KR102620574B1 - Method, server and computer program for providing visualized project information based on conversation analysis among project participants - Google Patents

Abstract

A method for providing visualized project information based on conversation analysis between project participants, a server, and a computer program are provided. A method of providing visualized project information based on conversation analysis between project participants according to various embodiments of the present invention is performed by a computing device, comprising the steps of analyzing messages sent and received between project participants and extracting one or more summaries. and providing a project management service based on the one or more extracted summaries.

Description

Method for providing visualized project information based on conversation analysis between project participants, server and computer program {METHOD, SERVER AND COMPUTER PROGRAM FOR PROVIDING VISUALIZED PROJECT INFORMATION BASED ON CONVERSATION ANALYSIS AMONG PROJECT PARTICIPANTS}

Various embodiments of the present invention relate to a method, server, and computer program for providing visualized project information based on conversation analysis between project participants.

With the spread of smart devices such as smart phones and smart pads, and the expansion of communication infrastructure, collaboration online and using smart devices is actively taking place.

In other words, not only collaboration that takes place by gathering together in offline spaces, but also collaboration using the Internet and smart devices in different spaces is becoming common along with technological development, and accordingly, various collaboration tools using Internet networks are being developed and used.

Conventional online collaboration tools provide various functions necessary to proceed with a project. For example, conventional online collaboration tools provide messaging services between participants participating in the same project and provide various functions related to projects and project progress, such as project progress management and schedule management.

However, conventional online collaboration tools only provide each function one-dimensionally, and have the disadvantage that two or more functions cannot be linked for the convenience of participants. Therefore, participants can manually manipulate each function they want to use (e.g., confirming the schedule through a messenger and registering directly in the schedule management tool) or registering in a limited way according to the designated interface (e.g., registering in the schedule management tool will There is the inconvenience of one-way registration for notifications.

The problem to be solved by the present invention is to improve the shortcomings of the conventional online collaboration tools as described above, by analyzing messenger conversations between project participants to extract one or more summaries and various types of information related to the project based on one or more extracted keywords. It relates to a method, server, and computer program for providing visualized project information based on conversation analysis between project participants that can provide services (project management services).

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned can be clearly understood by those skilled in the art from the description below.

A method of providing visualized project information based on conversation analysis between project participants according to an embodiment of the present invention to solve the above-described problem is performed by a computing device by analyzing messages sent and received between project participants. It may include extracting one or more summaries and providing a project management service based on the one or more extracted summaries.

In various embodiments, the step of extracting the one or more summary statements includes, when a request for schedule registration for a specific message is received from a first participant, one or more summary statements related to the schedule by analyzing the specific message - one or more summary statements related to the schedule. The summary includes at least one of the schedule name, date and time, location, and attendees - extracting the step, wherein the step of providing the project management service includes extracting the extracted schedule through a user interface (UI). providing one or more summaries related to the first participant, confirming one or more summaries related to the extracted schedule based on user input of the first participant input through the user interface, and It may include registering a schedule using one or more confirmed summaries, and providing a schedule management service that provides schedule guidance information to participants of the project according to the registered schedule.

In various embodiments, the step of extracting the one or more summaries includes analyzing the transmitted and received message to one or more summaries related to the schedule - the one or more summaries related to the schedule include the schedule name, date and time, place and attendees - The step of providing the project management service includes automatically registering a schedule using one or more summaries related to the extracted schedule, and registering participants of the project according to the automatically registered schedule. It may include providing a schedule management service that provides schedule guidance information to the user.

In various embodiments, the step of extracting the one or more summaries includes analyzing a plurality of messages transmitted and received between participants of the project to determine the importance of each of the plurality of messages, and the determined importance is set according to a preset standard. Providing guidance information for registering the above message as an important message, and when receiving a request to register an important message from a participant in response to the provided guidance information, extracting one or more summary sentences from the message for which registration of the important message has been requested. The step of providing the project management service includes registering a reminder for the important message using the one or more extracted summaries, and targeting the important message according to the registered reminder. It may include the step of providing an important message management service to guide people.

In various embodiments, the step of providing the project management service includes determining the properties of the project by analyzing messages transmitted and received between participants of the project, and project properties providing information about the determined properties of the project. It includes the step of providing an information provision service, wherein the step of providing the project attribute information provision service includes the project attribute determined for each of a plurality of projects in which the first participant is participating through a user interface (UI). Provides information about, and the user interface outputs a plurality of cards corresponding to each of the plurality of projects arranged in a grid form, and the front of each of the plurality of cards contains information about each of the plurality of projects - the plurality of projects. Information on each project includes at least one of the project name, the number of unconfirmed messages among messages sent and received between project participants, and project attribute information - and is printed on the back of each of the plurality of cards. It may include a step of outputting one or more keywords extracted from messages transmitted and received between participants of each of a plurality of projects.

In various embodiments, the step of determining the properties of the project includes extracting one or more summaries from a plurality of messages transmitted and received between participants of the project during a preset period, and analyzing the one or more extracted summaries to determine the properties of the project. A step of generating summary information related to progress, and providing the user interface, wherein the generated summary information is visualized and provided, wherein the visualized summary information contains one or more keywords related to the progress of the project. It may include steps visualized in the form of a word cloud.

In various embodiments, the step of determining the properties of the project includes at least one of the properties of a plurality of messages transmitted and received between participants of the project, the progress of the project, and issues occurring within the project and whether the issues are resolved. and determining the mood of the project using the step of providing the user interface, wherein the mood of the determined project is visualized and provided, wherein the visualized mood of the project is determined by using the plurality of transmitted and received signals. It is visualized in the form of a graph according to the weighted sum of a plurality of first points corresponding to each message, and displays a plurality of second points corresponding to issues occurring within the project in the atmosphere of the project visualized in the graph form, The color of each of the plurality of second points may be determined depending on whether an issue corresponding to each of the plurality of second points is resolved.

In various embodiments, the step of providing the project attribute information provision service includes generating a summary information list including summary information about attribute information for each of the plurality of projects in which the first participant is participating, and generating the generated summary information. It may include providing a message including a list from the first participant to the first participant at preset times.

In various embodiments, the step of extracting the one or more summary sentences includes analyzing a plurality of messages transmitted and received between participants of the project, and selecting a message that is set to be deactivated by at least one of the participants of the project among the plurality of messages. A step of excluding the summary text may be included.

A server providing visualized project information based on conversation analysis between project participants according to another embodiment of the present invention to solve the above-described problem is loaded into a processor, a network interface, a memory, and the memory, and is executed by the processor. Includes a computer program, wherein the computer program includes instructions for extracting one or more summaries by analyzing messages transmitted and received between project participants, and instructions for providing project management services based on the one or more extracted summaries. may include.

A computer program according to another embodiment of the present invention for solving the above-mentioned problem is combined with a computing device, analyzing messages transmitted and received between project participants and extracting one or more summaries, and the extracted one or more In order to execute steps for providing project management services based on the summary, it can be stored in a computer-readable recording medium.

Other specific details of the invention are included in the detailed description and drawings.

According to various embodiments of the present invention, one or more summaries are extracted by analyzing messenger conversations between project participants, and various services related to the project (project management services) are provided based on the one or more extracted summaries, thereby It has the advantage of overcoming the problems of online collaboration tools.

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

1 and 2 are diagrams illustrating a system for providing visualized project information based on conversation analysis between project participants according to an embodiment of the present invention.
Figure 3 is a hardware configuration diagram of a server providing visualized project information based on conversation analysis between project participants according to another embodiment of the present invention.
Figure 4 is a flowchart of a method for providing visualized project information based on conversation analysis between project participants according to another embodiment of the present invention.
Figure 5 is a flowchart of a method for providing a schedule management service performed by a server providing visualized project information based on conversation analysis between project participants in various embodiments.
Figures 6 and 7 are diagrams illustrating a schedule management service provided by a visualized project information providing server based on conversation analysis between project participants in various embodiments.
Figure 8 is a flowchart of a method of providing an important message management service performed by a server providing visualized project information based on conversation analysis between project participants in various embodiments.
Figure 9 is a diagram illustrating an important message management service provided by a visualized project information providing server based on conversation analysis between project participants in various embodiments.
10 is a flowchart of a method of providing a project attribute information service performed by a visualized project information providing server based on conversation analysis between project participants, in various embodiments.
11 to 14 are diagrams illustrating a project attribute information provision service provided by a visualized project information provision server based on conversation analysis between project participants, in various embodiments.
Figures 15 and 16 are diagrams illustrating a configuration for generating learning data for an artificial intelligence model that performs a method of providing visualized project information based on conversation analysis between project participants, in various embodiments.

The advantages and features of the present invention and methods for achieving them will become clear by referring to the embodiments described in detail below along with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various different forms. The present embodiments are merely provided to ensure that the disclosure of the present invention is complete and to provide a general understanding of the technical field to which the present invention pertains. It is provided to fully inform the skilled person of the scope of the present invention, and the present invention is only defined by the scope of the claims.

The terminology used herein is for describing embodiments and is not intended to limit the invention. As used herein, singular forms also include plural forms, unless specifically stated otherwise in the context. As used in the specification, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other elements in addition to the mentioned elements. Like reference numerals refer to like elements throughout the specification, and “and/or” includes each and every combination of one or more of the referenced elements. Although “first”, “second”, etc. are used to describe various components, these components are of course not limited by these terms. These terms are merely used to distinguish one component from another. Therefore, it goes without saying that the first component mentioned below may also be a second component within the technical spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used with meanings commonly understood by those skilled in the art to which the present invention pertains. Additionally, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless clearly specifically defined.

As used in the specification, the term “unit” or “module” refers to a hardware component such as software, FPGA, or ASIC, and the “unit” or “module” performs certain roles. However, “part” or “module” is not limited to software or hardware. A “unit” or “module” may be configured to reside on an addressable storage medium and may be configured to run on one or more processors. Thus, as an example, a “part” or “module” refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, Includes procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functionality provided within components and “parts” or “modules” can be combined into smaller components and “parts” or “modules” or into additional components and “parts” or “modules”. Could be further separated.

Spatially relative terms such as “below”, “beneath”, “lower”, “above”, “upper”, etc. are used as a single term as shown in the drawing. It can be used to easily describe the correlation between a component and other components. Spatially relative terms should be understood as terms that include different directions of components during use or operation in addition to the directions shown in the drawings. For example, if a component shown in a drawing is flipped over, a component described as “below” or “beneath” another component will be placed “above” the other component. You can. Accordingly, the illustrative term “down” may include both downward and upward directions. Components can also be oriented in other directions, so spatially relative terms can be interpreted according to orientation.

In this specification, a computer refers to all types of hardware devices including at least one processor, and depending on the embodiment, it may be understood as encompassing software configurations that operate on the hardware device. For example, a computer can be understood to include, but is not limited to, a smartphone, tablet PC, desktop, laptop, and user clients and applications running on each device.

Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings.

Each step described in this specification is described as being performed by a computer, but the subject of each step is not limited thereto, and depending on the embodiment, at least part of each step may be performed in a different device.

1 and 2 are diagrams illustrating a system for providing visualized project information based on conversation analysis between project participants according to an embodiment of the present invention.

Referring to Figures 1 and 2, the system for providing visualized project information based on conversation analysis between project participants according to an embodiment of the present invention includes a project management service providing server 100, a participant terminal 200, and an external server 300. may include.

Here, the system for providing visualized project information based on conversation analysis between project participants shown in FIGS. 1 and 2 is according to an embodiment, and its components are not limited to the embodiment shown in FIGS. 1 and 2, It may be added, changed, or deleted as needed.

In one embodiment, the project management service providing server 100 may extract one or more summaries by analyzing messages transmitted and received between project participants, and provide a project management service using one or more extracted summaries. . To this end, the project management service providing server 100 includes a collection server 101, a storage server 102, an analysis server 103, an interaction server 104, and a project management system 105, as shown in FIG. It can be included. However, it is not limited to this.

Here, the summary may be a single word (keyword), but is not limited to this and may be understood as encompassing all words, phrases, or sentences composed of two or more words.

In one embodiment, the collection server 101 may be connected to the participant terminal 200 of the project participants through the network 400, and messages transmitted and received between the project participants through the message relay module of the participant terminal 200 can be collected.

Here, the network 400 refers to a connection structure that allows information exchange between nodes such as a plurality of terminals and servers. Examples of such networks include a local area network (LAN), a wide area network (LAN), and a wide area network (LAN). It includes WAN (Wide Area Network), Internet (WWW: World Wide Web), wired and wireless data communication network, telephone network, and wired and wireless television communication network. Examples of wireless data communication networks include 3G, 4G, 5G, 3rd Generation Partnership Project (3GPP), 5th Generation Partnership Project (5GPP), Long Term Evolution (LTE), World Interoperability for Microwave Access (WIMAX), and Wi-Fi. , Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth network, NFC ( It includes, but is not limited to, Near-Field Communication (Near-Field Communication) network, satellite broadcasting network, analog broadcasting network, and DMB (Digital Multimedia Broadcasting) network.

In various embodiments, the collection server 101 may include a de-identification module 101A and a non-target message filtering module 101B, and may include regular expression pattern matching-based URL recognition and E-mail recognition through the de-identification module. , can perform phone number recognition and person recognition functions, and can perform non-targeted message filtering modules to prevent specific messages based on message metadata (e.g., messages automatically created by the system or messages deactivated by participants (e.g., messages not analyzed by participants) based on message metadata. Requested messages) can be filtered.

Here, the de-identification module 101A and the non-target message filtering module 101B can automatically collect work progress information for each of a plurality of projects conducted non-face-to-face.

In one embodiment, the storage server 102 may store messages transmitted and received between project participants collected through the collection server 101.

In one embodiment, the analysis server 103 may collect messages transmitted and received between project participants collected through the collection server 101 in real time, and provide a schedule management service using the schedule extraction module 103A. An important message management service can be provided using the important message classification module 103B.

Additionally, the analysis server 103 can collect messages stored in the storage server 102 and provide a project attribute information service using the project mood classification module 103C and the summary extract module 103D.

Here, the schedule extraction module 103A, the important message classification module 103B, the project mood classification module 103C, and the summary sentence extraction module 103D can recognize information related to the project included in the message, and through this, participants Manual work can be minimized.

In one embodiment, the interaction server 104 collects results of providing a schedule management service collected from the analysis server 103 (e.g., registered schedule information) and results of providing an important message management service (e.g., important messages, registration, etc.). (reminder information, etc.) can be provided to the project management system 105 through the message interaction module 104A.

In addition, the interaction server 104 uses the report interaction module 104B to display the results of providing a schedule management service (e.g., registered schedule information) and the results of providing an important message management service (e.g., important messages, registered reminders, etc.). A report containing (information, etc.) can be generated and provided to the participant terminal 200.

Here, the message interaction module 104A and the report interaction module 104B can generate and provide an interactive message that allows participants to access the project DB through a messenger based on information extracted from the message.

In one embodiment, the project management system 105 uses the project management service module 105A to provide a schedule management service, an important message management service, and a project attribute information provision service based on data already stored in the database 105B. We can provide various management services.

Additionally, the project management system 105 can be connected to an external monitoring device 500 and can provide an integrated dashboard user interface (UI) that integrates and outputs various information related to the project.

Here, the integrated dashboard outputs progress information for each of multiple projects and information on issues arising from each of the multiple projects, allowing participants to proactively identify issues and manage risks.

In one embodiment, the participant terminal 200 may be connected to the project management service providing server 100 through the network 400 and may receive various project management services from the project management service providing server 100.

In various embodiments, the participant terminal 200 includes a display at least in part and may be a smart-phone terminal including an operating system capable of running an application provided by the project management service providing server 100. , As the application provided by the project management service providing server 100 is downloaded, installed, and executed, UI related to various project management services can be output through the display. However, it is not limited to this, and the participant terminal 200 is a wireless communication device that guarantees portability and mobility, and includes navigation, Personal Communication System (PCS), Global System for Mobile communications (GSM), Personal Digital Cellular (PDC), and PHS. (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) It may include all types of handheld-based wireless communication devices such as terminals, smartpads, tablet PCs, etc.

In one embodiment, the external server 300 may be connected to the project management service providing server 100 through the network 400, and the project management service providing server 100 may provide visualized project information based on conversation analysis between project participants. Various information/data required to perform the process may be stored, or various information/data generated as the project management service providing server 100 performs a process of providing visualized project information based on conversation analysis between project participants. For example, the external server 300 may be a storage server separately provided outside the project management service providing server 100, but is not limited to this. Hereinafter, the hardware configuration of the project management service providing server 100 will be described with reference to FIG. 3.

Figure 3 is a hardware configuration diagram of a server providing visualized project information based on conversation analysis between project participants according to another embodiment of the present invention.

Referring to FIG. 3, a server 100 providing visualized project information based on conversation analysis between project participants according to another embodiment of the present invention (hereinafter referred to as “computing device 100”) includes one or more processors 110, a processor ( It may include a memory 120 that loads the computer program 151 executed by 110, a bus 130, a communication interface 140, and a storage 150 that stores the computer program 151. . Here, only components related to the embodiment of the present invention are shown in Figure 3. Accordingly, anyone skilled in the art to which the present invention pertains can recognize that other general-purpose components may be included in addition to the components shown in FIG. 3.

The processor 110 controls the overall operation of each component of the computing device 100. The processor 110 includes a Central Processing Unit (CPU), Micro Processor Unit (MPU), Micro Controller Unit (MCU), Graphic Processing Unit (GPU), or any other type of processor well known in the art of the present invention. It can be.

Additionally, the processor 110 may perform operations on at least one application or program for executing methods according to embodiments of the present invention, and the computing device 100 may include one or more processors.

In various embodiments, the processor 110 includes random access memory (RAM) (not shown) and read memory (ROM) that temporarily and/or permanently store signals (or data) processed within the processor 110. -Only Memory, not shown) may be further included. Additionally, the processor 110 may be implemented in the form of a system on chip (SoC) that includes at least one of a graphics processing unit, RAM, and ROM.

Memory 120 stores various data, commands and/or information. Memory 120 may load a computer program 151 from storage 150 to execute methods/operations according to various embodiments of the present invention. When the computer program 151 is loaded into the memory 120, the processor 110 can perform the method/operation by executing one or more instructions constituting the computer program 151. The memory 120 may be implemented as a volatile memory such as RAM, but the technical scope of the present disclosure is not limited thereto.

Bus 130 provides communication functionality between components of computing device 100. The bus 130 may be implemented as various types of buses, such as an address bus, a data bus, and a control bus.

The communication interface 140 supports wired and wireless Internet communication of the computing device 100. Additionally, the communication interface 140 may support various communication methods other than Internet communication. To this end, the communication interface 140 may be configured to include a communication module well known in the technical field of the present invention. In some embodiments, communication interface 140 may be omitted.

Storage 150 may store the computer program 151 non-temporarily. When performing a process for providing visualized project information based on conversation analysis between project participants through the computing device 100, the storage 150 stores various information necessary to provide a process for providing visualized project information based on conversation analysis between project participants. You can.

The storage 150 is a non-volatile memory such as Read Only Memory (ROM), Erasable Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), flash memory, a hard disk, a removable disk, or a device well known in the technical field to which the present invention pertains. It may be configured to include any known type of computer-readable recording medium.

The computer program 151, when loaded into the memory 120, may include one or more instructions that cause the processor 110 to perform methods/operations according to various embodiments of the present invention. That is, the processor 110 can perform the method/operation according to various embodiments of the present invention by executing the one or more instructions.

In one embodiment, the computer program 151 includes extracting one or more summaries by analyzing messages transmitted and received between project participants and providing project management services based on the one or more extracted summaries. It may include one or more instructions that perform a method of providing visualized project information based on conversation analysis between people.

The steps of the method or algorithm described in connection with embodiments of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or a combination thereof. The software module may be RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), Flash Memory, hard disk, removable disk, CD-ROM, or It may reside on any type of computer-readable recording medium well known in the art to which the present invention pertains.

The components of the present invention may be implemented as a program (or application) and stored in a medium in order to be executed in conjunction with a hardware computer. Components of the invention may be implemented as software programming or software elements, and similarly, embodiments may include various algorithms implemented as combinations of data structures, processes, routines or other programming constructs, such as C, C++, , may be implemented in a programming or scripting language such as Java, assembler, etc. Functional aspects may be implemented as algorithms running on one or more processors. Hereinafter, with reference to FIGS. 4 to 14, a method of providing visualized project information based on conversation analysis between project participants provided by the computing device 100 will be described.

Figure 4 is a flowchart of a method for providing visualized project information based on conversation analysis between project participants according to another embodiment of the present invention.

Referring to FIG. 4, in step S110, the computing device 100 may be connected to a plurality of participant terminals 200 and collect messages (e.g., message data transmitted and received between participants) from the plurality of participant terminals 200. can do. For example, the computing device 100 may collect messages transmitted and received by each of the plurality of participants from the message relay module of each of the plurality of participant terminals 200. However, it is not limited to this.

Here, the message may be a text message, but is not limited to this and may include a video (video, image) message, voice message, special characters, and emoticons.

In various embodiments, the computing device 100 may collect messages collected from a plurality of participant terminals 200 and classify the collected messages by project, but is not limited to this and may be used in projects in which a plurality of participants participate. Accordingly, by first classifying a plurality of participants and collecting messages through the participant terminal 200 of the participants classified by project, messages classified by project can be collected. Here, the computing device 100 may be implemented to collect messages transmitted and received between participants in real time through the message relay module of the participant terminal 200, but this is only an example and is not limited to this. Other general-purpose methods of collection (e.g., loading messages from a storage server that backs up and stores messages sent and received between participants) can be applied.

In step S120, the computing device 100 may extract one or more summaries by analyzing the messages collected in step S110. For example, the computing device 100 may extract one or more summaries included in the collected messages by analyzing the collected messages using an artificial intelligence model.

Here, the artificial intelligence model may be a model (e.g., entity name recognition model (NER model)) that has been previously learned using messages labeled with one or more summary sentences as learning data.

Here, an artificial intelligence model (e.g., a neural network) is composed of one or more network functions, and one or more network functions may be composed of a set of interconnected computational units, which can generally be referred to as ‘nodes.’ These ‘nodes’ may also be referred to as ‘neurons’. One or more network functions are composed of at least one or more nodes. Nodes (or neurons) that make up one or more network functions may be interconnected by one or more ‘links’.

Within an artificial intelligence model, one or more nodes connected through a link can form a relative input node and output node relationship. The concepts of input node and output node are relative, and any node in an output node relationship with one node may be in an input node relationship with another node, and vice versa. As described above, input node to output node relationships can be created around links. One or more output nodes can be connected to one input node through a link, and vice versa.

In a relationship between an input node and an output node connected through one link, the value of the output node may be determined based on data input to the input node. Here, the nodes connecting the input node and the output node may have a weight. Weights may be variable and may be varied by the user or algorithm in order for the artificial intelligence model to perform the desired function. For example, when one or more input nodes are connected to one output node by respective links, the output node is set to the values input to the input nodes connected to the output node and the links corresponding to each input node. The output node value can be determined based on the weight.

As described above, in an artificial intelligence model, one or more nodes are interconnected through one or more links to form an input node and output node relationship within the artificial intelligence model. The characteristics of the artificial intelligence model can be determined according to the number of nodes and links within the artificial intelligence model, the correlation between nodes and links, and the weight value assigned to each link. For example, if there are two artificial intelligence models with the same number of nodes and links and different weight values between the links, the two artificial intelligence models may be recognized as different from each other.

Some of the nodes constituting the artificial intelligence model may form one layer based on the distances from the initial input node. For example, a set of nodes with a distance n from the initial input node may constitute n layers. The distance from the initial input node can be defined by the minimum number of links that must be passed to reach the node from the initial input node. However, this definition of the layer is arbitrary for explanation purposes, and the order of the layer within the artificial intelligence model may be defined in a different way than described above. For example, a layer of nodes may be defined by distance from the final output node.

The initial input node may refer to one or more nodes in the artificial intelligence model into which data is directly input without going through links in relationships with other nodes. Alternatively, in an artificial intelligence model network, in the relationship between nodes based on links, it may mean nodes that do not have other input nodes connected by links. Similarly, the final output node may refer to one or more nodes that do not have an output node in their relationship with other nodes among the nodes in the artificial intelligence model. Additionally, hidden nodes may refer to nodes that constitute an artificial intelligence model rather than the first input node and the last output node. The artificial intelligence model according to an embodiment of the present disclosure may have more nodes in the input layer than the nodes in the hidden layer close to the output layer, and is an artificial intelligence model in which the number of nodes decreases as it progresses from the input layer to the hidden layer. You can.

An artificial intelligence model may include one or more hidden layers. The hidden node of the hidden layer can take the output of the previous layer and the output of surrounding hidden nodes as input. The number of hidden nodes for each hidden layer may be the same or different. The number of nodes in the input layer may be determined based on the number of data fields of the input data and may be the same as or different from the number of hidden nodes. Input data input to the input layer can be operated by the hidden node of the hidden layer and output by the fully connected layer (FCL), which is the output layer.

In various embodiments, the artificial intelligence model may be a deep neural network (DNN). A deep neural network may refer to an artificial intelligence model that includes multiple hidden layers in addition to the input layer and output layer. Deep neural networks allow you to identify latent structures in data. In other words, it is possible to identify the potential structure of a photo, text, video, voice, or music (e.g., what object is in the photo, what the content and emotion of the text are, what the content and emotion of the voice are, etc.) . Deep neural networks include convolutional neural networks (CNN), recurrent neural networks (RNN), auto encoders, generative adversarial networks (GAN), and restricted Boltzmann machines (RBMs). boltzmann machine), deep belief network (DBN), Q network, U network, Siamese network, etc. The description of the deep neural network described above is only an example and the present disclosure is not limited thereto.

In various embodiments, a network function may include an autoencoder. An autoencoder may be a type of artificial neural network to output output data similar to input data. The autoencoder may include at least one hidden layer, and an odd number of hidden layers may be placed between input and output layers. The number of nodes in each layer may be reduced from the number of nodes in the input layer to an intermediate layer called the bottleneck layer (encoding), and then expanded symmetrically and reduced from the bottleneck layer to the output layer (symmetrical to the input layer). The nodes of the dimensionality reduction layer and dimensionality restoration layer may or may not be symmetric.

Autoencoders can perform nonlinear dimensionality reduction. The number of input layers and output layers may correspond to the number of sensors remaining after preprocessing of the input data. In an auto-encoder structure, the number of nodes in the hidden layer included in the encoder may have a structure that decreases as the distance from the input layer increases. If the number of nodes in the bottleneck layer (the layer with the fewest nodes located between the encoder and decoder) is too small, not enough information may be conveyed, so if it is higher than a certain number (e.g., more than half of the input layers, etc.) ) may be maintained.

In various embodiments, the computing device 100 may generate learning data for supervised learning (teacher learning) of an artificial intelligence model by labeling one or more summary sentences included in the message. However, it is not limited to this, and the computing device 100 can learn an artificial intelligence model through unsupervised learning and semi-supervised learning. Here, the method by which the computing device 100 generates learning data will be described later with reference to FIGS. 15 and 16.

Here, supervised learning is a method that typically creates learning data by labeling specific data and information related to the specific data, and uses this to learn. Learning data is generated by labeling two data with a causal relationship, and the generated learning data is used. It refers to a method of learning through data.

More specifically, the computing device 100 may perform learning on one or more network functions constituting an artificial intelligence model using labeled learning data. For example, the computing device 100 inputs each of the learning input data into one or more network functions, compares each of the output data calculated by one or more network functions with each of the learning output data corresponding to the label of each of the learning input data, Errors can be derived. That is, in training an artificial intelligence model, learning input data may be input to the input layer of one or more network functions, and learning output data may be compared with the output of one or more network functions.

The computing device 100 may train an artificial intelligence model based on the calculation results of one or more network functions on the learning input data and the error of the learning output data (label).

Additionally, the computing device 100 may adjust the weight of one or more network functions based on the error using a backpropagation method. That is, the computing device 100 may adjust the weights so that the output of one or more network functions is closer to the learning output data based on the calculation results of one or more network functions on the learning input data and the error of the learning output data.

When learning of one or more network functions has been performed for more than a predetermined epoch, the computing device 100 may determine whether to stop learning using verification data. The predetermined epoch may be part of the overall learning target epoch.

Verification data may consist of at least some of the labeled training data. That is, the computing device 100 performs learning of the artificial intelligence model through learning data, and after learning of the artificial intelligence model is repeated for more than a predetermined epoch, the learning effect of the artificial intelligence model is set to a predetermined level using verification data. You can judge whether it is abnormal or not. For example, when the computing device 100 performs learning with a target repetition learning number of 10 using 100 learning data, it performs learning repetition 10 times, which is a predetermined epoch, and then performs learning using 10 verification data. By performing repeated learning three times, if the change in the output of the artificial intelligence model during three repeated learning is below a predetermined level, it is determined that further learning is meaningless and learning can be terminated.

In other words, verification data can be used to determine completion of learning based on whether the effect of learning for each epoch is above or below a certain level in the iterative learning of an artificial intelligence model. The above-described number of training data, verification data, and number of repetitions are only examples and the present disclosure is not limited thereto.

The computing device 100 may generate an artificial intelligence model by testing the performance of one or more network functions using test data and determining whether to activate one or more network functions. Test data may be used to verify the performance of an artificial intelligence model and may consist of at least part of the learning data. For example, 70% of the training data can be used for training the artificial intelligence model (i.e. learning to adjust the weights to output results similar to labels), and 30% can be used to verify the performance of the artificial intelligence model. It can be used as test data to do this. The computing device 100 may input test data into the trained artificial intelligence model, measure the error, and determine whether to activate the artificial intelligence model depending on whether it exceeds a predetermined performance.

The computing device 100 verifies the performance of the trained artificial intelligence model by using test data on the trained artificial intelligence model, and if the performance of the trained artificial intelligence model is higher than a predetermined standard, the artificial intelligence model can be used in another application. You can enable it for use.

Additionally, if the performance of the trained artificial intelligence model is below a predetermined standard, the computing device 100 may deactivate and discard the artificial intelligence model. For example, the computing device 100 may determine the performance of the generated artificial intelligence model model based on factors such as accuracy, precision, and recall. The above-described performance evaluation criteria are only examples and the present disclosure is not limited thereto. According to an embodiment of the present disclosure, the computing device 100 can independently learn each artificial intelligence model to create a plurality of artificial intelligence model models, and evaluate performance to use only artificial intelligence models with a certain performance or higher. .

In various embodiments, the computing device 100 may analyze a plurality of messages transmitted and received between project participants, and exclude from the summary text extraction a message that is set to be disabled by at least one of the project participants among the plurality of messages. there is. For example, in the process of transmitting a message, participants can set (e.g., activate or deactivate) the message they are transmitting, and the computing device 100 may set the message to be disabled by the participant, that is, a message set not to be analyzed. By excluding from the summary text extraction target, the message can not be analyzed. In some cases, the computing device 100 may not collect messages that are set to be deactivated from participants even if they go through step S110.

In step S130, the computing device 100 may provide a project management service based on one or more summaries extracted in step S120. For example, the computing device 100 may provide a schedule management service, an important message management service, and a project attribute information provision service using one or more summary sentences included in the message. Hereinafter, the schedule management service provided by the computing device 100 will be described with reference to FIGS. 5 to 7 .

Figure 5 is a flowchart of a schedule management service provision method performed by a visualized project information providing server based on conversation analysis between project participants in various embodiments, and Figures 6 and 7 are flowcharts of a method for providing schedule management services based on conversation analysis between project participants in various embodiments. This is a diagram showing the schedule management service provided by the visualized project information server.

Referring to FIGS. 5 to 7 , in step S210, the computing device 100 may obtain a schedule registration request from the participant. For example, the computing device 100 may receive a request from a participant to register a schedule for a specific message.

First, the computing device 100 may provide a message transmission/reception UI 10 that provides a message transmission/reception service between participants, as shown in FIG. 6 .

Thereafter, the computing device 100 may obtain a request for providing a context menu for a specific message from a participant through the message transmission/reception UI 10, and provide a context menu 11 for the specific message in response to the request for providing a context menu. can do.

Thereafter, the computing device 100 may receive a selection of the schedule registration request item 11A included in the context menu 11 from the participant, and may recognize this as requesting schedule registration for a specific message. However, it is not limited to this.

In step S210, in response to the schedule registration request obtained in step S210, the computing device 100 analyzes a specific message and generates one or more summary statements related to the schedule (e.g., at least one of schedule name, date and time, location, and attendees). It can be extracted.

For example, as shown in FIG. 7A, the computing device 100 uses a pre-learned entity name recognition model (NER model) to create “kickoff meeting” regarding the schedule and “May 6 (Wed)” regarding the date and time. ) 6:30 PM" and the "URL" for the location can be extracted. However, it is not limited to this.

In step S230, the computing device 100 may register a schedule using one or more summary sentences extracted in step S220.

First, the computing device 100 analyzes the properties of each of one or more summary statements related to the schedule extracted from the message, and places each of one or more summary statements related to the schedule on a preset schedule registration form based on the attribute analysis results. , one or more summaries placed on the schedule registration form may be provided to participants through the schedule registration UI 12.

At this time, the computing device 100 may convert and place one or more summary sentences related to the schedule according to a preset schedule registration form. For example, as shown in FIG. 7A, the computing device 100 uses a standard format conversion model (seq2seq model) to convert a summary related to a date and time among one or more summaries into a standard format (e.g., YYYY-MM-DD hh: mm) and can be placed on the schedule registration form. However, it is not limited to this.

In various embodiments, the computing device 100 places each of one or more summary sentences related to the schedule on a preset schedule registration form. However, if there is no summary to be placed in a specific area on the schedule registration form, the computing device 100 places another summary sentence in addition to the message subject to schedule registration. By analyzing the messages, the corresponding summary can be extracted.

For example, if there is no summary text related to the attendees among one or more summaries related to the schedule extracted by analyzing the specific message, the computing device 100 may send and receive a predetermined time before and at a predetermined time based on the time when the specific message was transmitted and received. Messages sent and received during the following period can be analyzed to extract summaries related to attendees.

At this time, if a summary related to the attendee is not extracted from the message sent or received before or after a predetermined time based on the time when the specific message was sent or received, the computing device 100 gradually increases the size of the predetermined time and one or more of the one or more related to the attendee. The summary can be extracted, and if the summary related to the attendee is not extracted despite increasing the size of the predetermined time to the preset maximum, the area where the attendee's information is placed on the schedule registration form can be set to blank. .

Thereafter, the computing device 100 may obtain user input (e.g., input for adding, modifying, deleting, and confirming one or more summaries placed on the schedule registration form) through the schedule registration UI 12. , one or more summaries related to the schedule may be confirmed based on participant input.

Thereafter, the computing device 100 registers a schedule using one or more summaries confirmed through the schedule registration UI 12, and sends information to participants of the project (or attendees included in the registered schedule) according to the registered schedule. A schedule management service that provides schedule information (e.g., information about registered schedules, schedule reminders based on registered schedules, etc.) may be provided.

In various embodiments, the computing device 100 registers a schedule using one or more summary statements confirmed through the schedule registration UI 12, but at the same time as the newly registered schedule based on a plurality of previously registered schedule information. If there is another schedule taking place at the location, guidance information may be provided to guide changes to the time and location of the newly registered schedule.

In addition, when a schedule to be held at the same time is newly registered for a first participant who has a different schedule at the first time, the computing device 100 notifies the first participant to change the time of the newly registered schedule or registers it as a new schedule. Guidance information indicating that the first participant cannot participate in the schedule may be provided.

Here, the method of providing the schedule management service according to FIGS. 5 to 7 is described as registering the schedule by extracting a summary included in the specific message when a participant selects a specific message and requests schedule registration, but is not limited to this. It can be implemented in various forms.

For example, even if the computing device 100 is not requested by a participant to register a schedule targeting a specific message, the computing device 100 automatically analyzes messages sent and received between participants and provides one or more summaries related to the schedule (e.g., schedule name, date, time, If a summary text related to the location and attendees or a summary text that can be identified as a schedule-setting message, such as schedule registration and schedule creation, is extracted, the schedule can be automatically registered using one or more summary sentences related to the extracted schedule.

In addition, the computing device 100 analyzes messages sent and received between participants and, when one or more summary sentences related to the schedule are extracted, outputs guidance information indicating that the schedule can be automatically registered using the corresponding message (e.g. By displaying effects in a pop-up window or at least part of the message, etc.), participants can be encouraged to request schedule registration for the message.

Additionally, the computing device 100 may automatically register a schedule by analyzing patterns of messages sent and received between participants even if the participant does not request to register a schedule targeting a specific message.

For example, when participants participating in a specific project show a pattern of discussing the next schedule about 10 to 20 minutes before the end of the meeting, the computing device 100 does not receive a request from the participants to register a separate schedule. Even if not, one or more summaries related to the schedule can be extracted by analyzing messages sent and received about 10 to 20 minutes before the end of the meeting the participants are conducting, and the next schedule can be automatically registered using the extracted summaries. there is.

Here, as shown in Figure 7A, the person in charge of the project may confirm the schedule by organizing the next schedule and notifying it to the participants. However, in some cases, the participants may modify the schedule organized and announced by the person in charge, or multiple participants may modify the schedule. In some cases, the schedule is finalized through discussion. For example, as shown in Figure 7B, when the person in charge of the project enters a Slack message related to the schedule using the Thread function, several participants enter a message in the form of a comment on the Slack message and schedule the schedule. In some cases, it is discussed and finalized.

At this time, when registering a schedule considering only one message, the schedule contents discussed and modified by the participants cannot be reflected, and in order to reflect this, the person in charge must manually modify the schedule contents automatically registered through message analysis. A problem may arise.

Considering this, when receiving a request to register a schedule for a specific message, the computing device 100 can extract a summary related to the schedule by analyzing not only the specific message but also the messages sent and received after the specific message is sent and received. , the schedule can be registered using the extracted summary. For example, as shown in Figure 7(B), when multiple threads are entered into one Slack message related to a schedule, each thread is separated and a thread with the same topic, that is, containing content related to the schedule, is created. A schedule can be registered by selecting a thread and extracting one or more summary sentences related to the schedule from the selected thread. Here, the computing device 100 selects threads with the same topic using an artificial intelligence model, and the artificial intelligence model is a model learned using learning data generated by sequential labeling (BIO tagging) of existing Slack messages. (It may be a BERT-based fine tuning model).

Here, in the above situation (e.g., when several people discuss and decide on a schedule), a plurality of summaries having the same properties (e.g., schedule name, date, time, location, etc.) may be extracted, and the computing device 100 When multiple summaries with the same properties are extracted, a schedule can be registered using the summary that is extracted the most among the plurality of summaries, a schedule can be registered using the last extracted summary, or a schedule can be registered using the summary that has been extracted most often, or Once confirmed, you can register your schedule. However, considering the flow of conversation, it may be desirable to register the schedule using the final value, that is, the last extracted summary, but the schedule is not limited to this. Additionally, the computing device 100 may register a new schedule by comparing the similarity between the schedule created as above and the existing schedule. Hereinafter, with reference to FIGS. 8 and 9, the important message management service provided by the computing device 100 will be described.

Figure 8 is a flowchart of a method of providing an important message management service performed by a visualized project information providing server based on conversation analysis between project participants in various embodiments, and Figure 9 is a flowchart of a method of providing a visualized project information based on conversation analysis between project participants in various embodiments. This diagram illustrates the important message management service provided by the project information provision server.

Referring to FIGS. 8 and 9 , in step S310, the computing device 100 may determine the importance of each message by analyzing messages transmitted and received between project participants, and provide guidance information based on the determined importance of each message. can be provided. For example, the computing device 100 may select important messages based on the importance of each message and provide guidance information instructing to register a reminder for the selected important message.

In various embodiments, the computing device 100 may select at least an important summary of messages transmitted and received between project participants based on one or more summaries extracted by analyzing messages transmitted and received between project participants and pre-stored important summary data. A message containing one can be judged to be an important message. For example, as shown in FIG. 8, the computing device 100 considers messages containing important summaries such as “edit”, “re-edited”, “review”, etc. among messages transmitted and received between project participants as important messages. You can judge.

In various embodiments, the computing device 100 analyzes messages transmitted and received between project participants based on pre-stored importance scores for each summary, adds up the importance scores for each of one or more abstracts, and the summed importance scores are A message with a preset standard score or higher may be judged to be an important message.

In various embodiments, the computing device 100 may determine that a message transmitted by a specific participant is an important message based on a preset level of importance for each participant. However, the method is not limited to this, and various methods for determining important messages among messages transmitted and received between project participants may be applied.

Thereafter, the computing device 100 may provide guidance information for registering the message as an important message for the message that is determined to be an important message. For example, as shown in FIG. 9, when an important message is identified among messages transmitted and received between project participants, the computing device 100 may provide the important message registration UI 20 to the participant, and register the important message. The registration UI 20 may provide a message 20A determined to be an important message and guidance information 20B guiding the user to register the message as an important message (e.g., register a reminder). However, it is not limited to this.

In step S320, the computing device 100 may receive a request from a participant to register an important message for the important message determined through step S310. For example, if the participant wishes to register the message as an important message, the participant can select the reminder registration button 20C displayed through the important message registration UI 20, and the computing device 100 allows the participant to select the reminder registration button 20C. Selecting (20C) may be recognized as an important message registration request, and an operation of registering the message as an important message (step S330) may be performed.

In step S330, the computing device 100 may register the message as an important message in response to an important message registration request obtained from the participant and register a reminder for the registered important message. For example, the computing device 100 may provide the reminder registration UI 21 in response to obtaining an important message registration request from a participant.

In various embodiments, the computing device 100 may extract one or more summaries by analyzing a message set as an important message, place one or more extracted summaries in a preset reminder registration form 21A, and register the reminder. A reminder registration form 21A in which one or more summaries are arranged may be provided to the participant through the UI 21. In addition, the computing device 100 confirms one or more summaries according to the participant's input 21B (e.g., correction, addition, deletion, and confirmation of one or more summaries) entered through the reminder registration UI 21 to provide a reminder. You can register.

Here, the reminder registration method performed by the computing device 100 (e.g., extracting a summary from a message, placing the extracted summary on a preset form, confirming and registering the participant for the summaries placed on the form) is shown in Figure 1. It may be implemented in the same or similar form as the schedule registration method performed in steps S220 and S230 of 5, but is not limited thereto.

Thereafter, the computing device 100 may provide an important message management service that guides important messages to the reminder target according to the registered reminder. For example, as shown in FIG. 9, the computing device 100 is a reminder device that outputs information about an important message (e.g., content of the important message and a link connected to the location of the important message, etc.) to the reminder target according to the registered reminder. UI 22 can be provided.

Here, the method of providing an important message management service according to FIGS. 8 and 9 determines the importance of a message, provides guidance information to participants to register a specific message as an important message, and provides guidance information to participants to register a specific message as an important message. When receiving a request to register an important message for a message, it is explained that the message is set as an important message and a reminder is registered, but it is not limited to this and can be implemented in various forms.

For example, if the computing device 100 determines the importance of the message and determines that a specific message is an important message, the computing device 100 sets the message as an important message and automatically sends a reminder even if a separate important message registration request is not obtained from the participant. You can register. Hereinafter, with reference to FIGS. 10 to 14, the project attribute information providing service provided by the computing device 100 will be described.

Figure 10 is a flowchart of a method of providing a project attribute information service provided by a visualized project information providing server based on conversation analysis between project participants, in various embodiments, and Figures 11 to 14 are diagrams of conversations between project participants in various embodiments. This is a diagram showing the project attribute information provision service provided by the analysis-based visualized project information provision server.

Referring to FIGS. 10 to 14 , in step S410, the computing device 100 may determine the properties of the project by analyzing messages transmitted and received between project participants.

In various embodiments, the computing device 100 determines the properties (e.g., positive, negative) of a plurality of messages transmitted and received between project participants, issues occurring within the project, and whether the issues are resolved. You can use it to judge the mood of the project (e.g. positive, negative, etc.). For example, based on the properties of a plurality of messages transmitted and received between project participants, the computing device 100 determines the atmosphere of the project when the number of messages with negative properties is greater than the number of messages with positive properties. can be judged as negative.

Additionally, the computing device 100 may analyze a plurality of messages transmitted and received between project participants and determine that the atmosphere of the project is negative when an issue has occurred within the project but the issue has not yet been resolved. However, it is not limited to this, if an issue has occurred within the project and the issue has not yet been dealt with, but the number of messages with positive attributes is greater than the number of messages with negative attributes than a preset number, the atmosphere of the project is changed to positive. Various methods can be applied to judge the atmosphere of the project, such as judging it to be.

In various embodiments, the computing device 100 extracts one or more summaries from a plurality of messages transmitted and received between project participants over a preset period of time, and analyzes the one or more extracted summaries to generate summary information related to the progress of the project. can do. For example, the computing device 100 may analyze messages sent and received between participants within at least one of 3 hours, 6 hours, 12 hours, and 24 hours to extract one or more keywords related to the progress of the project, Summary information can be created using one or more extracted keywords. However, it is not limited to this.

In step S420, the computing device 100 may provide a project attribute information providing service that provides information on the attributes of the project determined in step S410 through the project attribute information providing UI 30.

Here, the project attribute information providing UI 30 includes information on the attributes of the project determined for each of the plurality of projects in which the first participant is participating, and as shown in FIG. 11, a plurality of projects corresponding to each of the plurality of projects. It can be implemented in a form where the cards are arranged in a grid and output.

At this time, the color of each card may be determined according to the atmosphere of the project corresponding to each card. For example, when the mood of the third project is negative, the color of the card (30A) corresponding to the third project can be displayed as the first color, and when the mood of the fourth project is positive, the color of the card (30A) corresponding to the third project can be displayed as the first color. The color of the corresponding card 30B may be displayed as a second color.

Additionally, even if the atmosphere of the project is the same, two cards with different degrees of saturation can be set to have different saturation. For example, if the mood of the fourth project is somewhat positive, the color of the card 30B corresponding to the fourth project may be set to have the first saturation, and if the mood of the eighth project is very positive, the color of the card 30B corresponding to the fourth project may be set to have the first saturation. The color of the card 30C corresponding to the project may be set to have a second saturation greater than the first saturation. Here, the first color, the second color, and the first saturation and second saturation may be set in advance by the project manager or each participant, but are not limited to this.

In addition, on the front of the plurality of cards corresponding to each of the plurality of projects, information about each of the plurality of projects (e.g., project name, number of unconfirmed messages sent and received between project participants, and at least one of the project attribute information) (including one) can be printed, and on the back of each of the plurality of cards, one or more keywords extracted from messages sent and received between participants in each of the plurality of projects can be printed.

The computing device 100 defaults to outputting each of a plurality of cards corresponding to each of a plurality of projects facing the front, but when a specific card is selected by the user (e.g., a mouse click input for a specific card) ), you can turn the card over so that the back side is printed.

For example, the computing device 100 may provide the project attribute information providing UI 30 as shown in FIG. 11 in response to obtaining a request for a project attribute information providing service from a participant. At this time, each card of a plurality of projects included in the project property information providing UI (30) can be faced face-down, and when an input to select a specific card (30D) is received, the card (30D) is flipped over so that the back side is turned over. It can be printed to be visible. However, it is not limited to this.

In various embodiments, the computing device 100 may visualize and provide the atmosphere of the project determined in step S410. For example, the computing device 100 may provide a visualization of the atmosphere of the project in the form of a graph, as shown in FIG. 12 .

Here, the atmosphere of the project can be visualized in the form of a graph by using each of the plurality of transmitted and received messages as an individual first point (coordinates) and displaying it as a line according to the weighted sum of the plurality of first points.

Additionally, a plurality of second points corresponding to issues occurring within the project may be displayed on the atmosphere 31 of the project visualized in the form of a graph.

At this time, the color of the plurality of second points may be determined depending on whether the issue corresponding to each of the plurality of second points is resolved. For example, if an issue corresponding to a specific second point is resolved, the second point corresponding to that issue may be displayed in blue, and if not resolved, the second point corresponding to that issue may be displayed in red. You can. However, it is not limited to this.

In a non-limiting example, an analysis method based on a summary or sentence structure may be used as a method of determining whether an issue occurs and is resolved from a messenger conversation. For example, in a conversation, the name of a specific project or its subcomponents, program name, function, structure, or configuration, along with preset negative words such as “problem,” “no,” “error,” or “error.” If a summary similar to this is included, it can be determined that an issue has occurred. Depending on the embodiment, if the conversation volume increases after the issue message is recognized, it may be determined that a conversation to resolve the issue is in progress. If a summary corresponding to resolution of the issue (e.g. "resolved") is recognized later, the issue can be judged to have been resolved. Similarly, if the message volume decreases after the summary corresponding to resolving the issue is recognized, the situation has ended. It can be judged that

The above method can be understood as an example, and various analysis methods without limitation can be used. For example, based on natural language processing, it is possible to determine the flow of issue occurrence and resolution without being limited to specific summaries or terms.

Through this method, information on issues that arise for each project and messenger conversation history leading up to their resolution can be recorded. If a messenger conversation or question that appears to be a similar issue is recognized later, the conversation history can be provided to help resolve the same or similar issue quickly.

In various embodiments, when a point (e.g., a first point and a second point) is selected by a participant on the atmosphere 31 of the project visualized in a graph form, the computing device 100 responds to the point. Content can be provided. For example, if the point selected by the participant is the first point, the computing device 100 may provide message content corresponding to the first point, and if it is the second point, the computing device 100 may provide issue content corresponding to the second point. and the history of the issue (e.g., history information from issue occurrence to issue resolution) can be provided.

In various embodiments, the computing device 100 may visualize and provide summary information related to the progress of the project created in step S410. For example, as shown in FIG. 13, the computing device 100 may provide visualization 32 of one or more keywords related to the progress of a project in the form of a word cloud. However, it is not limited to this.

In various embodiments, the computing device 100 generates a summary information list 33 including summary information about attribute information of each of a plurality of projects in which the first participant is participating, and sends a message including the generated summary information list. may be provided from the first participant to the first participant at preset times. For example, as shown in FIG. 14, the computing device 100 provides summary information regarding attribute information for each of a plurality of projects in which the first participant is participating (e.g., project name, purpose of the project, participants of the project). It is possible to create a summary information list 33 including the number of messages sent and received (or the number of unconfirmed messages among messages), the atmosphere of the project, etc.), and when the time set by the first participant is 9 am, There is an advantage in that a message including a summary information list 33 is provided every 9 a.m., allowing participants to quickly obtain status information about the projects they are participating in.

The method of providing visualized project information based on conversation analysis between project participants described above was explained with reference to the flow chart shown in the drawing. For simple explanation, the method of providing visualized project information based on conversation analysis between project participants is illustrated and described as a series of blocks. However, the present invention is not limited to the order of the blocks, and some blocks are similar to those shown and performed in this specification. They may be performed in different orders or simultaneously. Additionally, new blocks not described in this specification and drawings may be added, or some blocks may be deleted or changed. Hereinafter, with reference to FIGS. 15 and 16, the process of generating learning data for an artificial intelligence model used by the computing device 100 to perform a method of providing visualized project information based on conversation analysis between project participants will be described.

Figures 15 and 16 are diagrams illustrating a configuration for generating learning data for an artificial intelligence model that performs a method of providing visualized project information based on conversation analysis between project participants, in various embodiments.

First, referring to FIG. 15, the computing device 100 analyzes messages sent and received between project participants and provides first learning data to generate an artificial intelligence model that extracts one or more summary sentences related to the schedule included in the message. can be created.

For example, the computing device 100 may provide a learning data generation UI 40 to the participant terminal 200, and a plurality of first messages collected to generate learning data through the learning data generation UI 40. Labeling can be performed on the summaries included in each. Here, the plurality of first messages collected to generate learning data include schedule-related information (e.g., information about when, where, who, and what). It may be a message, but is not limited to this.

Participants label one or more summaries included in each of the plurality of first messages collected to generate learning data with one of when, where, who, and what. By doing this, first learning data can be generated.

At this time, the labeling target is each summary included in the message, and the summary may be a single word, but is not limited to this and may be a phrase or entire sentence that is a combination of two or more words. Additionally, two or more labels may be labeled for one summary.

Next, referring to FIG. 16, the computing device 100 analyzes messages sent and received between project participants and generates second learning data to create an artificial intelligence model that determines the importance of each message. .

For example, the computing device 100 may provide a learning data generation UI 40 to the participant terminal 200, and a plurality of second messages collected to generate learning data through the learning data generation UI 40. Labeling can be performed on the summaries included in each. Here, the plurality of first messages collected to generate learning data are messages containing information on importance (e.g., schedule, whether requests are included) and signals (e.g., whether an issue has occurred and whether the issue has been resolved). However, it is not limited to this.

Participants must ensure that each of the plurality of second messages collected to generate learning data includes a summary corresponding to importance (e.g., schedule, whether requests are included) and signal (e.g., whether an issue has occurred and whether the issue has been resolved). Second learning data can be generated by labeling the message (e.g., important, very important, very very important, (strong positive/negative, weak positive/negative)) depending on whether the message is present or not. Here, the labeling target is the entire message. It may be, but is not limited to this.

Above, embodiments of the present invention have been described with reference to the attached drawings, but those skilled in the art will understand that the present invention can be implemented in other specific forms without changing its technical idea or essential features. You will be able to understand it. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive.

100: Project management service provision server (computing device)
200: Participant terminal
300: external server
400: Network

Claims (1)

In a method performed by a computing device,
Analyzing messages sent and received between project participants and extracting one or more summaries; and
It includes providing a project management service based on the one or more extracted summaries,
The step of extracting the one or more summaries includes:
Analyzing a plurality of messages transmitted and received between participants of the project and determining the importance of each of the plurality of messages;
providing guidance information instructing to register a message whose determined importance is higher than a preset standard as an important message; and
When registering an important message is requested from a participant in response to the provided guidance information, extracting one or more summary sentences from the message for which registration of the important message is requested,
The steps for providing the project management service are:
Registering a reminder for the important message using the one or more extracted summaries, and providing an important message management service that guides the important message to the reminder target according to the registered reminder,
The step of determining the importance of each of the plurality of messages is:
Based on the importance score for each summary that is already stored, adding up the importance scores for one or more summaries extracted from a specific message, and if the summed importance score is greater than or equal to a preset score, determining that the specific message is an important message. Includes,
The steps for providing the project management service are:
Analyzing messages transmitted and received between participants of the project to determine the properties of the project; and
Comprising a step of providing a project attribute information provision service that provides information on the attributes of the determined project,
The step of determining the properties of the project is,
Among the plurality of messages sent and received between participants in the project, at least one of the number of messages with positive and negative attributes, the progress of the project, and issues occurring within the project and whether or not the issues are resolved is used. It includes the step of determining the mood of the project,
The step of providing the project attribute information service is,
The atmosphere of the determined project is visualized and provided, wherein the visualized atmosphere of the project is visualized in the form of a graph according to the weighted sum of a plurality of first points corresponding to each of the plurality of messages transmitted and received, and is presented in the form of a graph. In the atmosphere of the visualized project, a plurality of second points corresponding to issues occurring within the project are displayed, and the color of each of the plurality of second points depends on whether the issue corresponding to each of the plurality of second points is resolved. Contains steps that are determined,
The step of providing the project attribute information service is,
Generating a summary information list containing summary information about the attribute information of each of the plurality of projects in which the first participant is participating, and the generated summary information list - The generated summary information list includes the plurality of projects in which the first participant is participating. A message containing the project name of each project, the purpose of the project, the number of unconfirmed messages among messages sent and received between project participants, and the atmosphere of the project - is sent from the first participant at a preset time to the first participant. It includes steps to provide participants,
The step of determining the properties of the project is,
Extracting one or more summaries from a plurality of messages transmitted and received between participants of the project during a preset period of time, analyzing the one or more extracted summaries to generate summary information related to the progress of the project,
The step of providing the project attribute information service is,
The generated summary information is visualized and provided, wherein the visualized summary information visualizes one or more keywords related to the progress of the project in the form of a word cloud, including the step of:
A method of providing visualized project information based on conversation analysis between project participants.