KR102433734B1 - Methods and Computer-Readable Medium for Providing User-customized National Assembly Minutes Information - Google Patents

Abstract

The present invention relates to a method and a computer-readable medium for providing user-customized national assembly minutes information and, more specifically, to a method and a computer-readable medium for providing user-customized national assembly minutes information. The method comprises the steps of: collecting a plurality of national assembly minutes; dividing each of the collected national assembly minutes into one or more speech units; tagging a plurality of pieces of information for each divided speech unit; searching for one or more speech units including the first keyword, when receiving the first keyword corresponding to a search term from a user terminal; and clustering the plurality of pieces of information tagged to each of the searched one or more speech units and providing the information to the user terminal. The present invention can prevent unnecessary content from being provided to a user.

Description

Methods and Computer-Readable Medium for Providing User-customized National Assembly Minutes Information

The present invention relates to a method for providing user-customized parliamentary minutes information and a computer-readable medium, and more particularly, to collecting a plurality of parliamentary minutes, dividing each of the plurality of collected minutes into one or more speech units, and dividing speech When a plurality of pieces of information are tagged for each unit, and when a first keyword corresponding to a search word is received from a user terminal, one or more speech units including the first keyword are searched for, and the plurality of pieces tagged with each of the searched one or more speech units It relates to a method and a computer-readable medium for providing user-customized meeting minutes information by clustering information of the user terminal and providing it to the user terminal.

The National Assembly and local councils in Korea conduct various meetings every year while carrying out their legislative activities. For example, in the National Assembly, various meetings such as plenary session, standing committee, special committee, budget and settlement special committee, state audit, subcommittee, state investigation, personnel hearing, public hearing and hearing are held for each session, and as a result of these various meetings, stenographic records and minutes are stored. is open to the public.

Specifically, 'National Assembly Minutes', a web service operated by the National Assembly of Korea, provides minutes of meetings presided over by the National Assembly. In the minutes of the National Assembly, the type of meeting, the duration, and any one of the agendas discussed at the meeting is input, and the full file of the minutes that meets the relevant conditions is provided.

However, from the point of view of the general public or those who want to find insights by analyzing the contents discussed in the National Assembly, users who lack knowledge about politics or laws may not know the names of laws or agendas related to their fields of interest. There is a problem in that it is difficult to search the minutes of the meeting on the subject to be found. For example, when a user wants to search by remarks in a plurality of minutes related to laws, agendas, or government audits related to keywords such as 'Netflix' and 'electric kickboard', the above-mentioned conventional web service can easily There is a problem that cannot be searched for.

Meanwhile, Prior Patent 1 (Korea Patent No. 10-2252096, registered on May 10, 2021) is a service provided to users by processing meeting minutes. It is provided in the same form as the word status. However, in the case of Prior Patent 1, since processed information is provided for one meeting minute, there is a problem in that it is difficult to provide comprehensive information on a plurality of meeting minutes including the keyword input by the user.

In addition, in Prior Patent 1, because only meeting minutes that contain the same keyword as the keyword entered by the user are searched, meeting minutes that do not contain the keyword entered by the user but have a very high relevance are not included in the search results, so that the user There is an additional problem in that it does not provide a meeting minutes search result in consideration of the context or relevance of the entered keyword.

Accordingly, the keywords by linking not only comprehensive information on a plurality of meeting minutes searched according to the keyword entered by the user, but also meeting minutes including other keywords with high relevance to the keyword, bills mentioned in the meeting, current progress, etc. The development of new technologies that provide various information related to

The present invention relates to a method for providing user-customized parliamentary minutes information and a computer-readable medium, and more particularly, to collecting a plurality of parliamentary minutes, dividing each of the plurality of collected minutes into one or more speech units, and dividing speech When a plurality of pieces of information are tagged for each unit, and when a first keyword corresponding to a search word is received from a user terminal, one or more speech units including the first keyword are searched for, and the plurality of pieces tagged with each of the searched one or more speech units An object of the present invention is to provide a method and a computer-readable medium for providing user-customized meeting minutes information by clustering the information of the user and providing the information to the user terminal.

In order to solve the above problems, a method of communicating with a user terminal and providing user-customized parliamentary minutes information performed in a server system including one or more processors and one or more memories, A first text in which one or more minutes stored in the external server are received by communicating with an external server in which the minutes are stored, and a corresponding statement is preset for each of a plurality of statements included in each of the received one or more minutes Minutes refining step of purifying the corresponding meeting minutes by removing the corresponding remarks when included in the set, and dividing the refined minutes into one or more speech units; For each of the one or more remarks units classified for the minutes refined through the minutes refining step, at least one detailed topic information for the remark unit, information on the type of remarks, and at least one understanding related to the remarks included in the remarks unit remark tagging step of tagging related information and automatic attribute information; and when receiving service request information including a first keyword from the user terminal, one or more speech units including the first keyword are searched for among a plurality of speech units tagged through the speech tagging step, and the searched A first service providing step of providing first service information to the user terminal by clustering information tagged in one or more speech units, wherein the automatic attribute information includes speaker information for the corresponding speech unit, and the first service information is provided to the user terminal. 1 The service providing step may include: the searched one or more utterance units; extracting one or more speakers who uttered the first keyword according to speaker information of the automatic attribute information tagged in each of the one or more searched speech units, and information on the number of times the first keyword was spoken by each speaker; and the number information of one or more detailed topic information uttered by one or more speakers who uttered the first keyword according to speaker information and one or more detailed topic information of automatic attribute information tagged to each of the searched one or more speech units; Provided is a method for providing user-customized parliamentary minutes information by providing first service information to the user terminal.

In an embodiment of the present invention, the type information of the remarks tagged through the remark tagging step corresponds to any one of a question type, an answer type, and an order type, and the first service providing step includes the searched one or more speech units. According to the speaker information of the automatic attribute information and the type information of the remarks tagged in each, the first service information further including information on the number of questions type, answer type, and order type for each at least one speaker who has spoken the first keyword is provided to the user It can be provided to the terminal.

In an embodiment of the present invention, the first service providing step does not include the first keyword among the plurality of speech units tagged through the remark tagging step, but the first keyword is one tagged as stakeholder information. The above utterance units can be additionally searched for.

In an embodiment of the present invention, the first service providing step includes, from the user terminal receiving the first service information, related agenda information for a specific speech unit among the searched one or more speech units included in the first service information. In the case of receiving a request, the bill information corresponding to each of the one or more bill numbers is retrieved with reference to the one or more bill numbers listed most recently on the basis of the particular comment unit recorded in the minutes including the particular comment unit, and the It is possible to provide the searched one or more bill information to the user terminal.

In an embodiment of the present invention, in the first service providing step, when service request information further including a meeting period and a parliamentary meeting type is received from the user terminal, corresponding to the meeting period and the parliamentary meeting type It is possible to search for one or more speech units including the first keyword among a plurality of tagged speech units for one or more meeting minutes.

In an embodiment of the present invention, the method for providing the user-customized parliamentary meeting minutes information further includes a second service providing step, wherein the second service providing step includes: When receiving selective input information for a specific speaker among one or more speakers who have spoken 1 keyword, social information obtained by crawling the SNS account of the specific speaker and news information obtained by crawling news mentioned by the specific speaker Second service information including a may be provided to the user terminal.

In order to solve the above problems, a computer-readable medium for implementing a method of communicating with a user terminal and providing user-customized parliamentary minutes information performed in a server system including one or more processors and one or more memories , wherein the computer-readable medium stores instructions for causing the server system to perform the following steps; Performs communication with an external server in which a plurality of parliamentary minutes according to the procedure are stored, receives one or more minutes stored in the external server, and corresponds to each of a plurality of remarks included in each of the received one or more minutes a minutes refining step of refining the minutes by removing the remarks when the remarks are included in the preset first text set, and dividing the refined minutes into one or more speech units; For each of the one or more remarks units classified for the minutes refined through the minutes refining step, at least one detailed topic information for the remark unit, information on the type of remarks, and at least one understanding related to the remarks included in the remarks unit remark tagging step of tagging related information and automatic attribute information; and when receiving service request information including a first keyword from the user terminal, one or more speech units including the first keyword are searched for among a plurality of speech units tagged through the speech tagging step, and the searched A first service providing step of providing first service information to the user terminal by clustering information tagged in one or more speech units, wherein the automatic attribute information includes speaker information for the corresponding speech unit, and the first service information is provided to the user terminal. 1 The service providing step may include: the searched one or more utterance units; extracting one or more speakers who uttered the first keyword according to speaker information of the automatic attribute information tagged in each of the one or more searched speech units, and information on the number of times the first keyword was spoken by each speaker; and the number information of one or more detailed topic information uttered by one or more speakers who uttered the first keyword according to speaker information and one or more detailed topic information of automatic attribute information tagged to each of the searched one or more speech units; A computer-readable medium is provided, which provides first service information to the user terminal.

According to an embodiment of the present invention, when each statement included in the minutes collected in the minutes refining step is related to the first text set, the statement is removed from the minutes, so unnecessary content can be prevented from being provided to the user. can have an effect.

According to an embodiment of the present invention, in the remark tagging step, one or more detailed topic information, remark type information, at least one stakeholder information and automatic attribute information related to remarks are tagged for each remark unit, so the first service providing step It is possible to exert the effect of processing and providing various information related to the keyword input by the user through a plurality of pieces of information tagged in each speech unit.

According to an embodiment of the present invention, the keyword input by the user through one or more stakeholder information tagged in the remark tagging step is not included, but the keyword is searched for up to the remark unit tagged with the stakeholder information and provided to the user. , it does not explicitly include the keyword, but it can have the effect of providing remarks related to the keyword.

According to an embodiment of the present invention, in the first service providing step, the number of utterances of the corresponding keyword and one or more including the uttered keyword for each speaker who uttered the keyword input by the user through speaker information included in the automatic attribute information. By providing the user with the status of the detailed topic for the unit of speech, it is possible to exert the effect of processing and providing information that is difficult to grasp only with the minutes of the meeting.

According to an embodiment of the present invention, in the first service providing step, one or more utterance units in which the keyword is uttered for each speaker who has uttered the keyword input by the user through speaker information and type information of the utterance included in the automatic attribute information. provides information on which one of a question type, an answer type, and an order type, so that the user can easily recognize what attitude the speaker holds toward the corresponding keyword.

According to an embodiment of the present invention, in the first service providing step, when a request for item information related to a speech unit retrieved from a user terminal is received, the item information is retrieved by referring to the item number corresponding to the remark unit from the corresponding meeting minutes. Thus, it is possible to exert the effect of providing bill information to the user terminal.

According to an embodiment of the present invention, in the second service providing step, when a specific speaker who spoke the keyword input by the user is selected, a post uploaded by the specific speaker on SNS and news related to the specific speaker are provided. Therefore, it is possible to exert the effect of providing information other than the minutes of the speaker selected by the user.

1 schematically shows components for performing a method for providing user-customized parliamentary minutes information according to an embodiment of the present invention.
2 schematically illustrates detailed steps of a method for providing user-customized parliamentary minutes information according to an embodiment of the present invention.
3 schematically shows a process of performing a meeting minutes refining step according to an embodiment of the present invention.
4 schematically illustrates a process of performing a speech tagging step according to an embodiment of the present invention.
5 schematically shows information on one or more stakeholders tagged in a utterance unit in the utterance tagging step according to an embodiment of the present invention.
6 schematically illustrates first service information provided in a first service providing step and displayed on a user terminal according to an embodiment of the present invention.
7 schematically illustrates another form of first service information provided in a first service providing step and displayed on a user terminal according to an embodiment of the present invention.
8 schematically illustrates a process of searching for a utterance unit related to a first keyword input by a user in a first service providing step according to an embodiment of the present invention.
9 schematically illustrates a process of providing agenda information related to a specific speech unit selected by a user to a user terminal in the first service providing step according to an embodiment of the present invention.
10 schematically illustrates a process of performing a second service providing step according to an embodiment of the present invention.
11 schematically illustrates third service information provided in a third service providing step and displayed on a user terminal according to an embodiment of the present invention.
12 schematically illustrates third service information provided in a third service providing step and displayed on a user terminal according to another embodiment of the present invention.
13 schematically illustrates an internal configuration of a computing device according to an embodiment of the present invention.

In the following, various embodiments and/or aspects are now disclosed with reference to the drawings. In the following description, for purposes of explanation, numerous specific details are set forth to provide a thorough understanding of one or more aspects. However, it will also be recognized by one of ordinary skill in the art that such aspect(s) may be practiced without these specific details. The following description and accompanying drawings set forth in detail certain illustrative aspects of one or more aspects. These aspects are illustrative, however, and some of the various methods in principles of various aspects may be employed, and the descriptions set forth are intended to include all such aspects and their equivalents.

Further, various aspects and features will be presented by a system that may include a number of devices, components and/or modules, and the like. It is also noted that various systems may include additional apparatuses, components, and/or modules, etc. and/or may not include all of the apparatuses, components, modules, etc. discussed with respect to the drawings. must be understood and recognized.

As used herein, “embodiment”, “example”, “aspect”, “exemplary”, etc. may not be construed as an advantage or an advantage in any aspect or design described above over other aspects or designs. . The terms '~part', 'component', 'module', 'system', 'interface', etc. used below generally mean a computer-related entity, for example, hardware, hardware A combination of and software may mean software.

Also, the terms "comprises" and/or "comprising" mean that the feature and/or element is present, but excludes the presence or addition of one or more other features, elements and/or groups thereof. should be understood as not

Also, terms including an ordinal number such as first, second, etc. may be used to describe various elements, but the elements are not limited by the terms. The above terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, a first component may be referred to as a second component, and similarly, a second component may also be referred to as a first component. and/or includes a combination of a plurality of related listed items or any of a plurality of related listed items.

In addition, in the embodiments of the present invention, unless otherwise defined, all terms used herein, including technical or scientific terms, are generally understood by those of ordinary skill in the art to which the present invention belongs. have the same meaning as Terms such as those defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in an embodiment of the present invention, an ideal or excessively formal meaning is not interpreted as

On the other hand, 'meeting minutes' described in the present invention can be understood as results prepared according to legislative activities performed by various institutions that discuss laws and policies such as bills and bills, such as the National Assembly and local councils. On the other hand, the minutes of the present invention may correspond to a form in which the remarks of various speakers who have participated in the corresponding legislative activity are described.

1 schematically illustrates components for performing a method for providing user-customized parliamentary minutes information according to an embodiment of the present invention.

As shown in FIG. 1 , as components for performing the method for providing user-customized parliamentary minutes information of the present invention, a server system 1000 , a user terminal 2000 , and an external server 3000 may be included.

The server system 1000 communicates with the user terminal 2000 and the external server 3000 to perform a method of providing user-customized parliamentary minutes information according to the present invention. Specifically, the server system 1000 performs a method of providing user-customized meeting minutes information, as shown in FIG. 1 , a minutes refining unit 1100, a remark tagging unit 1200, and a first service providing unit 1300 and a second service providing unit 1400 may be included.

The meeting minutes purification unit 1100 performs the meeting minutes purification step (S10), and collects one or more meeting minutes stored in the external server 3000, and unnecessary elements in each of the collected meeting minutes, for example, the meaning Formal remarks according to the meeting procedure such as no remarks and all remarks are removed, and remarks included in the minutes from which these elements have been removed are divided into one or more remarks. The utterance unit may correspond to a basic unit searched according to a keyword input by a user. Meanwhile, each of the speech units may include a speaker who has made a speech and a remark made by the speaker.

The remark tagging unit 1200 performs the remark tagging step (S20), and for each of the plurality of remark units divided by the meeting minutes refining unit 1100, a plurality of remarks included in the remark unit are taken into consideration. tag information. Information tagged to each speech unit through the speech tagging unit 1200 is clustered according to the keyword input by the user and provided to the user. can be provided to the user.

The first service providing unit 1300 performs a first service providing step (S30), and receives service request information including a first keyword input by the user from the user terminal 2000, and One or more speech units corresponding to one keyword are searched for, and information tagged to each of the searched one or more speech units is clustered to provide first service information to the user terminal 2000 . Specifically, the first service providing unit 1300 utilizes information tagged in each of one or more speech units corresponding to the first keyword input by the user, and the number of times for each one or more speakers who uttered the first keyword. The first service information may be generated by clustering whether the first keyword has been spoken, the status of the detailed topic of the speaking unit of the speaker for each of the one or more speakers, and the like.

The second service providing unit 1400 performs the second service providing step, and in addition to providing related information based on the minutes of the first service providing unit 1300, various information related to the speaker is provided to the user. can do. Specifically, when the user receiving the first service information selects a specific speaker, the second service providing unit 1400 is configured to include a post posted by the specific speaker on a social network service (SNS) and the News related to a specific speaker is provided to the user terminal 2000 . To this end, the server system 1000 performs communication with one or more SNS servers (not shown) for one or more social network services, crawls and stores posts uploaded by a plurality of speakers to the social network service, and the server system The 1000 may perform communication with one or more servers (not shown) that provide news, such as a portal service, to crawl and store news related to the speakers for each of a plurality of speakers.

Meanwhile, the meeting minutes refining unit 1100 , the remark tagging unit 1200 , the first service providing unit 1300 , and the second service providing unit 1400 corresponding to the components included in the server system 1000 . ) may be all included in one computing device and all included in one physical device. In another embodiment of the present invention, the server system 1000 includes a plurality of computing devices, and each of the plurality of computing devices communicates with each other. , and each of the plurality of computing devices may include one or more of the above-described components.

In addition, the server system 1000 may include additional components in addition to the components shown in FIG. 1 . For example, the server system 1000 is a component for providing information related to bills proposed by members of the parliament in addition to the minutes of the meeting, a component for tagging the speech unit of the minutes in a crowdsourcing method, the present invention It may further include a component for implementing a platform for providing information on the minutes of the meeting or comprehensively providing information related to the above-mentioned agenda.

The user terminal 2000 communicates with the server system 1000, transmits the keyword input by the user to search, to the server system 1000, and the server system 1000 receives the keyword according to the keyword. The first service information and/or the second service information is received and displayed.

The external server 3000 may store the minutes generated according to the legislative activity in the National Assembly or Parliament, and the external server 3000 communicates with the server system 1000, and the minutes purification unit 1100. One or more minutes of the meeting may be provided upon request. Specifically, the meeting minutes refining unit 1100 collects one or more meeting minutes stored in the external server 3000 according to a predetermined cycle in a crawling manner, or an Application Programming Interface (API) provided by the external server 3000 . One or more meeting minutes can be provided from the meeting minutes refining unit 1100 by using.

As described above, the meeting minutes refining unit 1100 may collect one or more meeting minutes stored in the external server 3000 by crawling or API method with the external server 3000, but in another embodiment of the present invention, the Through the input of the manager or operator of the server system 1000, the meeting minutes refining unit 1100 may receive one or more minutes, and in another embodiment of the present invention, the meeting minutes refining unit 1100 is an external separate server. Meeting minutes may be directly generated by receiving a file in which a meeting other than meeting minutes is recorded or recorded through (not shown) and converting the file into a Speech to Text (STT) method.

Meanwhile, in FIG. 1 , the external server 3000 is illustrated as a single number, but in another embodiment of the present invention, the server system 1000 may communicate with a plurality of external servers 3000 , and the plurality of external servers 3000 may be used. The external server 3000 may store minutes generated by each institution (National Assembly, local council, etc.) performing the legislative activity.

2 schematically illustrates detailed steps of a method for providing user-customized parliamentary minutes information according to an embodiment of the present invention.

As shown in FIG. 2 , a method of providing user-customized parliamentary minutes information performed in a server system 1000 including one or more processors and one or more memories by communicating with a user terminal 2000 and including one or more processors, the procedure of a decision Receives one or more minutes stored in the external server 3000 by communicating with the external server 3000 in which a plurality of parliamentary minutes according to Minutes refining step (S10) of removing the corresponding remarks when the corresponding remarks are included in the preset first text set for each, refining the corresponding minutes, and dividing the refined minutes into one or more speech units; For each of the one or more remarks units classified for the minutes refined through the minutes refining step (S10), one or more detailed topic information for the remark unit, type information of remarks, and remarks included in the remark unit are related remark tagging step of tagging one or more stakeholder information and automatic attribute information (S20); And when receiving the service request information including the first keyword from the user terminal 2000, one or more speech units including the first keyword among the plurality of speech units tagged through the speech tagging step (S20) may include; a first service providing step (S30) of searching for and providing first service information to the user terminal 2000 by clustering the information tagged to the searched one or more utterance units.

Specifically, in the meeting minutes purification step ( S10 ), one or more meeting minutes are received from the external server 3000 . To this end, in the meeting minutes purification step (S10), one or more meeting minutes are collected from the external server 3000 using a crawling or API method at a preset period or whenever new meeting minutes are updated in the external server 3000. , in another embodiment of the present invention, one or more meeting minutes may be directly input from the manager or operator of the server system 1000 .

Next, in the meeting minutes purification step (S10), a cleaning process is performed for each of the collected meeting minutes. Specifically, in the meeting minutes refining step (S10), when remarks included in each of the collected minutes are unnecessary or are remarks about a general meeting procedure, a process of removing the remarks from the minutes is performed. More specifically, in the meeting minutes purification step ( S10 ), a cleaning process for the meeting minutes may be performed using the first text set stored in the server system 1000 . The first text set includes one or more text information including one or more preset sentences or words and length information about a preset number of words. In the case of text information included in the set, the corresponding remark may be removed from the meeting minutes, and even if the corresponding remark is within the preset length information, the corresponding remark may be removed from the meeting minutes.

For example, the sentence "hello" may correspond to text information, and 'three words' may correspond to length information. Therefore, in the meeting minutes refining step (S10), if the remarks recorded in the minutes are "Hello", the remarks may be removed from the minutes, and if the remarks recorded in the minutes are "Yes, yes," the words of the remarks Since the number is less than three, the remarks may also be removed from the minutes.

Next, in the meeting minutes purification step (S10), a process of classifying the refined meeting minutes into one or more speech units is performed. The speech unit may correspond to individual remarks for each speaker recorded in the refined meeting minutes, or may correspond to a plurality of remarks in which a plurality of speakers continuously exchanged remarks in consideration of context. As such, the divided speech unit may correspond to a unit searched for according to the user's service request. Meanwhile, the meeting minutes purification step (S10) will be described in detail with reference to FIG. 3 .

In the speech tagging step (S20), a tagging operation is performed for each of the one or more speech units divided in the meeting minutes refining step (S10). More specifically, in the remark tagging step (S20), the text (speech) written in the remark unit is analyzed for each remark unit, and information on a plurality of types is tagged. The plurality of tagged types may correspond to a detailed topic for a corresponding utterance unit, a type of utterance, a stakeholder, and an automatic attribute. Among the plurality of tagged types, a detailed topic, a type of remark, and a stakeholder correspond to a type that is tagged in consideration of the meaning of the text (speech) included in the remark unit, and the automatic attribute is the remark unit or the remark unit. Explicit information recorded in the minutes of the meeting may correspond to the type of automatic tagging. In this way, the information tagged in each speech unit corresponds to information clustered according to the user's service request, and thus, the user explicitly includes information in which one or more minutes are processed through a plurality of pieces of information tagged in each speech unit and the minutes. Information not listed may be provided. Meanwhile, the remark tagging step (S20) will be described in detail with reference to FIGS. 4 and 5 .

In the first service providing step (S30), when the service request information including the first keyword input by the user through the user terminal 2000 is received, one or more speech units including the first keyword, specifically Searching for one or more speech units including the first keyword in speech content, clustering information tagged in each of the searched one or more speech units to generate first service information, and sending the first service information to the service request The information is provided to the transmitting user terminal (2000).

That is, in the first service providing step (S30), one or more utterance units corresponding to the first keyword input by the user are searched for, and based on information tagged to each of the searched one or more utterance units, the searched one or more utterance units are searched for. The first service information is comprehensively processed and provided to the corresponding user terminal 2000 . Meanwhile, the first service information provided to the user terminal 2000 in the first service providing step ( S30 ) will be described in detail with reference to FIGS. 6 and 7 .

3 schematically shows a process of performing the meeting minutes purification step (S10) according to an embodiment of the present invention.

As shown in FIG. 3 , in the meeting minutes refining step ( S10 ), each of the statements recorded in the collected minutes is refined (cleaned), and the refined minutes are divided into one or more speech units.

Specifically, the drawing shown on the left side of FIG. 3 corresponds to a part of the minutes of the Legislative and Judiciary Committee collected from the actual 'National Assembly Minutes' web service. As such, in the collected meeting minutes, the speaker and the contents of the speaker's speech are recorded for each basic speech A1 to A3 according to the order of speech. Meanwhile, in the meeting minutes refining step (S10), for each of a plurality of basic remarks recorded in the collected minutes, it is determined whether the corresponding basic remarks correspond to information included in the first text set, and the corresponding basic remarks are stored in the first text set. In the case of included information, a refining (cleaning) process is performed to remove the basic remarks from the meeting minutes. The basic remarks may refer to remarks recorded in the minutes before being refined.

As described above, the first text set includes one or more text information and length information, and in the meeting minutes refining step (S10), the text written in the basic statement corresponds to the one or more text information, or the basic statement is When the written text consists of the number of words less than or equal to the length information, the corresponding basic speech is removed from the meeting minutes. For example, when the length information included in the first text set is 3 with respect to 'Yes' corresponding to the remark in the basic remark corresponding to A2 of FIG. Since the remark 'yes' included in the basic remark consists of one word, the basic remark is removed from the meeting minutes.

As such, in the present invention, it is possible to prevent unnecessary information written in the meeting minutes from being provided to the user through the purification (cleaning) process performed in the meeting minutes purification step (S10), and unnecessary information is provided in the remark tagging step (S20) to be described later. By preventing the tagging process from being performed, it is possible to exert the effect of reducing the computing resources used through the execution of the remark tagging step (S20).

Next, the remark tagging step (S20) performs a process of classifying a plurality of remarks (basic remarks) recorded in the refined meeting minutes into one or more speech units. The unit of speech distinguished in the corresponding process may correspond to one basic remark as in A1 or may include a plurality of basic remarks as in A3. In other words, the unit of speech includes only one basic remark when the meaning can be grasped from the remarks written in the basic remarks. includes basic statements of

On the other hand, the process of classifying speech units in the speech tagging step (S20) is to use a machine learning model-based bot stored in the server system 1000, or to classify speech units by a worker through a crowdsourcing method, or A unit of speech for the meeting minutes refined by the manager or operator of the server system 1000 may be divided.

In another embodiment of the present invention, the purification (cleaning) process for the meeting minutes performed in the meeting minutes purification step (S10) may be performed in the remark tagging step (S20). In this case, the process of classifying the entire utterances included in the collected meeting minutes into one or more utterance units is performed without performing the refining (cleaning) process in the meeting minutes refining step (S10).

4 schematically shows a process of performing the speech tagging step (S20) according to an embodiment of the present invention.

As shown in FIG. 4 , the remark tagging step (S20) performs a process of tagging various information for each of one or more speech units divided through the meeting minutes refining step (S10).

Specifically, each utterance unit is described in column 1 of FIG. 4, and in the utterance tagging step (S20), as described in columns 2 to 8 of FIG. A plurality of pieces of information are tagged accordingly.

More specifically, in the remark tagging step (S20), for each speech unit, detailed subject information is tagged as shown in column 3 (A4) of FIG. 4, and as shown in column 4 (A5) of FIG. Similarly, the type information of the utterance of the corresponding utterance unit is tagged, and automatic attribute information is tagged as shown in columns 5 to 8 (A6) of FIG.

The detailed topic information may correspond to a subject for a remark included in the remark unit, and the subject may correspond to a specific word written in the remark of the remark unit, or may not be described in the remark of the remark unit, but represents the remark. It may correspond to a separate word that can be For example, 'domestic agent system' may be tagged as detailed subject information on the remark unit described in row 1 and column 1 of FIG. 4 . Meanwhile, although one piece of information is tagged for each speech unit in FIG. 4 , the present invention is not limited thereto, and a plurality of detailed subject information may be tagged with one speech unit.

The type information of the remark may correspond to information for tagging whether the remark included in the remark unit is a question type, an answer type, or an order (request) type. That is, the type information of the remark may be tagged as any one of a question type, an answer type, and an order type. As described above, by tagging the type information of remarks for each remark unit, the user can easily recognize whether the speaker who spoke the remark unit asked a question, answered a question, or placed an order.

The automatic attribute information includes information explicitly written in a corresponding utterance unit and information that can be derived according to the information explicitly written. As shown in FIG. 4, the automatic attribute information includes meeting classification information, committee information, member name (speaker) information, and party information, and the meeting classification information and the committee information are of meeting minutes including the corresponding speech unit. Corresponds to information explicitly written on the first page, and the member name (speaker) information corresponds to information explicitly written in each basic remark, as shown in FIG. 3 above, and party information is It corresponds to information that can be automatically derived according to the member name (speaker) information. Meanwhile, when the speech unit includes a plurality of basic speeches, each of the member name (speaker) information and the party information may include a plurality of pieces of information.

In addition, in another embodiment of the present invention, the remark date information described in column 2 of FIG. 4 may be further included in the automatic attribute information, and the remark date information is also explicitly written on the first page of the meeting minutes including the remark unit. It corresponds to the information that has been

Meanwhile, in the speech tagging step (S20), tagging is performed for each speech unit by using a separate machine learning model stored in the server system 1000 to tag a plurality of pieces of information for each speech unit, or A work including a speech unit is provided to a worker performing tagging using the crowdsourcing method, and tagging can be performed on the speech unit through the worker, or an administrator or operator of the server system 1000 directly The input tagging information for the divided speech unit may be received.

5 schematically shows information on one or more stakeholders tagged in a utterance unit in the utterance tagging step according to an embodiment of the present invention.

As shown in FIG. 5 , in the remark tagging step S20 , stakeholder information is tagged with respect to the speech unit in addition to the detailed topic information, speech type information, and automatic attribute information described above in FIG. 4 .

Specifically, the utterance unit is described in column 1 of FIG. 5 , detailed topic information for the corresponding utterance unit is tagged in column 3 of FIG. 5 , and type information of the utterance for the utterance unit in column 4 of FIG. is tagged, automatic attribute information for the corresponding utterance unit is tagged in columns 2, 5 to 8 of FIG. 5 , and stakeholder information for the corresponding utterance unit is tagged in column 9 (A7) of FIG. 5 .

The stakeholder information may correspond to a stakeholder related to a remark included in the remark unit, and the stakeholder is a stakeholder directly written in the remark included in the remark unit or is not specified in the remark, but the remark It may be relevant to the stakeholders involved in For example, since 'foreign giant telecommunication service provider' is mentioned in the remarks included in the remark unit shown in FIG. 5, stakeholder information tagged in the remark unit is not described in the remark unit, but 'overseas giant telecommunication service provider' 'Company A', 'Startup N' and 'Company Y' corresponding to can be tagged.

As described above, the stakeholder information tagged to the remark unit through the remark tagging step (S20) may provide the user with who the stakeholder for the remark unit searched for by the keyword input by the user, or input by the user. The effect of providing search results in consideration of the utterance units related to the keyword entered by the user by providing the utterance unit tagged with the relevant keyword as stakeholder information as a search result, although it does not directly include the keyword. can perform

6 schematically illustrates the first service information provided in the first service providing step S30 and displayed on the user terminal 2000 according to an embodiment of the present invention.

As shown in (A) and (B) of FIG. 6 , the automatic attribute information includes speaker information for a corresponding utterance unit, and the first service providing step (S30) includes: the searched one or more utterance units; extracting one or more speakers who uttered the first keyword according to speaker information of the automatic attribute information tagged in each of the one or more searched speech units, and information on the number of times the first keyword was spoken by each speaker; and the number information of one or more detailed topic information uttered by one or more speakers who uttered the first keyword according to speaker information and one or more detailed topic information of automatic attribute information tagged to each of the searched one or more speech units; The first service information may be provided to the user terminal 2000 .

Specifically, (A) of FIG. 6 shows the number of times information about how many times the first keyword has been uttered for each one or more speakers who have uttered the first keyword included in the first service information is displayed on the user terminal 2000. It corresponds to a drawing schematically showing the screen.

Taking FIG. 6A as an example, the user transmits service request information including the first keyword 'startup N' to the server system 1000 through the user terminal 2000, and provides the first service Step S30 searches for one or more speech units including 'startup N' (first keyword) included in the received service request information, and the speaker of automatic attribute information tagged to each of the searched one or more speech units. The information is regarded as the speaker who directly spoke the 'Startup N', and the number of times information about how many times the 'Startup N' has been spoken by each speaker is derived, and the number information is in the first service information. included and provided to the user terminal 2000 . Meanwhile, the user terminal 2000 displays the number of times information for each speaker included in the received first service information in a graphical form, as shown in FIG. 6A . Here, the information on the number of times for each speaker may correspond to information on how many times the first keyword is included in one or more utterances uttered by the speaker.

On the screen on which the number information is displayed on the user terminal 2000, the number of times the first keyword has been spoken is displayed for each speaker. In A8 of FIG. 6(A), the speaker ('ㅇㅇㅇ') who uttered the first keyword ('startup N') the most and the number of times information about how many times the speaker spoke the first keyword ('27 times) ') is indicated.

On the other hand, since the speaker can speak the first keyword more than once in the remarks written in the remarks unit, the information on the number of times the first keyword has been uttered for each speaker is equal to or greater than the number of remarks units in which the speaker has uttered the first keyword. can

In this way, the user can be provided with information on the number of utterances of the speaker and the first keyword in the order in which the user has spoken the most of the first keyword input by the user through the user terminal 2000 on which the first service information is displayed. Compared to the conventional method of receiving only the minutes of the meeting of the council, it is possible to easily recognize which speaker spoke the keyword of his/her interest and how many times the keyword was uttered without further processing by the user.

On the other hand, (B) of Figure 6 is one or more detailed topic information tagged to each of one or more speech units including the first keyword uttered by the speaker for each of the one or more speakers who have uttered the first keyword included in the first service information. The number information corresponds to a diagram schematically showing a screen displayed on the user terminal 2000 .

In detail, in the screen shown in FIG. 6(B), the user selects an area A8 for a specific speaker ('ㅇㅇㅇ' in FIG. 6(A)) on the screen shown in FIG. 6(A). Upon selection, one or more detailed topic information ('network', 'user protection', 'tax' and 'Copyright') corresponds to the screen on which each number information is displayed. As shown in (B) of FIG. 6, the number information is an area in which information on the number of remarks for a specific speaker is displayed among information on the number of remarks of the first keyword for each speaker who the user has spoken the first keyword. It may be displayed according to the selection of the area A8) in A), but is not limited thereto, and information on the number of each of one or more detailed topic information for each speaker who has spoken the first keyword is the utterance of the first keyword for each speaker. It may be displayed in various forms or according to various user inputs, such as displayed together with the number of times information.

On the other hand, in the first service providing step (S30), when receiving service request information including the first keyword ('startup N') from the user terminal 2000, in addition to the above-described number information, the number information is further included. And, the number information is the first keyword ('startup N') directly to the speaker information of the automatic attribute information tagged to each of one or more speech units including the searched first keyword ('startup N') It is regarded as the speaker who spoke, and for each speaker, the number information for each type of one or more detailed attribute information tagged to each of the one or more speech units including the first keyword ('startup N') is derived, and the number information is Further included in the first service information is provided to the user terminal (2000).

On the other hand, the user terminal 2000 shows the number information for each type of one or more detailed attribute information for each speaker who uttered the first keyword included in the received first service information in area A9 of FIG. As shown, it is displayed in graphical form. Taking the area A9 shown in FIG. 6B as an example, in each of one or more speech units including the first keyword ('startup N') spoken by a specific speaker ('ㅇㅇㅇ'), ( As in the area A9 shown in B), one or more detailed subject information corresponding to any one of 'network', 'user protection', 'tax' and 'copyright' is tagged, and the first service is provided In step S30, number information for each type of tagged one or more detailed subject information ('network', 'user protection', 'tax' and 'copyright') may be derived.

On the other hand, since two or more detailed topics can be tagged in each speech unit, information on the number of one or more detailed topic information tagged in one or more speech units including the first keyword for each speaker is a remark unit in which the speaker has uttered the first keyword. may be greater than or equal to the number of

In this way, the user uses the user terminal 2000 on which the first service information is displayed, as well as information on who has spoken the first keyword input by the user and how many times the first keyword has been uttered. It is possible to easily recognize which sub-topic the speaker who has spoken the first keyword uttered the first keyword.

As in (A) and (B) of FIG. 6 described above, by inputting the first keyword, the conventional method provides the meeting minutes including the inputted first keyword as a search result, that is, focusing on the meeting minutes. Although the search results are provided, in the present invention, who is the speaker who uttered the input first keyword, how many times the speaker spoke the first keyword, and in which detailed topic the speaker spoke the first keyword is provided as a search result, that is, remarks recorded in the meeting minutes are processed and provided with a focus on the speaker, so that the user can easily recognize which speaker is most interested in the first keyword, and the like.

Finally, the diagram shown in (C) of FIG. 6 schematically shows a screen in which information processed based on one or more detailed topics rather than the speaker-centered first keyword input by the user is displayed on the user terminal 2000. shown as

Specifically, in the first service providing step (S30), in addition to the above-mentioned number information and number information, the status information of one or more detailed topic information tagged in each of one or more speech units including the first keyword input by the user is derived. And, the status information may be further included in the first service information.

On the other hand, the user terminal 2000 receiving the first service information including the status information, as shown in (C) of Figure 6, one or more details tagged to each of one or more speech units including the first keyword The status (ratio) of the detailed topic information for each type of topic information ('network', 'user protection', 'tax', 'copyright' and 'other' shown in FIG. 6(C)) is displayed in graphic form. Display. In the area A10 shown in FIG. 6(C), the status of the detailed topic corresponding to 'network' is displayed as a graphic element, and specifically, in the corresponding area A10, the detailed topic corresponding to 'network' is displayed. The percentage of the number of cases tagged with is displayed as a graphic element.

Additionally, the status information may include information on the number of speakers who have mentioned the corresponding detailed topic for each of one or more detailed topics, and the number of people information is as shown in area A10 of FIG. 6(C), the user terminal ( 2000) can be displayed. In more detail, the number of speakers information may correspond to the number of speaker information of the automatic attribute information tagged to each of one or more speech units tagged with a corresponding detailed topic.

In this way, the user knows what the detailed topics related to the first keyword inputted by the user through the screen of the user terminal 2000 on which the above-described status information is displayed, and a specific detailed topic among all the detailed topics related to the first keyword It is easy to recognize the percentage of

That is, the status information on the type of one or more detailed topic information tagged in one or more remarks units including the first keyword shown in FIG. 6C is the first keyword shown in FIG. 6B. It may correspond to the current status information synthesized without distinction of speakers by counting information on the types of one or more detailed topic information tagged in one or more remarks units corresponding to each of one or more speakers who have made a remark.

7 schematically illustrates another type of first service information provided in the first service providing step ( S30 ) and displayed on the user terminal 2000 according to an embodiment of the present invention.

7, the type information of the remarks tagged through the remark tagging step (S20) corresponds to any one of a question type, an answer type, and an order type, and the first service providing step (S30) is, According to the speaker information of the automatic attribute information tagged to each of the searched one or more remark units and the type information of the remark, the question type, answer type and order type information for each at least one speaker who spoke the first keyword is further included. 1 service information may be provided to the user terminal 2000 .

Specifically, FIG. 7 is a view schematically showing a screen on which information on the number of cases by type of speech type of a speaker is displayed on the user terminal 2000 for each one or more speakers who have uttered the first keyword included in the first service information. corresponds to

In the screen shown in FIG. 7, as the user selects an area A8 for a specific speaker ('ㅇㅇㅇ' in FIG. 6(A)) on the screen shown in FIG. 6(A), the corresponding user On the screen displaying the number information for each type of remark ('answer', 'question' and 'order' in FIG. 7 ) for each of one or more speech units of a specific speaker who uttered the first keyword in the terminal 2000 corresponds to

In an embodiment of the present invention, the type of the speaker's remark includes a question type, an answer type, and an order type. Each remark unit is tagged with any one of a question type, an answer type, and an order type through the remark tagging step (S20). The question type is a type that is tagged when the speaker's statement is a statement for a question, the answer type is a type that is tagged when the speaker's statement is a statement for answering a certain question, and the order type is the speaker's statement It corresponds to the type of tagging when the remark is for an order, request, or request to the target (listener) of the remark.

Meanwhile, in the first service providing step (S30), using the first keyword included in the service request information received from the user terminal 2000, one or more utterance units including the first keyword are searched, and the searched The speaker information tagged in each of one or more speech units corresponds to the speaker who spoke the first keyword, and for each speaker, information on the number of cases by type of speech tagged in each of the one or more speech units of the speaker is derived. , The case information for each type of speech type information of the speakers who uttered the derived first keyword may be further included in the above-described first service information.

The user terminal 2000 that receives the first service information including the case number information displays the case number information in a graphical form as shown in an area A11 shown in FIG. 7 . Taking the area A11 shown in FIG. 7 as an example, the type information of the type of speech for each of one or more speech units including the first keyword ('Startup N') uttered by the specific speaker ('ㅇㅇㅇ') 'Answer', 'question', and 'order') may be displayed on the screen of the user terminal 2000 .

Meanwhile, as shown in FIG. 7, the case information is an area in which the number of statements information for a specific speaker is displayed among the number of statements information of the first keyword for each speaker who the user has spoken the first keyword (FIG. 6(A)). may be displayed according to selecting the area (A8)) in the It may be displayed in various forms or according to various user inputs, such as displayed together with information.

As described above, in the present invention, in processing and providing information centered on the speaker who uttered the first keyword, the speaker includes the first keyword according to the information on the number of cases by type of each type of remarks for each speaker who uttered the first keyword. Since the user can easily recognize how many questions, how many answers, and how many orders are made with respect to the remarks to be made, it is possible to exert the effect of estimating the speaker's stance with respect to the first keyword.

8 schematically illustrates a process of searching for a utterance unit related to a first keyword input by a user in the first service providing step (S30) according to an embodiment of the present invention.

As shown in FIG. 8 , the first service providing step ( S30 ) does not include the first keyword among the plurality of speech units tagged through the speech tagging step ( S20 ), but the first keyword is understood It is possible to additionally search for one or more speech units tagged as related information.

Specifically, in an embodiment of the present invention, when a user inputs a first keyword to be searched through the user terminal 2000 and receives service request information including the first keyword from the server system 1000 , the first service providing step (S30) basically derives one or more speech units in which the first keyword is specified in the speech contents as a search result.

However, from the user's point of view, although the first keyword is not specified in the remarks, remarks highly related to the first keyword may also correspond to important remarks. For example, if the user inputs 'startup N' as the first keyword, 'startup N' is not specified in the remarks, but the remarks that include 'overseas platform operator' are also sent to the user. It may correspond to the content of meaningful remarks. Accordingly, in the present invention, in consideration of this point, it is possible to derive a search result by additionally considering one or more stakeholder information tagged in a remark unit.

Specifically, as shown in FIG. 8, each speech unit is tagged with a plurality of pieces of information (detailed topic information, speech type information, automatic attribute information, and stakeholder information) through the speech tagging step (S20) described above. have. On the other hand, when receiving the service request information including the first keyword from the user terminal 2000, the first service providing step (S30), one or more speech units in which the first keyword is specified in the remarks and Although the first keyword is not specified in the remarks, one or more speech units in which the first keyword is tagged as stakeholder information may be derived as a search result for the first keyword.

8 as an example, the service request information transmitted from the user terminal 2000 includes a first keyword written as 'company Y', and in the first service providing step (S30), 'company Y' is included in the remarks. The specified remark unit ('Speech unit #1' in Fig. 8) (B1) is included as a search result, and 'Company Y' is not specified in the remarks, but the tagged stakeholder information is 'Company Y' The utterance unit ('speech unit #N' in FIG. 8 ) (B2) may be included as a search result.

As described above, in the present invention, for each utterance unit, one or more stakeholder information related to the content of the statement is tagged, and in the tagged stakeholder information, the first keyword input by the user is not specified, but the remark unit with high relevance is selected. It corresponds to a component that can be included in search results.

Meanwhile, in the first service providing step ( S30 ), when service request information further including a meeting period and a parliamentary meeting type is received from the user terminal 2000 , corresponding to the meeting period and the parliamentary meeting type It is possible to search for one or more speech units including the first keyword among a plurality of tagged speech units for one or more meeting minutes.

Specifically, the user can not only input the first keyword to search for the remarks he or she needs, but also additionally input search information for the meeting period and the parliamentary meeting type, and therefore, the service request information includes the 1 Keywords, meeting duration and parliamentary meeting type can be included.

On the other hand, in the first service providing step (S30), as described above, as the service request information is received, the first keyword is specified in the remarks or one or more remarks in which the first keyword is tagged as stakeholder information. Among the units, one or more speech units corresponding to the meeting period and parliamentary meeting type included in the service request information are derived as a search result.

The meeting period may correspond to a period set by a general type of user inputting two dates, or may correspond to a specific session or a period between two sessions in consideration of the unique schedule of the Parliament, or elected by members It may correspond to a specific logarithm to be The parliamentary meeting type may be set by inputting one or more of various meeting types performed by the parliament. For example, the user can use 'Plenary Meeting', 'Standing Committee', 'Special Committee', 'Special Committee on Budget and Settlement', 'State Audit', 'Subcommittee', 'National Investigation', 'Personnel Hearing', 'Public Hearing' and You can set the type of parliamentary meeting by selecting one or more of 'hearings'.

In this way, when the service request information including the meeting period and the parliamentary meeting type is received, the first service providing step (S30) includes tagging information (FIG. 4) included in the automatic attribute information tagged to each speech unit. Search results can be derived by determining whether the 'meeting classification' and 'date of remarks') correspond to the meeting period and parliamentary meeting type included in the service request information.

FIG. 9 schematically illustrates a process of providing agenda information related to a specific speech unit selected by the user to the user terminal 2000 in the first service providing step (S30) according to an embodiment of the present invention.

As shown in FIG. 9 , when receiving a request for information regarding a specific speech unit among the one or more searched speech units included in the first service information from the user terminal 2000 that has received the first service information , with reference to the one or more bill numbers previously recorded on the basis of the specific speech unit recorded in the meeting minutes including the specific speech unit, search for item information corresponding to each of the one or more item numbers, and search for the retrieved one or more item information may be provided to the user terminal 2000 .

Specifically, in the first service providing step (S30), one or more utterance units corresponding to the first keyword input by the user may be provided to the user terminal 2000 as a search result, and the user may provide the user terminal 2000 with the search result. ), by selecting a specific speech unit among one or more speech units displayed as a search result, information on one or more agenda items related to a specific speech unit can be provided.

In this way, in order to provide information on one or more items related to the specific speech unit selected by the user, the first service providing step (S30) is performed from the user terminal 2000 according to the user's input to the one or more items for the specific speech unit. When information on the bill is requested, the bill number for each of the one or more bills related to the comment unit may be extracted with reference to the minutes in which the relevant speech unit is recorded.

More specifically, as shown in FIG. 9, the parliamentary minutes generally collected from the external server 3000 record the remarks made by each speaker, and in the front of the recorded remarks, about any law or any agenda Whether it has been discussed is written, and in the description, not only the name of the law or bill, but also the article number or bill number is listed.

Accordingly, in the first service providing step (S30), in the meeting minutes in which the specific speech unit selected by the user is described, the article number or bill number for one or more laws or bills listed in the front row closest to the specific speech unit and input the extracted article number or bill number into the law or bill database built in the server system 1000 or the law or bill database built in a separate external server 3000 to extract the article number or bill By acquiring legal information or bill information corresponding to the number, and providing the obtained legal information or bill information to the user terminal 2000, information on laws or bills related to a specific unit of speech selected by the user (2000) can be displayed.

Taking Fig. 9 as an example, 'the first subcommittee for bill review ~' described on the left side of Fig. 9 corresponds to a specific speech unit selected by the user, and the first service providing step (S30) is as shown in the center of Fig. 9, In the minutes containing a specific speech unit, enter the article number or bill number in the description of the law or agenda in the preceding column of the specific speech unit ('1. Extract and use the legal information or bill information corresponding to the extracted article number or bill number recorded in the law or bill database ('<legislative bill on the use of electronic documents in criminal litigation, etc.>' listed on the right side of FIG. 9) provided to the terminal 2000 .

Meanwhile, in the first service providing step (S30), legal information or bill information itself may be provided to the user terminal 2000 . In another embodiment of the present invention, the first service providing step (S30) provides link information for accessing legal information or bill information recorded in the law or bill database to the user terminal 2000, and the user terminal (2000) may display legal information or bill information through the law or bill database using the provided link information.

10 schematically illustrates a process of performing a second service providing step according to an embodiment of the present invention.

As shown in FIG. 10 , the method for providing the user-customized meeting minutes information further includes a second service providing step, wherein the second service providing step includes a user terminal 2000 provided with the first service information. When receiving selection input information for a specific speaker among one or more speakers who have spoken the first keyword from Second service information including one piece of news information may be provided to the user terminal 2000 .

Specifically, in the present invention, through the second service providing step, not only information about the speaker who made a remark containing a specific keyword in the meeting minutes is provided, but also external information related to the speaker in addition to the meeting minutes can be additionally provided to the user. have.

To this end, the server system 1000 collects SNS posts of each of the plurality of speakers corresponding to the plurality of speaker information tagged in each of the plurality of speaking units and news in which the speaker is specified. Specifically, the server system 1000 collects posts uploaded by accessing the SNS account of the speaker in a crawling manner when the speaker has one or more SNS accounts for each speaker, and collects a plurality of news articles such as a portal service. In a service that provides information, it searches and collects news that the speaker is listed in a crawling method. Posts collected by accessing the SNS account may correspond to the social information, and news collected by searching for news in which the speaker is described may correspond to the news information. Meanwhile, this collection process may be performed at a preset cycle or whenever a new post or news is found.

On the other hand, information related to one or more speakers who uttered the first keyword input by the user is displayed on the user terminal 2000 provided with the first service information, and on the screen, the user is a specific speaker who wants to receive SNS posts and news can be selected, and the user terminal 2000 transmits selection input information including information on a specific speaker selected by the user to the server system 1000, and as described above, the second service providing step includes each Among the social information and news information collected for each speaker, second service information including social information and news information on a specific speaker selected by the user is transmitted to the corresponding user terminal 2000 .

As described above, the user terminal 2000 that has received the second service information displays social information and news information for a specific speaker selected by the user, and the user can check social information and news information related to the specific speaker selected by the user. , it is possible to easily receive additional information (SNS posts and news) related to the speaker who made the remark including the first keyword.

11 schematically illustrates third service information provided in a third service providing step and displayed on a user terminal according to an embodiment of the present invention.

11 , the method for providing the user-customized parliamentary minutes information further includes a third service providing step, wherein the third service providing step includes receiving service request information including a keyword from the user terminal. In this case, one or more utterance units including a keyword included in the service request information are provided to the user terminal as a result of a service, and according to a selection input input by a user with respect to a service result displayed on the user terminal, the 3 The service providing step may provide an additional detailed service to the user terminal.

The diagram shown in FIG. 11 corresponds to a screen displayed on the user terminal in response to a request for a third service received from the user terminal in the third service providing step.

In the screen shown in FIG. 11, area A20 corresponds to an area in which the user can input service request information including keywords. In the area A20, the user may input service request information after inputting a keyword ('creator' in FIG. 11). Accordingly, in the third service providing step, one or more remarks including the keyword of the service request information. A unit may be provided to the user terminal.

Additionally, as shown in the area A20, specific information including the corresponding keyword can be selected from among various information (all minutes, meeting classification, meeting name, speaker name, affiliated committee, agenda number, etc.) recorded in the meeting minutes. For example, when the user inputs 'Hong Gil-dong' as a keyword and selects 'speaker's name', the third service providing step uses one or more utterance units uttered by the speaker 'Hong Gil-dong' as a service result of the user terminal. can be provided to

In addition, one or more keywords input by the user in the past may be displayed in the area A20, and through this, the user may input keywords by selecting keywords that have been input in the past, rather than directly inputting the keywords.

Meanwhile, an area A21 illustrated in FIG. 11 corresponds to an area in which a service result provided in the third service providing step is displayed according to the service request information. 11 , in the area A21, the total number of one or more utterance units including the keyword ('57 utterances' in FIG. 11 ) and each of the one or more utterance units including the keyword are displayed.

As shown in the area A21, each speech unit displayed on the user terminal includes a meeting date, speaker name, speaker's party, speaker's affiliation committee, meeting type, and a statement including the corresponding keyword. In this case, in the case of a remark including the keyword, the keyword included in the remark is visually highlighted differently so that the user can easily recognize where the keyword entered by the user is located in the remark.

Meanwhile, the area A21 includes one or more elements ('newest order', 'oldest order' and 'relevance order' in FIG. 11) for sorting one or more speech units provided as a service result in the third service providing step. and, when the user selects a specific element, one or more speech units may be arranged and displayed in the area A21 corresponding to the specific element.

In addition, when the user selects a specific speech unit among one or more speech units displayed in the area A21, the third service providing step may provide a detailed service result for the selected specific speech unit, for which FIG. 12 to explain.

12 schematically illustrates third service information provided in a third service providing step and displayed on a user terminal according to another embodiment of the present invention.

As described above, when the user selects a specific speech unit among one or more speech units displayed in the area A21, the third service providing step may provide a detailed service result for the selected specific speech unit, 12 corresponds to a screen on which a detailed service result for the selected specific speech unit is displayed on the user terminal.

In the screen shown in FIG. 12 , in the area A22, the specific speech unit included in the meeting minutes corresponding to the specific speech unit selected by the user and the next speech unit or previous speech units are displayed based on the specific speech unit. In this way, since the user can read both the front and back speech units of the specific speech unit selected by the user, it is possible to easily understand the context of the specific speech unit selected by the user.

Meanwhile, as shown in FIG. 12 , the area A22 may be displayed visually differently from other speech units in the case of a specific speech unit selected by the user. For example, as shown in FIG. 12 , a border of a region in which the specific utterance unit is displayed may be displayed in different colors and in an emphasized form.

In addition, when the name of a specific bill is included in the unit of speech displayed in the area A22, the user can select the name of the specific bill displayed in the area A22, and the third service providing step includes the original text of the selected specific bill. may provide access information to the user terminal, and the original text of a specific bill may be displayed on the user terminal based on the access information.

In another embodiment of the present invention, a notification element and a bookmark element may be displayed in the area A22, and when the user selects the notification element, the third service providing step is performed like a subsequent meeting for the corresponding meeting. When a meeting related to , it is possible to provide the user terminal that the meeting has occurred, and at the same time provide access information for viewing or listening to the meeting.

On the other hand, when the user selects the bookmark element, the corresponding meeting minutes are stored in the corresponding user's account or the corresponding user terminal, so that the user can easily read the corresponding meeting minutes without inputting service request information including the above-mentioned keywords. .

In the area A23, the agenda made in the meeting corresponding to the specific speech unit selected by the user is displayed. When the user selects the specific agenda, the area A22 includes the first speech unit and the first speech unit in the corresponding agenda. One or more of the following speech units may be displayed.

Area A24 displays one or more participants attending the meeting corresponding to a specific speech unit selected by the user. More specifically, as shown in FIG. 12 , the number of participants by affiliation of all participants attending the meeting may be displayed in the area A24.

Also, in the area A24, one or more participants who have attended the meeting may be displayed, and preferably, one or more participants may be displayed for each affiliation. More specifically, in the case of one or more participants displayed in the area A24, an element indicating that they have made a speech ('speaking' in FIG. 12) is displayed in the case of a participant who has made a speech at the corresponding meeting, and the user selects the corresponding element. In this case, in the area A22, one or more speech units spoken by a specific participant corresponding to a corresponding element in a corresponding meeting may be displayed. Through this configuration, the user can easily recognize who spoke and who did not speak in the meeting through only the area A24, and can show the effect of filtering and viewing only the speech units of a specific participant who has spoken. can

In addition, when the names of one or more participants displayed in area A24 are selected, the third service providing step provides person information about the selected participants to the user terminal, and the provided person information may be displayed on the user terminal. have.

On the other hand, the third service providing step described in FIGS. 11 to 12 may be understood as a separate step different from the first service providing step, but in another embodiment of the present invention, the third service providing step is the first service It may be understood that the service result included in the providing step and provided in the third service providing step is included in the first service information provided in the first service providing step.

13 schematically illustrates an internal configuration of a computing device according to an embodiment of the present invention.

The above-described server system 1000 illustrated in FIG. 1 may include components of the computing device 11000 illustrated in FIG. 13 .

13, the computing device 11000 includes at least one processor 11100, a memory 11200, a peripheral interface 11300, an input/output subsystem ( It may include at least an I/O subsystem) 11400 , a power circuit 11500 , and a communication circuit 11600 . In this case, the computing device 11000 may correspond to the server system 1000 illustrated in FIG. 1 .

The memory 11200 may include, for example, high-speed random access memory, a magnetic disk, SRAM, DRAM, ROM, flash memory, or non-volatile memory. . The memory 11200 may include a software module, an instruction set, or other various data required for the operation of the computing device 11000 .

In this case, access to the memory 11200 from other components such as the processor 11100 or the peripheral device interface 11300 may be controlled by the processor 11100 .

Peripheral interface 11300 may couple input and/or output peripherals of computing device 11000 to processor 11100 and memory 11200 . The processor 11100 may execute a software module or an instruction set stored in the memory 11200 to perform various functions for the computing device 11000 and process data.

The input/output subsystem may couple various input/output peripherals to the peripheral interface 11300 . For example, the input/output subsystem may include a controller for coupling a peripheral device such as a monitor or keyboard, mouse, printer, or a touch screen or sensor as required to the peripheral interface 11300 . According to another aspect, input/output peripherals may be coupled to peripheral interface 11300 without going through an input/output subsystem.

The power circuit 11500 may supply power to all or some of the components of the terminal. For example, the power circuit 11500 may include a power management system, one or more power sources such as batteries or alternating current (AC), a charging system, a power failure detection circuit, a power converter or inverter, a power status indicator, or a power source. It may include any other components for creation, management, and distribution.

The communication circuit 11600 may enable communication with another computing device using at least one external port.

Alternatively, as described above, if necessary, the communication circuit 11600 may transmit and receive an RF signal, also known as an electromagnetic signal, including an RF circuit, thereby enabling communication with other computing devices.

This embodiment of FIG. 13 is only an example of the computing device 11000, and the computing device 11000 may omit some components shown in FIG. 13 or further include additional components not shown in FIG. 13, or 2 It may have a configuration or arrangement that combines two or more components. For example, a computing device for a communication terminal in a mobile environment may further include a touch screen or a sensor in addition to the components shown in FIG. 13 , and may include various communication methods (WiFi, 3G, LTE) in the communication circuit 11600 . , Bluetooth, NFC, Zigbee, etc.) may include a circuit for RF communication. Components that may be included in the computing device 11000 may be implemented in hardware, software, or a combination of both hardware and software including an integrated circuit specialized for one or more signal processing or applications.

Methods according to an embodiment of the present invention may be implemented in the form of program instructions that can be executed through various computing devices and recorded in a computer-readable medium. In particular, the program according to the present embodiment may be configured as a PC-based program or an application dedicated to a mobile terminal. An application to which the present invention is applied may be installed in the computing device 11000 through a file provided by the file distribution system. For example, the file distribution system may include a file transmission unit (not shown) that transmits the file according to the request of the computing device 11000 .

The device described above may be implemented as a hardware component, a software component, and/or a combination of the hardware component and the software component. For example, devices and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA). , a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions, may be implemented using one or more general purpose or special purpose computers. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, although one processing device is sometimes described as being used, one of ordinary skill in the art will recognize that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that may include For example, the processing device may include a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as parallel processors.

Software may comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be any kind of machine, component, physical device, virtual equipment, computer storage medium or device, to be interpreted by or to provide instructions or data to the processing device. , or may be permanently or temporarily embody in a transmitted signal wave. The software may be distributed over networked computing devices, and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic such as floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

According to an embodiment of the present invention, when each statement included in the minutes collected in the minutes refining step is related to the first text set, the statement is removed from the minutes, so unnecessary content can be prevented from being provided to the user. can have an effect.

According to an embodiment of the present invention, in the remark tagging step, one or more detailed topic information, remark type information, at least one stakeholder information and automatic attribute information related to remarks are tagged for each remark unit, so the first service providing step It is possible to exert the effect of processing and providing various information related to the keyword input by the user through a plurality of pieces of information tagged in each speech unit.

According to an embodiment of the present invention, the keyword input by the user through one or more stakeholder information tagged in the remark tagging step is not included, but the keyword is searched for up to the remark unit tagged with the stakeholder information and provided to the user. , it does not explicitly include the keyword, but it can have the effect of providing remarks related to the keyword.

According to an embodiment of the present invention, in the first service providing step, the number of utterances of the corresponding keyword and one or more including the uttered keyword for each speaker who uttered the keyword input by the user through speaker information included in the automatic attribute information. By providing the user with the status of the detailed topic for the unit of speech, it is possible to exert the effect of processing and providing information that is difficult to grasp only with the minutes of the meeting.

According to an embodiment of the present invention, in the first service providing step, one or more utterance units in which the keyword is uttered for each speaker who has uttered the keyword input by the user through speaker information and type information of the utterance included in the automatic attribute information. provides information on which one of a question type, an answer type, and an order type, so that the user can easily recognize what attitude the speaker holds toward the corresponding keyword.

According to an embodiment of the present invention, in the first service providing step, when a request for item information related to a speech unit retrieved from a user terminal is received, the item information is retrieved by referring to the item number corresponding to the remark unit from the corresponding meeting minutes. Thus, it is possible to exert the effect of providing bill information to the user terminal.

According to an embodiment of the present invention, in the second service providing step, when a specific speaker who spoke the keyword input by the user is selected, a post uploaded by the specific speaker on SNS and news related to the specific speaker are provided. Therefore, it is possible to exert the effect of providing information other than the minutes of the speaker selected by the user.

As described above, although the embodiments have been described with reference to the limited embodiments and drawings, various modifications and variations are possible by those skilled in the art from the above description. For example, the described techniques are performed in a different order than the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (7)

A method of communicating with a user terminal and providing user-customized parliamentary minutes information performed in a server system including one or more processors and one or more memories,
Performs communication with an external server in which a plurality of parliamentary minutes according to the procedure are stored, receives one or more minutes stored in the external server, and corresponds to each of a plurality of remarks included in each of the received one or more minutes a meeting minutes refining step of refining the minutes by removing the remarks when the remarks are included in the preset first text set, and dividing the refined minutes into one or more speech units;
For each of the one or more remarks units classified for the minutes refined through the minutes refining step, one or more detailed topic information for the remark unit, type information of remarks, and remarks included in the remarks unit are not directly specified. However, a remark tagging step of tagging one or more stakeholder information and automatic attribute information related to the remark; and
When receiving service request information including a first keyword from the user terminal, one or more speech units including the first keyword are searched for among a plurality of speech units tagged through the speech tagging step, and the searched 1 A first service providing step of providing the first service information to the user terminal by clustering the information tagged in the above speech unit;
The automatic attribute information includes speaker information for the corresponding speech unit,
The first service providing step is,
the retrieved one or more utterance units; extracting one or more speakers who uttered the first keyword according to speaker information of the automatic attribute information tagged to each of the searched one or more utterance units, and information on the number of times the first keyword was uttered for each speaker; and the number information of one or more detailed topic information uttered by one or more speakers who uttered the first keyword according to speaker information and one or more detailed topic information of automatic attribute information tagged to each of the searched one or more speech units; providing first service information to the user terminal;
The type information of the remarks tagged through the remarks tagging step corresponds to any one of a question type, an answer type, and an order type,
The first service providing step is,
According to the speaker information of the automatic attribute information tagged to each of the searched one or more remarks units and the type information of the remark, the question type, answer type, and order type information for each at least one speaker who has spoken the first keyword is further included. 1 A method of providing user-customized parliamentary minutes information by providing service information to the user terminal.
delete The method according to claim 1,
The first service providing step is,
It does not include the first keyword among the plurality of remarks units tagged through the remark tagging step, but additionally searches for one or more remarks units tagged with the first keyword as stakeholder information, providing user-customized parliamentary minutes information Way.
The method according to claim 1,
The first service providing step is,
When receiving a request from the user terminal that has received the first service information for information related to a specific speech unit among the one or more searched speech units included in the first service information, it is recorded in the meeting minutes including the specific speech unit A user-customized assembly that searches for bill information corresponding to each of the one or more bill numbers with reference to one or more bill numbers written most earlier based on the specific speech unit, and provides the retrieved one or more bill information to the user terminal How to provide meeting minutes information.
The method according to claim 1,
The first service providing step is,
When receiving service request information further including a meeting period and a parliamentary meeting type from the user terminal, the first keyword among a plurality of tagged speech units for one or more minutes corresponding to the meeting period and the parliamentary meeting type A method of providing user-customizable parliamentary minutes information, retrieving one or more speaking units comprising a.
The method according to claim 1,
The method of providing the user-customized parliamentary minutes information further includes a second service providing step,
The second service providing step is,
When receiving selection input information for a specific speaker among one or more speakers who have spoken the first keyword from the user terminal receiving the first service information, social information obtained by crawling the specific speaker's SNS account and the A method of providing user-customized parliamentary minutes information for providing second service information including news information obtained by crawling news mentioned by a specific speaker to the user terminal.
A computer-readable medium for implementing a method of communicating with a user terminal and providing user-customized parliamentary minutes information performed in a server system including at least one processor and at least one memory, the computer-readable medium comprising: , storing instructions for causing the server system to perform the following steps, wherein the following steps include;
Performs communication with an external server in which a plurality of parliamentary minutes according to the procedure are stored, receives one or more minutes stored in the external server, and corresponds to each of a plurality of remarks included in each of the received one or more minutes a meeting minutes refining step of refining the minutes by removing the remarks when the remarks are included in the preset first text set, and dividing the refined minutes into one or more speech units;
For each of the one or more remarks units classified for the minutes refined through the minutes refining step, one or more detailed topic information for the remark unit, type information of remarks, and remarks included in the remarks unit are not directly specified. However, a remark tagging step of tagging one or more stakeholder information and automatic attribute information related to the remark; and
When receiving service request information including a first keyword from the user terminal, one or more speech units including the first keyword are searched for among a plurality of speech units tagged through the speech tagging step, and the searched 1 A first service providing step of providing the first service information to the user terminal by clustering the information tagged in the above speech unit;
The automatic attribute information includes speaker information for the corresponding speech unit,
The first service providing step is,
the retrieved one or more utterance units; extracting one or more speakers who uttered the first keyword according to speaker information of the automatic attribute information tagged to each of the searched one or more utterance units, and information on the number of times the first keyword was uttered for each speaker; and the number information of one or more detailed topic information uttered by one or more speakers who uttered the first keyword according to speaker information and one or more detailed topic information of automatic attribute information tagged to each of the searched one or more speech units; providing first service information to the user terminal;
The type information of the remarks tagged through the remarks tagging step corresponds to any one of a question type, an answer type, and an order type,
The first service providing step is,
According to the speaker information of the automatic attribute information tagged to each of the searched one or more remark units and the type information of the remark, the question type, answer type and order type information for each at least one speaker who spoke the first keyword is further included. 1 A computer-readable medium that provides service information to the user terminal.

Images