Device and method for providing meeting records in artificial intelligence-based chat room

JP2025028780AActive Publication Date: 2025-03-03DELTA PDS +2
View PDF 9 Cites 0 Cited by

Patent Information

Application Number
JP2024137048
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2024-07-26
Filing Date
2024-08-16
Publication Date
2025-03-03
Estimated Expiration
2044-08-16

AI Technical Summary

Benefits of technology

【0026】 本発明による人工知能ベースのチャットルーム内の議事録提供装置及び方法は、プロジェクトの進行過程で業務参加者間の会議内容を議事録に自動記録後、チャットルームを通じて共有し、業務参加者間のコミュニケーションを支援することにより、プロジェクトや業務を効果的に実行することができる。

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2025028780000001_ABST
    Figure 2025028780000001_ABST
Patent Text Reader

Abstract

To provide a device and a method for providing meeting records in an artificial intelligence-based chat room capable of effectively performing of a project and work.SOLUTION: A device for providing meeting records in an artificial intelligence-based chat room includes a memory and a processor that is electrically connected to the memory. The processor is configured to: receive from a user terminal a user's selection for a chat room in which work participants are participating; receive a conversation record file in which a conversation among the work participants related to meeting contents is recorded; generate meeting records obtained by converting the meeting contents into a text form as a result of applying an artificial intelligence model to the conversation record file according to the user's request for generating meeting records; and share the meeting records through a chat room related to the user's selection.SELECTED DRAWING: Figure 3
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to a technology for providing minutes of meetings, and more specifically, to a technology for automatically recording the contents of meetings between business participants during the progress of a project into minutes, and then sharing the minutes via a chat room, thereby supporting communication between business participants and enabling projects and business to be carried out effectively. [Background technology]

[0002] Generally, an Internet messenger corresponds to an application that transmits messages including text or graphics between users, and may be realized as a chat room in which multiple users participate. In one embodiment, the Internet messenger includes a mobile messenger executed in a mobile environment (e.g., a mobile phone), such as KakaoTalk (registered trademark), LINE (registered trademark), WeChat (registered trademark), Facebook Messenger (registered trademark), etc. There is a tendency that such Internet messengers are increasingly being used in a variety of ways in the management and progress of business.

[0003] In particular, as the scale of projects gradually increases and project structures become more complex, the number of chat rooms in which business participants simultaneously participate within a single project also increases, and business participants may find it difficult to easily grasp the flow of related work in the process of communication that is distributed and proceeding in multiple chat rooms.

[0004] For this reason, various tools have been developed to support communication between the various participants in a project. For example, meeting minutes are used to record the contents of meetings between participants, and can be shared between users to easily share the progress of a project.

[0005] However, since creating minutes and creating tasks requires additional manpower and time, there is a demand for a technique for improving work efficiency in creating minutes and creating tasks. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Korean Patent No. 10-1182535 Summary of the Invention [Problem to be solved by the invention]

[0007] The object of the present invention is to provide an AI-based device and method for providing minutes in a chat room, which can automatically record the contents of a meeting between business participants during the progress of a project, and then share them through a chat room to support communication between business participants, thereby enabling projects and tasks to be carried out effectively. [Means for solving the problem]

[0008] In order to achieve the above-mentioned object, according to one aspect of the present invention, an artificial intelligence based device for providing minutes in a chat room includes a memory and a processor electrically connected to the memory, and the processor is configured to receive a user's selection of a chat room in which business participants are participating from a user terminal, receive a dialogue recording file in which a dialogue between the business participants regarding the content of the meeting is recorded, generate minutes in which the content of the meeting is converted into a text form as a result of applying an artificial intelligence model to the dialogue recording file in response to a request for generating minutes from the user, and share the minutes via a chat room related to the user's selection.

[0009] When the processor receives a task recommendation request for the minutes from the user terminal, the processor can generate a task recommendation for the meeting content through the artificial intelligence model.

[0010] The processor may generate a recommended task list including the recommended tasks and selection options by recommended task, and add the recommended task list to the minutes or provide the recommended task list via the chat room.

[0011] The processor may generate a task related to a recommendation role when a selection of a particular business participant is input via the recommendation role selection option in the chat room.

[0012] The processor may, if multiple selection options are selected by the particular business participant, sequentially generate tasks for each of the corresponding recommendation duties.

[0013] The processor may activate the recommendation role selection option if the particular business participant has access to the minutes, and if not, may request approval from a business participant having the access to activate the recommendation role selection option.

[0014] The processor may insert the minutes into the chat room or a conference map for managing minutes depending on the location of the minutes generation request.

[0015] The processor may provide a listing of the minutes upon request of any one of the business participants in the chat room or on the conference map.

[0016] The processor can receive the dialogue between the business participants in real time, inputted in a streaming manner from each user terminal, and generate the dialogue recording file.

[0017] The processor can input the dialogue recording file into the artificial intelligence model to generate a script in which the speech of the business participants is converted into text and a summary of the script, and then generate the minutes based on at least one of the script and the summary.

[0018] The processor may display the script or the summary as a chat room dialogue message associated with the user's selection.

[0019] The processor may display an interface associated with the interactive message when the processor receives a selection of the interactive message from any one of the business participants.

[0020] The processor may provide at least one of a plurality of functions including a script view related to the dialogue message, a summary view, dialogue recording file listening, and task generation through the interface.

[0021] The processor can identify a dialogue style of each business participant in the process of recognizing the voice of the business participant, and convert the script or the summary text into a dialogue message to which the dialogue style is applied in the process of displaying the script or the summary text in the dialogue message.

[0022] The processor may selectively provide a translation function in the course of providing the minutes, the script, or the summary.

[0023] The processor may share the minutes using at least one of a number of methods including displaying a message within a chat room, attaching a file, and sharing a link.

[0024] In order to achieve the above-mentioned object, one aspect of the present invention provides an artificial intelligence based method for providing minutes in a chat room, which is executed by a minutes providing device including a memory and a processor electrically connected to the memory, and the method is executed by the processor and includes the steps of receiving a user's selection of a chat room in which business participants are participating from a user terminal, receiving a dialogue recording file in which a dialogue between the business participants regarding the content of the meeting is recorded, generating minutes in which the content of the meeting is converted into a text form as a result of applying an artificial intelligence model to the dialogue recording file in accordance with the user's request to generate minutes, and sharing the minutes via a chat room related to the user's selection. Effect of the Invention

[0025] The present invention has the following effects. However, this does not mean that a specific embodiment should include all of the following effects or should include only the following effects, and the technical scope of the present invention should not be understood to be limited thereby.

[0026] The AI-based chat room minutes providing device and method according to the present invention automatically records meeting contents between business participants in the course of a project into minutes and shares them through a chat room, thereby supporting communication between business participants and enabling projects and tasks to be carried out effectively. [Brief description of the drawings]

[0027] [Figure 1] FIG. 1 is a diagram illustrating a minutes providing system according to the present invention. [Diagram 2] 2 is a diagram illustrating a system configuration of the minutes providing device of FIG. 1. [Diagram 3] 3 is a diagram illustrating a functional configuration of the processor in FIG. 2. [Figure 4] 2 is a flow chart illustrating an artificial intelligence based method for providing minutes in a chat room according to the present invention. [Diagram 5]FIG. 1 is a diagram illustrating an embodiment of minutes according to the present invention. [Figure 6] 2 is a diagram illustrating an embodiment of a dialogue message generation process according to the present invention; FIG. [Figure 7] 1 is a diagram illustrating an embodiment of a process for providing related functions in a chat room according to the present invention; [Figure 8] FIG. 2 is a diagram illustrating an embodiment of a task generation process according to the present invention. [Figure 9] FIG. 1 is a diagram illustrating an embodiment of a task modification process according to the present invention. [Figure 10] 1 is a diagram illustrating a general meeting minutes and a task minutes according to the present invention. FIG. [Figure 11] 1 is a diagram illustrating an embodiment of a recommended task list update process according to the present invention; [Figure 12A] 1A-1C are diagrams illustrating various embodiments of a minutes sharing process in a chat room according to the present invention. [Figure 12B] 1A-1C are diagrams illustrating various embodiments of a minutes sharing process in a chat room according to the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0028] The description of the present invention is merely an embodiment for structural or functional description, and therefore the technical scope of the present invention should not be interpreted as being limited by the embodiment described in the present specification. In other words, since the embodiment can be modified in various ways and can have various forms, the technical scope of the present invention should be understood to include equivalents that can realize the technical idea. In addition, the objectives or effects presented in the present invention do not mean that a specific embodiment should include all of them or should include only such effects, and therefore the technical scope of the present invention should not be understood as being limited thereby.

[0029] Meanwhile, the meanings of the terms used in this specification should be understood as follows.

[0030] The terms "first", "second", etc. are used to distinguish one component from another component, and should not be used to limit the scope of the technology. For example, the first component may be called the second component, and similarly, the second component may be called the first component.

[0031] When an element is said to be "connected" to another element, it should be understood that it may be directly connected to the other element, but there may be other elements in between. In contrast, when an element is said to be "directly connected" to another element, it should be understood that there are no other elements in between. However, other expressions describing the relationship between elements, such as "between" and "directly between," or "adjacent to" and "directly adjacent to," should be interpreted in the same way.

[0032] Singular expressions should be understood to include plural expressions unless the context clearly indicates otherwise, and terms such as "comprise" or "have" are intended to specify the presence of embodied features, numerals, steps, operations, components, parts, or combinations thereof, but do not preclude the presence or additional possibility of one or more other features, numerals, steps, operations, components, parts, or combinations thereof.

[0033] The identifiers (e.g., a, b, c, etc.) in each step are used for convenience of description, and the identifiers do not describe the order of each step, and each step may occur in a different order than specified unless the context clearly dictates a specific order. That is, each step may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.

[0034] The present invention is embodied by computer readable code stored in a computer readable recording medium, which includes all kinds of recording devices in which data readable by a computer system is stored. Examples of computer readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. Also, the computer readable recording media may be distributed among computer systems connected via a network, so that the computer readable code may be stored and executed in a distributed manner.

[0035] All terms used herein, unless otherwise defined, have the same meaning as commonly understood by a person of ordinary skill in the art to which the present invention belongs. Terms commonly used and defined in advance should be interpreted as being consistent with the meaning they have in the context of the relevant art, and should not be interpreted as having an ideal or overly formal meaning unless expressly defined herein.

[0036] FIG. 1 is a diagram illustrating a minutes providing system according to the present invention.

[0037] Referring to FIG. 1, a minutes providing system 100 includes a plurality of user terminals 110, a minutes providing device 130, and a database 150.

[0038] The user terminal 110 corresponds to a computing device operated by a user. For example, the user terminal 110 may be realized as a desktop PC, a notebook PC, a tablet PC, or a smartphone, but is not limited thereto, and may be realized as various devices.

[0039] There may be one or more user terminals 110, and in this case, the user terminal may be any one or more of a first user terminal 110a, a second user terminal 110b, and a third user terminal 110c. For convenience, the user terminal 110 used by the first user is referred to as the first user terminal 110a, the user terminal 110 used by the second user is referred to as the second user terminal 110b, the user terminal 110 used by the third user is referred to as the third user terminal 110c, etc.

[0040] In an embodiment of the present invention, multiple users are included in one or more user groups, which are referred to as a first user group, a second user group, a third user group, etc. Meanwhile, one user may be included in one or more user groups at the same time.

[0041] Furthermore, the multiple users correspond to business participants who participate in a joint project or business. For example, business participants include a business director who instructs the business, a business executor who executes the business, and business associates related to the business.

[0042] In this case, there is one whole project, which can include multiple business projects that proceed independently. In addition, plans, cards, notes, tasks, etc. are created and stored in relation to the whole project or the business projects.

[0043] Here, a plan corresponds to a business plan established to achieve a specific goal, a card corresponds to a management card for a series of tasks, a note corresponds to a business record that stores content related to the tasks, and a task corresponds to various unit tasks that are created and processed according to a plan, card, or note.

[0044] Furthermore, in the process of processing a plan, a card, a note, or a task, objects such as messages, files, and photos (or images) can be shared between users, and a chat room can be provided for users to have a conversation and share objects. In this case, messages shared through the chat room can include conversation messages related to daily content and business messages related to business content.

[0045] In one embodiment, at least one of the user terminals 110 is a mobile terminal and is connected to the minutes providing apparatus 130 via cellular communication or Wi-Fi communication. In another embodiment, at least one of the user terminals 110 is a desktop PC and is connected to the minutes providing apparatus 130 via the Internet.

[0046] The minutes providing device 130 corresponds to a computing device connected to at least one user terminal 110 via a network. In one embodiment, the minutes providing device 130 can manage at least one user group in which other users associated with one user are included as members, i.e., business participants.

[0047] In one embodiment, the minutes providing device 130 is connected to the user terminal 110 via a dedicated agent installed in the user terminal 110. Here, the dedicated agent corresponds to an agent program, which is software that can link the user terminal 110 and the minutes providing device 130 with each other under the approval of the user terminal 110 when installed in the user terminal 110.

[0048] Meanwhile, the connection and coupling between the minutes providing device 130 and the user terminal 110 described here corresponds to one embodiment and can be modified and applied in various forms within normal limits depending on various operating and implementation environments.

[0049] The database 150 corresponds to a storage device that stores various information required in the operation process of the meeting minutes providing device 130. For example, the database 150 may store, but is not limited to, a dialogue recording file that records the contents of a meeting, a voice file that records a user's voice, or text information converted through voice recognition. The meeting minutes providing device 130 may store information collected or processed in various forms in the process of performing the AI-based task recommendation method according to the present invention.

[0050] Furthermore, in FIG. 1, the database 150 is shown as a logical storage device included in the minutes providing device 130, but is not necessarily limited to this and can be realized as a device independent of the minutes providing device 130.

[0051] FIG. 2 is a diagram for explaining the system configuration of the minutes providing device of FIG.

[0052] Referring to FIG. 2, the minutes providing device 130 includes a processor 210, a memory 230, a user input / output unit 250, and a network input / output unit 270.

[0053] The processor 210 executes the artificial intelligence based chat room minutes provision procedure of the present invention, manages the memory 230 that is read or written in such process, and schedules synchronization times between the volatile and non-volatile memories in the memory 230.

[0054] The processor 210 controls the overall operation of the minutes providing device 130, and is electrically connected to the memory 230, the user input / output unit 250, and the network input / output unit 270 to control the data flow among them. The processor 210 is realized by a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit) of the minutes providing device 130.

[0055] The memory 230 includes a secondary storage device implemented as a non-volatile memory such as a solid state disk (SSD) or a hard disk drive (HDD) used to store all data required for the minutes providing device 130, and a primary storage device implemented as a volatile memory such as a random access memory (RAM). Thus, the memory 230 may be implemented as both a volatile and non-volatile memory, and if implemented as a non-volatile memory, it may be implemented to be connected via a hyperlink.

[0056] The user input / output unit 250 includes an environment for receiving user input and an environment for outputting specific information to a user, and includes, for example, an input device including or connected to an adapter such as a mouse, trackball, touchpad, graphic tablet, scanner, touch screen, keyboard, or pointing device, and an output device including an adapter such as a monitor or touch screen. In one embodiment, the user input / output unit 250 corresponds to a computing device connected via a remote connection, in which case the minutes providing device 130 acts as a server.

[0057] The network input / output unit 270 provides a communication environment for connecting to the user terminal 110 via a network, and includes, for example, adapters for communication such as a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), and a value added network (VAN). In addition, the network input / output unit 270 is realized to provide a short-range communication function such as WiFi (registered trademark) or Bluetooth (registered trademark) for wireless data transmission, or a wireless communication function of 4G or higher.

[0058] FIG. 3 is a diagram illustrating the functional configuration of the processor in FIG.

[0059] 3, the minutes providing device 130 executes the AI-based minutes providing method in a chat room according to the present invention through the processor 210. To this end, the processor 210 includes a data receiving unit 310, a minutes generating unit 330, a task recommending unit 350, a task managing unit 370, and a control unit (not shown in FIG. 3).

[0060] In this case, the embodiment of the present invention does not include all of the above functional configurations at the same time, but may be realized by omitting some of the above configurations or selectively including some or all of the above configurations according to each embodiment. Furthermore, one embodiment of the present invention is realized as an independent module selectively including some of the above configurations, and the AI-based chat room minutes providing method according to the present invention is performed through the interworking between each module. The operation of each configuration will be described in detail below.

[0061] The data receiving unit 310 receives a user's selection of a chat room in which a business participant is participating from the user terminal 110. That is, the user checks a list of chat rooms in which the user is participating on the user terminal 110 and selects a specific chat room from the list. Here, a chat room corresponds to a virtual conversation space for a group of users who communicate in real time. For example, a chat room is realized through a messenger program. A plurality of users can simultaneously participate in a chat room, and participants can share text, voice, images, videos, files, etc. in the chat room in real time. Furthermore, a chat room is configured around a specific subject, and for convenience of explanation, it is assumed here that business participants who are working on the same project participate in the chat room.

[0062] Also, the data receiving unit 310 operates in conjunction with the user terminal 110 and receives the user's selection through a dedicated agent executed on the user terminal 110. The user can check or inquire on the user terminal 110 about a list of chat rooms in which business participants are participating, and can select a specific chat room. As a result, an input signal corresponding to the user's selection action is generated on the user terminal 110, and the input signal is transmitted from the user terminal 110 to the data receiving unit 310. In this case, the input signal includes user identification information (e.g., a user ID) and chat room identification information (e.g., a chat room ID), etc.

[0063] The data receiving unit 310 also receives a dialogue recording file in which dialogue between business participants regarding the contents of the conference is recorded. Here, the dialogue recording file corresponds to a file in which dialogue voice between business participants is recorded. At this time, the dialogue between business participants is recorded using a recording function included in the user terminal 110. That is, the data receiving unit 310 may generate and store a dialogue recording file after receiving dialogue voice from the user terminal 110, or may directly receive a dialogue recording file generated on the user terminal 110. Also, the data receiving unit 310 may provide an interface for inputting the dialogue recording file via the user terminal 110, and the interface may be realized via a dedicated agent operating on the user terminal 110.

[0064] In one embodiment, the data receiving unit 310 receives a search key including a keyword from the user terminal 110, and determines that a user's selection has been input for one of the chat rooms searched based on the search key. That is, the user can basically select a corresponding chat room from among the chat rooms in which the user is participating, and can specify and select a chat room in various ways from outside the chat rooms as necessary. In addition, when a user is participating in multiple chat rooms, the user can input a keyword associated with the chat room, and the data receiving unit 310 searches for a chat room related to the user based on the keyword input by the user. For example, the keyword includes a user's name, ID, or a word related to the business content. When one chat room is searched, the data receiving unit 310 determines that a user's selection has been input for the corresponding chat room, and when multiple chat rooms are searched, the data receiving unit 310 selects some of the multiple chat rooms and determines that a user's selection has been input.

[0065] In one embodiment, the data receiving unit 310 may receive in real time the dialogue between the business participants inputted in a streaming manner from each user terminal 110 to generate a dialogue recording file. The data receiving unit 310 may receive in real time the dialogue voice between the business participants in a streaming manner in conjunction with each user terminal 110 participating in the dialogue to generate a dialogue recording file in a voice data format such as WAV or MP3. In this case, the business participants participating in the dialogue may input their individual voices using a dialogue or recording function in the chat room while participating in the same chat room, and may input the dialogue contents in real time using an independent dialogue channel (e.g., video image conference, etc.) outside the chat room as necessary. In addition, the data receiving unit 310 may compress the voice data received in real time to save storage space for the dialogue recording file, and may determine the compression method in consideration of the network state, etc.

[0066] In one embodiment, the data receiving unit 310 receives a user's voice file recorded on the user terminal 110. At this time, the user's voice file corresponds to one of various forms of the dialogue recording file. That is, the user's voice file corresponds to a case where one business participant is recorded in the dialogue recording file. Therefore, the following description of the dialogue recording file can be similarly applied to the user's voice file to the extent possible. The data receiving unit 310 receives the voice file transmitted from the user terminal 110 and stores it in the database 150. A user can directly record his / her voice through a user terminal 110 equipped with a voice recording function such as a smartphone, tablet, or PC to generate a voice file, or can select one of various voice files stored in the user terminal 110 and transmit the corresponding voice file.

[0067] The minutes generating unit 330 generates minutes in which the contents of the meeting are converted into text form as a result of applying an artificial intelligence model to the dialogue recording file in response to a user's request to generate minutes. Here, the request to generate minutes corresponds to a user request regarding the generation of minutes. The user request corresponds to a command or information that the user requests the system to execute regarding the minutes, and is input by a user (e.g., a business participant) on the user terminal 110. For example, the user request includes a request to generate minutes, a request to view minutes, a request to remove minutes, a request to correct minutes, etc. The minutes generating unit 330 receives and interprets the user request input from the user terminal 110, and then supports the execution of a series of operations related to various requests including the generation of minutes.

[0068] Furthermore, the minutes correspond to a business record that records the contents of a meeting discussed during a meeting between business participants, and correspond to a type of note that is generated in relation to an entire project or a business project. Therefore, the minutes are generated including at least the meeting contents converted into text form. At this time, the minutes are manually generated by business participants who attended the meeting, or are automatically generated by artificial intelligence based on a file that records the meeting contents, and the generated minutes are stored and managed in the database 150. Also, the minutes generating unit 330 operates in conjunction with an independent module for generating minutes. That is, the minutes generating unit 330 calls the minutes generating module to start the minutes generating operation.

[0069] More specifically, the minutes generating unit 330 converts the dialogue recording file into text to generate dialogue text related to the contents of the meeting, and then generates minutes including a summary of the dialogue text and a selection option for each recommended task. The minutes generating unit 330 recognizes the dialogue voices of the business participants from the dialogue recording file using a STT (Speech-To-Text) algorithm or a voice recognition model, identifies the dialogue contents of each business participant from the dialogue voices, and generates dialogue text as the dialogue text. At this time, the dialogue text corresponds to a text file (or document) generated by converting the dialogue contents recorded during the meeting between the business participants into text, and is generated via an external STT (Speech-To-Text) server as necessary.

[0070] Furthermore, the dialogue text is used as input data for the text summarization model, and the text summarization model generates a summary sentence summarizing the dialogue text as an output. Here, the text summarization model corresponds to a language model that receives a text or a text file as an input and generates a summary sentence summarizing the corresponding text or text file. Furthermore, the text summarization model may be designed to generate a summary sentence regarding the conference content while also generating a recommendation task related to the conference content.

[0071] For example, a text summarization model is realized as ChatGPT. ChatGPT is a conversational AI chatbot that is a super-large language model. In particular, GPT is an abbreviation for "Generative Pre-trained Transformer," and corresponds to a generative AI that pre-trains a huge amount of data through machine learning and generates sentences. In this case, the text summarization model can selectively generate at least one of a summary sentence and a recommendation task by setting the input and output data format and structure.

[0072] In one embodiment, the minutes generating unit 330 may insert the minutes into a chat room or a conference map for managing minutes according to the position of the minutes generation request. Here, the conference map corresponds to a dedicated management tool for managing minutes. Also, when the minutes are generated and inserted into the chat room in response to the minutes generation request, a message regarding the minutes generation is shared through the chat room, and the business participants can directly select the message to access the minutes or download the minutes file. Also, when the minutes are generated and inserted into the conference map in response to the minutes generation request, various functions such as inquiry, modification, and deletion of the minutes are performed through a dedicated interface provided on the conference map. Meanwhile, the minutes inserted into the conference map or chat room are stored and managed through an independent memory area associated with the conference map or chat room.

[0073] In one embodiment, the minutes generating unit 330 may generate and provide a minutes list according to a request for inquiry from any one of the business participants on a chat room in which the business participants participate or on a conference map for managing minutes. The minutes generating unit 330 provides an interface through which a request for inquiry of minutes can be input for each position where the minutes can be inquired, and the interface is realized through an application running on the user terminal 110. For example, a business participant may activate a minutes inquiry function through a menu in a chat room, or may activate the minutes inquiry function through a dedicated interface provided on the conference map.

[0074] In addition, when minutes are viewed in a chat room in response to a request to view minutes, a minutes list generated as a result of the view is shared through the chat room, and business participants can directly select a particular minute from the minutes list to access the minute or download the minute file. In this case, the minutes list is displayed in the chat room in the form of a message, and is displayed independently through a separate interface on the conference map. The minutes list provided in the form of a list is sorted and displayed according to the time when the minutes were created, and can be sorted according to various criteria other than time.

[0075] In addition, when minutes are viewed on the conference map in response to a minutes view request, various functions such as confirmation, modification, and deletion of each minutes can be performed along with the minutes list through a dedicated interface. Meanwhile, the minutes list viewed in the conference map or chat room is temporarily generated, shared, and then deleted, and is selectively stored and managed through an independent memory area associated with the conference map or chat room as necessary.

[0076] In one embodiment, the minutes generating unit 330 may generate an independent inquiry result for each type of minutes. For example, the minutes generating unit 330 may generate an inquiry result by classifying general minutes and task minutes in response to a minutes inquiry request, in which case, a minutes list for general minutes and task minutes is generated independently. Here, the general minutes correspond to minutes that record regular meeting contents, and the task minutes correspond to minutes that are generated including one or more recommended tasks in addition to regular meeting contents.

[0077] In one embodiment, the minutes generating unit 330 inputs the dialogue recording file into an artificial intelligence model, generates a script in which the voices of the business participants are converted into text and a summary of the script, and generates minutes based on at least one of the script and the summary. That is, the script corresponds to the result of converting the dialogue contents of the business participants stored in the dialogue recording file into text, and the summary corresponds to the result of briefly summarizing the main contents of the script.

[0078] Here, the artificial intelligence model corresponds to a model constructed to receive a dialogue recording file as an input and generate an output in the form of text. For example, the artificial intelligence model is realized by including a voice recognition model that recognizes the voice of the dialogue recording file and outputs a script in the form of text, and a text summarization model that summarizes the text of the script and generates a summary. That is, the artificial intelligence model is realized in a structure in which a voice recognition model and a text summarization model are connected to each other, and at least one of the script and the summary can be selectively output through the output of each model.

[0079] In one embodiment, the artificial intelligence model is trained and constructed to receive a dialogue recording file as an input and generate at least one of a script and a summary sentence as an output. For example, the artificial intelligence model may be constructed as a first model that receives a dialogue recording file as an input and generates a script as an output. The artificial intelligence model may be constructed as a second model that receives a dialogue recording file as an input and generates a summary sentence as an output. The artificial intelligence model may be constructed as a third model that receives a dialogue recording file as an input and generates a script and a summary sentence as an output, respectively. Furthermore, the artificial intelligence model may be constructed to support various forms of input and output.

[0080] In one embodiment, the minutes generating unit 330 may share the minutes through a chat room related to the user's selection. The minutes may include information such as the title of the meeting, the date and time of the meeting, a list of participants, a summary of the meeting by topic, the contents of the meeting, decisions, and a list of tasks (to-dos). The minutes generating unit 330 may provide some of the information included in the minutes through the chat room, and may selectively provide information requested by the user. In addition, the minutes generating unit 330 may share the minutes in the chat room through various methods, and may transmit a notification message to the user if an error occurs during the sharing process.

[0081] In one embodiment, the minutes generating unit 330 can share the minutes in a chat room using at least one of a number of methods including message display, file attachment, and link sharing. For example, in the case of the message display method, the contents of the minutes are inserted and displayed in the chat room as a text message. In the case of the file attachment method, the minutes file is shared in the chat room as an attachment, and users participating in the chat room can download the attachment. In the case of the link sharing method, a link of a server (e.g., a cloud server, etc.) that can access the minutes is displayed and shared in the chat room, and users participating in the chat room can access the minutes via the link.

[0082] In one embodiment, the minutes generating unit 330 may display the script or summary as a dialogue message in a chat room related to the user's selection. At this time, other users participating in the chat room may recognize the dialogue message as a message input by the user. That is, the dialogue subject of the dialogue message is the user who requested the creation or sharing of the minutes. For example, when a business participant A participating in the chat room requests the creation of minutes, the script or summary associated with the created minutes is displayed in the chat room as a dialogue message of the business participant A. The minutes generating unit 330 may basically convert the text of the script or summary into a dialogue message form to share in the chat room, and may display an image or video related to the contents of the script or summary together with the dialogue message as necessary.

[0083] In one embodiment, when the minutes generator 330 receives a selection of a conversation message from any one of the business participants, it displays an interface related to the conversation message. That is, each user participating in the chat room can directly select a shared conversation message, and when the minutes generator 330 detects a selection of each user for each conversation message, it can provide a function related to the conversation message through a separate interface. In this case, the corresponding interface basically includes basic functions such as copying, removing, and sharing a message.

[0084] In one embodiment, the minutes generating unit 330 may provide at least one of a plurality of functions including a script view, a summary view, a dialogue recording file listening, and a task generation associated with the dialogue message through the interface. That is, when the dialogue message corresponds to a script or a summary generated from a dialogue recording file, the minutes generating unit 330 additionally provides a function related to the script or the summary through the interface. The script view function corresponds to a function of providing detailed contents of a script related to the corresponding summary, and the summary view function corresponds to a function of providing detailed contents of a summary related to the corresponding script. In addition, the dialogue recording file listening function corresponds to a function of playing a dialogue recording file associated with the corresponding script or summary, and the task generation function corresponds to a function of generating one or more recommended tasks (or tasks) associated with the corresponding script or summary. A user can select a specific function on the interface to perform an operation for the function.

[0085] In one embodiment, the minutes generating unit 330 identifies the dialogue style of each business participant in the process of recognizing the voice of the business participant, and converts the dialogue style into a dialogue message in the process of displaying a script or summary as a dialogue message. Here, the dialogue style corresponds to the linguistic features of each user used in a voice dialogue situation, and represents the speaker's emotions, intentions, relationships, etc. The dialogue style is determined by features such as words and expressions used (e.g., casual speech, honorific language, etc.), sentence structure and rules, pronunciation, speed, and accent. The minutes generating unit 330 extracts feature information such as vocabulary, grammar, and voice from the text in the process of converting the voice signal into text during voice recognition of the dialogue recording file, and identifies each user participating in the dialogue and the dialogue style based on the extracted feature information. The process of identifying the dialogue style is performed through a process of classifying various feature information and determining each user and the dialogue style that matches the classification result.

[0086] In addition, the minutes generating unit 330 converts the script or summary into a dialogue message expressed in one of the identified dialogue speaking styles in the process of displaying the script or summary as a dialogue message in the chat room. For example, if one of the dialogue speaking styles identified in the dialogue process is a "friendly and comfortable tone," the minutes generating unit 330 converts the script or summary according to the dialogue speaking style to generate a dialogue message in a comfortable speaking style that allows a user to talk to friends in a friendly atmosphere. In this case, the minutes generating unit 330 receives at least one of the script and summary and the dialogue speaking style as input, and performs a dialogue message conversion operation using a speaking style conversion model trained to generate a dialogue message expressed in the dialogue speaking style as an output.

[0087] Meanwhile, the minutes generating unit 330 can selectively apply a specific dialogue style to the already generated script and summary to regenerate them, and if the style of speech of the script and the summary differ, it can compare the corresponding styles as necessary and automatically or selectively convert the script and summary to a specific style to make them consistent.

[0088] In one embodiment, the minutes generating unit 330 generates and provides a plurality of dialogue messages to which various dialogue speaking styles are applied in the process of displaying the script or summary sentence as a dialogue message, and displays a dialogue message selected by a user from the plurality of dialogue messages through a chat room. The minutes generating unit 330 generates a plurality of dialogue messages to which each dialogue speaking style is applied using a speaking style conversion model. The minutes generating unit 330 provides a plurality of dialogue messages to a user through separate interfaces on the user terminal 110, and the user can select a particular dialogue message to be displayed in the chat room.

[0089] In one embodiment, the minutes generating unit 330 may update and display at least one of the dialogue messages displayed in the chat room in a dialogue style set by the user. The user may select a dialogue message already displayed in the chat room and apply a specific dialogue style to it, and when the dialogue style is changed by the user, the minutes generating unit 330 converts the dialogue message into the changed dialogue style and then updates and displays the existing dialogue message. At this time, the user may apply a specific dialogue style to one or more dialogue messages so that the dialogue messages are updated and displayed at the same time. The user may also select only dialogue messages entered at a specific time from among the dialogue messages displayed in the chat room and apply a specific dialogue style to them.

[0090] In one embodiment, the minutes generating unit 330 may selectively provide a translation function in the process of providing the minutes, script, or summary. The minutes generating unit 330 provides detailed content through a detail page of the minutes, script, or summary, and provides a separate and independent interface for the detail page. That is, the minutes generating unit 330 provides a message translation function as one of various functions in an independent interface provided through a chat room. For this purpose, the interface is realized to operate in conjunction with a translation engine. A user can receive translation content of the minutes, script, or summary in the chat room by selecting the message translation function. In addition, the minutes generating unit 330 may provide each message displayed in the chat room together with its translation content through the interface, and replace a specific message with the translation content and display it.

[0091] When the task recommendation unit 350 receives a task recommendation request related to the minutes from the user terminal 110, it generates a recommended task related to the meeting contents through an AI model. Here, the task recommendation request corresponds to a user request for one or more task recommendations related to the meeting contents. In this case, the AI ​​model for task recommendation corresponds to an AI model used in the process of generating the minutes from the dialogue recording file. That is, the AI ​​model outputs the meeting contents in text form during the process of generating the minutes, and also outputs the recommended tasks related to the meeting contents.

[0092] The task recommendation unit 350 also generates the recommended tasks through a separate task recommendation model. Here, the task recommendation model is realized as a deep learning model that receives text related to the meeting content as an input and generates a recommended task as an output, but is not necessarily limited thereto. The task recommendation model is also constructed in conjunction with a task table that stores the recommended tasks, and in this case, the task recommendation model generates index information of the table as recommended task information. That is, the task recommendation unit 350 queries the task table based on the index information output by the task recommendation model to generate the recommended task.

[0093] In one embodiment, the task recommendation unit 350 generates a recommended task list including recommended tasks and selection options for each recommended task, and adds the recommended task list to the minutes or provides the recommended task list through a chat room. Here, the selection options correspond to functions that are activated according to a user's selection for each of one or more recommended tasks. For example, the selection options are implemented as checkboxes, etc. That is, the recommended task list corresponds to a list of recommended tasks and is expressed as a set of pairs between the recommended tasks and the selection options. That is, the user can individually select a recommended task through each selection option on the recommended task list. The task recommendation unit 350 generates a recommended task list in response to a task recommendation request and provides it to the user terminal 110, and the recommended task list is displayed through a dedicated interface or chat room implemented on the user terminal 110.

[0094] In one embodiment, the task recommendation unit 350 activates the recommended task selection option if a specific business participant has access rights to the minutes, and if not, requests approval for activating the recommended task selection option from the business participant with access rights. Basically, the business participants who attended the meeting are given access rights to the minutes, and when the task recommendation unit 350 receives a task recommendation request, it activates the recommended task selection option only for the business participants who have normal access rights according to the authority inquiry result of the business participant.

[0095] If a business participant without access rights requests a recommended task, the task recommendation unit 350 provides a recommended task list with the selection option of the recommended task inactivated. Also, the task recommendation unit 350 requests approval for activation of the selection option from a business participant with access rights to the minutes, and provides a recommended task list with the selection option activated according to the approval of the business participant.

[0096] In one embodiment, the task recommendation unit 350 adds a recommended task list to a specific meeting minutes corresponding to a general meeting minutes, and converts the specific meeting minutes into a task minutes. Here, the general meeting minutes correspond to meeting minutes that do not include a recommended task, and the task minutes correspond to meeting minutes that include a recommended task. That is, the meeting minutes are basically generated in the state of a general meeting minutes, and when a recommended task is generated in response to a task recommendation request from a business participant, the recommended task is generated and managed as an object separate from the meeting minutes. At this time, the task recommendation unit 350 adds the generated recommended task list to the meeting minutes as necessary, and as a result of adding the recommended task list to the meeting minutes, the general meeting minutes are converted into task minutes. The task recommendation unit 350 performs an operation of converting the general meeting minutes into task minutes when it receives a request from a business participant or when a preset condition is met.

[0097] In one embodiment, the task recommendation unit 350 removes a specific recommended task from the recommended task list when a task is generated for a specific recommended task included in the task minutes. For example, when recommended tasks a and b are included in the minutes A, if a task for recommended task b is generated by a business participant, recommended task b is removed from the minutes A. Thereafter, when the minutes A is referenced, only recommended task a is referenced together with the minutes A. Meanwhile, even if a task related to the task minutes is generated, the task recommendation unit 350 maintains the recommended task as it is. In other words, in the above example, even if a task for recommended task b is generated, the minutes A is still maintained in a state in which recommended tasks a and b are included, and recommended tasks a and b are also referenced when the minutes A is referenced.

[0098] In one embodiment, the task recommendation unit 350 recommendation converts the task minutes into general minutes when all recommended tasks are removed from the recommended task list. For example, when recommended tasks a and b are included in the minutes A, when a task for recommended task b is generated by a business participant, recommended task b is removed from the minutes A. Thereafter, when a task for recommended task a is generated by a business participant, recommended task a is removed from the minutes A, and as a result of removing all recommended tasks included in the recommended task list, the task minutes are converted into general minutes.

[0099] When a selection of a particular business participant is inputted through a selection option for each recommendation task in the chat room, the task management unit 370 generates a task related to the recommendation task. A business participant participating in the chat room can request the generation of a task related to a recommendation task by selecting an active selection option from a recommendation task list provided through an interface. The task management unit 370 starts a task generation operation related to the recommendation task for which the selection of the business participant is inputted through the selection option.

[0100] In one embodiment, the task management unit 370 sets a specific business participant as a task instructor of a task, and sets the corresponding recommended duties as the task contents of the task. A task is generated including various business-related items. For example, a task is generated including a task instructor who generated the task, task contents, etc. The task management unit 370 automatically sets the business participant who requested the generation of the task as the task instructor, and automatically sets the corresponding recommended duties as the task contents.

[0101] In one embodiment, when multiple selection options are selected by a specific business participant, the task management unit 370 sequentially generates tasks related to each of the corresponding recommendation tasks. When multiple recommendation tasks exist in one minutes, the task generator selects a selection option for each recommendation task to generate a task for each recommendation task. In this case, the corresponding tasks are generated sequentially according to the selection order of the task generator for the selection options. In addition to the recommendation tasks, the task management unit 370 also receives input of task contents directly from the task generator and generates tasks, thereby sequentially generating multiple tasks related to one minutes.

[0102] In one embodiment, the task manager 370 inserts a task into a chat room, into a task tab associated with the chat room, or into a task tab associated with the minutes if the minutes are generated in the chat room. The task manager 370 generates and inserts a task in various locations, and the location of the task generation and insertion is determined depending on the location of the minutes, among other things. For example, if the minutes are generated in a chat room, a task related to the recommendation of the minutes is generated and inserted in the same chat room. If a task is inserted in a chat room, a notification of the task generation and insertion is provided via a chat room message.

[0103] As another example, a task generated in a chat room is inserted into a task tab related to the chat room. Here, the task tab corresponds to a dedicated management tool for independently managing tasks, and when associated with a specific chat room, it is used to independently manage only tasks generated in the chat room. As another example, a task generated for a recommendation of a specific meeting is inserted into a task tab related to the specific meeting. When a task tab is linked to a specific meeting, it is used to independently manage only tasks generated in association with the specific meeting. Thus, depending on the location where the task is inserted after it is generated, the task is queried via the location, i.e., the chat room, the chat room associated task tab, or the meeting associated task tab.

[0104] In one embodiment, the task manager 370 inserts a task into a task tab associated with a conference map when minutes are generated in the conference map, inserts a task into a task tab related to the minutes, or inserts a chat room associated with the minutes after the chat room is generated. The task manager 370 generates and inserts a task in the conference map, which determines the location of task generation and insertion. For example, a task when minutes are generated in a conference map is inserted into a task tab associated with the conference map. When a task tab is linked to a particular conference map, it is used to independently manage only tasks generated in the conference map.

[0105] In another example, a task generated for a recommendation of a particular meeting minutes is inserted into the task tab associated with the particular meeting minutes, and if there is no chat room associated with the particular meeting minutes, the task is inserted directly into the chat room after the chat room is created. When a task is inserted into a chat room, a notification of the task generation and insertion is provided through a chat room message. In this case, a business participant can select the chat room message to go to the conference map where the task was generated or to access the particular meeting minutes.

[0106] The control unit (not shown in FIG. 3) controls the overall operation of the minutes providing device 130 and manages the control flow or data flow between the data receiving unit 310, the minutes generating unit 330, the task recommending unit 350, and the task managing unit 370.

[0107] FIG. 4 is a flow chart illustrating an artificial intelligence based method for providing minutes in a chat room according to the present invention.

[0108] 4, the minutes providing device 130 receives a user selection for a chat room in which the business participants are participating from the user terminal 110 via the processor 210 (step S410). The minutes providing device 130 receives a dialogue recording file in which dialogue between the business participants regarding the contents of the meeting is recorded via the processor 210 (step S430).

[0109] In addition, the minutes providing device 130 generates minutes in which the contents of the meeting are converted into a text format as a result of applying an artificial intelligence model to the dialogue recording file in response to a user's request to generate minutes via the processor 210 (step S450). The minutes providing device 130 shares the minutes via a chat room related to the user's selection via the processor 210 (step S470).

[0110] FIG. 5 is a diagram for explaining an embodiment of the minutes of a meeting according to the present invention.

[0111] 5, the minutes providing device 130 queries and provides minutes 510 that record meeting contents 550 between business participants in response to a minutes query request. At this time, the minutes 510 are manually generated by the business participants or automatically generated by an artificial intelligence model.

[0112] In one embodiment, the minutes 510 are generated including meeting contents 550 automatically summarized by the AI ​​model and recommended tasks 560 recommended by the AI ​​model, and may include various items, as shown in Fig. 5. For example, the minutes 510 may include a generator 520, a meeting date and time 530, a storage location 540, meeting contents 550, recommended tasks 560, etc.

[0113] The creator 520 corresponds to the user who created the minutes, and corresponds to any one of the business participants who attended the meeting. The creator information is automatically determined in response to a request to create minutes. The meeting date and time 530 includes the date, day of the week, time, etc., when the meeting was held, and is automatically determined based on the time of the request to create minutes.

[0114] Also, the storage location 540 corresponds to a location where the minutes 510 are generated and stored. For example, the storage location 540 corresponds to information on a space (e.g., a folder name, etc.) where the actual minutes are stored in the user terminal 110 or the minutes providing device 130, and in some cases, is represented by link information that allows access to the minutes 510.

[0115] In addition, the meeting contents 550 corresponds to a summary of the meeting contents automatically summarized by the AI ​​model, and corresponds to text information generated through voice recognition from a dialogue recording file that records the meeting contents. The recommended tasks 560 corresponds to task information automatically recommended by the AI ​​model, and includes task information related to the meeting contents. The recommended tasks 560 are generated including one or more detailed tasks 570 and selection options 580. The detailed tasks 570 express the task title, task purpose, etc. in simple text. The selection options 580 are generated independently for each detailed task 570, and are realized in various ways such as a checkbox, a radio button, etc.

[0116] In addition, the minutes 510 may include the name of the meeting, information on the meeting participants, etc., and include various minutes menus. For example, the minutes menu may include a task generation reservation menu, a shared link generation menu, and an upload menu for files, images, videos, etc. In this case, the minutes menu is provided together with the minutes when the minutes are referenced after the minutes are generated.

[0117] The task creation reservation menu corresponds to a function that allows a business participant with access rights to reserve task creation based on a specific point in time after the minutes are generated. In other words, when task creation is reserved for time A, a notification or reminder for task creation is provided to the business participant who made the reservation at time A. The shared link creation menu corresponds to a function that generates a shared link that allows direct access to the minutes from outside as a link for sharing the minutes. The upload menu corresponds to a function that allows files and images related to the meeting contents to be added to the minutes after they are generated.

[0118] FIG. 6 is a diagram illustrating an embodiment of a process for generating a dialogue message according to the present invention.

[0119] Referring to FIG. 6, in response to a user's request to generate minutes, the minutes providing device 130 inputs a dialogue recording file 610 into an artificial intelligence model 630 to generate a script and summary of the meeting contents, and shares the script or summary via a chat room 650 associated with the user's selection.

[0120] To this end, the minutes providing device 130 receives a dialogue recording file 610 relating to dialogue contents between users A and B, etc., recorded on the user terminal 110. The minutes providing device 130 recognizes the voice of the dialogue recording file 610 and generates a script and a summary that are converted into text. At this time, the summary is generated based on the script. That is, the artificial intelligence model 630 is designed to receive the dialogue recording file as an input and output a script and a summary in text form relating to the contents of the meeting. Thereafter, the minutes providing device 130 displays the text contents of the script or the summary as a dialogue message in a chat room 650 related to the user's selection.

[0121] In addition, the minutes providing device 130 stores and manages the script, summary, and dialogue message associated with the dialogue recording file 610 in which the dialogue contents of users A and B are recorded in the database 150. When a dialogue message is selected in the chat room 650, the minutes providing device 130 queries the database 150 and provides the dialogue recording file, script, summary, etc. associated with the corresponding dialogue message.

[0122] For this purpose, the providing device 130 provides a detailed view page of the conversation message while displaying the conversation message through the chat room 650. That is, the lock providing device 130 provides a detailed view menu along with the conversation message. A user can access a detailed view page that provides detailed content of the conversation message by selecting (e.g., clicking) the detailed view menu of the conversation message. For example, the detailed view page of the conversation message provides at least one of a conversation recording file, a script, and a summary related to the conversation message. In this case, the access of other users to the conversation recording file, script, or summary provided through the detailed view page is restricted according to a private setting set by the user who created the conversation message.

[0123] FIG. 7 is a diagram illustrating an embodiment of a process for providing related functions in a chat room according to the present invention.

[0124] 7, when the minutes providing device 130 receives a selection of a dialogue message from a chat room participant of a chat room, it displays an interface related to the dialogue message. In this case, the interface includes functions related to the dialogue message. For example, functions such as (1) listening to a dialogue recording file, (2) script view, (3) summary view, and (4) task creation are provided through the interface, and a user can select a specific function to access the corresponding content. The minutes providing device 130 accesses the database 150 to inquire about data related to the user's selection, and then provides the data through the user terminal 110.

[0125] Furthermore, even if a user participates in a chat room, the minutes providing device 130 restricts the provision of an interface if the user does not have the access right to the dialogue message (or minutes). That is, if a dialogue message is selected by a user who does not have the access right, the minutes providing device 130 does not execute an interface providing operation according to the message selection. For this reason, when the minutes providing device 130 displays a dialogue message related to a script or a summary via a chat room, it can set an access right to the dialogue message.

[0126] That is, when the minutes providing device 130 displays the script or summary extracted from the dialogue recording file between the business participants as a dialogue message in the chat room, the device 130 grants the access authority preset by the user. For example, when the contents of a meeting between multiple business participants are shared as a dialogue message through the chat room, the device 130 sets the access authority to be restricted to other users who are not participating in the meeting among the users in the chat room. That is, the minutes providing device 130 restricts access by canceling the access authority of other users while displaying the corresponding dialogue message in the chat room.

[0127] FIG. 8 is a diagram illustrating one embodiment of a task generation process according to the present invention.

[0128] 8, the minutes providing device 130 queries general minutes or task minutes 810 according to whether the minutes include recommended tasks, and generates a query result. Unlike general minutes, task minutes 810 include a list of recommended tasks 870 related to the contents of the meeting in the minutes. That is, a business participant can select a specific minutes on the minutes list provided as a result of querying the minutes to check detailed items, and can select some of the recommended tasks included in the minutes to generate related tasks. Here, a task corresponds to the smallest unit of work related to a project.

[0129] Specifically, the detailed items of the minutes provided to the business participant include a summary of the meeting contents and a recommendation task related to the meeting contents, and the recommendation task includes an individually selectable selection option 830. At this time, the minutes providing device 130 changes the activation state of each recommendation task according to the business participant and provides it. For example, if the business participant has normal authority or the corresponding recommendation task has a high priority, the minutes providing device 130 activates and provides the selection option 830. In other words, the activation state of the selection option 830 corresponds to a state selectable by the business participant.

[0130] In Fig. 8, when task #1 and task #2 are selected by a business participant (USER1), the corresponding selection option 830 is converted to the "selected" state, and the minutes providing device 130 generates tasks (Task1 and Task2) that match the corresponding tasks. At this time, Task 2 (Task2) corresponds to the task 850 generated corresponding to task #2 among the recommended tasks. The corresponding task 850 corresponds to a temporary task with some items being blank.

[0131] In this case, when the corresponding task 850 is generated, the task instructor is automatically set to "USER1" who requested the generation of the corresponding task, and the task content is automatically set to the content of "duty #2" selected by USER1. Also, the corresponding task 850 is generated and stored with information on the remaining items other than the task instructor and task content left blank (empty), and then the corresponding items are input by the business participant (USER1).

[0132] Meanwhile, the corresponding task 850 may be generated and stored with all items filled in through additional input from the business participant, or may be generated and stored with some items blank depending on selective input from the business participant.

[0133] FIG. 9 is a diagram illustrating an embodiment of a task modification process according to the present invention.

[0134] 9, the minutes providing device 130 generates a task 850 according to the selection of the business participant for each recommended task included in the minutes. At this time, the minutes providing device 130 grants the task modification authority to the business participant who generated the task 850.

[0135] In the case of Fig. 9, the task 850 is generated with the task instructor set to the business participant "USER1" who requested task generation of the recommended "duty #2" in Fig. 8, and the selected "duty #2" content is set as the task content. After that, the minutes providing device 130 receives inputs for blank items from the business participant "USER1" who has the authority to modify via the input interfaces 910 and 930, and updates the corresponding task 850.

[0136] For example, the task executor is set to another business participant "USER4" selected by the business participant "USER1" on the first input interface 910, and the task deadline is set to "00.05.05" input by the business participant "USER1" on the second input interface 930. That is, the minutes providing device 130 updates the corresponding task 850 when the remaining information is input by the business participant.

[0137] FIG. 10 is a diagram for explaining the general minutes and the task minutes according to the present invention.

[0138] Referring to FIG. 10, the minutes providing device 130 adds a recommended task list 1030 to a general minutes 1010 to convert it into a task minutes 1050. The general minutes 1010 correspond to a minutes that do not include a recommended task, and the task minutes 1050 correspond to a minutes that include a recommended task. That is, the minutes providing device 130 basically generates and stores the general minutes 1010 that do not include a recommended task. If a business participant requests or meets a specific condition, the minutes providing device 130 converts it into a task minutes 1050 by adding a recommended task list 1030 to the general minutes 1010. In this case, the business participant can also check the recommended tasks related to the minutes through the inquiry result for the minutes, and can easily generate a task related to the recommended task by selecting the recommended task as necessary.

[0139] FIG. 11 is a diagram illustrating an embodiment of a recommended task list updating process according to the present invention.

[0140] 11, the minutes providing device 130 removes a specific recommended task from the recommended task list 1110 when a task is generated according to a selection by a business participant for a specific recommended task on the recommended task list 1110 included in the task minutes. For example, in FIG. 11, when the recommended task list 1110 includes task #1, task #2, and task #3, the business participant "USER1" selects the selection option of task #1 to generate the first task 1131 of task #1. When the generation of the first task 1131 of task #1 is completed, the minutes providing device 130 removes task #1 from the recommended task list 1110.

[0141] Also, the business participant "USER1" selects the selection option for task #2 to generate a second task 1133 for task #2. When the generation of the second task 1133 for task #2 is completed, the minutes providing device 130 removes task #2 from the recommended task list 1110. If all the recommended tasks are removed from the recommended task list 1110 for the generation of the sequential tasks of the remaining recommended tasks including task #3, the minutes providing device 130 converts the task minutes into general minutes.

[0142] 12A and 12B are diagrams illustrating various embodiments of a minutes sharing process in a chat room according to the present invention.

[0143] Referring to FIG. 12A, the minutes providing device 130 shares minutes in a chat room 1200 in which a user participates, using a message display method. That is, in the case of the message display method, the contents of the minutes are inserted and displayed in the chat room 1200 as a text message 1210. The message 1210 displayed in the chat room 1200 includes the entire contents of the minutes, and if the entire contents are long, some of the contents are omitted. For example, in FIG. 12A, if some of the contents of the minutes are omitted, a "detailed view" menu 1211 is displayed together, and the user can select the corresponding menu to display the entire contents of the minutes.

[0144] 12B, the minutes providing device 130 shares the minutes using a file attachment method or a link sharing method in a chat room 1200 in which a user participates. That is, in the case of the file attachment method, a minutes file is shared as an attachment to the chat room 1200, and in the case of the link sharing method, a link to a server (e.g., a cloud server) that can access the minutes is provided via the chat room 1200.

[0145] 12B, for example, a file 1230 attached in a chat room 1200 is stored as a text file including the entire contents of the minutes, and a user participating in the chat room 1200 can download the attached file 1230 by selecting a "download" menu 1231 of the attached file 1230. Furthermore, a minutes link 1250 shared via the chat room 1200 includes an address that allows direct access to the minutes, and a user participating in the chat room 1200 can move to another page where the entire contents of the shared minutes can be confirmed by selecting a "link jump" menu 1251 of the minutes link 1250.

[0146] Although the present invention has been described above with reference to preferred embodiments thereof, it will be understood that those skilled in the art can make various modifications and changes to the present invention without departing from the spirit and technical scope of the present invention. [Explanation of symbols]

[0147] 100: Meeting minutes system 110: User terminal 130: Meeting minutes providing device 150: Database 210: Processor 510:Minutes 630: Artificial Intelligence Model 650, 1200: Chat rooms 810, 1050: Minutes of service 830:Selection options 850: Task 870: Recommended Work List 910: First input interface 930: Second input interface 1010: General minutes 1030, 1110: Recommended Work List 1131: First Task 1133: Second Task

Claims

1. Memory, a processor electrically connected to the memory; The processor, receiving from the user terminal a user selection for a chat room in which the business participant is participating; receiving a dialogue recording file in which a dialogue between the business participants regarding the contents of the conference is recorded; generating minutes in which the contents of the meeting are converted into a text form as a result of applying an artificial intelligence model to the dialogue recording file in response to a request from the user to generate minutes; An artificial intelligence based in-chat room minutes provider configured to share the minutes via a chat room related to a selection of the user.

2. The processor, The AI-based meeting minutes providing device according to claim 1, characterized in that, when a request for recommendation of tasks regarding the minutes is received from the user terminal, a recommended task regarding the meeting content is generated through the AI ​​model.

3. The processor, Generate a recommendation task list including the recommendation tasks and selection options for each recommendation task; 3. The AI ​​based minutes providing device in a chat room according to claim 2, further comprising: adding the recommended duties list to the minutes or providing the recommended duties list via the chat room.

4. The processor, The AI-based meeting minutes providing device according to claim 3, characterized in that when a selection of a specific business participant is input via the recommendation role selection option in the chat room, a task related to the recommendation role is generated.

5. The processor, The AI-based chat room minutes providing device according to claim 4, characterized in that, when multiple selection options are selected by the particular business participant, tasks related to each of the recommendation tasks are generated in sequence.

6. The processor, The AI-based meeting minutes providing device according to claim 4, characterized in that if the specific business participant has access rights to the meeting minutes, the recommendation role-specific selection option is activated, and if not, the business participant having the access rights is requested to approve the activation of the recommendation role-specific selection option.

7. The processor, The AI-based chat room minutes providing device of claim 1, further comprising: inserting the minutes into the chat room or a conference map for managing the minutes according to a position of the minutes generation request.

8. The processor, The artificial intelligence-based meeting minutes providing device according to claim 7, characterized in that it provides a list regarding the meeting minutes upon request of any one of the business participants on the chat room or the conference map.

9. The processor, The AI-based meeting minutes providing device according to claim 1, characterized in that the conversation between the business participants is received in real time from each user terminal in a streaming manner, and the conversation recording file is generated.

10. The processor, The AI-based chat room minutes providing device according to claim 1, further comprising: inputting the dialogue recording file into the AI ​​model to generate a script in which the voices of the business participants are converted into text and a summary of the script; and then generating the minutes based on at least one of the script and the summary.

11. The processor, The AI-based chat room minutes provider according to claim 10, characterized in that the script or the summary sentence is displayed as a chat room dialogue message related to the user's selection.

12. The processor, The artificial intelligence-based chat room minutes providing device of claim 11, characterized in that when a selection of the dialogue message is received from any one of the business participants, an interface related to the dialogue message is displayed.

13. The processor, The artificial intelligence-based chat room minutes providing device of claim 12, characterized in that at least one of a plurality of functions including a script view related to the dialogue message, a summary view, a dialogue recording file listening, and a task generation is provided through the interface.

14. The processor, The AI-based meeting minutes providing device according to claim 11, characterized in that, in the process of recognizing the voices of the business participants, the dialogue style of each business participant is identified, and in the process of displaying the script or the summary sentence in the dialogue message, the dialogue message is converted to an applied dialogue style.

15. The processor, The AI-based chat room minutes providing device according to claim 10, further comprising a translation function selectively provided during the process of providing the minutes, the script, or the summary.

16. The processor, The artificial intelligence-based chat room minutes providing device of claim 1, characterized in that the minutes are shared within the chat room using at least one of a number of methods including displaying a message, attaching a file, and sharing a link.

17. Memory, A method implemented in a minutes providing device including a processor electrically connected to the memory, the method comprising: The method is executed by a processor, receiving, from the user terminal, a user's selection of chat rooms in which the business participant is participating; receiving a dialogue recording file in which a dialogue between the business participants regarding the content of the conference is recorded; generating minutes in which the contents of the meeting are converted into a text form as a result of applying an artificial intelligence model to the dialogue recording file in response to a request from the user to generate minutes; and sharing the minutes via a chat room associated with the user's selection.

Citation Information

Patent Citations

  • Temporally correlated activity streams for conferences

    JP2016029574A

  • Information processing device, information processing method and program

    JP2020149628A

  • Program, displaying method and terminal

    JP2021177321A

  • Remote work assisting system and remote work assisting method

    JP2022042423A

  • Information processing device and program

    JP2022085578A