Active ai messenger system and method for providing service therefor

Abstract

The present invention aims to provide an active AI messenger system that actively conducts a chat with a user rather than passively responding to the user's questions, and a method for providing a service therefor. An active AI messenger system, according to one aspect of the present invention, comprises: an instant messenger server; a user terminal communicating with the instant messenger server; and a large language model (LLM) server that transmits and receives data from the instant messenger server, wherein the instant messenger server primarily processes chat data and inputs same into a large language model, and adopts or secondarily processes answer data outputted by the large language model and transmits same to the user terminal.

Description

Active AI messenger system and method for providing its service The present invention relates to an AI messenger system and a service providing method thereof, and more specifically, to an active AI messenger system that avoids passively answering users' questions and a service providing method thereof. An instant messenger (IM) is a client used for instant (real-time) text communication between two or more people via a network, such as the Internet. It's also called simply "messenger," and is also called "internet messenger" for messaging over the Internet, and "mobile messenger" for messaging via mobile devices. An instant messenger is a client that relays instant messages. It differs from email in that instant messengers allow chats to take place in real time. Additionally, most instant messaging services offer a user information feature that displays a list of currently connected and available users. This is commonly referred to as a "friends list." Transmission occurs as each person in a conversation types a single line of text, making it more like a phone call than exchanging letters. The earliest form of instant messaging was the PLATO system of the 1970s. Since the introduction of ICQ, the first widely used instant messenger, in November 1996, numerous similar services have emerged. Nowadays, many instant messengers support video conferencing, voice over Internet Protocol (VoIP), and even web conferencing services that combine video conferencing and instant messenger services. Consequently, the boundaries between these technologies are becoming increasingly blurred, and in some cases, chatbots, a type of AI, are even used on one side of the instant messenger. However, despite the development of generative AI, Large Language Models (LLMs), typical chatting with AI is not yet possible. Currently, commercialized services like OpenAI only involve inputting questions to AI and receiving responses, making them a distinct concept from chatting. Furthermore, prior art documents only describe chatbot programs recognizing conversational commands corresponding to questions, and then generating and providing appropriate responses. [Prior Art Literature] [Patent Document] Korean Patent Publication No. 10-2021-0072792 (June 17, 2021), Automated Chat Bot Processing The present invention is intended to solve the problems of the above-mentioned prior art, and the purpose of the present invention is to provide an active AI messenger system and a service provision method thereof that avoids the form of passively answering users' questions and allows chatting in an active form. An active AI messenger system according to one aspect of the present invention includes an instant messenger server, a user terminal communicating with the instant messenger server, and a large language model (LLM) server transmitting and receiving data from the instant messenger server, wherein the instant messenger server first processes chat data and inputs it into the large language model, and adopts or secondarily processes response data output by the large language model and transmits it to the user terminal. At this time, the instant messenger server may collect at least one of the following data for the first processing: chat data of a current chat room, chat data of a recent chat room, chat data of which a chat volume exceeds a set value, chat data of a chat room of which a chat frequency exceeds a set value, data stored in a user terminal, data stored in a commercial server, and data stored in an SNS server. Additionally, the collection of the above data may be initiated when the number of utterances constituting the chat data reaches a set number, when the chat data occupies a set capacity, or by a collection command from a user terminal. Additionally, the first processing can be performed by extracting feature codes from chat data and generating query words to be input into the large language model using the feature codes. In addition, the large language model is composed of multiple large language models, and the instant messenger server can select a matching large language model according to the extracted feature code. Additionally, the above feature code can be extracted by determining whether a word stored in an instant messenger server or a word with a similar meaning is included in the chat data. Additionally, the above feature code can be extracted by determining whether a specific word or a similar word appears repeatedly in the chat data. In addition, the above feature codes are extracted in multiple pieces, and the query word can be formed into a sentence by combining the above feature codes. In addition, the second processing may trim the response data output by the large language model and perform spoken language processing according to the conversation purpose or conversation type of the current chat room. Meanwhile, a method for providing an AI active messenger service according to one aspect of the present invention includes, for an active AI messenger system including an instant messenger server managing a chat, a user terminal where a chat is made, and a large language model for sending and receiving data from the instant messenger server, a step of initiating a chat, a step of collecting chat data, a step of extracting a feature code from the collected chat data, a step of first processing the extracted feature code into the form of a query word input into a large language model, and a step of secondly processing answer data output by the large language model into a form that matches the conversation purpose or conversation type of the current chat room. At this time, in the first step of processing the extracted feature code into the form of a query word input to a large language model, a step of selecting a matching large language model according to the extracted feature code may be further included. The present invention implements an active AI messenger system and a service provision method thereof, which collects chat data, processes it in a first step, inputs it into a large language model, and inputs the response of the large language model in a second step, thereby avoiding a passive form of answering a user's questions and allowing chatting to be performed in an active form. Figure 1 is a configuration diagram of an AI messenger system according to one embodiment of the present invention. FIG. 2 is a drawing illustrating the user terminal of FIG. 1 in more detail. Figure 3 is a drawing illustrating the messenger server of Figure 1 in more detail. Figure 4 is a drawing illustrating the control module of the messenger server of Figure 3 in more detail. FIG. 5 is a drawing illustrating an initial service screen of an AI messenger system according to one embodiment of the present invention. FIG. 6 is a diagram exemplarily showing the range of data collection in an AI messenger system according to one embodiment of the present invention. Figure 7 is a diagram exemplifying AI's active participation in a chat in an AI messenger system according to one embodiment of the present invention (data collection, feature code extraction). Figure 8 is another diagram exemplifying AI's active participation in a chat in an AI messenger system according to one embodiment of the present invention (data collection, feature code extraction, first transformation, second transformation). Figure 9 is a flowchart of a method for providing an active AI messenger service according to one embodiment of the present invention. In order to more clearly explain the features and advantages of the problem-solving means of the present invention, the present invention will be described in more detail with reference to specific embodiments of the present invention illustrated in the attached drawings. However, detailed descriptions of known functions or components that may obscure the gist of the present invention in the following description and attached drawings are omitted. It should also be noted that, where possible, identical components are indicated with identical reference numerals throughout the drawings. The terms and words used in the following description and drawings should not be interpreted as limited to their conventional or dictionary meanings, but should be interpreted with meanings and concepts that conform to the technical idea of ​​the present invention based on the principle that the inventor can appropriately define the concept of the term to best describe his or her own invention. Therefore, the embodiments described in this specification and the configurations illustrated in the drawings are merely the most preferred embodiments of the present invention and do not represent all of the technical idea of ​​the present invention. Therefore, it should be understood that there may be various equivalents and modified examples that can replace them at the time of filing this application. Additionally, unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by those of ordinary skill in the art to which this invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and shall not be interpreted in an idealized or overly formal sense unless explicitly defined herein. Additionally, terms containing ordinal numbers, such as "first," "second," etc., are used to describe various components, and are only used to distinguish one component from another, not to limit said components. For example, without departing from the scope of the present invention, a second component could be referred to as a "first component," and similarly, a first component could also be referred to as a "second component." In addition, the terminology used in this specification is only used to describe specific embodiments and is not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly indicates otherwise. In addition, it should be understood that the terms "comprises" or "has" described in this specification are intended to specify the presence of a feature, number, step, operation, component, part, or combination thereof described in the specification, but do not exclude in advance the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof. Additionally, terms such as "unit," "device," and "module" described in the specification mean a unit that processes at least one function or operation, which may be implemented by hardware, software, or a combination of hardware and software. Additionally, terms such as "a" or "an," "one," "the," and similar related words may be used in the context of describing the present invention (especially in the context of the claims below) to include both singular and plural meanings, unless otherwise indicated in the specification or clearly contradicted by the context. In addition, the term '~module' used in the embodiments of the present invention means a software component, and the '~module' performs certain roles. For example, '~module' includes components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, properties, procedures, subroutines, segments of program code, drivers, data, databases, data structures, tables, arrays, and variables. In addition, the functions provided within the components and '~modules' may be combined into a smaller number of components and '~modules' or further separated into additional components and '~modules'. In various examples of the present disclosure, " / " and "," should be interpreted as indicating "and / or". For example, "A / B" can mean "A and / or B". Furthermore, "A, B" can mean "A and / or B". Furthermore, "A / B / C" can mean "at least one of A, B, and / or C". Furthermore, "A, B, C" can mean "at least one of A, B, and / or C". In various examples of this disclosure, "or" should be interpreted as meaning "and / or." For example, "A or B" can include "only A," "only B," and / or "both A and B." In other words, "or" should be interpreted as meaning "additionally or alternatively." In addition to the terms described above, specific terms used in the following description are provided to help understand the present invention, and the use of these specific terms may be changed to other forms without departing from the technical spirit of the present invention. Additionally, embodiments within the scope of the present invention include computer-readable media having or carrying computer-executable instructions or data structures stored on the computer-readable media. Such computer-readable media may be any available media that can be accessed by a general-purpose or special-purpose computer system. By way of example, and not limitation, such computer-readable media may include physical storage media such as RAM, ROM, EPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage, or any other medium that can be used to store or carry predetermined program code means in the form of computer-executable instructions, computer-readable instructions or data structures, and that can be accessed by a general-purpose or special-purpose computer system. Furthermore, the present invention can be practiced in a network computing environment having various types of computer system configurations, including personal computers, laptop computers, handheld devices, multiprocessor systems, microprocessor-based or programmable consumer electronics, network PCs, minicomputers, mainframe computers, mobile phones, PDAs, pagers, etc. The present invention can also be practiced in a distributed system environment in which both local and remote computer systems perform tasks linked by wired data links, wireless data links, or a combination of wired and wireless data links over a network. In a distributed system environment, program modules can be located in local and remote memory storage devices. Additionally, it will be appreciated that each block of the processing flowchart drawings and combinations of the flowchart drawings can be performed by computer program instructions. These computer program instructions can be installed in a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing equipment, such that the instructions, when executed by the processor of the computer or other programmable data processing equipment, create a means for performing the functions described in the flowchart block(s). These computer program instructions can also be stored in a computer-available or computer-readable memory that can direct a computer or other programmable data processing equipment to perform the functions in a specific manner, such that the instructions stored in the computer-available or computer-readable memory can produce an article of manufacture that includes an instruction means for performing the functions described in the flowchart block(s). Since the computer program instructions may be installed on a computer or other programmable data processing device, a series of operational steps may be performed on the computer or other programmable data processing device to create a computer-executable process, and the instructions that cause the computer or other programmable data processing device to perform the steps for performing the functions described in the flowchart block(s) 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 contains one or more executable instructions for performing a specific logical function(s). It should also be noted that in some alternative implementation examples, the functions described in the blocks may occur out of order. For example, two blocks depicted in succession may actually be executed substantially concurrently, or the blocks may sometimes be executed in reverse order, depending on their respective functions. In specifically describing the embodiments of the present disclosure, examples of specific systems will be primarily targeted, but the main points claimed in this specification can be applied to other communication systems and services having similar technical backgrounds within a scope that does not significantly exceed the scope disclosed in this specification, and this can be done at the discretion of a person skilled in the relevant technical field. Hereinafter, an active AI messenger system according to an embodiment of the present invention will be described. FIG. 1 is a block diagram of an AI messenger system according to an embodiment of the present invention, FIG. 2 is a diagram illustrating the user terminal of FIG. 1 in more detail, FIG. 3 is a diagram illustrating the messenger server of FIG. 1 in more detail, FIG. 4 is a diagram illustrating the control module of the messenger server of FIG. 3 in more detail, FIG. 5 is a diagram illustrating an initial screen of a service of an AI messenger system according to an embodiment of the present invention, FIG. 6 is a diagram illustrating a range of data collection in an AI messenger system according to an embodiment of the present invention, FIG. 7 is a diagram illustrating an AI actively participating in a chat in an AI messenger system according to an embodiment of the present invention, and FIG. 8 is another diagram illustrating an AI actively participating in a chat in an AI messenger system according to an embodiment of the present invention. Referring to the drawings, an active AI messenger system (1000) according to one embodiment of the present invention can basically provide real-time online chat to two or more users who have installed the same instant messenger. To this end, the users utilize a user terminal (100) on which a messenger application is installed. The user terminal (100) communicates with an instant messenger server (200) via a network (10), and each user is identified by logging into the application. In addition, as described below, an active AI messenger system (1000) according to one embodiment of the present invention is characterized in that the instant messenger server (200) creates a virtual AI user and performs a chat with the user. At this time, the network (10) plays a role in transmitting data for data transmission and reception between the user terminal (100) and the instant messenger server (200), and depending on the system implementation method, a wired communication method such as Ethernet, xDSL (ADSL, VDSL), HFC (Hybrid Fiber Coaxial Cable), FTTC (Fiber to The Curb), FTTH (Fiber to The Home) may be used, and a wireless communication method such as WLAN (Wireless LAN), Wi-Fi, Wibro, WiMAX, HSDPA (High Speed ​​Downlink Packet Access), LTE (Long Term Evolution), LTE-A (Long Term Evolution Advanced) may be used. In addition, such a network (10) may be configured to include, for example, a plurality of access networks (not shown) and a core network (not shown), and may include an external network, for example, an Internet network (not shown). Here, the access network (not shown) is a network that performs wired and wireless communication with the user terminal (100), and may be implemented with, for example, a plurality of base stations such as a BS (Base Station), a BTS (Base Transceiver Station), a NodeB, an eNodeB, a gNodeB, etc., and a base station controller such as a BSC (Base Station Controller) and an RNC (Radio Network Controller). In addition, as described above, the digital signal processing unit and the wireless signal processing unit that were integrally implemented in the base station may be each divided into a digital unit (hereinafter referred to as a DU) and a wireless unit (hereinafter referred to as a RU), and a plurality of RUs (not shown) may be installed in each of a plurality of areas, and the plurality of RUs (not shown) may be connected to a centralized DU (not shown) to configure the configuration. In addition, the core network (not shown), which constitutes the mobile network together with the access network (not shown), plays a role in connecting the access network (not shown) and an external network, such as the Internet network (not shown). As described above, the core network (not shown) is a network system that performs major functions for mobile communication services, such as mobility control and switching between the access networks (not shown), and performs circuit switching or packet switching, and manages and controls packet flow within the mobile network. In addition, the core network (not shown) may manage inter-frequency mobility, and may play a role in interworking with traffic within the access network (not shown) and the core network (not shown) and other networks, such as the Internet network (not shown). The core network (not shown) may further include a Serving GateWay (SGW), a PDN GateWay (PGW), a Mobile Switching Center (MSC), a Home Location Register (HLR), a Mobile Mobility Entity (MME), and a Home Subscriber Server (HSS). In addition, the Internet network (not shown) refers to a typical open communication network, i.e. a public network, in which information is exchanged according to the TCP / IP protocol, and is connected to a user terminal (100), and information provided from the user terminal (100) can be provided to the instant messenger server (200) via the core network (not shown) and the access network (not shown), and conversely, information provided to the instant messenger server (200) can be provided to the user terminal (100) via the core network (not shown) and the access network (not shown). However, it is not limited thereto, and the instant messenger server (200) may be implemented as an integral part of the core network (not shown). In addition to the above-described communication method, it may include all forms of communication methods that are widely known or will be developed in the future. In addition, in this embodiment, a large language model server (LARGE LANGUAGE MODEL; 300) transmits and receives data from an instant messenger server (200) through the network (10), and a commercial server (400) and an SNS server (500) that provide services other than messenger services can transmit and receive data from the instant messenger server (200) through the network (10). At this time, the large language model server (300) is a language model comprised of an artificial neural network with numerous parameters (typically over several billion weights). It is trained on a significant amount of unlabeled text using self-supervised or semi-self-supervised learning. Large language models emerged around 2018 and are used for a variety of tasks. The focus has shifted from the previous training paradigm of specialized supervised learning models for specific tasks to research on natural language processing. Here, a large language model can refer to a language model capable of inference without fine tuning, and can have more parameters than existing general language models. For example, the large language model of the present invention can utilize OpenAI's CHAT GPT, Meta's OPT, etc., and is not limited to a specific large language model. This is because the present invention can obtain the result by inputting a query (the result of the first processing described below) into the large language model using the API (Application Programming Interface) provided by the large language model. Meanwhile, activities related to instant messenger services may refer to engaging in real-time online communication by participating in a chat room. Here, a chat room may refer to a virtual space created on an instant messenger server (200) where two or more users (including virtual AI users) can participate and exchange instant messages. The user terminal (100) may refer to a client of an active AI messenger system, and refers to a device that communicates with the instant messenger server (200), detects a user, inputs user data, and outputs the contents of a messenger service to the user. These user terminals (100) cannot be listed all because the modifications of portable devices are very diverse in accordance with the convergence trend of digital devices, but units of the same level as the above-mentioned units can be used as the user terminal (100) according to the present invention, and any device that can download and install a program for performing the active AI messenger system (1000) according to the present invention can be used as the user terminal (100) according to an embodiment of the present invention. Accordingly, the user terminal (100) may refer to any user device capable of installing and executing a messenger application related to a server, such as an electronic device such as a computer, an Ultra Mobile PC (UMPC), a workstation, a net-book, a PDA (Personal Digital Assistants), a portable computer, a web tablet, a wireless phone, a mobile phone, a smart phone, an e-book, a portable multimedia player (PMP), a portable game console, a navigation device, a black box, or a digital camera. The user terminal may perform overall service operations, such as configuring a service screen, entering data, transmitting and receiving data, and storing data, under the control of a messenger providing program (240) or an instant messenger server (200). In more detail, the user terminal (100) includes a camera module (110), a sensor module (120), an input device (130), an audio output unit (140), a display device (150), a memory (160), a program (165), a power supply unit (170), a communication module (180), and a control unit (190) that controls these as a whole. The camera module (110) captures still images or videos of the user, and the instant messenger server (200) can create an avatar to appear in a chat or change and output the avatar by having the camera module (110) capture still images or videos of the user. That is, the active AI messenger system according to the present embodiment can provide services by avatarizing the user by utilizing the camera module (110). This camera module (110) includes, in more detail, a lens section (not shown), an image sensor (not shown), a flash (not shown), a stabilizer (not shown), a camera memory (not shown), and a signal processor (not shown). The lens unit can collect light emitted from a subject that is the subject of an image capture. The lens unit can include one or more lenses. According to one embodiment, the camera module (110) can include multiple lens units. In this case, the camera module can form, for example, a dual camera, a 360-degree camera, or a spherical camera. Some of the plurality of lens elements may have the same lens properties (e.g., angle of view, focal length, autofocus, f-number, or optical zoom), or at least one lens assembly may have one or more lens properties that differ from the lens properties of the other lens assemblies. The lens element may include, for example, a wide-angle lens or a telephoto lens. An image sensor can obtain an image corresponding to a subject by converting light emitted or reflected from the subject and transmitted through a lens into an electrical signal. According to one embodiment, the image sensor may include one image sensor selected from image sensors having different properties, such as an RGB sensor, a BW (black and white) sensor, an IR sensor, or a UV sensor, a plurality of image sensors having the same properties, or a plurality of image sensors having different properties. Each image sensor included in the image sensor may be implemented using, for example, a CCD (charged coupled device) sensor or a CMOS (complementary metal oxide semiconductor) sensor. A flash can emit light that is used to enhance light emitted or reflected from a subject. In one embodiment, the flash can include one or more light-emitting diodes (e.g., red-green-blue (RGB) LEDs, white LEDs, infrared LEDs, or ultraviolet LEDs), or a xenon lamp. The stabilizer can move at least one lens or image sensor included in the lens unit (110) in a specific direction or control the operating characteristics of the image sensor (e.g., adjusting the read-out timing, etc.) in response to the movement of the camera module (110) or the user terminal (100) including the same. This allows compensating for at least some of the negative effects of the movement on the image being captured. According to one embodiment, the stabilizer can detect the movement of the camera module (110) or the user terminal (100) using a gyro sensor (not shown) or an acceleration sensor (not shown) disposed inside or outside the camera module (110). According to one embodiment, the stabilizer can be implemented as, for example, an optical image stabilizer. Accordingly, in the active AI messenger system according to the present embodiment, the AI, which is a virtual user described below, can select the timing of entering a conversation or the purpose of the conversation by reflecting the movement status of the user. The camera memory can temporarily store at least a portion of an image acquired through the image sensor for subsequent image processing operations. For example, when image acquisition is delayed due to a shutter, or when multiple images are acquired at high speed, the acquired original image (e.g., a Bayer-patterned image or a high-resolution image) is stored in the camera memory, and a corresponding copy image (e.g., a low-resolution image) can be previewed through the display device (150). Thereafter, when a specified condition is satisfied (e.g., a user input or a system command), at least a portion of the original image stored in the camera memory can be acquired and processed, for example, by a signal processor. According to one embodiment, the camera memory can be configured as at least a portion of the memory (160) or as a separate memory that operates independently therefrom. The image signal processor can perform one or more image processing operations on an image acquired through an image sensor or an image stored in a camera memory. The one or more image processing operations can include, for example, depth map generation, 3D modeling, panorama generation, feature point extraction, image synthesis, or image compensation (e.g., noise reduction, resolution adjustment, brightness adjustment, blurring, sharpening, or softening). Meanwhile, the sensor module (120) can detect the operating status (e.g., power or temperature) of the user terminal (100) or the external environmental status (e.g., user status) and generate an electrical signal or data value corresponding to the detected status. According to one embodiment, the sensor module (120) may include, for example, a gesture sensor, a gyro sensor, a pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biosensor, a temperature sensor, a humidity sensor, or an illuminance sensor. In addition, the sensor module (120) herein may further include a tactile sensor including at least one of a gas sensor or a smoke sensor for detecting the sense of smell, an ion sensor or a biosensor for detecting the sense of taste, and a magnetic sensor, temperature sensor, pressure sensor, and humidity sensor for detecting the sense of touch. Depending on the detection value of the sensor module (120), the AI, which is a virtual user described later, together with the camera module (110) described above, can be considered when selecting the timing of initiation of a conversation, the purpose of the conversation, and the type of conversation. The input device (130) can receive commands or data to be used in a component of the user terminal (100) (e.g., control unit (190)) from an external source (e.g., a user) of the user terminal (100). The input device (130) can include, for example, a touch panel, a microphone, a mouse, a keyboard, or a digital pen (e.g., a stylus pen), and any type of input means that can be developed in the future can be used. In addition, the input device (130) receives various information such as voice and / or text information, and transmits signals input in relation to setting various functions and controlling functions of the user terminal (100) to the control module (220). In addition, the input device (130) may further include at least one of a keypad and a touchpad that generate an input signal according to a user's touch or operation, and / or a microphone that generates an input signal for voice according to a user's speech. At this time, the input device (130) is configured in the form of a single touch panel (or touch screen) together with the display device (150) so that input and display functions can be performed simultaneously. In addition, the input device (130) may further include a camera module as described above. In particular, the input device (130) according to one embodiment of the present invention detects input information input from a user and transmits it to the control module (220). In particular, in the present invention, the user terminal (100) can input information for logging into a chat service, moving to a chat room, having a conversation, creating an avatar, etc., through the input device (130). In addition, information requested by the instant messenger service server (200) can be input through the input device (130). The audio output unit (140) can output audio signals provided by the active AI messenger service to the outside of the user terminal (100). The audio output unit (140) may include, for example, a speaker or a receiver. The speaker may be used for general purposes, such as multimedia playback or recording playback, and the receiver may be used to receive incoming calls. According to one embodiment, the receiver may be implemented separately from the speaker or as part of the speaker. The display device (150) can visually provide information to an external party (e.g., a user) of the user terminal (100). The display device (150) may include, for example, a display, a holographic device, or a projector and a control circuit for controlling the device. According to one embodiment, the display device (150) may include a touch circuitry configured to detect a touch, or a sensor circuitry configured to measure the intensity of a force generated by the touch (e.g., a pressure sensor). In addition, the display device (150) displays information about a series of operation states and operation results that occur during the performance of the functions of the user terminal (100). In addition, the display device (150) can display a menu of the user terminal (100) and user data input by the user. Here, the display device (150) can be configured as a liquid crystal display (LCD), a thin film transistor LCD (TFT-LCD), a light emitting diode (LED), an organic light emitting diode (OLED), an active matrix OLED (AMOLED), a retina display, a flexible display, a 3-dimensional display, etc. In addition, when the display device (150) is configured in the form of a touch screen, the display device (150) can perform some or all of the functions of the input device (130). In particular, in the present invention, a chat service implemented by an instant messenger server (200) can be displayed through the display device (150). The output chat service may be in the form of text, images, 3D images implemented on flat displays, or 360-degree 3D images implemented through VR devices. Additionally, the user's avatar may be output through the display device (150). Furthermore, guidance messages and the like may be output through speakers. Meanwhile, the memory (160) can store various data used by at least one component of the user terminal (100) (e.g., the control unit (190) or the sensor module (120). The data may include, for example, software (e.g., program (165)) and input data or output data for commands related thereto. The memory (160) may include volatile memory or non-volatile memory. In addition, a program (165) necessary for the functional operation of the user terminal (100) may be stored as software in the memory (160), and may be, for example, an operating system, middleware, and may include a metaverse application. In addition, the power supply (170) may supply power to at least one component of the user terminal (100). According to one embodiment, the power supply (170) may include a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell. The communication module (180) can support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the user terminal (100) and an external electronic device or an instant messenger server (200), and the performance of communication through the established communication channel. The communication module (180) operates independently from the control unit (190) (e.g., application processor) and can include one or more communication processors that support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module (180) can include a wireless communication module (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (394) (e.g., a local area network (LAN) communication module, or a power line communication module). Any of these communication modules can communicate with an external electronic device via a network (10) (e.g., a short-range communication network such as Bluetooth, WiFi direct, or IrDA (infrared data association)) or a second network (e.g., a long-range communication network such as a cellular network, the Internet, or a computer network (e.g., a LAN or WAN)). The control unit (190) may be a processing device that drives an operating system (OS) and each component. For example, it may execute software (e.g., a program (165)) to control at least one other component (e.g., a hardware or software component) of the user terminal (100) connected to the control unit (190) and perform various data processing or operations. According to one embodiment, as at least a part of the data processing or operation, the control unit (190) may load a command or data received from another component (e.g., a sensor module (120) or a communication module (180)) into a volatile memory, process the command or data stored in the volatile memory, and store the resulting data in a non-volatile memory. According to one embodiment, the control unit (190) may include a main processor (e.g., a central processing unit or an application processor) and an auxiliary processor (e.g., a graphics processing unit, an image signal processor, a sensor hub processor, or a communication processor) that can operate independently or together therewith. In addition, the control unit (190) controls to transmit a signal input through the input device (130) to the instant messenger server (200) through the communication module (180), controls to output information transmitted from the instant messenger server (200) and received through the communication module (180) through the display device (150), and controls to store such information or data in the memory (180). Alternatively, the control unit (190) of the user terminal (100) can control the input device (130) to process the signal received through the input device (130) and output it through the display device (150) without communicating with the instant messenger server (200) through the communication module (180), and can control the information or data generated in this process to be stored in the memory (180). The user terminal (100) is requested to input speech data (a speech act of speaking out loud or a description of the speech act in text form) from the instant messenger server (200), and the input data can be transmitted to the instant messenger server (200). In addition, at this time, the data input by the user terminal (100) refers to at least one of text, image, sound, voice, and video. The data input here can be generated through the camera module (110), sensor module (120), and / or input device (130) included in the user terminal (100). Meanwhile, such input data may be changed, and the changed input data may be transmitted back to the instant messenger server (200). In addition, the user terminal (100) may input other input data or the input data may be changed based on information detected by the sensor module. Meanwhile, the service server (200) according to one embodiment of the present invention performs the role of transmitting and receiving data for chat between users. More specifically, the messenger server (200) can serve as a service platform that provides an instant messenger service to a client user terminal (100). Users can sign up for the instant messenger service provided by the instant messenger server (200) through a messenger application and create an account for the instant messenger service. A user can create a general profile linked to their instant messenger service account. This general profile may be one that discloses account-related information to users with whom the user has a specific relationship (e.g., a friendship), while only providing limited information to users outside the specific relationship. Furthermore, the account-related information for the instant messenger service may include at least one of the user's ID, phone number, and email address. In more detail, the instant messenger server (200) includes a server communication module (210), a control module (220), and a storage module (230). The server communication module (210) performs the role of transmitting or receiving data including text or voice data for the instant messenger server (200) to provide an instant messenger service to the user terminal (100). This server communication module (210) is for communicating with a user terminal (100), and it is preferable that the communication network for the server communication module (210) to perform its function uses a wireless communication method such as WLAN (Wireless LAN), Wi-Fi, Wibro, WiMAX, HSDPA (High Speed ​​Downlink Packet Access), etc., but is not limited thereto, and depending on the system implementation method, a wired communication method such as Ethernet, xDSL (ADSL, VDSL), HFC (Hybrid Fiber Coaxial Cable), FTTC (Fiber to The Curb), FTTH (Fiber to The Home) may be used. In addition, the storage module (230) is a device for storing data, including a main memory device and an auxiliary memory device, and stores application programs required for the functional operation of the instant messenger server (200). This storage module (230) may largely include a program area and a data area. Here, when the instant messenger server (200) activates each function in response to a user's request, it executes the corresponding application programs under the control of the control unit (190) to provide each function. In particular, the storage module (230) of the present invention can store an active AI messenger program (240). Furthermore, chat data received from a user terminal (100) can be encrypted, stored, and then deleted upon termination of the chat. Furthermore, AI for creating avatars and the like can be stored in the storage module (230). For example, an artificial neural network can be stored in the storage module (230). Meanwhile, the control module (220) is responsible for operating a general messenger system. That is, the control module (220) controls the process of providing messenger services to the user terminal (100). Furthermore, in order to implement the active AI messenger system according to the present invention, the control module (220) includes a data collection module (221), a first data processing module (222), a second data processing module (223), a GUI display control module (224), and a virtual user creation module (225). First, the virtual user creation module (225) creates AI users who can enter a specific chat room. Here, AI users are created with names like AI1, AI2, etc., or with the names of specific companies or services, and chat with users who have previously entered or been invited. In Figure 5, it is exemplified that these AI users are indicated as AI1 or AI2, who have been added as friends in advance, or as recommended AI, etc., as friends who have not been added as friends but are recommended. Meanwhile, the data collection module (221) collects chat data for the AI ​​user to conduct a chat. In other words, since the chat spoken by the AI ​​user is determined based on the chat content of the human user, the data collection module (221) collects the chat content input from the user terminal (100), which is processed as described below and finally output to enable the chat. Here, chat data refers to text, voice, images, videos, etc. input by the user terminal during the chat. In more detail, the data collection module (221) collects at least one of the following data: chat data of the current chat room, chat data of the recent chat room, chat data of which the chat volume is greater than a set value, chat data of which the chat frequency is greater than a set value, data stored in a user terminal, data stored in a commercial server, and data stored in an SNS server. Referring to FIG. 6, the data collection module (221) basically collects chat data entered by the user in the current chat room 1, but can also collect chat data from another room (chat room 2) where chat is currently in progress. Additionally, the data collection module (221) can collect chat data to extract feature codes from other recently chatted rooms (recent chat rooms 1 to 4). Here, feature codes refer to words that can identify the purpose or type of conversation in text, voice, or images. Additionally, a recent chat room refers to a room that has been chatted for a first set amount of time (e.g., 1 minute) or within a second set amount of time (e.g., within 10 minutes) after the chat has ended. Furthermore, the data collection module (221) can collect chat records from other rooms that are not recent chat rooms but still have chat records, and use them to extract specific codes to be described later. In addition, the data collection module (221) can extract feature codes by utilizing data stored in the memory (160) of the user terminal (100), and can extract feature codes by utilizing data disclosed on a commercial server (400) that is usually used, or by utilizing user data disclosed on an SNS server (500). Meanwhile, it may be desirable to initiate data collection necessary for feature code extraction when a set number of utterances constituting the chat data are secured. This is because when the user inputs only one chat, it may be relatively more difficult to find feature codes than when multiple chats or sentences exist. Furthermore, for the same purpose, it is desirable to secure chat data input by the user in amounts exceeding the set capacity. However, in the active AI messenger system (1000) according to the present embodiment, the user may want an AI response even for the input of the fewest chats. Therefore, the active AI messenger system (1000) provides a separate response request output icon, and when selected, the user can request an AI user response based on the minimum number of utterances. Meanwhile, the first data processing module (222) extracts these feature codes and uses the feature codes to generate queries to be input into a large language model (this is referred to as “first processing”, hereinafter the same). Here, the feature code refers to a word that can identify the purpose or type of conversation in text, voice, or image, etc. That is, referring to FIG. 7, when Gil-dong Kim calls a virtual user after inputting the response “It might rain tomorrow” in response to the conversation “Let’s check the weather in Seoul tomorrow and meet”, the first data processing module (222) can extract “tomorrow”, “Seoul”, “weather”, and “rain” as feature codes. That is, words such as 'tomorrow', 'rain', 'Seoul', 'weather', and 'rain' are already stored in the form of a database in the storage module (230) of the instant messenger server (200). The first data processing module first determines whether the words extracted from the chat match the words stored in the storage module (230), and if they do, determines them as feature codes. Also, in Fig. 7, in response to the conversation "Let's check the weather in Seoul tomorrow and meet again," Kim Gil-dong enters the user's response "It might rain tomorrow." Since "weather" and "rain" are classified as synonyms and stored in the storage module (230), the first data processing module (222) can determine "weather," which is the upper concept among them, as a feature code. In other words, the feature code can be extracted by determining whether a word stored in the instant messenger server (200) or a word with a similar meaning thereto is included in the chat data. Furthermore, in Figure 7, "tomorrow" and "weather" (determined as synonyms for "rain") appear repeatedly. Words that appear repeatedly are more likely to be identified as feature codes for conversation purposes. Therefore, the first data processing module (222) can further determine whether a specific word or a similar word appears repeatedly in the chat data and extract feature codes. In addition, referring further to FIG. 8, the active AI system (1000) according to the present embodiment can actively initiate a conversation by utilizing chat data from another chat room, data stored in a commercial server (400), or data (500) stored in an SNS server, even in the absence of chat data as described above. In this case, it may be desirable to utilize the form of the initially initiated conversation stored in the storage module (230) described above, and it is desirable to utilize conversation text of an AI that has been well-received by other users. Fig. 8 illustrates the creation of an initial conversation using the "weather," which is currently an issue in other chat rooms or SNS servers. At this time, "Isn't the weather too hot these days?" may be an utterance stored in the storage module (230). At this time, the user responds with "Oh, I couldn't sleep yesterday because it was a tropical night." Here, the first data processing module (222) determines the feature code "tropical night" from the repeated appearance of the AI's "weather" that appeared first and the similar phrase "tropical night" in my answer. At this time, the first data processing module (222) uses the feature code extracted above to generate a query to be input into the large language model. That is, since 'tropical night' is determined as the feature code above, the first data processing module (222) inputs the query 'tropical night' into the large language model using 'tropical night'. At this time, it is also desirable for the first processing module (222) to input a request to output various one-line answers for 'tropical night'. This is because the large language model generally outputs a large amount of answer results, so a simple form of answer that fits the chat is required. Furthermore, it goes without saying that these feature codes can be extracted in multiple pieces, as in the example of FIG. 7. In this case, the first data processing module (222) uses the extracted feature codes to generate a query to be input into a large-scale language model. Furthermore, in this case, the query can be formed as a sentence composed of feature codes. In this case, the sentence structure can be achieved by utilizing a database stored in the instant messenger server. Meanwhile, it is desirable for the large language model here to consist of multiple large language models, with the large language model that requests responses based on the feature code being selected. In other words, the instant messenger server can select a matching large language model based on the extracted feature code. For example, if the feature code is determined to be related to car purchases, it would be desirable for the first data processing module to select a large language model related to car purchases and input the query into it. Therefore, selecting large language models by product or service can encourage competition and contribute to the development of more advanced large language models. Meanwhile, when a query is input as described above, the large language model outputs a response. In Figure 8, in Chat 1 (11) and Chat 2 (12), "tropical night" is both a feature code and a query input to the large language model. As described above, a request to output various one-line responses to "tropical night" was input along with the query, so the large language model outputs multiple responses to "tropical night." At this time, the second data processing module (223) trims the response data output by the large language model and performs spoken processing according to the conversation purpose or conversation type of the current chat room. The second data processing module (223) can perform processing such as selecting multiple responses or removing some of the responses, for example. Fig. 8 illustrates an example in which the large language model outputs five responses to the query word 'tropical night' and one of the responses selected is output in the form of AI chatting. In addition, it is of course possible for the second data processing module (223) to select each response output by the large language model and output it as a separate chat. Meanwhile, a character dialogue DB is stored in the storage module (230). The character dialogue DB refers to data about a specific character persona in response to the user's speech. The character persona is composed of a dialogue style, a world view, and a personality. At this time, the second data processing module (223) determines the form of the dialogue from the data entered by the user. In the case of the dialogue style, it is classified into comfortable / strict, etc., in the case of the world view, it is classified into domestic / world / universe, etc., and in the case of the personality, it is classified into emotional / extroverted, etc., and the dialogue style can be changed into a colloquial style while processing it. In this regard, the example of FIG. 8 exemplifies a dialogue processed as Chat 3 (t3). In response to this, the user re-enters chat 4 (t4), and the first data processing module (222) selects 'electricity bill' as the query word, and the second data processing module (223) can change the response of the large language model output as 'electricity bill' into colloquial language reflecting the character persona and output it. However, as previously described, the data collection module (221) is capable of collecting data from locations other than the current chat room. In FIG. 8, since the data collection module (221) has already obtained text such as the user's high electricity bill last month, the second processing module (222) can include such information in the final output. Meanwhile, the instant messenger server (200) may further include a chat data calculation module (224). In the messenger system, a large amount of chat data is mutually transmitted between users chatting in a chat room. At this time, the chat data calculation module (224) calculates the amount of text entered between the user and the other user chatting, the duration of the chat between the users, the amount of data transmitted between the users, the location information of the user terminal (100), and the number of times the chat was performed between the users, thereby calculating the affinity between the users. Here, the amount of text can refer not only to the size of the text data entered into the chat room, but also to the number of conversations entered in a chat between users. For example, if a first user enters two conversations in the form of speech bubbles, and a second user enters two conversations, also in the form of speech bubbles, the amount of text can be counted as 4. Here, the relationship between the two can be calculated as increasing as the number of conversations entered increases. Additionally, the duration of a chat between users here refers to the total time the chat took place based on a set period. This set period can be set to, for example, three days. The longer the actual time for multiple consecutive chats within three days, the stronger the relationship between users can be calculated. Furthermore, the duration of a chat here can also include the time the chat window was opened with a specific user. In addition, the sensor module (120) of the user terminal (100) here includes GPS and can detect information on the location of the user terminal (100) within a set period of time, and the chat data calculation module (224) can further calculate the relationship with the user located within a set distance within the set period of time. In this way, the chat data operation module (224) can generate an index called affinity by incorporating at least one of the amount of text entered during a chat between users, the duration of the chat between users, the amount of data transmitted between users, location information of the user terminal, and the number of times the chat between users was performed. At this time, the affinity can be formed by adding up the result values ​​that have the above factors as variables, or by setting a weight to the result values ​​that have each factor as a variable and then adding them up. Furthermore, in this case, it is also preferable for the chat data operation module (224) to set a higher affinity for the user with whom the chat was most recently performed. In this process, data that changes the graphical user interface (GUI) of the friend list or chat list according to the affinity produced can be generated and transmitted to the user terminal (100) for output. FIG. 5 illustrates an example in which the size is set according to this affinity. In fact, if the affinity for AI1 (2) or Kim Gil-dong (1) among friends is maintained relatively high for a set period of time, AI1 (2) or Kim Gil-dong (1) may be placed at the top of the friend list, and the area of ​​the icon may increase. In addition, since the time of the chat with AI1 (2) or Kim Gil-dong (1) is closest to the present, the icon may also be placed at the top. Hereinafter, a method for providing an active AI messenger service according to one embodiment of the present invention will be described. However, any content that overlaps with the previously described content will be omitted. Figure 9 is a flowchart of a method for providing an active AI messenger service according to one embodiment of the present invention. A method for providing an active AI messenger service according to one embodiment of the present invention includes a step of initiating a chat (S110), a step of collecting chat data (S120), a step of extracting feature codes from the collected chat data (S130), a step of first processing the extracted feature codes into the form of a query word input into a large language model (S140), and a step of secondly processing the response data output by the large language model into a form that matches the conversation purpose or conversation type of the current chat room (S150). At this point, the functions of each step have been fully explained. Notably, step S140 further includes selecting a matching large-scale language model based on the extracted feature code. This allows for the selection of large-scale language models by product and service, thereby encouraging competition and contributing to the development of more advanced large-scale language models. The above-described method may be provided as a computer program stored on a computer-readable recording medium for execution on a computer. The medium may be one that continuously stores a computer-executable program or one that temporarily stores it for execution or download. In addition, the medium may be various recording means or storage means in the form of a single or multiple hardware combinations, and is not limited to a medium directly connected to a computer system, but may also be distributed over a network. Examples of the medium may include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and those configured to store program instructions, including ROM, RAM, and flash memory. In addition, examples of other media may include recording or storage media managed by app stores that distribute applications, sites that supply or distribute various software, servers, etc. The methods, operations, or techniques of the present disclosure may be implemented by various means. For example, these techniques may be implemented in hardware, firmware, software, or a combination thereof. Those skilled in the art will appreciate that the various exemplary logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various exemplary components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software will depend on the particular application and the design requirements imposed on the overall system. Those skilled in the art may implement the described functionality in various ways for each particular application, but such implementations should not be construed as departing from the scope of the present disclosure. In a hardware implementation, the processing units used to perform the techniques may be implemented within one or more ASICs, DSPs, digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, electronic devices, other electronic units designed to perform the functions described herein, a computer, or a combination thereof. Accordingly, the various exemplary logical blocks, modules, and circuits described in connection with the present disclosure may be implemented or performed by any combination of a general-purpose processor, a DSP, an ASIC, an FPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or those designed to perform the functions described herein. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration. In a firmware and / or software implementation, the techniques may be implemented as instructions stored on a computer-readable medium, such as random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable PROM (EEPROM), flash memory, a compact disc (CD), a magnetic or optical data storage device, etc. The instructions may be executable by one or more processors and may cause the processor(s) to perform certain aspects of the functionality described herein. When implemented in software, the techniques may be stored on or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media, including any medium that facilitates transfer of a computer program from one place to another. Storage media may be any available media that can be accessed by a computer. By way of example, and not limitation, such computer-readable media can include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. Also, any connection is properly termed a computer-readable medium. For example, the software may be transmitted over a coaxial cable, fiber optic cable, twisted pair, digital subscriber line, or other similar medium.

[0089] When transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line, or wireless technologies such as infrared, radio, and microwave, the coaxial cable, fiber optic cable, twisted pair, digital subscriber line, or wireless technologies such as infrared, radio, and microwave are included within the definition of media. Disk and disc, as used herein, include compact discs, laser discs, optical discs, digital versatile discs (DVDs), floppy disks, and Blu-ray discs, where disks typically reproduce data magnetically, while discs reproduce data optically using lasers. Combinations of the above should also be included within the scope of computer-readable media. A software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium may be coupled to the processor such that the processor can read information from, and write information to, the storage medium. Alternatively, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. Alternatively, the processor and the storage medium may reside as discrete components in the user terminal. While the embodiments described above have been described as utilizing aspects of the presently disclosed subject matter in one or more standalone computer systems, the present disclosure is not limited thereto and may be implemented in conjunction with any computing environment, such as a network or distributed computing environment. Furthermore, aspects of the present disclosure may be implemented in multiple processing chips or devices, and storage may be similarly affected across multiple devices. Such devices may include personal computers, network servers, and portable devices. While the present disclosure has been described in connection with certain embodiments herein, various modifications and variations may be made without departing from the scope of the present disclosure, which would be apparent to those skilled in the art. Furthermore, such modifications and variations are intended to fall within the scope of the claims appended to this specification. [Explanation of symbols] 1000: Active AI Messenger System 10: Network 100. 100_1 쪋 100_n, 101: User terminal 110: Camera module 120: Sensor module 130: Input device 140: Audio output section 150: Display device 160: Memory 165: Program 170: Power supply 180: Communication module 190: Processor 200: Instant Messenger Server 210: Server Communication Module 220: Control module 221: Data Collection Module 222: Data Processing Module 1 223: Data Second Processing Module 224: GUI display control module 230: Storage module 240: Messenger Provider Program 300, 300_1 쪋 300_n: Large Language Model Server 400: Commercial Server 500: SNS server

Claims

1. Instant messenger server; A user terminal communicating with the instant messenger server; and A large language model (LLM) server that sends and receives data from the instant messenger server; Including, An active AI messenger system characterized in that the instant messenger server first processes chat data and inputs it into a large language model, and then adopts or secondarily processes the response data output by the large language model and transmits it to a user terminal.

2. In paragraph 1, An active AI messenger system characterized in that the instant messenger server collects at least one of the following data for the first processing: chat data of a current chat room, chat data of a recent chat room, chat data in which a chat volume exceeds a set value, chat data in a chat room in which a chat frequency exceeds a set value, data stored in a user terminal, data stored in a commercial server, and data stored in an SNS server.

3. In paragraph 2, An active AI messenger system characterized in that the collection of the above data is initiated when the number of utterances constituting the chat data reaches a set number, when the chat data occupies a set capacity, and by a collection command from a user terminal.

4. In paragraph 1, An active AI messenger system characterized in that the above first processing is performed by extracting a feature code from chat data and generating a query word to be input into the large language model using the feature code.

5. In paragraph 4, The above large language model is composed of multiple parts, An active AI messenger system characterized in that the instant messenger server selects a large language model that matches the extracted feature code.

6. In paragraph 4, An active AI messenger system characterized in that the above feature code is extracted by determining whether a word stored in an instant messenger server or a word with a similar meaning thereto is included in the chat data.

7. In paragraph 4, An active AI messenger system characterized in that the above feature code is extracted by determining whether a specific word or a similar word appears repeatedly in chat data.

8. In paragraph 4, An active AI messenger system characterized in that the above feature codes are extracted in multiple pieces, and the query word is formed into a sentence by combining the above feature codes.

9. In paragraph 1, An active AI messenger system characterized in that the second processing trims the response data output by a large language model and performs spoken language processing according to the conversation purpose or conversation type of the current chat room.

10. For an active AI messaging system including an instant messenger server that manages chat, a user terminal where chatting takes place, and a large language model that sends and receives data from the instant messenger server. Steps to initiate a chat; Steps in which chat data is collected; Step of extracting feature codes from collected chat data; A first step of processing the extracted feature code into the form of a query word that is input to a large language model; and A second step in which the response data output by the large language model is processed into a form that matches the conversation purpose or conversation type of the current chat room; A method for providing an AI active messenger service, characterized by including:

11. In paragraph 10, A method for providing an AI active messenger service, characterized in that in a first step of processing the extracted feature code in the form of a query word input to a large language model, the method further includes a step of selecting a large language model that matches the extracted feature code.

Images