KR102536992B1 - Communication system providing chatbot service - Google Patents

Abstract

The present invention relates to a system for a chatbot service that provides response information and changes the appearance of a character in consideration of a user's desired time.
In addition, the present invention relates to an artificial intelligence-based communication system using time information.

Description

Communication system providing chatbot service {Communication system providing chatbot service}

The present invention relates to a communication system providing a chatbot service.

In addition, the present invention relates to a system for a chatbot service that provides response information and changes the appearance of a character in consideration of a user's desired time.

In addition, the present invention relates to an artificial intelligence-based communication system using time information.

In general, an artificial intelligence conversation system used in a personal assistant system, a chatbot platform, and an artificial intelligence (AI) speaker understands the intention of a person's command and provides a response phrase corresponding to it.

Mainly, an artificial intelligence conversation system is a method in which a person conveys a functional request and a machine provides an answer to the person's request, receiving a user's voice input through a microphone and based on the received voice input You can control behavior or content delivery.

Patent Registration Publication No. 10-2030803 discloses a chatbot conversation processing apparatus and method.

In the above document, a conversation processing apparatus connected to one or more user terminals through a network, providing a question to the user terminal and processing a voice response transmitted from the user terminal is disclosed.

In addition, the dialogue processing apparatus in the above document determines whether a question/answer generator generates a question to be transmitted to the user terminal, and whether the user's answer transmitted from the user terminal is an answer to the question or a question to the dialogue processing apparatus. A user answer analysis unit that classifies and determines whether the user's answer is the same as the existing user's answer, a new answer/reaction generator that determines whether the user's answer can be classified as a new answer based on the knowledge base, and Based on the determination result of the user answer analysis unit and the determination result of the new answer/response generation unit, a user response response unit generating a question or answer to be transmitted to the user terminal and providing the result to the question/answer generation unit do.

Accordingly, the present invention intends to propose an artificial intelligence-based communication system using more enhanced time information.

Patent Registration Publication No. 10-2030803

An object of one embodiment of the present invention is to provide an artificial intelligence-based communication system using time information.

In addition, an object of one embodiment of the present invention is to provide an artificial intelligence-based communication system that is set in consideration of a tendency that a user may have in the future.

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

An embodiment of the present invention is an artificial intelligence-based communication system, wherein at least one of a user's user terminal and software, programs, websites, and mobile apps for performing communication with the user terminal and using a communication platform is provided. and a management server that operates, wherein the management server acquires the user's personal information through the user terminal, uses the user's personal information as learning data, and controls the artificial intelligence network model to be learned, and controls the learned artificial intelligence network model to be learned. We propose a communication system characterized by generating a chatbot based on an intelligent network model and controlling the chatbot to output through the user terminal.

The management server acquires the user's desired time information through the user terminal, sets the appearance of the chatbot based on the desired time information, and outputs the chatbot having the set appearance through the user terminal You can control it.

The management server may generate response information based on the personal information and the desired time information, and control the chatbot having the set appearance to output the response information to the user terminal.

The user terminal may photograph an appearance of the user, generate image information, and transmit the image information to the management server, and the management server sets the appearance of the chatbot based on the image information.

The artificial intelligence network model may include at least one of a recurrent neural network (RNN), a deep neural network (DNN), and a dynamic recurrent neural network (DRNN).

As such, an embodiment of the present invention may propose an artificial intelligence-based communication system using enhanced time information.

In addition, according to an embodiment of the present invention, an artificial intelligence-based communication system can provide the user with communication optimized for the user by learning the user's personal information.

In addition, an embodiment of the present invention may provide a user with an artificial intelligence-based communication system that is set in consideration of a tendency that the user may have in the future. Through this, the user can feel the satisfaction of having a conversation with the future self, which is meaningful for the purpose of psychotherapy.

In addition, one embodiment of the present invention is meaningful in terms of providing additional information that the user can refer to in that it enables questions and answers about what decisions the user made in the past based on the user's past chatting records. can

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

Also other aspects as described above, features and benefits of certain preferred embodiments of the present invention will become more apparent from the following description taken in conjunction with the accompanying drawings.
1 is a diagram showing how an artificial intelligence-based communication system is implemented according to an embodiment of the present invention.
2 is a block diagram illustrating an artificial intelligence-based communication system according to an embodiment of the present invention.
3 is a block diagram illustrating a management server of an artificial intelligence-based communication system according to an embodiment of the present invention.
4 is a flowchart illustrating an operation method of an artificial intelligence-based communication system according to an embodiment of the present invention.
5 is a flowchart illustrating an operating method of an artificial intelligence-based communication system according to an embodiment of the present invention.
6 is a block diagram illustrating a management server of an artificial intelligence-based communication system according to an embodiment of the present invention.
It should be noted that throughout the drawings, like reference numbers are used to show the same or similar elements, features and structures.

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

In describing the embodiments, descriptions of technical contents that are well known in the technical field to which the present invention pertains and are not directly related to the present invention will be omitted. This is to more clearly convey the gist of the present invention without obscuring it by omitting unnecessary description.

For the same reason, in the accompanying drawings, some components are exaggerated, omitted, or schematically illustrated. Also, the size of each component does not entirely reflect the actual size. In each figure, the same reference number is assigned to the same or corresponding component.

Advantages and features of the present invention, and methods for achieving them, will become clear with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only the present embodiments make the disclosure of the present invention complete, and common knowledge in the art to which the present invention belongs It is provided to fully inform the holder of the scope of the invention, and the present invention is only defined by the scope of the claims. Like reference numbers designate like elements throughout the specification.

At this time, it will be understood that each block of the process flow chart diagrams and combinations of the flow chart diagrams can be performed by computer program instructions. These computer program instructions may be embodied in a processor of a general purpose computer, special purpose computer, or other programmable data processing equipment, so that the instructions executed by the processor of the computer or other programmable data processing equipment are described in the flowchart block(s). It creates means to perform functions. These computer program instructions may also be stored in a computer usable or computer readable memory that can be directed to a computer or other programmable data processing equipment to implement functionality in a particular way, such that the computer usable or computer readable memory The instructions stored in are also capable of producing an article of manufacture containing instruction means that perform the functions described in the flowchart block(s). The computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operational steps are performed on the computer or other programmable data processing equipment to create a computer-executed process to generate computer or other programmable data processing equipment. Instructions for performing processing equipment may also provide steps for performing the functions described in the flowchart block(s).

Additionally, each block may represent a module, segment, or portion of code that includes one or more executable instructions for executing specified logical function(s). It should also be noted that in some alternative implementations it is possible for the functions mentioned in the blocks to occur out of order. For example, two blocks shown in succession may in fact be executed substantially concurrently, or the blocks may sometimes be executed in reverse order depending on their function.

At this time, the term '~unit' used in this embodiment means software or a hardware component such as a field-programmable gate array (FPGA) or application specific integrated circuit (ASIC), and what role does '~unit' have? perform them However, '~ part' is not limited to software or hardware. '~bu' may be configured to be in an addressable storage medium and may be configured to reproduce one or more processors. Therefore, as an example, '~unit' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables. Functions provided within components and '~units' may be combined into smaller numbers of components and '~units' or further separated into additional components and '~units'. In addition, components and '~units' may be implemented to play one or more CPUs in a device or a secure multimedia card.

In describing the embodiments of the present invention in detail, an example of a specific system will be the main target, but the main subject matter to be claimed in this specification extends the scope disclosed herein to other communication systems and services having a similar technical background. It can be applied within a range that does not deviate greatly, and this will be possible with the judgment of those skilled in the art.

1 is a diagram showing how an artificial intelligence-based communication system is implemented according to an embodiment of the present invention.

delete

Referring to FIG. 1 , the artificial intelligence-based communication system of the present invention may be provided to a user through a user terminal 120 . The artificial intelligence-based communication system of the present invention may be provided to the user through the artificial intelligence-based chatbot 10 (or chatbot). Here, the chatbot 10 (or chatterbot) may represent a computer program designed to perform a specific task through a conversation with a human through voice or text.

In addition, the chatbot 10 may be implemented in a form (or form, create) a voice recognition assistant. In addition, the chatbot 10 converts the contents spoken by the user into text so that the computer can understand it based on voice recognition technology, considers it as a query, generates a response to the query, and converts the generated response into text (TTS) Text to Speech) and/or a voice synthesizing system may be implemented through a process of converting into voice (eg, mechanical voice). Meanwhile, the output and/or response information generated by the management server 110 is information corresponding to text, and after the information is transmitted to the user terminal 120, the information corresponding to the text in the user terminal 120 It may be provided to the user by applying a TTS and/or a voice synthesis system to it.

For example, the chatbot 10 and/or communication system 100 of the present invention performs an operation based on an activation trigger for activating a device with a predetermined keyword (ie, a start command) or a predetermined action can begin. The start command may include, for example, a device name corresponding to the user terminal 120, a name set or assigned to the chatbot 10, and the like. In this way, the chatbot 10 of the present invention can perform a voice recognition function based on a keyword call. For example, when a user calls the name of the chatbot 10, the user terminal 120 and / or the communication platform of the present invention By activating software (and/or program) and/or website (and/or mobile app) providing

2 is a block diagram illustrating an artificial intelligence-based communication system according to an embodiment of the present invention.

delete

Referring to FIG. 2 , the system 100 of the present invention may include a management server 110 and a user terminal 120 .

The management server 110 may include a first control module 210, a first communication module 220, a first input module 230, a first output module 240, and/or a storage module 250. And, the management server 110 may be a server that operates a website and/or mobile app that provides or supports the artificial intelligence-based communication platform of the present invention. In addition, the user terminal 120 may include a second control module 260, a second communication module 270, a second input module 280 (not shown), and/or a second output module 290 (not shown). can In addition, the user terminal 120 may be a user's mobile device such as a smart phone, a mobile phone, a laptop computer, a digital broadcasting terminal, a personal digital assistant (PDA), a portable multimedia player (PMP), a tablet PC, and the like. Also, the user terminal 120 may be a personal PC or desktop.

The control modules 210 and 260 may directly/indirectly control the management server 110 and/or the user terminal 120 to implement an operation/step/process according to an embodiment of the present invention. Also, the control modules 210 and 260 may include at least one processor, and the processor may include at least one central processing unit (CPU) and/or at least one graphic processing unit (GPU).

In addition, the control module (210, 260) is based on API (Application Programming Interface), IoT (Internet of Things), IIoT (Industrial Internet of Things), ICT (Information & Communication Technology) technology based on control information (eg, commands), etc. can create and/or manage.

The communication modules 220 and 270 may transmit and receive various data, signals, and information to the management server 110, the user terminal 120, and/or other network entities (not shown). In addition, the communication modules 220 and 270 may be a wireless communication module (eg, a cellular communication module, a short-distance wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (eg, a local area network (LAN) communication module). module, or a power line communication module). In addition, the communication modules 220 and 270 may be a first network (eg, a short-distance communication network such as Bluetooth, WiFi direct, or Infrared Data Association (IrDA)) or a second network (eg, a cellular network, the Internet, or a computer network (eg, a local communication network)). It may communicate with an external electronic device through a telecommunications network (such as a LAN or WAN). These various types of communication modules may be integrated into one component (eg, a single chip) or implemented as a plurality of separate components (eg, multiple chips).

The input modules 230 and 280 manage commands or data to be used for components (eg, control module 210, etc.) of the management server 110, the user terminal 120, and/or other network entities (not shown). It can be received from the outside of the server 110 and/or the user terminal 120 (eg, a user (eg, a first user, a second user, etc.), a manager of the management server 110, etc.). In addition, the input modules 230 and 280 include a touch recognition capable display installed in the management server 110 and/or the user terminal 120, a touch pad, a button type recognition module, a voice recognition sensor, a microphone, a mouse, or a keyboard. can do. Here, the touch-recognizable display, touchpad, and button-type recognition module may recognize a touch through a user's body (eg, a finger) through a pressure-sensitive and/or capacitive method.

The output modules 240 and 290 are generated by the management server 110 and/or the control module 210 and 260 of the user terminal 120 or acquired through the communication modules 220 and 270 (eg, voice signals). ), a module that displays information, data, images, and/or various objects. For example, the output modules 240 and 290 may include a display, a screen, a displaying unit, a speaker, and/or a light emitting device (eg, an LED lamp).

The storage module 250 stores data such as basic programs, application programs, and setting information for the operation of the management server 110 and/or the user terminal 120 . In addition, the storage module is a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (eg, SD or XD memory, etc.), Magnetic memory, magnetic disk, optical disk, RAM (Random Access Memory, RAM), SRAM (Static Random Access Memory), ROM (Read-Only Memory, ROM), PROM (Programmable Read-Only Memory), EEPROM (Electrically Erasable Programmable Read -Only Memory) may include at least one storage medium.

In addition, the storage module 250 may store personal information of a customer (or first user) using the management server 110 and/or user terminal 120, personal information of a manager (or second user), and the like. Here, the personal information includes name, identifier (ID), password, road name address, phone number, mobile phone number, e-mail address, and/or a reward (eg, points, etc.) generated by the management server 110. information may be included. In addition, the control modules 210 and 260 may perform various operations using various images, programs, contents, and data stored in the storage module 250 .

In addition, the storage module 250 stores past chat records, communication records, and/or response information selected by the user in response to a predetermined question (or selected by the user in response to a predetermined input) through the communication platform of the present invention. output) can be stored further. This information is delivered to the artificial intelligence module 310 and can be used as learning data for learning the artificial intelligence network model.

delete

3 is a block diagram illustrating a management server of an artificial intelligence-based communication system according to an embodiment of the present invention.

Referring to FIG. 3, the management server 110 includes a first control module 210, a first communication module 220, a first input module 230, a first output module 240, It may include a storage module 250 and/or an artificial intelligence module 310, wherein the first control module 210, the first communication module 220, the first input module 230, and the first output module 240 and the description of the storage module 250 refer to the above description in FIG. 2 .

The artificial intelligence module 310 includes a voice processing module for recognizing the received voice and synthesizing a voice to be output; A vision processing module for analyzing and processing the received image or video; a dialog processing module for determining an appropriate dialog to output an appropriate voice according to the received voice; a recommendation module for recommending a function suitable for the received voice; NMT (Neural Machine Translation) module that supports artificial intelligence to translate language in sentence units through data learning; It may include various modules for providing voice-based services, such as the like.

The artificial intelligence module 310 may generate various outputs (eg, first output) and/or various information (eg, first response information) described in the present invention based on the artificial intelligence network model. In addition, the artificial intelligence module 310 uses machine learning on big data stored in a database to perform various outputs (eg, first output) and/or various information (eg, first output) described in the present invention. first response information) may be generated. In addition, the artificial intelligence module 310 uses the big data stored in the database 250 of the management server 110 as an input variable to learn the artificial intelligence network. Specifically, a deep learning technique, which is a field of machine learning Learning can be performed so that an accurate correlation can be derived using In addition, eventually, the artificial intelligence module 310 may calculate weights of a plurality of inputs in the function through deep learning through learning. In addition, various models such as RNN (Recurrent Neural Network), DNN (Deep Neural Network), and DRNN (Dynamic Recurrent Neural Network) can be used as artificial intelligence network models used for such learning.

Here, RNN is a deep learning technique that simultaneously considers current data and past data, and recurrent neural network (RNN) represents a neural network in which connections between units constituting an artificial neural network constitute a directed cycle. Furthermore, various methods can be used for the structure capable of configuring the recurrent neural network (RNN), for example, a Fully Recurrent Network, a Hopfield Network, an Elman Network, ESN (Echo state network), long short term memory network (LSTM), bi-directional RNN, continuous-time RNN (CTRNN), hierarchical RNN, and quadratic RNN are representative examples. In addition, as a method for learning a recurrent neural network (RNN), methods such as gradient descent, Hessian Free Optimization, and Global Optimization Method may be used.

In addition, the artificial intelligence module 310 directly recognizes and analyzes input (eg, voice input) received according to the user's speech (eg, "interior change", "KOSPI purchase", etc.) and outputs (eg, voice output). can In addition, the management server 110 (and/or the control module 210) converts the user's first input (eg, voice input) into a second input corresponding to text (eg, "interior change", "KOSPI purchase", etc.) When converted to and transmitted to the artificial intelligence module 310, the artificial intelligence module 310 generates a first output (eg text information) corresponding to the second input and transmits it to the control module 210. , The control module 210 may generate a second output (eg, audio output) based on the first output and transmit it to the user terminal 120 .

For example, when a user utters “(house) interior change”, the user terminal 120 obtains it through a microphone, which is an input module 380, and transmits it to the management server 120 so that the artificial intelligence module It can be input to 310 as an input. At this time, the artificial intelligence module 310 may obtain information on recommended interiors from an external server through an external network based on the input, and output the obtained information in voice as "Recommended interiors are..." . In addition, based on the information described below, when the desired time information is set to '20 years later', the result of the judgment of the user '20 years later' is estimated, and the estimated result is "It is still too early to change the interior..." It can also be output with a voice such as, and a specific operation for this will be described later.

As another example, when the user utters the content of "KOSPI purchase", the user terminal 120 acquires it through the microphone of the input module 380, and transfers it to the management server 120 so that the artificial intelligence module 310 can be entered as an input. At this time, the artificial intelligence module 310 obtains information on the recent KOSPI trend (eg, statistics, articles, information, etc. on the KOSPI index) from an external server through an external network based on the above input, and based on the acquired information It can be output by voice, such as "Don't buy KOSPI...".

delete

4 is a flowchart illustrating an operation method of an artificial intelligence-based communication system according to an embodiment of the present invention.

Referring to FIG. 4 , the present invention may include obtaining, by a management server, first information of a user through a user terminal (S410).

The user receives the first information through the program (and/or software) and/or website (and/or mobile app) of the present invention that provides the artificial intelligence-based communication platform of the present invention executed through the user terminal 120. can be entered. The first information may be transmitted from the user terminal 120 to the management server 110 and recorded in the management server 110 and/or the storage module 250 .

The first information may include the user's personal information, where the personal information is the user's name, ID (identifier), password, road name address, phone number, mobile phone number, e-mail address, and/or a management server ( 110) may include information indicating a reward (eg, points, etc.) generated by the program (and/or software) and/or website (and/or mobile app) of the present invention by the user. ), information on the payment amount and/or details (payment details), and information on rewards (points) paid or used by the user may be further included.

In addition, the user's personal information may further include information indicating the user's type of business. In addition, the information indicating the user's type of business may include 'first job information' and 'second job information', and the second job information is information indicating a sub-type of the type of business indicated by the first job information, may include information indicating

The first job information may represent categories of higher concepts related to jobs, such as development, management/business, marketing/advertisement, design, sales, customer service/retail (retail, distribution), personnel/education, media, engineering/ May include Design, Investment/Analysis/Real Estate, Manufacturing/Production, Game Production, Logistics/Trade, Food and Beverage (F&B), Legal/Law Enforcement, Medical/Pharma/Bio, Government/Non-Profit, Construction/Facilities .

The second job information may indicate a category of a sub-concept related to a job, and the second job information may be matched with the first job information.

The second job information is, for example, web developer, server developer, front-end developer, Java developer, Android developer, iOS developer, Python developer, DevOps/system manager, data related to or matching development (first job information). This can include engineers, Node.js developers, system/network administrators, C/C++ developers, development managers, machine learning engineers, data scientists, and more. In addition, the second job information is, for example, service planner, business developer / planner, project manager, strategic planner, operation manager, data analyst, accountant / bookkeeper, etc. related to or matched with management / business (first job information). can include In addition, the second job information is, for example, digital marketers, marketers, marketing strategy planners, content marketers, brand marketers, social marketing, advertising planners (AE) that are related to or matched with marketing/advertising (first job information). can include In addition, the second job information includes, for example, UX designer, UI / GUI designer, web designer, graphic designer, mobile designer, video / motion designer, product designer, etc. related to or matching design (first job information) can do. In addition, the second job information includes, for example, a corporate sales manager, a sales manager, a technical sales specialist, an external sales specialist, a major customer company manager, a solution consultant, and a customer success manager that are related to or matched with sales (first job information). can include

In addition, the second job information may include, for example, CS manager, MD, CS advisor, retail MD, CRM specialist, fashion MD, store clerk, etc. related to or matched with customer service/retail (first job information). there is. In addition, the second job information is, for example, a human resource manager, recruiter, organization management expert, personnel evaluation expert, HRD / education expert, salary / compensation expert, HRBP, etc. related to or matched with human resources / education (first job information). can include In addition, the second job information may include, for example, content creator, video editor, producer, editor, video producer, writer, sound engineer, etc. related to or matched with media (first job information). In addition, the second job information may include, for example, an automotive engineer, a mechanical engineer, an electrical engineer, a product engineer, an electrical mechanical engineer, a control engineer, an electronic engineer, and the like that are related to or matched with engineering/design (first job information). can In addition, the second job information may include, for example, an accountant related to or matched with investment/analysis/real estate (first job information), a financial analyst, an accountant/accountant, an analyst, an IR, a CPA, a compliance officer, and the like. can In addition, the second job information is, for example, quality manager, production manager, manufacturing engineer, test engineer, process manager, machine manufacturing technician, machine / facility operation, safety related to or matching manufacturing / production (first job information) This may include managers, chemists, materials managers, and production workers.

In addition, the second job information is, for example, a game client developer, game planner, mobile game developer, unity developer, game server developer, game artist, game graphic designer, game related to or matched with game production (first job information). May include operators (GM), Unreal developers, and the like. In addition, the second job information is, for example, logistics/trade (first job information) related or matched logistics manager, logistics analyst, transport manager, delivery manager, warehouse specialist, shipping/delivery clerk, transportation manager, cargo This may include truck driver, trade office, etc. Also, the second job information may include, for example, a chef, a food MD, a restaurant worker, a food service menu developer, a nutritionist, a bartender, a restaurant manager, and the like that are related to or matched with F&B (first job information). In addition, the second job information may include, for example, a legal person in charge or matched with a law/law enforcement agency (first job information), a legal advisor, a lawyer, a patent attorney, a specifier, and the like. In addition, the second job information is, for example, a researcher related to or matching medical/pharmaceutical/bio (first job information), a biotechnology researcher, a clinical trial researcher, a case manager, a veterinarian, a pharmaceutical analytical chemist, a clinical trial nurse, microbiologists, and the like. In addition, the second job information may include, for example, information analysts, counselors, civil servants, occupational soldiers, environmental experts, regional experts, volunteers, etc. related to or matched with government/non-profit (first job information). Also, the second job information may include, for example, a maintenance manager, a estimator, a mechanic, a manager, and the like that are related to or matched with construction/facility (first job information).

In addition, the first information may further include 'third job information' and 'fourth job information', and the third job information directly identifies the place of work, office and/or company where the user is (currently) working. may contain information indicated by In addition, the third job information may include information indicating an upper category and/or a lower category corresponding to the place of work, office, and/or company where the user (currently) works. On the other hand, for specific details of the information indicating the upper category and/or the information indicating the lower category, refer to the above-described information related to the first job information and/or the second job information.

In addition, the fourth job information is related to the user if the user has worked at multiple workplaces (or offices or companies), worked at multiple workplaces (or offices or companies), and/or has a career of changing jobs. It may include information about a plurality of workplaces, offices and/or companies. For example, the fourth occupational information may include information indicating an upper category of business and/or information indicating a lower category of business corresponding to a plurality of workplaces (or offices or companies) in which the user was engaged. On the other hand, for specific details of the information indicating the upper category and/or the information indicating the lower category, refer to the above-described information related to the first job information and/or the second job information.

Through this, the artificial intelligence network model learned using at least one of the first job information to the fourth job information as learning data outputs the same output that would have been selected by a person matching at least one of the first job information to the fourth job information ( and/or response information).

In addition, the program (and/or software) and/or website (and/or mobile app) of the present invention performs steps S420 to S440 of FIG. 5 only when a predetermined authentication process is completed through the first information of the user. Operations described based on the flow chart may be performed.

For example, the predetermined criterion may include a predetermined authentication procedure, and the predetermined authentication procedure may include a user authentication process based on personal information of the user.

And, the method may include the step of controlling to learn the artificial intelligence network model by using the first information as learning data (S420).

The management server 110 and/or the artificial intelligence module 310 sets at least one of the user's personal information and the first job information to the fourth job information as learning data, and the set learning data It is possible to learn the artificial intelligence network model operated by the artificial intelligence module 310 by using. In other words, the artificial intelligence module 310 uses at least one of the user's personal information and the first to fourth job information to i) learn the artificial intelligence network model, ii) update the artificial intelligence network model, and/or iii) control to generate an adaptive artificial intelligence network model customized for the user. The artificial intelligence network model learned through this process can generate an output (and/or response information) that would have been selected by a person matching at least one of personal information such as the user and first job information to fourth job information. .

And, the method may include generating a user-customized chatbot based on the learned artificial intelligence network model (S430).

The management server 110 may generate a chatbot that displays the output of the learned artificial intelligence network model as text, voice, or the like, or expresses it as a facial expression.

For example, when the output (and/or response information) includes negative content, the chatbot 10 may make a negative expression, for example, a crying expression, a sad expression, an angry expression, and the like. If the output (and/or response information) includes positive content, the chatbot 10 may make a positive expression, for example, a smiling expression or an excited expression.

In addition, the management server 110, for example, models, renders, and characterizes 2D and/or 3D external images based on video and/or image information captured through a camera device of the user terminal 120. The external appearance of the chatbot may be determined or set using the generated 2D and/or 3D external image. A specific operation for this will be described later with reference to the camera module 620 .

And, the method may include providing a communication platform and/or system to a user using a user-customized chatbot (S440).

For example, a first input from a user may be obtained through the communication platform and/or system of the present invention. And, when the first input is transmitted to the learned artificial intelligence network model and the learned artificial intelligence network model generates a first output based on the input, the management server 110 generates the chatbot based on the first output. A second output that can be output through is generated, and the second output can be controlled to be output or displayed through the chatbot.

In this way, a chatbot based on an artificial intelligence network model learned based on the user's personal information, etc. can be created, and when the user's input (eg, question) is acquired in the chatbot created in this way, a predetermined output (eg; Responses and answers) may be provided to the user (and/or the user terminal 120) through the chatbot.

Meanwhile, the S410 to S440 may be implemented sequentially, but the order may be changed and implemented, and only some of the S410 to S440 may be implemented in combination with other descriptions (methods) of the present invention.

delete

5 is a flowchart illustrating an operating method of an artificial intelligence-based communication system according to an embodiment of the present invention.

Referring to FIG. 5 , the present invention may include acquiring desired time information of a user through a user terminal (S510).

The user inputs the second information through the program (and/or software) and/or website (and/or mobile app) that provides the artificial intelligence-based communication platform of the present invention executed through the user terminal 120. can The second information may be transmitted from the user terminal 120 to the management server 110 and recorded in the management server 110 and/or the storage module 250 .

The second information may include user's desired time information, and the desired time information herein may be a time (arbitrarily) set by the user. The desired time information may be, for example, a time representing the future based on the current time (eg, '20XX year XX month XX day', 'XX years later', etc.). In addition, the desired time information, as another example, may be a time representing the past based on the current time (e.g., 'XX day, XX month, 19XX', 'XX day, XX month, 20XX', 'XX years ago', etc.) .

Also, the second information may include desired age information, and the desired age information herein may be an age set (arbitrarily) by a user. For example, the desired age information is 'XX years old (eg 16 years old, 56 years old, etc.)', 'XX years old (eg 25 years old, 73 years old, etc.)', 'XX generations (eg 10 years old, 20 years old, etc.)' )'.

And, the method may include setting the appearance of the chatbot based on the desired time information (S520).

For example, the input module 280 of the user terminal 120 may include a camera device, and the user's appearance is photographed through the camera device and/or an object extracted from image information is used to perform the The appearance of the chatbot can be set, and this will be described in detail based on the camera module of FIG. 6 .

For example, the management server 110 may transform the appearance of the chatbot into an appearance corresponding to the time indicated by the desired time information. For example, when the desired time information indicates a time corresponding to the future based on the present, the appearance of the chatbot generated based on the video and / or image information captured through the camera device (e.g., first appearance information ), an appearance (eg, second appearance information) of a chatbot corresponding to the desired time information may be created or set. Here, edging processing is image processing that reflects or adds biological changes that may occur to the face, skin, hair, etc. as a person ages, such as wrinkles, age spots, gray hair, reduction in the number of hairs, and hair loss, to the first appearance information. etc. may be included.

And, the method may include generating response information based on the first information and desired time information (S530).

For example, a response and/or an answer expected to be given by an object corresponding to the time indicated by the desired time information may be generated as an output.

And, the method may include providing the generated response information to a communication platform and/or system through a chatbot having the set appearance (S540).

For example, a user's second input may be obtained through the communication platform and/or system of the present invention. And, when the second input is transmitted to the learned artificial intelligence network model and the learned artificial intelligence network model generates a third output based on the input, the management server 110 generates the chatbot based on the third output. A fourth output that can be output through is generated, and the fourth output can be controlled to be output or displayed through the chatbot.

Meanwhile, the S510 to S540 may be implemented sequentially, but the order may be changed and implemented, and only some of the S510 to S540 may be implemented in combination with other descriptions (methods) of the present invention.

In addition, an embodiment of the present invention may include a feature of generating or recommending appearances of a plurality of chatbots to a user. For example, the management server 120 may set a plurality of recommended time information, and may generate a plurality of chatbot appearances (eg, a plurality of third appearance information) corresponding to each of the plurality of recommended time information. . In addition, the management server 120 may transmit the plurality of third appearance information generated in this way to the user terminal 120 so that they are output or displayed through the user terminal 120 . In addition, when the management server 120 transmits the plurality of third appearance information to the user terminal 120, the plurality of third appearance information is grouped and/or hashed using blockchain technology, and the user terminal 120 ), which can be referred to the following description of the blockchain module 620.

And, in one embodiment of the present invention, when the desired time information indicates a time corresponding to the past, the first output based on the user's chat record, communication record, etc. recorded in the storage module 250 of the management server 110, A second output, response information, and the like may be generated. In addition, the artificial intelligence module 310 sets at least one of the user's personal information and first to fourth job information as learning data, and further sets the user's chatting history as additional learning data, so that the artificial intelligence module The artificial intelligence network model of (310) can be trained. In addition, based on the artificial intelligence network model learned in this way, the management server 110 may generate output and/or response information for user input and/or question information, and the output and/or response information thus generated is as if Information on what decisions and/or responses the user has made (record) and/or what decisions and/or responses may have been made (estimation) in the past can be obtained. Through this, the user can obtain the effect of having a conversation with the past self and/or enjoyment.

Also, the output and/or response information of the present invention may be based on information received from other network nodes (not shown) other than the management server 110 and the user terminal 120, for example. In this case, the network node may be a block chain node. For example, when the personal information of the first user indicates the age of the first user as '32 years old' and the desired time information of the first user is set as '10 years later', another user corresponding to '42 years old' Input (and/or question information), and when the other user (fourth user) inputs an answer (and/or response information) in response to the input (and/or question information), it may be received and provided to the user.

delete

6 is a block diagram illustrating a management server of an artificial intelligence-based communication system according to an embodiment of the present invention.

Referring to FIG. 6 , the management server 110 of the present invention includes an artificial intelligence module 310, a camera module 610, a blockchain module 620, and/or an IoT module 630. A description of the artificial intelligence module 310 refers to the contents described above with reference to FIGS. 3 to 5 .

The artificial intelligence module 310 may generate or set the aforementioned first output and/or second output based on the artificial intelligence network model. In addition, the artificial intelligence module 310 may generate or set the first output and/or the second output by using machine learning on big data stored in the storage module 250 .

In addition, the artificial intelligence module 310 may train an artificial intelligence network model by using big data stored in the storage module 250 of the management server 110 as an input variable. For example, the artificial intelligence module 310 may perform learning so that an accurate correlation can be derived using a deep learning technique, which is a field of machine learning. For example, the artificial intelligence module 310 prior to the first user using the program (and/or software) and/or website (and/or mobile app) of the present invention, the program (and/or software) and/or Alternatively, the artificial intelligence network may be trained using information input by a plurality of third users (ie, previous customers) who used the website (and/or mobile app) as learning data.

For example, the artificial intelligence module 310 may train the artificial intelligence network model according to a first learning mode, and the artificial intelligence module 310 may perform the user's personal information in the first learning mode. And it is possible to learn the artificial intelligence network model by using the first job information as first learning data.

For example, the artificial intelligence module 310 may train the artificial intelligence network model according to a second learning mode, and the artificial intelligence module 310 may perform the personal information of the user in the first learning mode. , and the second to fourth job information as the second learning data (learning data) to learn the artificial intelligence network model.

For example, the artificial intelligence module 310 outputs from the learned artificial intelligence network model based on inputs (eg, first input, second input, etc.) input to the learned artificial intelligence network as described above. (output) (eg, first output, second output, third output, fourth output, etc.) may be obtained.

In addition, the artificial intelligence module 310 may calculate weights of a plurality of inputs in the function through deep learning through learning. In addition, various models such as RNN (Recurrent Neural Network), DNN (Deep Neural Network), and DRNN (Dynamic Recurrent Neural Network) can be used as artificial intelligence network models used for such learning.

Here, RNN is a deep learning technique that simultaneously considers current data and past data, and recurrent neural network (RNN) represents a neural network in which connections between units constituting an artificial neural network constitute a directed cycle. Furthermore, various methods can be used for the structure capable of configuring the recurrent neural network (RNN), for example, a Fully Recurrent Network, a Hopfield Network, an Elman Network, ESN (Echo state network), long short term memory network (LSTM), bi-directional RNN, continuous-time RNN (CTRNN), hierarchical RNN, and quadratic RNN are representative examples. In addition, as a method for learning a recurrent neural network (RNN), methods such as gradient descent, Hessian Free Optimization, and Global Optimization Method may be used.

The camera module 610 may receive or obtain an image captured and/or obtained image information (eg, a static image, a dynamic image, etc.) through a camera device included in the input module 280 of the user terminal 120. there is.

The camera module 610 may obtain first object information by extracting an object included in the obtained image and/or image information. The camera module 610 uses various algorithms for extracting object features such as Histogram of Oriented Gradient (HOG), Haar-like feature, Co-occurrence HOG, local binary pattern (LBP), and features from accelerated segment test (FAST). , From the image (and/or image information) obtained through the camera device, an outline of an object in an image or a text (or an outline (or shape) representing information) that can be extracted from the object may be obtained. In addition, the camera module 610 may recognize (or identify) an object from the acquired image (and/or image information) through image analysis, and mask a region corresponding to the recognized object to generate masking image information. there is. At this time, the masking process is, for example, a difference image method, a model of Gaussian (MOG) algorithm using GMM (Gaussian Mixture Models), a codebook algorithm, etc. First object information may be extracted and/or acquired by using a method of extracting a corresponding object candidate region.

In addition, the camera module 610 may acquire a plurality of images (and/or a plurality of image information) through the camera device, and a process of extracting an object included in the plurality of images (and/or a plurality of image information) A plurality of pieces of first object information may be obtained by repeating.

For example, the artificial intelligence module 610 may further learn the artificial intelligence network model by further considering the plurality of first object information as learning data.

As another example, the artificial intelligence module 610 may include a first artificial intelligence network model and a second artificial intelligence network model, and may use the user's first information and/or second information as first learning data to perform the first learning data. The artificial intelligence network model may be trained, and the second artificial intelligence network model may be trained by using the plurality of first object information as training data. At this time, the management server 110 may generate at least one of the first to fourth outputs using the (learned) first artificial intelligence network model, and the (learned) second artificial intelligence network model. You can set or reset (or update) the appearance of the chatbot 10 by using it.

The blockchain module 620 is a user terminal 120 and / or information indicating the above-described first information, second information, first to fourth inputs, first outputs, and second outputs based on blockchain technology. At least one piece of block data may be generated based on the information indicating the first information, the second information, the first to fourth inputs, the first output, and the second output so as to be delivered to other network nodes. At least one piece of block data generated by the blockchain module 620 may be transmitted to the user terminal 120 through the communication module 220 . In addition, the management server 110 may store at least one element included in the at least one piece of block data in a block chain (not shown) implemented in the storage module 250 .

In general, a block chain is a tamper-proof distributed storage created and managed by a peer-to-peer (P2P) network. Block chain refers to a collection of data blocks created by transactions (indivisible unit operations between both parties) connected one after another in the form of a chain. Since the previous block is successively encrypted and the data agreed upon by more than half of the users is recognized as real data, data once recorded cannot be forged and/or tampered with. A typical application of block chain is bitcoin, a decentralized electronic currency that records the transaction process of cryptocurrency. Confirmed transaction details occurring between users for a certain period of time can be stored in the block chain. And, many users each have their own copy of the blockchain, and transaction history can be made public to everyone. In this way, only the transaction details agreed upon by more than half of the users are recognized as actual data, and can be stored in a block to be permanently stored.

On the other hand, each of the management server 110, the user terminal 120, and other network nodes of the present invention may include a blockchain or may be a blockchain node capable of controlling block data. For example, the management server 110 receives first information from the user terminal 120 (or is obtained through the user terminal 120), second information, first to fourth inputs, first output, Information representing the second output, etc. is grouped and/or hashed and stored in the block chain, and then information representing the first information, the second information, the first to fourth inputs, the first output, the second output, etc. Forgery and / or tampering can be verified or determined. For example, the blockchain module 620 includes a Merkle hash based on information representing the first information, the second information, the first to fourth inputs, the first output, and the second output. Information indicating the first information, the second information, the first to fourth inputs, the first output, the second output, etc. so that user information block data (matching score block data) is generated and the generated merkle hash is included. can be grouped.

The management server 110 includes at least one element stored in a blockchain (not shown) implemented in the storage module 250 and the first element based on at least one of a predetermined time and the number of pieces of information indicating the stored matching score. At least one element included in the information representing information, second information, first input to fourth input, first output, second output, etc. is compared, and the first information, second information, first input to fourth input, etc. are compared. Integrity of information representing inputs, first outputs, second outputs, etc. may be verified. The management server 110, if the information representing the first information, the second information, the first to fourth inputs, the first output, the second output, etc. is not integrity, through the output module (240, 290) Whether or not the integrity is present can be output.

The management server 110 stores information representing the first information, second information, first to fourth inputs, first outputs, second outputs, etc. stored in the storage module 250 forged and/or altered or damaged. In this case, the integrity status can be output through the output module 240 so that an administrator (eg, a second user) who manages the management server 110 can know this. The control module 210 may generate a certificate for determining the integrity of the stored blockchain and transmit it to the user terminal 120 and/or other blockchain nodes. The certificate may include information indicating the stored grouped first information, second information, first to fourth inputs, first outputs, second outputs, and the like. The certificate may be used by the management server 110 to determine whether the information indicating the first information, the second information, the first to fourth inputs, the first output, and the second output is integrity.

In addition, the blockchain module 620 converts the input and/or question information based on a privacy level corresponding to the plurality of inputs and/or the plurality of question information input by the user through the user terminal 120. i) hashing and/or grouping and forwarding it to other network nodes in the form of hash data, or ii) skipping the hashing and/or grouping process and forwarding the input and/or question information as it is to other network nodes. This means that information related to the user's privacy is transmitted to other network nodes by applying (or transforming/converting) blockchain technology to protect the user's privacy and/or personal information, but in the case of information that is not, there is no transformation/conversion. A technical effect of saving energy resources and/or processing time resources can be expected by omitting unnecessary processes for other network nodes without conversion.

The IoT module 630 is the user terminal in order to receive various information and/or signals required by the present invention based on IoT technology and/or to output various information and/or signals generated in the present invention. 120 and/or information to perform communication with other network nodes (not shown) may be modified. For example, the IoT module 630 may be included in the communication module 220 or implemented as the communication module 220 .

Then, the management server 110 receives residual power information representing the residual power of the internal battery of the user terminal 120 from the user terminal 120, and based on a comparison result between the residual power information and a predetermined threshold value. to generate (and/or display) information about the appearance of the chatbot 10 differently and/or to select (and/or set) differently how the chatbot 10 outputs output and/or response information You can control it. To this end, the user terminal 120 may transmit information indicating the residual power of the user terminal 120 (ie, residual power information) to the management server 110, and the communication module of the management server 110 ( 220) may receive residual power information of the user terminal 120.

The management server 110 (and/or the control module 210) may set a first threshold value for residual power and a second threshold value lower than the first threshold value (eg, the first threshold value - 70). %, second threshold - 30%).

For example, the management server 110, when information indicating the residual power of the user terminal 120 (ie, residual power information) indicates power higher than the first threshold value, the user terminal 120 It can be controlled to operate as 1 operation mode. The first operation mode may be a mode in which a 3D character generated by photographing a user's face and a 3D image generated in relation to an advertisement are output together. For example, in the first operation mode, the user's face of the user terminal 120 is photographed through the camera device of the user terminal 120 to obtain image information on the user's face, and the user's face Based on the image information for , information indicating information on the appearance of the chatbot 10 (eg, at least one of the shape, color, or texture of the chatbot 10) may be generated or the appearance of the 3D character may be determined. . For example, in the case of operating in the first operation mode, after image information on the user's face is rendered, information on the appearance of the chatbot 10 may be generated based on the rendered result. That is, the management server 110 of the present invention can control the chatbot 10 having a 2D or 3D image of the user's face to be displayed through the user terminal.

In addition, when the remaining power information of the user terminal 120 indicates power less than the first threshold and greater than or equal to the second threshold, the management server 110 causes the user terminal 120 to operate in a second operation mode. You can control it. The second operation mode may be a mode in which a 3D character of a preset appearance is displayed as the chatbot 10 according to a user's selection and/or preset by the management server 110 0 . As such, the second operation mode omits the process of photographing the user's face through the camera device, so it can be regarded as a low-power mode compared to the first operation mode.

In addition, when the remaining power information of the user terminal 120 indicates power less than the second threshold and greater than or equal to the third threshold, the management server 110 causes the user terminal 120 to operate in a third operation mode. You can control it. The third operation mode may be a mode in which a 3D character of a preset appearance is displayed as the chatbot 10 according to a user's selection and/or preset by the management server 110 0 . In addition, when set to the third operation mode, the output and/or response information generated by the control module 210 and/or the artificial intelligence module 310 is a kind of text message (eg, speech bubble) and/or a pre-recorded voice. It may be a mode that displays or outputs only. In other words, a voice synthesis process such as TTS may be omitted. For example, the output and/or response information generated by the management server 110 is information corresponding to text, and after the information is transmitted to the user terminal 120, the user terminal 120 corresponds to the text. TTS and/or voice synthesis system are not applied to the information, and only pre-recorded information in text form and/or corresponding to the text may be output through the user terminal.

In this way, the third operation mode is to output information about the appearance of the chatbot 10 that is preset, rather than generating or rendering information about the appearance of the chatbot 10 in real time by photographing the user's face. It may be implemented as a low power mode compared to the operation mode and the second operation mode.

Embodiments of the present invention disclosed in this specification and drawings are only presented as specific examples to easily explain the technical content of the present invention and help understanding of the present invention, and are not intended to limit the scope of the present invention. That is, it is obvious to those skilled in the art that other modifications based on the technical idea of the present invention can be implemented. In addition, each of the above embodiments may be operated in combination with each other as needed. For example, all embodiments of the present invention may be implemented by the system 100, the management server 110, and/or the user terminal 120 by combining parts with each other.

In addition, the method for controlling the system 100, the management server 110, and/or the user terminal 120 according to the present invention is implemented in the form of program commands that can be executed through various computer means, and is stored in a computer readable medium. can be recorded.

As such, various embodiments of the present invention may be implemented as computer readable codes in a computer readable recording medium from a specific point of view. A computer readable recording medium is any data storage device capable of storing data readable by a computer system. Examples of computer readable recording media include read only memory (ROM), random access memory (RAM), and compact disk-read only memory (CD-ROM). ), magnetic tapes, floppy disks, optical data storage devices, and carrier waves (such as data transmission over the Internet). The computer readable recording medium may also be distributed across networked computer systems, so that computer readable code is stored and executed in a distributed manner. In addition, functional programs, code, and code segments for achieving various embodiments of the present invention can be easily interpreted by programmers skilled in the field to which the present invention is applied.

It will also be appreciated that the apparatus and method according to various embodiments of the present invention can be realized in the form of hardware, software, or a combination of hardware and software. Such software may include, for example, volatile or non-volatile storage devices such as ROM, whether removable or rewritable, or memory, such as RAM, memory chips, devices or integrated circuits, or For example, it may be stored in an optically or magnetically recordable and machine (eg, computer) readable storage medium such as a compact disk (CD), DVD, magnetic disk, or magnetic tape. Methods according to various embodiments of the present invention may be implemented by a computer or portable terminal including a control unit (control module 210, 260) and a memory, and such a memory contains instructions for implementing the embodiments of the present invention. It will be appreciated that this is an example of a machine-readable storage medium suitable for storing a program or programs including.

Accordingly, the present invention includes a program including code for implementing the device or method described in the claims of this specification and a storage medium readable by a machine (such as a computer) storing such a program. In addition, such a program may be transmitted electronically through any medium, such as a communication signal transmitted through a wired or wireless connection, and the present invention appropriately includes equivalents thereto.

Embodiments of the present invention disclosed in the present specification and drawings are merely presented as specific examples to easily explain the technical content of the present invention and help understanding of the present invention, and are not intended to limit the scope of the present invention. In addition, the embodiments according to the present invention described above are merely exemplary, and those skilled in the art will understand that various modifications and embodiments of equivalent range are possible therefrom. Therefore, the true technical protection scope of the present invention should be defined by the following claims.

Claims (1)

In a communication system providing a chatbot service,
A first user terminal of a first user using the chatbot service; and
A management server that operates at least one of software, programs, websites, and mobile apps for using a communication platform for providing the chatbot service to the user; including,
The first user terminal,
Receiving power information indicating a remaining amount of an internal battery of the first user terminal from the first user terminal;
First image information corresponding to the appearance of the first user is set, but when the power information indicates a threshold or higher, the appearance of the first user is photographed using a camera and modeling or rendering is performed. A first mode for generating the first image information is set by performing at least one, and when the power information indicates less than the threshold, setting a three-dimensional character preset in the management server as the first image information A second mode is set,
receiving a command voice from the first user through an input module;
receiving personal information representing the age of the first user from the first user;
Delivering the first image information and the voice command to the management server, -The voice command includes a desired time indicating a time reference for a response to a question indicated by the voice command -
The management server,
Extracting a first text corresponding to a question indicated by the command voice from the command voice;
Extracting information indicating the desired time from the first text;
The management server, when the desired time indicates a time corresponding to the future:
Converting the appearance of the first user represented by the first image information into second image information representing an aged appearance by the desired time; The number of gray hairs and the degree of hair loss are set to increase -
Delivering the first text to a second user terminal of a second user whose age is determined based on the age of the first user and the desired time;
Receiving second text indicating a response of the second user to the question indicated by the first text from the second user terminal;
By applying the second text to Text to Speech (TTS), the voice corresponding to the response is controlled to be output from the first user terminal through the chatbot service, and the appearance is based on the second image information Control the character object for the determined chatbot service to be displayed on the display of the first user terminal;
The management server, when the desired time indicates a time corresponding to the past:
Learning the artificial intelligence model of the management server by setting the chat records, communication records, and personal information of the first user recorded in the memory of the management server as learning data;
Based on the learned artificial intelligence model, response information corresponding to the input of the question indicated by the first text is obtained as an output,
A communication system that provides chatbot services.

Images