. 8 .
10 is a flowchart illustrating a method of selecting inappropriate speech unit data according to a speaker's facial expression and behavior according to another embodiment.
11 is a diagram illustrating a process of selecting inappropriate speech unit data according to the method of selecting inappropriate speech unit data according to the expression and behavior of the speaker described with reference to FIG. 10 .
12 to 14 are diagrams exemplarily illustrating a form in which the meeting minutes reading document generated through the meeting minutes reading document generating method described with reference to FIG. 2 is output to the meeting minutes reading apparatus.
15 is a hardware configuration diagram of an apparatus for generating meeting minutes reading documents according to another embodiment of the present invention.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. Advantages and features of the present invention, and a method for achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments published below, but may be implemented in various different forms, only these embodiments make the publication of the present invention complete, and common knowledge in the technical field to which the present invention pertains It is provided to fully inform the possessor of the scope of the invention, and the present invention is only defined by the scope of the claims. Like reference numerals refer to like elements throughout.

Unless otherwise defined, all terms (including technical and scientific terms) used herein may be used with the meaning commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, terms defined in a commonly used dictionary are not to be interpreted ideally or excessively unless clearly defined in particular. The terminology used herein is for the purpose of describing the embodiments and is not intended to limit the present invention. As used herein, the singular also includes the plural unless specifically stated otherwise in the phrase.

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

1 is a diagram illustrating a system for generating and providing a meeting minutes reading document according to an embodiment of the present invention.

Referring to FIG. 1 , a system for generating and providing meeting minutes reading documents according to an embodiment of the present invention includes a meeting minutes reading document generating device 100 , a meeting recording device 200 , a log management server 300 , and a plurality of microphones 400 . -1 to 400-n) and a meeting minutes reading device 500 may be included.

Here, the system for generating and providing a meeting minutes reading document shown in FIG. 1 is according to an embodiment, and its components are not limited to the embodiment shown in FIG. 1, and may be added, changed, or deleted as necessary. take note of

In addition, the system for generating and providing meeting minutes reading document shown in FIG. 1 represents functional elements in which each component is functionally separated, and any one or more components may be implemented by being integrated with each other in an actual physical environment.

First, the meeting recording device 200 may generate data on the meeting minutes for the meeting and transmit it to the meeting minutes reading document generating device 100 . More specifically, the meeting recording device 200 may generate draft meeting minutes data and provide it to the meeting minutes reading document generating device 100 .

Here, a conference is a procedure in which two or more participants exchange opinions and information on one or more proposed agendas and make decisions. The meeting according to some embodiments of the present invention may include, but is not limited to, a plenary session, a legislative and judicial committee, the relevant committee, a special committee, a standing committee, administrative affairs audit and investigation, state audit and investigation, and the like. In addition, the participants of the meeting according to an embodiment of the present invention may include, but is not limited to, a chairperson or chairperson, a member of the council or a member of the committee.

In addition, the draft meeting minutes are documents in which the progress of the meeting, remarks of the meeting participants or meeting results, etc. are recorded, and the draft meeting minutes data means character string data, voice data, and video data including such information. However, the present invention is not limited thereto.

Next, the log management server 300 may generate log data generated according to the progress of the meeting and transmit it to the meeting minutes management server 300 .

Here, the log data is string data in which a log of an event generated in the course of a meeting is recorded. For example, the log data may be string data in which information about the time when the speakers' microphones 400-1, 400-2, and 400-n are activated may be recorded, but is not limited thereto.

The meeting minutes reading document generating device 100 may generate a plurality of speech unit data by dividing the draft meeting minutes data provided from the meeting recording device 200 using the log data provided from the log management server 300 .

In addition, the meeting minutes reading document generating apparatus 100 may perform a suitability evaluation for each of a plurality of speech unit data to determine whether it is suitable for the agenda of the meeting, and through this process, by selecting inappropriate speech unit data, It is possible to filter speech unit data regarding remarks that do not fit the agenda.

Next, the meeting minutes reading apparatus 500 may receive and output the meeting minutes reading document generated from the meeting minutes reading document generating apparatus 100 . For example, the meeting minutes reading apparatus 500 according to an embodiment of the present invention includes a desktop, a workstation, a server, a laptop, a tablet, and a smart phone. ) or a phablet, but is not limited thereto, and is not limited thereto, and a portable multimedia player (PMP), a personal digital assistant (PDA), or an e-book reader (E-Book Reader). ), etc., may be a type of device.

In one embodiment, the meeting minutes reading document is a document generated by the meeting minutes reading document generating device 100 in response to the request of the meeting minutes reading device 400, and includes the progress of the meeting, the content of the speech, the time of speech and the meeting results. can

In addition, the meeting minutes reading document may be a web document in a format such as HTML (Hyper Text Markup Language) or XML (eXtensible Markup Language), but is not limited thereto, and may be a PDF (Portable Document Format) document. Hereinafter, with reference to FIGS. 2 to 13 , a method for generating the meeting minutes reading document generating apparatus 100 will be described in detail.

2 is a flowchart illustrating a method of generating a meeting minutes reading document according to another embodiment of the present invention. The method for generating a meeting minutes reading document according to another embodiment of the present invention may be performed by a computing device. For example, the computing device may be the meeting minutes reading document generating device 100 of FIG. 1 . Hereinafter, when the description of the subject of the operation is omitted in the description related to the present embodiment, it may be understood that the subject is the apparatus 100 for generating the meeting minutes reading document of FIG. 1 .

Referring to Figure 2, first, the draft meeting minutes data is obtained (S110). For example, the meeting minutes reading document generating apparatus 100 may receive text, voice, or video-based draft meeting minutes data generated from the meeting recording apparatus 200 through a network. However, the present invention is not limited thereto.

Next, by dividing the draft meeting minutes data, a plurality of speech unit data is generated (S120). More specifically, the meeting minutes reading document generating apparatus 100 may generate a plurality of speech unit data by dividing the draft meeting minutes data according to a preset criterion. For example, the meeting minutes reading document generating apparatus 100 may identify the speaker for the speech content by using the microphone activation time of each of the plurality of speakers included in the log data, and use the identified speaker as the mood of the draft meeting minutes data. A plurality of speech unit data may be generated by dividing the speech content by the speaker. However, the present invention is not limited thereto, and the apparatus 100 for generating meeting minutes reading documents divides and remarks by the speaker in the draft meeting minutes data, such as a division method according to a page progress signal of a prompter and a division method according to a user input signal, etc. Any method capable of generating unit data is applicable.

As shown in FIG. 3, in the case of the conventional meeting minutes, the speaker's position (1), the speaker's name (2), the speaker's name (2) and the speaker's name (2) and the content of the speech (3) for distinguishing the separator (4) and the content of the speech (3) is described in succession. And, the conventional speaker identification method distinguishes the speaker's name (2) and the remarks (3) based on the separator (4) included in the conventional meeting minutes data.

However, the conventional speaker identification method cannot correctly identify the speaker's name (2) and the remarks (3) when the speaker's title (1) or the speaker's name (2) includes the separator (4). . For example, in the conventional speaker identification method, when the delimiter 4 is a blank character, the speaker's title (1) is "local traffic director" and the speaker's name (2) is "XXX", despite the fact that the speaker's name (2) is "XXX" The position (1) is "local", the speaker's name (2) is "Director of Transportation", and the content of the speech (3) is "XXX related laws … are assumed first".

However, the meeting minutes reading document apparatus 100 according to an embodiment of the present invention uses the speaker information 5 using which microphone is activated at the time the corresponding remark is spoken, and which speaker the activated microphone is assigned to. ) and the content of the speech (3), there is an advantage in that the problems of the conventional speaker identification method as described above can be solved.

Next, suitability evaluation is performed on the remarks included in each of the plurality of speech unit data generated in step S120 (S130), and inappropriate speech unit data among the plurality of speech unit data is selected according to the suitability evaluation result ( S140).

Here, the conformity evaluation refers to evaluating and quantifying how appropriate the content of a specific speaker's remarks to the agenda of the meeting through the conformity evaluation algorithm. Hereinafter, various embodiments of a method for the apparatus 100 for generating a meeting minutes reading document to select inappropriate speech unit data through a suitability evaluation will be described with reference to FIGS. 3 to 11 .

4 is a flowchart for explaining a method of selecting inappropriate speech unit data through a similarity comparison between keywords, according to an embodiment.

Referring to FIG. 4 , according to an embodiment, the apparatus 100 for generating meeting minutes reading documents may compare keywords extracted from each of a plurality of speech unit data to select inappropriate speech unit data.

First, a keyword is extracted from each of the plurality of speech unit data generated in step S120 ( S210 ).

Here, the keyword is a main word included in the remarks. For example, the keyword may include, but is not limited to, a key word, a key word, a frequent word, a meeting name, a session, an order, or an agenda name.

Next, the degree of similarity between keywords extracted from each of the plurality of speech unit data in step S210 is calculated (S220). For example, as shown in FIG. 5 , the apparatus 100 for generating meeting minutes reading documents includes keywords of “A, B, C, D, E” ( 30b) can be extracted, the keyword 30c of “A, F, G, HI” can be extracted from the speech unit data 20c including the remarks of the third speaker, and the remarks of the fourth speaker A keyword 30d of “B, C, D, E, P” may be extracted from the included speech unit data 20d. Thereafter, the meeting minutes reading document generating apparatus 100 includes a set of keywords "A, B, C, D, E, G, K, L, M" and a first speaker and a second speaker preset according to the agenda of the meeting, that is, according to the topic. and keywords extracted from the speech unit data 20b, 20c, and 20d including the speech content of the third speaker, respectively, and a similarity determination result 50 may be calculated through the comparison result. The similarity determination result 50 shown in FIG. 5 is shown in the form of a percentage (%), but the present invention is not limited thereto.

Keyword extraction method Regarding the method of determining the similarity between keywords, "Improved automatic keyword extraction given more linguistic knowledge", Anette Hulth, 2003, "Study on single document keyword extraction using term clustering", Seunghee Han, 2010 and "Clustering technique" Various documents such as "Expansion of User Query according to Keyword Similarity Ranking Algorithm Using However, in order to compare the similarity determination result with the reference value, it is preferable that an algorithm of a method for obtaining a numerical similarity determination result is used.

Next, the similarity between keywords calculated in step S220 is compared with a preset reference value (S230).

In step S230, utterance unit data whose similarity between keywords is less than or equal to a reference value is selected, and utterance unit data whose similarity is less than or equal to the reference value is selected as unsuitable statement unit data (S240), and utterance unit data whose similarity exceeds the reference value is suitable It is selected as speech unit data (S250). For example, when the preset reference value is 70%, the apparatus 100 for generating meeting minutes reading documents includes the remarks of the third speaker having a similarity of 70% or less according to the similarity determination result calculated in step S220. (20c) can be selected as non-conforming speech unit data. In addition, the apparatus 100 for generating meeting minutes reading documents appropriately remarks the speech unit data 20b including the remarks of the first speaker having a similarity of 70% or more and the speech unit data 20d including the remarks of the fourth speaker. It can be selected as unit data. However, the present invention is not limited thereto, and the apparatus 100 for generating meeting minutes reading documents may select only inappropriate speech unit data through similarity comparison, and may select all remaining unselected speech unit data as suitable speech unit data.

Through this, there is an advantage in that it is possible to reduce the time required for the suitability evaluation performed for each of the plurality of speech unit data by reducing the unnecessary process (the process of selecting the appropriate speech unit data). Next, a method of selecting inappropriate speech unit data according to another exemplary embodiment will be described with reference to FIG. 6 .

6 is a flowchart illustrating a method of selecting inappropriate speech unit data using microphone activation information according to another embodiment.

Referring to FIG. 6 , in another embodiment, the apparatus 100 for generating meeting minutes reading documents may select inappropriate speech unit data using microphone activation information.

First, after a plurality of speech unit data is generated through step S120, a check operation for checking whether the microphone of the first speaker is activated is started (S310).

Next, according to the start of the microphone activation check operation in step S310, it is checked whether the microphone of the first speaker is activated by using the microphone activation time information included in the log data (S320), and through the step S320, the first speaker's When it is confirmed that the microphone is activated, a check operation for checking whether the microphone of the second speaker is activated is started ( S330 ).

Next, according to the start of the microphone activation check operation of step S330, it is checked whether the second speaker's microphone is activated using the microphone activation time information included in the log data (S340), and the second speaker's microphone is activated through the step S340. When it is confirmed that the microphone is activated, the second speech unit data including speech content input through the microphone of the second speaker is selected as inappropriate speech unit data (S350).

That is, as shown in FIG. 7 , in the meeting minutes reading document generating apparatus 100, the second speaker is in a state in which the microphone of the first speaker is activated, that is, in a state in which the first speaker is speaking on the agenda of the meeting. When the microphone is activated and remarks are input, the second speech unit data 20b including remarks of the second speaker may be selected as inappropriate speech unit data.

On the other hand, when it is confirmed that the microphone of the second speaker is not activated through step S340, the first speech unit data including the speech input through the microphone of the first speaker is selected as the appropriate speech unit data (S360). Next, a method of selecting inappropriate speech unit data according to another embodiment will be described with reference to FIG. 8 .

8 is a flowchart for explaining a method of selecting inappropriate speech unit data according to the existence of a keyword, according to another embodiment.

Referring to FIG. 8 , in another embodiment, the apparatus 100 for generating meeting minutes reading documents includes the name of the second speaker and a keyword for selecting inappropriate speech unit data in the remarks of the first speaker, the second speaker It is possible to select the speech unit data including the remarks of the inappropriate speech unit data.

First, after a plurality of speech unit data is generated through step S120, a keyword is extracted from the first speech unit data of the first speaker (S410). Here, as for the keyword extraction method, the same method as the method for extracting the keyword in the keyword extraction step S210 shown in FIG. 4 may be applied.

Next, it is determined whether a keyword for selecting information of the second speaker and inappropriate speech unit data is included among the keywords extracted in step S410 ( S420 ). For example, as shown in FIG. 9 , in the first speech unit data 20c including the remarks of the first speaker, the name of the second speaker among the information of the second speaker and "unnecessary", "restraint", " When the keyword 30c for selecting unsuitable speech unit data, such as "don't," is included, the meeting minutes reading document generating apparatus 100 returns the second speech unit data 20b including the remarks of the second speaker inappropriate. It can be selected by speech unit data. Here, as keywords for selecting inappropriate speech unit data, only "unnecessary", "restraint" and "abstain" are described, but the present invention is not limited thereto, and an expression method used by a speaker who plays a role of mediating a plurality of speakers Accordingly, various keywords may be registered in advance. Next, a method of selecting inappropriate speech unit data according to another embodiment will be described with reference to FIG. 10 .

10 is a flowchart illustrating a method of selecting inappropriate speech unit data according to a speaker's facial expression and behavior according to another embodiment.

Referring to FIG. 10 , in another embodiment, the apparatus 100 for generating meeting minutes reading documents analyzes expression changes and behavior patterns of a plurality of speakers participating in the meeting, and according to the analysis result, remarks including the contents of the current speaker's remarks Appropriateness of unit data can be evaluated.

First, after a plurality of speech unit data is generated through step S120, image data for a plurality of speakers is obtained (S510). For example, as shown in FIG. 11 , the meeting minutes reading document generating device 100 is connected to a separately provided photographing device 50 through a network and photographing the faces and actions of a plurality of speakers through the photographing device 50 . image data can be obtained. However, the present invention is not limited thereto. In addition, although one photographing device 50 is illustrated in the form of photographing a plurality of speakers in FIG. 11 , the present invention is not limited thereto, and in order to perform more accurate image data analysis, a photographing device 50 is provided for each speaker can be provided.

Next, by analyzing the image data for each speaker captured in step S510, the amount of change in expression and behavior pattern for each speaker are analyzed (S520).

Here, a method of analyzing the expression change amount and behavior pattern is described in "Recognizing action units for facial expression analysis", Y.-I. Various literatures such as Tian et al., 2001 and "Design and construction of a three-dimensional gesture database for human behavior analysis", Myung-Chul Noh et al., 5, 2005 can be referred to. However, in order to compare the amount of change of expression with a reference value, it is preferable to use an algorithm in which the amount of change of expression can be obtained as a numerical value.

Next, it is determined whether an abnormality occurs in the expression change amount and behavior pattern of the speaker according to the analysis result of the expression change amount and behavior pattern analyzed in step S520 ( S530 ). For example, as shown in FIG. 11 , the apparatus 100 for generating meeting minutes reading documents provides a second speaker 40-2 and a third speaker 40-3 at a time point when the first speaker 40-1 speaks. ), by analyzing the image data of the fourth speaker 40-4 and the fifth speaker 40-5, the expression change amount and behavior pattern of each speaker can be analyzed. At this time, the expression changes of the second speaker 40-2, the third speaker 40-3, the fourth speaker 40-4, and the fifth speaker 40-5 are 7, 5, 9, and 6, respectively. , when the reference value is 5, the apparatus 100 for generating meeting minutes reading documents is the second speaker 40-2, the third speaker 40-3, the fourth speaker 40-4, and the fifth speaker 40- 5), it can be judged that an abnormality has occurred by judging that the amount of change in expression exceeds the reference value. In addition, the meeting minutes reading document generating apparatus 100 records the behavior patterns of the second speaker 40-2, the third speaker 40-3, the fourth speaker 40-4, and the fifth speaker 40-5. Analyzes, compares the behavior pattern with a preset behavior pattern, When the behavior pattern matches the preset behavior pattern, it may be determined that an abnormality has occurred.

Here, the preset behavior pattern refers to a behavior pattern that speakers can see when a statement is made that does not fit the agenda of the meeting, and may be information registered in advance before analyzing the image data.

Next, when it is determined that an abnormality has occurred in the expression change amount and behavior pattern of the speaker through step S530, speech unit data including the remarks made at the time when the abnormality occurred, that is, including the remarks of the first speaker The first speech unit data is selected as inappropriate speech unit data (S540).

On the other hand, if it is determined that there is no abnormality in the expression change amount and behavior pattern of the speaker through step S530, the first speech unit data including the speech contents of the first speaker is selected as the appropriate speech unit data (S550).

Returning to FIG. 2 again, when inappropriate speech unit data is selected from among the plurality of speech unit data through step S140, a meeting minutes reading document is generated using the remaining speech unit data excluding the unsuitable speech unit data selected in step S140 ( S150).

In an embodiment, the apparatus 100 for generating a meeting minutes reading document includes a first meeting minutes reading document including all of a plurality of statement unit data and a second statement unit data including only the remaining statement unit data except for the inappropriate statement unit data among the plurality of statement unit data A meeting minutes reading document can be created, and when a reading request for the meeting minutes reading document is received through the meeting minutes reading device 500, one of the first meeting minutes reading document or the second meeting minutes reading document according to the reading request. can be optionally provided. For example, when a reading request for the first meeting minutes reading document 60a is received from the meeting minutes reading device 100, the meeting minutes reading document generating device 100 may generate a plurality of speech unit data 20a as shown in FIG. , 20b, 20c) may provide a first meeting minutes reading document (60a) including all. In addition, when a reading request for the second meeting minutes reading document 60b is received from the meeting minutes reading device 100, the meeting minutes reading document generating device 100 provides a plurality of speech unit data 20a, It is possible to provide the second meeting minutes reading document 60b including only the remaining speech unit data 20a and 20b except for the unsuitable speech unit data 20c among 20b and 20c.

In an embodiment, the apparatus 100 for generating meeting minutes reading documents includes a plurality of speech unit data 20a, 20b, 20c including remarks and information 40 of a speaker who has made remarks included in each remark unit data. ) can be matched and printed together. However, the present invention is not limited thereto.

Through this, there is an advantage that a user who reads the meeting minutes reading document can not only check the contents of the speaker's remarks, but also easily obtain information about the speaker of the corresponding remarks.

In one embodiment, the meeting minutes reading document generating apparatus 100 outputs all of the plurality of speech unit data as shown in FIG. 14 , but the speech unit data selected as the inappropriate speech unit data is hidden in the form of a display box 63 . A third meeting minutes reading document to be output can be provided, and when a user input is input to the hidden display box 63 through the meeting minutes reading device 500, as shown in FIG. 13, inappropriate speech unit data can be output. there is.

Through this, there is an advantage that the user can selectively receive inappropriate speech unit data through a simple input button operation, without the need to transmit a separate reading request in order to provide a different type of meeting minutes reading document.

In an embodiment, the apparatus 100 for generating meeting minutes reading documents when receiving a reading request for meeting minutes reading documents 60a and 60b as shown in FIGS. 12 and 13 , a plurality of speech unit data 20a, 20b , 20c) and the suitability evaluation result 62 for each of the plurality of speech unit data 20a, 20b, and 20c may be output together.

Through this, there is an advantage that it is easy for a user who reads the meeting minutes reading document to intuitively determine how appropriate the contents of the remarks are for the agenda of the meeting.

The methods according to the embodiments of the present invention described so far may be performed by executing a computer program embodied as computer readable code. The computer program may be transmitted from the first computing device to the second computing device through a network such as the Internet and installed in the second computing device, thereby being used in the second computing device. The first computing device and the second computing device include all of a server device, a physical server belonging to a server pool for cloud services, and a stationary computing device such as a desktop PC.

The computer program may be stored in a recording medium such as a DVD-ROM or a flash memory device. Hereinafter, with reference to FIG. 15 , a hardware configuration of the apparatus 100 for generating meeting minutes reading documents according to another embodiment of the present invention will be described.

15 is a hardware configuration diagram of an apparatus for generating meeting minutes reading documents according to another embodiment of the present invention.

15 , the apparatus 100 for generating meeting minutes reading documents according to another embodiment of the present invention includes at least one processor 110 , a communication interface 120 , and a computer program 141 executed by the processor 110 . It may include a memory 130 for loading (Load), a storage 140 and a bus 150 for storing a computer program and various data. Here, only the components related to the embodiment of the present invention are shown in FIG. 15 . Accordingly, those skilled in the art to which the present invention pertains can see that other general-purpose components other than the components shown in FIG. 15 may be further included.

The processor 110 controls the overall operation of each component of the meeting minutes reading document generating apparatus 100 . The processor 110 includes a central processing unit (CPU), a micro processor unit (MPU), a micro controller unit (MCU), a graphic processing unit (GPU), or any type of processor well known in the art. can be In addition, the processor 110 may perform an operation on at least one application or program for executing the method according to the embodiments of the present invention. The meeting minutes reading document generating apparatus 100 may include one or more processors.

The communication interface 120 supports wired/wireless Internet communication of the meeting minutes reading document generating apparatus 100 . In addition, the communication interface 120 may support various communication methods other than Internet communication. To this end, the communication interface 120 may be configured to include a communication module well known in the art. In some embodiments, the communication interface 120 may be omitted.

The memory 130 stores various data, commands and/or information. The memory 130 may load the computer program 141 from the storage 140 to execute methods/operations according to various embodiments of the present disclosure. When the computer program 141 is loaded into the memory 130 , the processor 110 may perform the method/operation by executing one or more instructions constituting the computer program 141 . The memory 130 may be implemented as a volatile memory such as RAM, but the technical scope of the present invention is not limited thereto.

The storage 140 may non-temporarily store the computer program 141 . When the meeting minutes reading document generating process is performed through the meeting minutes reading document generating apparatus 100 , the storage 140 may store various data necessary for the meeting minutes reading document generating process. For example, log data and image data may be stored in order to perform a suitability evaluation of a plurality of speech unit data divided from the draft meeting minutes data, the draft meeting minutes data, and the speaker's remarks. To this end, the speech unit database 142 and It may include a video conference minutes database (143).

The storage 140 is a non-volatile memory such as a read only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a flash memory, a hard disk, a removable disk, or well in the art to which the present invention pertains. It may be configured to include any known computer-readable recording medium.

The computer program 141 may include one or more instructions that, when loaded into the memory 130 , cause the processor 110 to perform methods/operations according to various embodiments of the present invention. That is, the processor 110 may perform the method/operation according to various embodiments of the present invention by executing the one or more instructions.

In one embodiment, the computer program 141 divides the draft meeting minutes data to generate a plurality of speech unit data, and performs a suitability evaluation for the speech content included in each of the plurality of speech unit data according to a preset condition and , an instruction for selecting non-conforming speech unit data according to the result of conformity evaluation, and an instruction for generating a meeting minutes reading document using the remaining speech unit data excluding the selected non-conforming speech unit data among a plurality of speech unit data.

The bus 150 provides a communication function between components of the apparatus 100 for generating meeting minutes reading documents. The bus 150 may be implemented as various types of buses, such as an address bus, a data bus, and a control bus.

So far, various embodiments of the present invention and effects according to the embodiments have been described with reference to FIGS. 1 to 15 . Effects according to the technical spirit of the present invention are not limited to the above-mentioned effects, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

Although embodiments of the present invention have been described with reference to the accompanying drawings, those of ordinary skill in the art to which the present invention pertains can realize that the present invention can be implemented in other specific forms without changing the technical spirit or essential features. can understand Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

Claims (9)

A method performed by a computing device, comprising:
generating a plurality of speech unit data by dividing the draft minutes data for the conference;
performing a suitability evaluation on the utterances included in each of the plurality of utterance unit data according to a preset condition, and selecting inappropriate utterance unit data according to a result of the suitability evaluation; and
and generating a meeting minutes reading document using the remaining speech unit data excluding the selected inappropriate speech unit data among the plurality of speech unit data,
The step of selecting inappropriate speech unit data according to the result of the suitability evaluation includes:
extracting a keyword from each of the plurality of utterance unit data and determining a similarity between the keywords by comparing the extracted keywords; and
selecting, as the unsuitable speech unit data, the speech unit data having the determined similarity equal to or less than a preset reference value;
How to create a meeting minutes viewing document. delete According to claim 1,
The plurality of speech unit data is
It includes first speech unit data including remarks of the first speaker and second speech unit data including remarks of the second speaker,
The step of selecting inappropriate speech unit data according to the result of the suitability evaluation includes:
When the speech content included in the first speech unit data includes information on the second speaker and a keyword for selecting the inappropriate speech unit data, selecting the second speech unit data as the inappropriate speech unit data comprising steps,
How to create a meeting minutes viewing document. According to claim 1,
The step of selecting inappropriate speech unit data according to the result of the suitability evaluation includes:
determining whether the microphones of the first speaker and the second speaker are activated by using the log data of the microphone used for speaking in the conference; and
When it is determined that the microphone of the second speaker is activated while the microphone of the first speaker is activated, speech unit data including speech contents input through the microphone of the second speaker is converted into the inappropriate speech unit data comprising the step of selecting
How to create a meeting minutes viewing document. According to claim 1,
The method of generating the meeting minutes reading document is,
Further comprising the step of obtaining image data for a plurality of speakers participating in the conference from a photographing device,
The step of selecting inappropriate speech unit data according to the result of the suitability evaluation includes:
Using the image data, the expression change amount and behavior pattern of other speakers are analyzed at the point in time when the specific speaker speaks, and the speech including the speech content of the specific speaker using the analysis result of the expression change amount and the behavior pattern Comprising the step of evaluating suitability for unit data,
How to create a meeting minutes viewing document. According to claim 1,
The step of selecting inappropriate speech unit data according to the result of the suitability evaluation includes:
determining whether to speak with respect to a plurality of speakers participating in the meeting by using the progress scenario information for the meeting; and
selecting, as the inappropriate speech unit data, speech unit data including speech content of a speaker determined not to be the speech target among the plurality of speech unit data,
How to create a meeting minutes viewing document. According to claim 1,
The step of generating the meeting minutes reading document,
generating a first meeting minutes reading document including all of the plurality of speech unit data and a second meeting minutes reading document including only the remaining speech unit data excluding the inappropriate speech unit data among the plurality of speech unit data; and
Comprising the step of selectively providing one of the first meeting minutes reading document or the second meeting minutes reading document according to the reading request when receiving a reading request for the meeting minutes reading document,
How to create a meeting minutes viewing document. According to claim 1,
The step of generating the meeting minutes reading document,
Comprising the step of outputting together the content of the speech of the plurality of speech unit data and the suitability evaluation result for each of the plurality of speech unit data when receiving a request to read the meeting minutes reading document,
How to create a meeting minutes viewing document. a communication interface for receiving draft minutes data for the meeting;
a storage for storing software for generating and providing meeting minutes reading documents;
a memory into which a plurality of instructions are loaded according to the execution of the software; and
A processor for executing the plurality of instructions,
The plurality of instructions,
instructions for dividing the draft meeting minutes data to generate a plurality of speech unit data;
an instruction for performing a suitability evaluation on speech content included in each of the plurality of speech unit data according to a preset condition, and selecting inappropriate speech unit data according to a result of the suitability evaluation; and
and an instruction for generating a meeting minutes reading document using the remaining speech unit data excluding the selected inappropriate speech unit data among the plurality of speech unit data,
The instruction for selecting inappropriate speech unit data according to the result of the suitability evaluation is,
an instruction for extracting a keyword from each of the plurality of utterance unit data and determining a degree of similarity between the keywords by comparing the extracted keywords; and
and an instruction for selecting speech unit data whose determined similarity is less than or equal to a preset reference value as unsuitable speech unit data,
Meeting minutes reading document generating device.

Images