WO2024096194A1

WO2024096194A1 - Information sharing platform service system and method based on inter-chatbot conversation technology using deep learning

Info

Publication number: WO2024096194A1
Application number: PCT/KR2022/021031
Authority: WO
Inventors: 박춘우
Original assignee: 박춘우
Priority date: 2022-11-04
Filing date: 2022-12-22
Publication date: 2024-05-10
Also published as: KR102630697B1

Abstract

The present invention relates to an information sharing platform service method based on inter-chatbot conversation technology using deep learning, the chatbot service-based information sharing method using user terminals and a platform server, and comprising: (a) a step for requesting a to-do list input from a first user terminal through an application service of the platform server; (b) a step in which a first chatbot corresponding to a first user of the platform server recommends sharing information including result information about the result of performing the to-do list generated on the basis of the requested to-do list information and information about the first user and derives information about subjects with which to share the sharing information; and (c) a step in which the first chatbot of the platform server shares the sharing information with a second chatbot, corresponding to at least one subject in the derived subject information, through an inter-chatbot conversation process.

Description

Information sharing platform service system and method based on chatbot conversation technology using deep learning

The present invention relates to an information sharing platform service system and method, and more specifically, to an information sharing platform service system and method based on a chatbot capable of deep learning-based communication and a data-based advertising target recommendation algorithm.

Chatbots are interactive messengers that can handle inquiries or simple services regardless of time or person, so they are used as a platform to connect various functions.

Chatbots have become a service at the level of providing predetermined answers according to pre-entered algorithms, but as natural language analysis and processing technology develops along with big data processing technology, it is providing optimal answers that take into account various variables.

Meanwhile, information providers are changing from providing one-sided advertising information and investment information to an unspecified number of people to providing customized information according to the user's interests.

However, in order to present customized advertisements according to the user's interests, it is necessary to use chat data, but estimating the user's interests only with real-time chat data has limitations, so the effect of targeted advertising is very limited.

Therefore, there is a need for the development of technical means that can more precisely match users' interests with advertising products. In addition, additional technology development is needed to effectively guide users into the area of targeted advertising.

Additionally, chatbots used in existing messenger applications cannot provide services through the chatbot without the user who wants to use the chatbot selecting it.

For this reason, even though various chatbot services exist, there was the inconvenience of users having to search for and use chatbots themselves.

The purpose of the present invention to solve the conventional problems described above is to provide an information sharing platform service system and method based on a chatbot capable of deep learning-based communication and a data-based advertising target recommendation algorithm.

In addition, the purpose of the present invention to solve the conventional problems as described above is to provide services such as shopping mall linkage, individual live streaming, advertising, metaverse linkage, and electronic business cards based on a platform that enables communication between chatbots. To provide service systems and methods.

In order to achieve the above purpose, the information sharing platform service method based on chatbot-to-chatbot conversation technology using deep learning according to the present invention is an information sharing method based on a chatbot service with a user terminal and a platform server, (a) 1. Requesting a requested task (to do list) entered through the application service of the platform server from the user terminal; (b) The first chatbot corresponding to the first user of the platform server recommends shared information including the requested task information and result information of performing the requested task generated based on the first user information. and deriving target information to be shared; and (c) sharing the shared information through an inter-chatbot conversation process with a second chatbot corresponding to at least one target among the target information derived from the first chatbot of the platform server. do.

In addition, step (a) includes registering a plurality of user terminals by accessing the platform server and entering user information and login information; And requesting a requested task (to do list) entered through the application service of the platform server from the registered first user terminal, wherein the user information includes the user's occupation, age, gender, and interest information. It is characterized by including.

In addition, the application service includes a personal page creation service based on user activity and electronic business cards, a ranked relationship network service, a live streaming service, an SNS advertisement sharing service, a shopping mall linkage service, a host information sharing service, and a metaverse linkage service. It is characterized by

In addition, step (b) includes: (b1) the platform server pre-processing user-related information including the user information, user activity information, and network information and forming a database; and (b2) the first chatbot recommends shared information including the result information of performing the requested task from the AI module based on the requested task information and requests information on the person to be shared, and the target person derived by the AI module Characterized in that it includes a step of receiving information.

In addition, in step (b2), the AI module generates the target information using a collaborative filtering method that recommends a target host based on the user-related information of the first user, and uses an optimized Bayesian personalized ranking method (OBPR). : It is characterized by applying an adaptive sampling algorithm based on Optimizer Bayesian personalized ranking.

In addition, step (c) includes: (c1) the first chatbot sharing the shared information with the second chatbot through a conversation process; (c2) the second chatbot requesting additional information of interest from the first chatbot through a conversation process; and (c3) the step of the first chatbot responding to the additional request through a conversation process with the second chatbot and sharing additional shared information.

In addition, after step (c), the AI module may periodically visualize and provide information obtained by analyzing the user's information satisfaction data to the first chatbot and the second chatbot.

And, in order to achieve the above purpose, the information sharing platform service system based on conversation technology between chatbots using deep learning according to the present invention is an information sharing platform system in which a user terminal and a platform server are connected through a network, the platform server A plurality of user terminals that access and register users by entering user information and login information, and execute application services provided by the platform server; And executing the application service, receiving request task (to do list) information from the user terminal, a first chatbot corresponding to the first user who entered the request task information and the first user Based on the information, a conversation process between a chatbot and a second chatbot corresponding to at least one target among the derived target information by recommending shared information including information as a result of performing the request task to derive target information to be shared. It is characterized in that it includes a platform server that shares the shared information through.

In addition, the platform server includes a user registration unit that performs a user registration procedure with the user terminal; a service execution unit that executes the application service; a platform DB unit that stores and manages user information input from the user terminal and user-related information generated by execution of the application; And the first chatbot recommends sharing information including result information of performing the requested task based on the requested task information and the first user information to derive target information to be shared, and at least one of the derived target information A chatbot system that shares the shared information through a conversation process between a second chatbot corresponding to one target and the chatbot.

The chatbot system includes a chatbot unit provided with a plurality of chatbots that individually correspond to each user terminal and perform a request task (to do list) conversation process requested by each user terminal; Information input or output to the chatbot is generated through NLP processing and transmitted to the chatbot unit, and the information input to the at least one chatbot is analyzed to make the request based on the request task information and the first user information. An AI module that recommends shared information including information on the results of performing a task and derives information about the person to be shared; and a chatbot sharing unit that shares the shared information through a conversation process with the first chatbot and a second chatbot corresponding to at least one of the derived target information.

In addition, the platform DB unit is characterized in that the platform server includes a preprocessing unit for preprocessing user-related information including the user information, user activity information, and relationship network information.

In addition, the AI module generates the target information using a collaborative filtering method that recommends a target host based on the user-related information of the first user, and is based on Optimizer Bayesian personalized ranking (OBPR). It is characterized by applying an adaptive sampling algorithm.

Specific details of other embodiments are included in “Specific Details for Carrying Out the Invention” and the attached “Drawings.”

The advantages and/or features of the present invention and methods for achieving them will become clear by referring to the various embodiments described in detail below along with the accompanying drawings.

However, the present invention is not limited to the configuration of each embodiment disclosed below, but may also be implemented in various different forms. However, each embodiment disclosed in this specification ensures that the disclosure of the present invention is complete, and the present invention It is provided to fully inform those skilled in the art of the present invention, and it should be noted that the present invention is only defined by the scope of each claim.

According to the present invention, a request task set by the host is performed by using a request task (To do list) set by the host and an intelligent data-based recommendation system to find a host to share information optimized for the information to be shared by various hosts on the personal network. A platform service system and method can be provided to perform the tasks on the (To do list) by oneself and analyze and share the results with the host.

In addition, according to the present invention, it is possible to provide a technology-based mobile complex communication platform service system and method for a deep learning-based chatbot-to-chatbot conversation method.

In addition, according to the present invention, an information sharing platform based on a chatbot capable of deep learning-based communication and a data-based advertising target recommendation algorithm, and a shopping mall linkage based on this, individual live streaming, advertisements, metaverse linkage, electronic business cards, etc. A platform service system and method that can provide services can be provided.

Figure 1 is a diagram showing the detailed flow of an information sharing platform service method based on conversation technology between chatbots using deep learning according to an embodiment of the present invention.

Figure 2 is a diagram showing the block configuration of an information sharing platform service system based on conversation technology between chatbots using deep learning according to an embodiment of the present invention.

Figure 3 is a flowchart showing the algorithm configuration of a chatbot system applied to an information sharing platform service system and method based on chatbot-to-chatbot conversation technology using deep learning according to an embodiment of the present invention.

Figure 4 is a diagram illustrating the concept of deriving shared information subjects applied to the information sharing platform service system and method based on conversation technology between chatbots using deep learning according to an embodiment of the present invention.

Figure 5 is a diagram illustrating the information sharing process applied to the information sharing platform service system and method based on conversation technology between chatbots using deep learning according to an embodiment of the present invention.

Figure 6 is a diagram showing the flow of information sharing through the chatbot-to-chatbot conversation process of the chatbot system applied to the information sharing platform service system and method based on chatbot-to-chatbot conversation technology using deep learning according to an embodiment of the present invention.

Figure 7 is a diagram showing the flow of additional information sharing through a conversation process between chatbots in a chatbot system applied to an embodiment of the present invention.

Figure 8 is a diagram illustrating the main screen of a personal page applied to the information sharing platform service system and method based on conversation technology between chatbots using deep learning according to an embodiment of the present invention.

Figure 9 is a diagram illustrating the main functions of the platform service applied to the information sharing platform service system and method based on conversation technology between chatbots using deep learning according to an embodiment of the present invention.

Figure 10 is a diagram illustrating SNS marketing and live streaming services applied to the information sharing platform service system and method based on conversation technology between chatbots using deep learning according to an embodiment of the present invention.

The present invention relates to a chatbot service-based information sharing method comprising a user terminal and a platform server, comprising: (a) requesting a request task (to do list) entered through an application service of the platform server from a first user terminal; ; (b) The first chatbot corresponding to the first user of the platform server recommends shared information including the requested task information and result information of performing the requested task generated based on the first user information. and deriving target information to be shared; and (c) deep learning comprising the step of sharing the shared information through an inter-chatbot conversation process with a second chatbot corresponding to at least one target among the target information derived from the first chatbot of the platform server. Provides an information sharing platform service method based on conversation technology between chatbots.

Before explaining the present invention in detail, the terms or words used in this specification should not be construed as unconditionally limited to their ordinary or dictionary meanings, and the inventor of the present invention should not use the terms or words in order to explain his invention in the best way. It should be noted that the concepts of various terms can be appropriately defined and used, and furthermore, that these terms and words should be interpreted with meanings and concepts consistent with the technical idea of the present invention.

That is, the terms used in this specification are only used to describe preferred embodiments of the present invention, and are not used with the intention of specifically limiting the content of the present invention, and these terms refer to various possibilities of the present invention. It is important to note that this is a term defined with consideration in mind.

In addition, it should be noted that in this specification, singular expressions may include plural expressions, unless the context clearly indicates a different meaning, and may include singular meanings even if similarly expressed in plural. .

Throughout this specification, when a component is described as “including” another component, it does not exclude any other component, but includes any other component, unless specifically stated to the contrary. It could mean that you can do it.

Furthermore, if a component is described as being "installed within or connected to" another component, it means that this component may be installed in direct connection or contact with the other component and may be installed in contact with the other component and may be installed in contact with the other component. It may be installed at a certain distance, and in the case where it is installed at a certain distance, there may be a third component or means for fixing or connecting the component to another component. It should be noted that the description of the components or means of 3 may be omitted.

On the other hand, when a component is described as being “directly connected” or “directly connected” to another component, it should be understood that no third component or means is present.

Likewise, other expressions that describe the relationship between each component, such as "between" and "immediately between", or "neighboring" and "directly neighboring", have the same meaning. It should be interpreted as

In addition, in this specification, terms such as "one side", "other side", "one side", "the other side", "first", "second", etc., if used, refer to one component. It is used to clearly distinguish it from other components, and it should be noted that the meaning of the component is not limited by this term.

In addition, in this specification, terms related to position such as "top", "bottom", "left", "right", etc., if used, should be understood as indicating the relative position of the corresponding component in the corresponding drawing. Unless the absolute location is specified, these location-related terms should not be understood as referring to the absolute location.

In addition, in this specification, when specifying the reference numeral for each component in each drawing, the same component has the same reference number even if the component is shown in different drawings, that is, the same reference is made throughout the specification. The symbols indicate the same component.

In the drawings attached to this specification, the size, position, connection relationship, etc. of each component constituting the present invention is exaggerated, reduced, or omitted in order to convey the idea of the present invention sufficiently clearly or for convenience of explanation. It may be described, and therefore its proportions or scale may not be exact.

In addition, hereinafter, in describing the present invention, detailed descriptions of configurations that are judged to unnecessarily obscure the gist of the present invention, for example, known technologies including prior art, may be omitted.

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

As shown in Figure 1, the information sharing platform service method based on chatbot-to-chatbot conversation technology using deep learning according to an embodiment of the present invention is provided with a user terminal 100 and a platform server 200 to provide a chatbot service-based service. In the information sharing method, (a) requesting a requested task (to do list) entered through an application service of the platform server 200 from the first user terminal 100 (S100); (b) Sharing including result information of performing the requested task generated by the first chatbot corresponding to the first user of the platform server 200 based on the requested task information and the first user information. Recommending information and deriving information about the person to share (S200); and (c) the shared information through a conversation process between the second chatbot 251b and the chatbot corresponding to at least one target among the target information derived from the first chatbot 251a of the platform server 200. It may be configured to include a sharing step (S300).

As such, the information sharing platform service method based on conversation technology between chatbots using deep learning according to an embodiment of the present invention is a mobile complex communication application platform service method through a conversation process between chatbots based on deep learning that allows free communication between chatbots. provides.

In addition, the information sharing platform service method based on conversation technology between chatbots using deep learning according to an embodiment of the present invention includes providing a chatbot service capable of deep learning-based communication and an information sharing platform service using an advertising target recommendation algorithm. In addition, it provides a complex platform service method that provides services such as shopping mall linkage, individual live streaming, SNS advertising, metaverse linkage, and electronic business cards.

More specifically, as shown in Figure 1, step (a) (S100) requests a request task (to do list) entered through the application service of the platform server 200 from the first user terminal 100. This may be a step.

In addition, step (a) (S100) is a step of registering a plurality of user terminals 100 by accessing the platform server 200 and entering user information and login information, and the registered first user It may include the step of requesting a requested task (to do list) entered through the application service of the platform server 200 at the terminal 100.

That is, the registration step may be a step of accessing the platform server 200 through an application executing a service method according to an embodiment of the present invention and entering user information and login information (ID and password).

Here, the user information may include the user's occupation, age, gender, and interest information.

Additionally, the user information may include electronic business card-based information such as the user's career or history, and may also include relationship network information that appears when multiple registered users form relationship information with each other according to a preset method.

In addition, the application service provided through the information sharing platform service method based on conversation technology between chatbots using deep learning according to an embodiment of the present invention includes a personal page creation service based on user activity and electronic business cards, a ranked relationship network service, It may include live streaming services, SNS advertising sharing services, shopping mall linking services, host information sharing services, and metaverse linking services.

That is, in an embodiment of the present invention, multiple registered users access the platform server 200 through each user terminal 100, create personal pages based on the electronic business cards described above, and share each other's personal pages. It is possible to provide a service that allows you to create a relationship network (first-degree connections, etc.).

In addition, each user can provide a personal live streaming service to provide various content that the individual wants to share as a broadcast streaming service, and it is also possible to share various advertising information related to the provided content through SNS.

In addition, a service that links with a shopping mall can be provided so that information such as shared products can be purchased in real time, and a service that can share the host's interest information or setting information through a chatbot-to-chatbot conversation system, which will be described later, is provided through Metaverse. It is also possible to provide services that link with .

In step (S200), the first chatbot corresponding to the first user of the platform server 200 performs the requested task created based on the requested task information and the first user information. This may be the step of recommending shared information including result information and deriving information about the person to be shared.

More specifically, step (b) includes (b1) the platform server 200 preprocessing user-related information including the user information, user activity information, and relationship network information and converting it into a database (S210), (b2) ) The first chatbot recommends shared information including the result information of performing the requested task from the AI module 253 based on the requested task information and requests information about the person to be shared, and the AI module 253 derives the information. It may be configured to include a step of receiving the target information (S230).

Step (b1) (S210) is user-related, including the user information entered in step (a), activity information generated while the user is active in the application service provided in the embodiment of the present invention, and relationship network information established between users. Information can be stored in the platform DB.

In order to efficiently store and manage the user-related information described above, the platform DB unit 240 first pre-processes the generated user-related information through a preprocessing unit. Preprocessing refers to the processing step so that it can be efficiently used and managed in applications, and may include tasks such as language preprocessing, keyword/content separation, and Korean DB storage for Korean information processing.

In addition, the generation of the target information in the AI module 253 in step (b2) (S230) is a collaborative filtering method that recommends a target host based on the user-related information of the first user, and the optimization Bayesian personalization ranking An adaptive sampling algorithm based on OBPR (Optimizer Bayesian personalized ranking) may be applied.

As such, in an embodiment of the present invention, a personalized recommendation system that can recommend specific information tailored to each individual can be used to derive the people with whom to share shared information.

In general, a personalized recommendation system is a system that recommends products by predicting the user's preference for products from the user's past history data such as ratings, transactions, clicks, viewing history, etc., but in an embodiment of the present invention Conversely, technology can be applied to predict or derive subjects who may be interested in information set or created by the host.

There are two main types of data that can be analyzed to develop a recommendation system: explicit feedback data and implicit feedback data.

Explicit feedback refers to data that directly reveals the user's preference, such as the rating given by the user, ranging from ‘very bad’ to ‘very good’.

In conventional research, many statistical modeling techniques have been used to analyze the prediction of users' product preferences from explicit feedback data.

On the other hand, implicit feedback refers to behavioral data that can indirectly reveal a user's preference for a product, such as the number of times a user views a product/clicks and the user's purchase history. In general, users' implicit feedback data is more common and easier to obtain than explicit feedback. Moreover, implicit feedback material can exist even in the absence of explicit feedback.

Therefore, from the intrinsic feedback data that appears in the activities of the platform service provided in the embodiment of the present invention, the reliability of information sharing and interest increase by deriving the people with whom the host will share information that is set or of interest through an appropriate personalized recommendation system. This can contribute to the revitalization of platform services.

Additionally, in this embodiment of the present invention, the Bayesian personalized ranking (BPR) method can be used by probabilistically modeling preferences between products.

The Bayesian personalized ranking method can apply a personalized recommendation system that optimizes the personalized ranking that maximizes the area under the receiver operating characteristic (ROC) curve (area under ROC curve (AUC)).

This Optimizer Bayesian personalized ranking method (OBPR) empirically shows superior performance compared to conventional recommendation system techniques in many cases.

Additionally, the numerical size of implicit data can be viewed as the certainty of feedback, which can be useful information about an individual's preferences.

In addition, the collaborative filtering (CF) method can be applied to embodiments of the present invention, where 'collaboration' refers to similar usage behavior of a specific user group, and 'collaborative filtering' is based on information obtained from collaboration. This is a method of extracting recommendations and recommending them to consumers.

That is, in the embodiment of the present invention, each user can be said to 'collaborate' as a group of similar specific users using network information, and can recommend information sharing partners through the related information of users in this network.

Here, similar behavior of a group of users may be activity information about various platform services provided by multiple users belonging to a relationship network in an embodiment of the present invention.

And, as shown in FIG. 1, in step (c) (S300), the first chatbot 251a of the platform server 200 chats with a second chatbot corresponding to at least one of the derived target information. This may be a step of sharing the shared information through a conversation process between the chatbot 251b and the chatbot.

More specifically, step (c) includes (c1) the first chatbot sharing the shared information through a conversation process with the second chatbot (251b) (S310), and (c2) the second chatbot A step of requesting additional information of interest through a conversation process with the first chatbot (S320), and (c3) the first chatbot responds to the additional request through a conversation process with the second chatbot and shares additional shared information. It may include a step (S330).

In addition, as another embodiment of the present invention, after step (c) (S300), the AI module 253 periodically analyzes the user's information satisfaction data with the first chatbot and the second chatbot 251b. It may further include the step of providing visualization.

As such, in the embodiment of the present invention, through a deep learning-based chatbot-to-chatbot conversation process or system, the chatbot corresponding to the person to share the shared information derived in step (b) and the host chatbot have a conversation using the conversation AI module 253. May include information sharing steps throughout the process.

As shown in Figure 2, the information sharing platform service system based on conversation technology between chatbots using deep learning according to an embodiment of the present invention is an information sharing system in which the user terminal 100 and the platform server 200 are connected through a network. In the platform system, a plurality of user terminals 100 connect to the platform server 200, register users by entering user information and login information, and execute application services provided by the platform server 200; And executing the application service, receiving the requested task (to do list) information from the user terminal 100, and a first chatbot corresponding to the first user who entered the requested task information and the requested task information and the Based on the first user information, a second chatbot (251b) recommends shared information including information as a result of performing the requested task, derives target information to be shared, and corresponds to at least one target among the derived target information. ) and a platform server 200 that shares the shared information through a conversation process between chatbots.

Here, the user terminal 100 is a computing device equipped with a communication device carried by the user, such as a smartphone or tablet PC, and is a device that installs the platform application program provided in the embodiment of the present invention and executes the platform service. You can.

In addition, the user terminal 100 and the platform server 200 can communicate through a network, and the network for communication applied to the system of the embodiment of the present invention is a network between each node such as a plurality of terminals and servers. It refers to a connection structure that allows information exchange. Examples of such networks include Local Area Network (LAN), Wide Area Network (WAN), World Wide Web (WWW), wired and wireless data communication networks, Includes telephone networks, wired and wireless television networks, etc.

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 the following, the term at least one is defined as a term including singular and plural, and even if the term at least one does not exist, each component may exist in singular or plural, and may mean singular or plural. This should be self-explanatory. In addition, whether each component is provided in singular or plural form may be changed depending on the embodiment.

More specifically, the shared platform server 200 shown in FIG. 2 includes a communication unit 210, a user registration unit 220, a service execution unit 230, a platform DB unit 240, and a chatbot system 250. It can be configured.

The communication unit 210 may be a communication device that communicates with the user terminal 100 over a network to exchange information about platform services.

The user registration unit 220 may be configured to access the platform server 200 through an application UI installed on the user terminal 100 and perform a user registration procedure when each user enters user information and login information.

The service execution unit 230 is a component that executes platform application services, including user activity and electronic business card-based personal page creation service, ranked relationship network service, live streaming service, SNS advertisement sharing service, shopping mall linkage service, and host information sharing. You can run services and metaverse interconnected services.

The platform DB unit 240 is a database device provided in the server and may be a device that stores and manages user information input from the user terminal 100 and user-related information generated by execution of the application.

And, as shown in FIG. 2, the chatbot system 250 may be configured to execute a deep learning-based chatbot service including an AI module 253.

In addition, the chatbot system 250 is one of each chatbot corresponding to the plurality of user terminals 100, and the first chatbot corresponding to the host user provides request task (to do list) information and the first user information. Based on this, it is possible to derive information about the person to be shared by recommending shared information including information as a result of performing the above request task.

Additionally, the chatbot system 250 may share the shared information through a conversation process between chatbots and a second chatbot 251b corresponding to at least one target among the derived target information.

And, as shown in FIG. 2, the chatbot system 250 includes a chatbot unit equipped with a plurality of chatbots, an AI module 253 that provides software such as a deep learning-based algorithm for performing chatbot services, and a chatbot-to-chatbot system. It may be configured to include a chatbot sharing unit 255 that shares shared information between users through a conversation process.

More specifically, the chatbot unit may be equipped with a plurality of chatbots that individually correspond to each user terminal 100 and perform a request task (to do list) conversation process requested by each user terminal 100.

The AI module 253 generates information input or output to the chatbot through deep learning-based NLP processing and delivers it to the chatbot unit, and analyzes the information input to the at least one chatbot to provide the requested task information. And based on the first user information, shared information including information on the results of performing the requested task can be recommended to derive information about the person to be shared.

The chatbot sharing unit 255 may share the shared information through a conversation process with the first chatbot and the second chatbot 251b corresponding to at least one of the derived target information.

And, as shown in FIG. 2, the platform DB unit 240 may include a preprocessing unit in which the platform server 200 preprocesses user-related information including the user information, user activity information, and network information. .

Here, the preprocessing unit preprocesses the input language for the chatbot's conversation process, separates keywords and content, analyzes data from users or hosts subscribed to the platform network, and stores the analysis results in a DB. Saving requested task (to do list) information in the DB, storing Korean information for information processing such as Korean in the DB, storing host schedule information in the DB, host-based relationship network information (1st connection or more) You can store registered platform member or user information in the DB.

In addition, the AI module 253 generates the target information using a collaborative filtering method that recommends a target host based on the user-related information of the first user, and as described above, the optimized Bayesian personalization ranking method (OBPR) is used. : Optimizer Bayesian personalized ranking)-based adaptive sampling algorithm can be applied.

Figure 3 is a flowchart showing the algorithm configuration of the chatbot system 250 applied to the information sharing platform service system and method based on chatbot-to-chatbot conversation technology using deep learning according to an embodiment of the present invention.

As shown in FIG. 3, when input information that causes the chatbot service of the chatbot system 250 to start is received, a conversation system (Talk system) such as a messenger of the chatbot system can be started.

And, when a conversation language such as text is input into the conversation system, the text data is processed using machine learning for the language input through NLP (Natural Language Processing).

LNP-processed language text information understands the meaning of the input text information through NLU (Natural Language Understanding), and uses a deep learning chatbot algorithm to generate NLG (Natural Language Generation) response information to generate corresponding response information. can be created.

Here, natural language processing (NLP) is a field of artificial intelligence (AI) technology that allows computers to understand, generate, and manipulate human language, and natural language processing (NLP) is a field of artificial intelligence (AI) technology that interconnects data with natural language text or voice. This is also called ‘language in’.

Natural language understanding (NLU) and natural language generation (NLG) each refer to the use of computers to understand and generate human language, and in the case of NLG, can provide a verbal explanation of what happened, a concept called 'graphical grammar'. It can also be called 'language output' by summarizing meaningful information into text.

And, as shown in Figure 3, the deep learning chatbot algorithm applied to the embodiment of the present invention recognizes sentences by applying the Seq2Seq (Sequence-to-Sequence) method and uses convolutional neural networks (ConvNets) to recognize sentences. After analyzing and recognizing the entity name in the sentence using the NER (Named Entity Recognition)/Bi-LSTM algorithm, an accurate conversation process between chatbots can be performed.

Here, Seq2Seq (Sequence-to-Sequence) is a method that takes a sentence as input and outputs the sentence immediately, and can be implemented using two RNNs: an encoder and a decoder.

In addition, convolutional neural networks are character-level convolutional networks, a text classification technology that extracts useful information by applying a character level model that receives text information as a raw signal. It can be a technology that shows high performance.

The chatbot system 250 according to an embodiment of the present invention using the artificial intelligence-based technology described above is capable of communicating between chatbots, performs host commands (to do list), and performs a conversation process in conjunction with an avatar. It is possible to perform a voice recognition service based on a preset language (Korean, etc.).

In addition, it is possible to create chatbot functions for each user, link avatars and chatbots, communicate between chatbots using a messenger system, and perform notification and invitation functions of live streaming information executed by users.

Figure 4 is a diagram illustrating the concept of deriving shared information subjects applied to the information sharing platform service system and method based on conversation technology between chatbots using deep learning according to an embodiment of the present invention, and Figure 5 is an implementation of the present invention. This is a diagram illustrating the information sharing process applied to the information sharing platform service system and method based on conversation technology between chatbots using deep learning according to an example.

As shown in Figure 4, in the embodiment of the present invention, the artificial intelligence chatbot system 250 can derive the optimal information sharing target through a target recommendation algorithm.

In other words, it is possible to apply collaborative filtering technology that recommends a target host based on the interest information of first-degree members or hosts of other groups included in the network information with similar tendencies as the host (first user).

An adaptive sampling algorithm based on Optimizer Bayesian personalized ranking (OBPR) can be applied.

Here, OBPR is a probability model of preference between products and analyzes the information preferred by the host (user) by categorizing it step by step.

Based on the OBPR analysis results, the intelligent chatbot selects target hosts and performs the requested tasks (to do list) set by the main host.

And, as shown in FIG. 5, in the embodiment of the present invention, graded relationship network information (1st-degree connections information, etc.) stored in the platform DB unit 240 can be stored, and each registered user can log in through membership authorization. Information sharing process can be performed between members.

For example, communication through a conversation process can be performed through a messenger in conjunction with each avatar of the chatbot system 250 between hosts, and chatbot messenger communication between hosts is also possible, as well as advertising between hosts or between first-degree connections. It is also possible to share information.

Figure 6 is a diagram showing the flow of information sharing through the chatbot-to-chatbot conversation process of the chatbot system 250 applied to the information sharing platform service system and method based on chatbot-to-chatbot conversation technology using deep learning according to an embodiment of the present invention; Figure 7 is a diagram showing the flow of additional information sharing through a conversation process between chatbots of the chatbot system 250 applied to an embodiment of the present invention.

The characteristic of the interactive chatbot applied to the embodiment of the present invention is that it is an intelligent chatbot and can perform rule-based, information exchange chatbot functions in accordance with requested task (to do list) information.

As shown in FIG. 6, when a request task or to-do list is entered into the first chatbot 251a corresponding to the first user, the first chatbot 251a sends a to-do task to the AI module 253. and request parsing of a text word, and the AI module 253 parses the requested tasks and words and transmits the parsed information to the first chatbot 251a.

Based on the analyzed parsing information, the first chatbot again requests word analysis to the AI module 253, and the AI module 253 transmits the analysis information to the first chatbot 251a.

The first chatbot 251a requests target information with which to share the information based on the analysis information received from the AI module 253, and the AI module 253 transmits information about the conversation target with which to share the information. and share it.

Based on the shared information sharing target information, the first chatbot transmits the information set by the first user to the chatbots (second chatbot 251b) corresponding to the target, and the second chatbot 251b Share information in a responsive manner.

Figure 7 shows the flow of additional information sharing through the conversation process between chatbots of the chatbot system 250 applied to an embodiment of the present invention. After sharing information between the first chatbot 251a and the second chatbot, the first 2 The chatbot 251b may request additional information of interest from the first chatbot 251a.

When the second chatbot 251b requests additional information of interest from the first chatbot 251a, the first chatbot 251a requests word parsing from the AI module 253 for the additional information of interest, and the AI module After parsing (253), the parsed information is transmitted to the first chatbot (251a).

Again, the first chatbot 251a requests word analysis from the AI module 253 based on the parsed information, and after analyzing the word, the AI module 253 sends the analyzed information to the first chatbot 251a. send.

Then, the first chatbot majors in the second chatbot (251b) the response information to the additional request requested by the second chatbot (251b) based on the analyzed word information and sends the first and second chatbots to the first and second chatbots for additional information of interest. (251b) It can be shared between people.

And, after performing this sharing process between chatbots, the AI module 253 visualizes the satisfaction data analysis information and transmits it to the first chatbot 251a and the second chatbot 251b, so that each chatbot that performed the conversation process The contents of the information performed can be stored in the platform DB unit 240, and the data analysis results can be visualized and displayed on each host user terminal 100 for a set period such as day/week/month. .

In addition, the preprocessing unit shown in FIGS. 6 and 7 can perform the above-described preprocessing work and link with each chatbot to provide information necessary or selected for the conversation process between chatbots.

Figure 8 is a diagram illustrating the main screen of a personal page applied to the information sharing platform service system and method based on conversation technology between chatbots using deep learning according to an embodiment of the present invention, and Figure 9 is a diagram illustrating the main screen of the personal page according to an embodiment of the present invention. A diagram illustrating the main functions of the platform service applied to the information sharing platform service system and method based on conversation technology between chatbots using deep learning, and Figure 10 shows conversation technology between chatbots using deep learning according to an embodiment of the present invention. This is a diagram illustrating SNS marketing and live streaming services applied to the information sharing platform service system and method.

The platform service according to the embodiment of the present invention illustrated in Figures 8 to 10 is an electronic business card-based artificial intelligence advertising sharing platform service that provides natural communication between users using an 'intelligent network management system' using relationship network information stored in the DB. Through communication, we can provide services that enable cultural exchange and quick delivery of information.

In addition, the information sharing platform service based on chatbot-to-chatbot conversation technology using deep learning according to an embodiment of the present invention includes 1) shopping mall linkage 2) personal page creation 3) host and first-degree connection creation and management 4) live streaming communication function 5) Services such as advertising sharing (live streaming, SNS, VOD, etc.) 6) host information sharing 7) metaverse linkage can be performed.

As shown in Figure 8, the main screen of the personal page of the platform service applied to the embodiment of the present invention contains the user's profile information, relationship network information such as first-degree connections, a chatbot system 250 linked to an avatar, and a live stream and service. Information can be provided through UI.

Here, the host's network information is personal network information and may be information automatically classified based on information such as Kakao Talk, email, and region and stored in the platform DB unit 240.

Additionally, each user can be equipped with a chatbot that is linked to the corresponding avatar, and the avatar composed of characters can be selected or changed by the user.

As shown in Figure 9, the main functions of the platform service applied to the embodiment of the present invention may include a personal avatar function, an artificial intelligence chatbot function, a live streaming function, a personal page creation function, a video chat function, etc., Avatar-linked chatbot-to-chabot chat and video chat functions can be used both 1:1 and 1:N to increase users' service utilization and participation.

And, as shown in FIG. 10, the platform service according to an embodiment of the present invention posts photo information of advertising products, and the chatbot system 250 automatically posts the photo information to Naver, Facebook, Instagram, blogs, and YouTube. It can perform SNS marketing functions such as automatically uploading and posting on SNS.

In addition, the live streaming service can perform a one-to-one live broadcasting service to manage each user's network information, perform individual live on-site relay services, and also provide a service that allows users to upload videos in real time. do.

Above, various preferred embodiments of the present invention have been described by giving some examples, but the description of the various embodiments described in the "Detailed Contents for Carrying out the Invention" section is merely illustrative and the present invention Those skilled in the art will understand from the above description that the present invention can be implemented with various modifications or equivalent implementations of the present invention.

In addition, since the present invention can be implemented in various other forms, the present invention is not limited by the above description, and the above description is intended to make the disclosure of the present invention complete and is commonly used in the technical field to which the present invention pertains. It is provided only to fully inform those with knowledge of the scope of the present invention, and it should be noted that the present invention is only defined by each claim in the claims.

The present invention relates to an information sharing platform service system and method, and more specifically, to an information sharing platform service system and method based on a chatbot capable of deep learning-based communication and a data-based advertising target recommendation algorithm, so it has industrial applicability. There is.

(doesn't exist)

Claims

In a chatbot service-based information sharing method equipped with a user terminal and a platform server,

(a) requesting a requested task (to do list) entered through an application service of the platform server from a first user terminal;

(b) The first chatbot corresponding to the first user of the platform server recommends shared information including the requested task information and result information of performing the requested task generated based on the first user information. and deriving target information to be shared; and

(c) sharing the shared information through an inter-chatbot conversation process with a second chatbot corresponding to at least one target among the target information derived from the first chatbot of the platform server. ,

Information sharing platform service method based on conversation technology between chatbots using deep learning.
According to claim 1,

In step (a),

Registering a plurality of user terminals by accessing the platform server and entering user information and login information; and

Including requesting a requested task (to do list) entered through an application service of the platform server from a registered first user terminal,

The user information is characterized in that it includes the user's occupation, age, gender and interest information,

Information sharing platform service method based on conversation technology between chatbots using deep learning.
According to claim 1,

The application service is,

Characterized by including a personal page creation service based on user activity and electronic business cards, a ranked relationship network service, a live streaming service, an SNS advertisement sharing service, a shopping mall linkage service, a host information sharing service, and a metaverse linkage service.

Information sharing platform service method based on conversation technology between chatbots using deep learning.
According to claim 1,

In step (b),

(b1) the platform server preprocesses and creates a database of user-related information including the user information, user activity information, and network information; and

(b2) The first chatbot recommends shared information including the result information of performing the requested task from the AI module based on the requested task information and requests target information to be shared, and the target information derived by the AI module Characterized in that it includes the step of receiving;

Information sharing platform service method based on conversation technology between chatbots using deep learning.
According to claim 4,

In step (b2) above,

The generation of the subject information of the AI module is,

It is a collaborative filtering method that recommends a target host based on the user-related information of the first user,

Characterized by applying an adaptive sampling method algorithm based on Optimizer Bayesian personalized ranking (OBPR),

Information sharing platform service method based on conversation technology between chatbots using deep learning.
According to claim 1,

In step (c),

(c1) sharing the shared information from the first chatbot to the second chatbot through a conversation process;

(c2) the second chatbot requesting additional information of interest from the first chatbot through a conversation process; and

(c3) characterized in that it includes the step of the first chatbot responding to the additional request through a conversation process with the second chatbot and sharing additional shared information,

Information sharing platform service method based on conversation technology between chatbots using deep learning.
According to claim 6,

After step (c) above,

Characterized in that the AI module further comprises a step of providing visualization of information obtained by analyzing the user's information satisfaction data periodically to the first chatbot and the second chatbot.

Information sharing platform service method based on conversation technology between chatbots using deep learning.
In an information sharing platform system where a user terminal and a platform server are connected through a network,

A plurality of user terminals that connect to the platform server, enter user information and login information to register as a user, and execute application services provided by the platform server; and

Executing the application service, receiving requested task (to do list) information from the user terminal, a first chatbot corresponding to the first user who entered the requested task information and the first user information Based on this, share information including information as a result of performing the request task is recommended to derive target information to be shared, and a conversation process between the chatbot and a second chatbot corresponding to at least one target among the derived target information is performed. Characterized in that it includes a platform server that shares the shared information through

An information sharing platform service system based on conversation technology between chatbots using deep learning.
According to claim 8,

The platform server is,

a user registration unit that performs a user registration procedure with the user terminal;

a service execution unit that executes the application service;

a platform DB unit that stores and manages user information input from the user terminal and user-related information generated by execution of the application; and

The first chatbot recommends sharing information including result information of performing the requested task based on the requested task information and the first user information to derive target information to be shared, and at least one of the derived target information A chatbot system that shares the shared information through a conversation process between a second chatbot corresponding to one subject and the chatbot,

An information sharing platform service system based on conversation technology between chatbots using deep learning.
According to clause 9,

The chatbot system is,

A chatbot unit provided with a plurality of chatbots that individually correspond to each user terminal and perform a request task (to do list) conversation process requested by each user terminal;

Information input or output to the chatbot is generated through NLP processing and transmitted to the chatbot unit, and the information input to the at least one chatbot is analyzed to make the request based on the request task information and the first user information. An AI module that recommends shared information including information on the results of performing a task and derives information about the person to be shared; and

Characterized in that it includes a chatbot sharing unit that shares the shared information through a conversation process with the first chatbot and a second chatbot corresponding to at least one of the derived target information,

An information sharing platform service system based on conversation technology between chatbots using deep learning.
According to claim 10,

The platform DB unit,

Characterized in that the platform server includes a preprocessing unit that preprocesses user-related information including the user information, user activity information, and relationship network information.

An information sharing platform service system based on conversation technology between chatbots using deep learning.
According to claim 8,

The generation of the subject information of the AI module is,

It is a collaborative filtering method that recommends a target host based on the user-related information of the first user,

Characterized by applying an adaptive sampling method algorithm based on Optimizer Bayesian personalized ranking (OBPR),

An information sharing platform service system based on conversation technology between chatbots using deep learning.