Server and method for providing an online trading service platform for raw materials and industrial goods

The server-based platform with AI chatbots addresses the challenge of new companies entering the raw materials market by enabling real-time communication and automated negotiation, enhancing transaction efficiency and document generation.

KR103043961B1Active Publication Date: 2026-11-10TROLLY HOLDINGS CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
KR1020240166638
Authority / Receiving Office
KR · KR
Patent Type
Patents
Current Assignee / Owner
Priority Date
2023-11-21
Filing Date
2024-11-20
Publication Date
2026-11-10
Estimated Expiration
2044-11-20

AI Technical Summary

Technical Problem

The existing raw materials trading market faces challenges in allowing new companies to enter due to transactions being conducted primarily between established business relationships, and lacks real-time communication and automated negotiation tools for transaction conditions.

Method used

A server-based online trading platform with AI-powered chatbots facilitates company-to-company communication, automates transaction negotiations, and generates transaction condition confirmation documents and contracts based on conversation content.

Benefits of technology

Enables seamless transaction negotiations and automatic document generation, facilitating entry of new companies and enhancing efficiency in raw materials trading.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 112024128051883-PAT00003_ABST
    Figure 112024128051883-PAT00003_ABST
Patent Text Reader

Abstract

The present disclosure relates to a server providing an online trading service platform for raw materials and industrial goods. When a chat room is created in response to a client's purchase request, a transaction negotiation is conducted based on the conversation content in the chat room. When the transaction conditions are finalized, a transaction condition confirmation document can be automatically generated. When the client's confirmation of the transaction condition confirmation document is received, an invoice and a contract regarding the transaction conditions can be automatically generated.
Need to check novelty before this filing date? Find Prior Art

Description

Technology Field

[0001] The present disclosure relates to a server that provides an online trading service platform for raw materials and industrial goods. Background Technology

[0002] The existing raw materials trading market had a problem in that it was difficult for new companies to enter because transactions were conducted only between companies with existing business relationships.

[0003] In particular, the raw materials market involves many trading conditions that fluctuate in real time, and since work is often conducted based on personal relationships between personnel, real-time work discussions frequently took place via social media or chat to ensure rapid communication.

[0004] In order to solve the above problems, there is a need for technology that can provide a chat function for company-to-company communication within the platform and an automatic response function using an AI-based chatbot, but currently, such technology is not publicly available. Prior art literature

[0005] Republic of Korea Published Patent Application No. 10-2001-0111866 The problem to be solved

[0006] The embodiments disclosed in this disclosure are intended to provide a server for an online trading service platform for raw materials and industrial goods.

[0007] In addition, the embodiments disclosed herein aim to provide a service platform capable of conducting transaction negotiations based on conversation content within a chat room when a chat room is created by a client's purchase request, and automatically generating a transaction condition confirmation document when the transaction conditions are finalized.

[0008] In addition, the embodiments disclosed herein aim to provide a service platform capable of automatically generating an invoice and a contract regarding transaction conditions when a client's confirmation of the transaction conditions is received.

[0009] The problems that this disclosure aims to solve are not limited to those mentioned above, and other unmentioned problems will be clearly understood by a person skilled in the art from the description below. means of solving the problem

[0010] A server providing an online trading service platform for raw materials and industrial goods according to an embodiment of the present disclosure for solving the above-mentioned problem comprises: a server providing an online trading service platform for goods including raw materials and industrial goods, a storage module storing an artificial intelligence-based chatbot; and a communication module communicating with a first terminal of a first client and a second terminal of a second client. It includes a control module, wherein the control module provides sales conditions including the country of origin, minimum order quantity, sales price, and lead time of a product sold by the first client on the service platform to the second client's second terminal, and when a chat window requesting the purchase of the product is called from the second client's terminal, it creates a chat room for transaction negotiation between the first client and the second client, and controls the transaction negotiation to proceed based on the conversation content within the created chat room using the chatbot, wherein it recognizes the second client's requirements for each item included in the conversation content based on the currently set sales conditions, determines whether the recognized requirements meet the sales conditions, and if the recognized requirements meet the sales conditions for all items for the contract, it generates a transaction condition confirmation document with these as transaction conditions and provides it to the second terminal, and when the second client's confirmation regarding the transaction condition confirmation document is received, it determines that a contract has been concluded, generates an invoice and a contract regarding the transaction conditions, and provides them to the second terminal, and stores the conversation content, the transaction condition confirmation document, and the invoice and contract. Save to the module.

[0011] In addition, a method for providing an online trading service platform for raw materials and industrial goods according to an embodiment of the present disclosure for solving the aforementioned problem comprises: a method for providing an online trading service platform for goods including raw materials and industrial goods performed by a server, the method comprising the steps of: providing sales conditions including the country of origin, minimum order quantity, sales price, and lead time of goods sold by a first client on the service platform to a second terminal of a second client; when a chat window requesting the purchase of the goods is called from the second terminal, creating a chat room for transaction negotiation between the first client and the second client, and controlling the transaction negotiation to proceed based on the conversation content within the created chat room using the chatbot; recognizing the requirements of the second client for each item included in the conversation content based on the currently set sales conditions; determining whether the recognized requirements meet the sales conditions; and, if the recognized requirements meet the sales conditions for all items for the contract, generating a transaction condition confirmation document with these as transaction conditions and providing it to the second terminal. The method includes the step of determining that a contract has been concluded and generating an invoice and a contract regarding the transaction conditions and providing them to the second terminal when the client’s confirmation regarding the transaction conditions is received; and the step of storing the conversation content, the transaction conditions confirmation, and the invoice and contract.

[0012] In addition, a computer program stored on a computer-readable recording medium for executing a method for implementing the present disclosure may be further provided.

[0013] In addition, a computer-readable recording medium for recording a computer program for executing a method for implementing the present disclosure may be further provided. Effects of the invention

[0014] According to the above-described means for solving the problem of the present disclosure, the effect of providing an online trading service platform for raw materials and industrial goods is provided.

[0015] In addition, according to the aforementioned means for solving the problem of the present disclosure, when a chat room is created by a client's purchase request, a transaction negotiation can be conducted based on the conversation content in the chat room, and when the transaction conditions are finalized, a transaction condition confirmation document can be automatically generated.

[0016] In addition, according to the aforementioned means for solving the problem of the present disclosure, when a client's confirmation of the transaction conditions is received, an invoice and a contract regarding the transaction conditions can be automatically generated.

[0017] The effects of the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art from the description below. Brief explanation of the drawing

[0018] FIG. 1 is a schematic diagram of a system providing an online trading service platform for raw materials and industrial goods according to an embodiment of the present disclosure. FIG. 2 is a drawing illustrating a list of raw materials and industrial materials handled on an online trading service platform for raw materials and industrial materials according to an embodiment of the present disclosure. Figure 3 is a diagram illustrating the creation of a chat room for the client's transaction process. FIG. 4 is a block diagram of a server providing an online trading service platform for raw materials and industrial goods according to an embodiment of the present disclosure. FIGS. 5 to 10 are flowcharts of a method for providing an online trading service platform for raw materials and industrial goods according to an embodiment of the present disclosure. FIGS. 11 to 15 are diagrams illustrating how a transaction negotiation is conducted using an artificial intelligence-based chatbot. FIG. 16 is a diagram illustrating an example in which an artificial intelligence model generates a purchase contract and a sales contract in accordance with the conclusion of a contract. Figure 17 is a diagram illustrating an example of an artificial intelligence model dividing a contract into two contracts, a sales contract and a purchase contract. Specific details for implementing the invention

[0019] Throughout this disclosure, the same reference numerals denote the same components. This disclosure does not describe all elements of the embodiments, and general content in the art to which this disclosure pertains or content that overlaps between embodiments is omitted. The terms 'part, module, component, block' as used in the specification may be implemented in software or hardware, and depending on the embodiments, a plurality of 'parts, modules, components, blocks' may be implemented as a single component, or a single 'part, module, component, block' may include a plurality of components.

[0020] Throughout the specification, when a part is described as being "connected" to another part, this includes not only cases where they are directly connected but also cases where they are indirectly connected, and indirect connections include connections made via a wireless communication network.

[0021] Furthermore, when it is stated that a part "includes" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0022] Throughout the specification, when it is stated that a component is located "on" another component, this includes not only cases where a component is in contact with another component, but also cases where another component exists between the two components.

[0023] Terms such as "first," "second," etc., are used to distinguish one component from another, and the components are not limited by the aforementioned terms.

[0024] Singular expressions include plural expressions unless there is an obvious exception in the context.

[0025] In each step, identification codes are used for convenience of explanation and do not describe the order of the steps; the steps may be performed differently from the specified order unless a specific order is clearly indicated in the context.

[0026] The operating principles and embodiments of the present disclosure will be described below with reference to the attached drawings.

[0027] In this specification, the term "server according to the present disclosure" includes all various devices capable of performing computational processing and providing results to a user. For example, the server according to the present disclosure may include a computer, a server device, and a portable terminal, or may be in the form of any one of these.

[0028] Here, the computer may include, for example, a laptop, desktop, notebook, tablet PC, slate PC, etc. equipped with a web browser.

[0029] The above server device is a server that processes information by communicating with an external device, and may include an application server, a computing server, a database server, a file server, a game server, a mail server, a proxy server, and a web server.

[0030] The above portable terminal may include, for example, all types of handheld-based wireless communication devices such as PCS, GSM, PDC (Personal Digital Cellular), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), WiBro (Wireless Broadband Internet) terminals, smartphones, etc., as well as wearable devices such as watches, rings, bracelets, anklets, necklaces, glasses, contact lenses, or head-mounted devices (HMDs).

[0031] The artificial intelligence-related functions according to the present disclosure are operated through a processor and a storage module. The processor may be composed of one or more processors. In this case, the one or more processors may be general-purpose processors such as CPUs, APs, and DSPs (Digital Signal Processors), graphics-dedicated processors such as GPUs and VPUs (Vision Processing Units), or artificial intelligence-dedicated processors such as NPUs. The one or more processors control the processing of input data according to predefined operation rules or artificial intelligence models stored in the storage module. Alternatively, if the one or more processors are artificial intelligence-dedicated processors, the artificial intelligence-dedicated processors may be designed with a hardware structure specialized for processing a specific artificial intelligence model.

[0032] The predefined rules of operation or artificial intelligence models are characterized by being created through learning. Here, being created through learning means that a basic artificial intelligence model is trained using a number of training data by a learning algorithm, thereby creating predefined rules of operation or artificial intelligence models configured to perform desired characteristics (or objectives). Such learning may be performed on the device itself where the artificial intelligence according to the present disclosure is executed, or it may be performed through a separate server and / or system. Examples of learning algorithms include supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but are not limited to the examples described above.

[0033] An artificial intelligence model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weights and performs neural network operations through operations between the results of previous layers and the multiple weights. The multiple weights possessed by the multiple neural network layers can be optimized based on the learning results of the artificial intelligence model. For example, the multiple weights can be updated so that the loss value or cost value obtained by the artificial intelligence model is reduced or minimized during the learning process. Artificial neural networks may include deep neural networks (DNNs), such as Convolutional Neural Networks (CNNs), Deep Neural Networks (DNNs), Recurrent Neural Networks (RNNs), Restricted Boltzmann Machines (RBMs), Deep Belief Networks (DBNs), Bidirectional Recurrent Deep Neural Networks (BRDNNs), or Deep Q-Networks, but are not limited to the examples mentioned above.

[0034] According to an exemplary embodiment of the present disclosure, a processor can implement artificial intelligence. Artificial intelligence refers to a machine learning method based on artificial neural networks that enables a machine to learn by mimicking human biological neurons. Methodologies of artificial intelligence can be classified according to the learning method into supervised learning, where input data and output data are provided together as training data and the solution (output data) to the problem (input data) is predetermined; unsupervised learning, where only input data is provided without output data and the solution (output data) to the problem (input data) is not predetermined; and reinforcement learning, where a reward is given from the external environment whenever an action is taken in the current state, and learning proceeds in a direction that maximizes such reward. Additionally, methodologies of artificial intelligence may be classified according to the architecture, which is the structure of the learning model. The architectures of widely used deep learning technologies can be classified into convolutional neural networks, recurrent neural networks, transformers, generative adversarial networks, etc.

[0035] The device may include an artificial intelligence model. The artificial intelligence model may be a single model or may be implemented as multiple models. The artificial intelligence model may be composed of a neural network (or artificial neural network) and may include statistical learning algorithms that mimic biological neurons in machine learning and cognitive science. A neural network may refer to a model that possesses problem-solving capabilities by having artificial neurons (nodes) that form a network through synaptic connections and change the strength of synaptic connections through learning. The neurons of a neural network may include combinations of weights or biases. A neural network may include one or more layers composed of one or more neurons or nodes. For example, the device may include an input layer, a hidden layer, and an output layer. The neural network constituting the device can infer a result to be predicted from an arbitrary input by changing the weights of the neurons through learning.

[0036] The processor can create a neural network, train or learn a neural network, perform operations based on received input data, generate information signals based on the results of the operations, or retrain the neural network. The neural network models may include, but are not limited to, various types of models such as CNN, R-CNN, RPN, RNN, S-DNN, S-SDNN, Deconvolution Network, DBN, RBM, Fully Convolutional Network, LSTM Network, and Classification Network, such as GoogleNet, AlexNet, and VGG Network. The processor may include one or more processors for performing operations according to the neural network models. For example, the neural network may include a deep neural network.

[0037] Neural networks include CNN, RNN, percept, multilayer perceptron, FF (Feed Forward), RBF (Radial Basis Network), DFF (Deep Feed Forward), LSTM (Long Short Term Memory), GRU (Gated Recurrent Unit), AE (Auto Encoder), VAE (Variational Auto Encoder), DAE (Denoising Auto Encoder), SAE (Sparse Auto Encoder), MC (Markov Chain), HN (Hopfield Network), BM (Boltzmann Machine), RBM (Restricted Boltzmann Machine), DBN (Depp Belief Network), DCN (Deep Convolutional Network), DN (Deconvolutional Network), DCIGN (Deep Convolutional Inverse Graphics Network), GAN (Generative Adversarial Network), LSM (Liquid State Machine), ELM (Extreme Learning) Machine), ESN (Echo State Network), DRN (Deep Residual Network), DNC (Differentiable Neural Network) A person skilled in the art will understand that any neural network may be included, but is not limited to, Computer (NTM), Neural Turning Machine (NTM), Capsule Network (CN), Kohonen Network (KN), and Attention Network (AN).

[0038] According to an exemplary embodiment of the present disclosure, the processor comprises a Convolutional Neural Network (CNN) such as GoogleNet, AlexNet, VGG Network, Region with Convolutional Neural Network (R-CNN), Region Proposal Network (RPN), Recurrent Neural Network (RNN), Stacking-based Deep Neural Network (S-DNN), State-Space Dynamic Neural Network (S-SDNN), Deconvolution Network, Deep Belief Network (DBN), Restructured Boltzmann Machine (RBM), Fully Convolutional Network, Long Short-Term Memory (LSTM) Network, Classification Network, Generative Modeling, eXplainable AI, Continual AI, Representation Learning, AI for Material Design, BERT, SP-BERT, MRC / QA, Text Analysis, Dialog System, GPT-3, GPT-4 for Natural Language Processing, Visual Analytics, Visual Understanding, Video Synthesis for Vision Processing, Anomaly Detection, Prediction, Time-Series Forecasting, Optimization for ResNet Data Intelligence, Various artificial intelligence structures and algorithms, such as recommendation and data creation, may be used, but are not limited thereto. Hereinafter, embodiments of the present disclosure will be described in detail with reference to the attached drawings.

[0039] FIG. 1 is a schematic diagram of a system providing an online trading service platform for raw materials and industrial goods according to an embodiment of the present disclosure.

[0040] FIG. 2 is a drawing illustrating a list of raw materials and industrial materials handled on an online trading service platform for raw materials and industrial materials according to an embodiment of the present disclosure.

[0041] Figure 3 is a diagram illustrating the creation of a chat room for the client's transaction process.

[0042] Referring to FIG. 1, a system (10) providing an online trading service platform for raw materials and industrial materials according to an embodiment of the present disclosure provides B2B-based trading and mediates trading between corporate clients.

[0043] And, as shown in Fig. 2, the server handles various raw materials and industrial materials to satisfy the supply and demand of various corporate clients.

[0044] As shown in FIG. 1, the server communicates with the first terminal (210) of the first client through a network and communicates with the second terminal (310) of the second client through a network.

[0045] Through this, the server provides a B2B-based online trading service platform for raw materials and industrial goods. More specifically, it provides clients with sales management pages and purchase management pages through a single UI, offers automated response and negotiation services using chatbots, and provides various services such as automatically generating contracts.

[0046] As a representative example of this, referring to FIG. 3, when the server receives a request to create a chat room for a transaction of goods sold by the second client from the first terminal (210) of the first client, the server creates a chat room (31) for a transaction negotiation between the first client and the second client.

[0047] At this time, if the second client has the automatic negotiation function using a chatbot activated, the server enables the artificial intelligence model (140) to activate the chatbot function and conduct negotiations for the transaction of goods based on the conversation content in the chat room with the first client (200).

[0048] In an embodiment of the present disclosure, a chat room may be created after the target product that the second client wishes to purchase is selected, or the target product that the second client wishes to purchase may be selected after the chat room is created. For example, an AI-based chatbot (140) may recognize the product that the second client wishes to purchase based on the conversation content of the second client.

[0049] In this embodiment, the artificial intelligence model (140) may present sales conditions for the transaction of goods to the first client, accept the requirements of the second client, or present new sales conditions. Additionally, if the artificial intelligence model (140) determines that a contract has been concluded, it may generate Terms & Conditions, an Invoice, and a Contract.

[0050] Below, the various services provided by the server will be explained in more detail with reference to other drawings.

[0051] FIG. 4 is a block diagram of a server providing an online trading service platform for raw materials and industrial goods according to an embodiment of the present disclosure.

[0052] Referring to FIG. 4, a server providing an online trading service platform for raw materials and industrial materials according to an embodiment of the present disclosure includes a control module, a communication module, and a storage module.

[0053] However, in some embodiments, the server may include fewer or more components than the components shown in FIG. 1.

[0054] The control module may include at least one processor.

[0055] The processor may be implemented as a storage module that stores data regarding an algorithm for controlling the operation of components within the device or a program that reproduces the algorithm, and at least one processor that performs the aforementioned operation using the data stored in the storage module. In this case, the storage module and the processor may each be implemented as separate chips. Alternatively, the storage module and the processor may be implemented as a single chip.

[0056] In addition, the processor may control one or a combination of the components described above in order to implement various embodiments according to the present disclosure described in the drawings below on the device.

[0057] In addition to operations related to the aforementioned application, the processor can generally control the overall operation of the device. The processor can provide or process appropriate information or functions to the user by processing signals, data, information, etc., input or output through the components described above, or by running an application stored in a storage module.

[0058] In addition, the processor may control at least some of the components of the device to run an application stored in a storage module. Furthermore, the processor may combine at least two or more of the components included in the device to operate the application.

[0059] A processor may be implemented in one or more ways. Hereinafter, even if a processor is expressed in the singular, it may be regarded as plural. A processor can control the configurations of a server. A processor may refer to a data processing device embedded in hardware having a physically structured circuit to perform a function expressed by code or instructions included in a program. As such, a processor may encompass processing devices such as a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an application-specific integrated circuit (ASIC), and a field programmable gate array (FPGA) as examples of data processing devices embedded in hardware, but the scope of the present invention is not limited thereto. A processor may separately provide a learning processor for performing artificial intelligence computations, or it may provide a learning processor itself.

[0060] In various embodiments, the processor may include one or more of a Central Processing Unit (CPU), an Application Processor (AP), or a Communication Processor (CP). At least a portion of the processor may be hardware capable of accessing memory and performing functions related to instructions stored in memory.

[0061] The communication module may include one or more modules that connect the server to one or more networks.

[0062] The communication module may include one or more components that enable communication with an external device, and may include, for example, at least one of a broadcast receiving module, a wired communication module, a wireless communication module, a short-range communication module, and a location information module.

[0063] The wired communication module may include various wired communication modules such as a Local Area Network (LAN) module, a Wide Area Network (WAN) module, or a Value Added Network (VAN) module, as well as various cable communication modules such as USB (Universal Serial Bus), HDMI (High Definition Multimedia Interface), DVI (Digital Visual Interface), RS-232 (recommended standard 232), power line communication, or POTS (plain old telephone service).

[0064] In addition to Wi-Fi modules and WiBro (Wireless broadband) modules, the wireless communication module may include wireless communication modules that support various wireless communication methods such as GSM (global System for Mobile Communication), CDMA (Code Division Multiple Access), WCDMA (Wideband Code Division Multiple Access), UMTS (universal mobile telecommunications system), TDMA (Time Division Multiple Access), LTE (Long Term Evolution), 4G, 5G, and 6G.

[0065] The wireless communication module may include a wireless communication interface comprising an antenna and a transmitter that transmit a communication signal. Additionally, the wireless communication module may further include a signal conversion module that modulates a digital control signal output from the processor through the wireless communication interface into an analog wireless signal under the control of the processor.

[0066] A short-range communication module is for short-range communication and can support short-range communication by using at least one of Bluetooth, RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra-Wideband), ZigBee, NFC (Near Field Communication), Wi-Fi (Wireless-Fidelity), Wi-Fi Direct, and Wireless USB (Wireless Universal Serial Bus) technologies.

[0067] The communication module may also use the name of the communication interface.

[0068] A communication interface can establish communication between an electronic device and an external device. For example, the communication interface can communicate with the external device via wireless communication (e.g., Wi-Fi (Wireless Fidelity), Bluetooth, NFC (Near Field Communication), MST (magnetic stripe transmission), etc.) or wired communication.

[0069] In an embodiment of the present disclosure, the storage module may include storage means such as a database, memory, or cloud storage.

[0070] The storage module can store data that supports various functions of the device. The storage module can store a number of application programs (or applications) running on the device, data for the operation of the device, and instructions. At least some of these application programs may exist for the basic functions of the device. Meanwhile, the application programs may be stored in the storage module, installed on the device, and executed by the processor to perform operations (or functions).

[0071] The storage module can store data supporting various functions of the device and programs for the operation of the processor, and can store input / output data (e.g., music files, still images, videos, etc.), and can store multiple application programs (or applications) running on the device, data for the operation of the device, and instructions. At least some of these application programs may be downloaded from an external server via wireless communication.

[0072] Such storage modules may include at least one type of storage medium among flash memory type, hard disk type, SSD type (Solid State Disk type), SSD type (Silicon Disk Drive type), multimedia card micro type, card type memory (e.g., SD or XD storage module, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, and optical disk. Additionally, the storage module may be a database that is separated from the device but connected via wired or wireless connection.

[0073] Memory can be electrically connected to a processor and can store at least one piece of code executed by the processor. Memory can be a general term for various types of storage devices. Memory can store information necessary to perform calculations using artificial intelligence, machine learning, and artificial neural networks.

[0074] Memory can store various learning models. Learning models stored in memory can infer result values ​​for new input data other than the training data, and the inferred values ​​can be used as a basis for making decisions to perform certain actions. Learning can be performed on memory-stored learning models based on label information, and various backpropagation algorithms can be applied to ensure that the loss function obtains a target value in order to increase learning accuracy.

[0075] In addition, the storage module may be equipped with multiple processes for the operation of the server.

[0076] FIGS. 5 to 10 are flowcharts of a method for providing an online trading service platform for raw materials and industrial goods according to an embodiment of the present disclosure.

[0077] FIGS. 11 to 15 are diagrams illustrating how a transaction negotiation is conducted using an artificial intelligence-based chatbot.

[0078] FIG. 16 is a diagram illustrating an example in which an artificial intelligence model generates a purchase contract and a sales contract in accordance with the conclusion of a contract.

[0079] Figure 17 is a diagram illustrating an example of an artificial intelligence model dividing a contract into two contracts, a sales contract and a purchase contract.

[0080] Referring to FIGS. 5 to 17, a server and method for providing an online trading service platform for raw materials and industrial materials according to an embodiment of the present disclosure will be described.

[0081] Referring to FIG. 5, the processes of S51 to S55 will be described.

[0082] The control module provides the sales conditions of the product sold by the first client to the second terminal of the second client. (S51)

[0083] More specifically, the control module controls the communication module to transmit sales conditions, including the country of origin, minimum order quantity, sales price, and lead time of a product being sold by the first client on the service platform, to the second terminal, and the information of the sales conditions is displayed on the screen of the second terminal.

[0084] When a second client connects to the server through the second terminal and selects a specific product, the process of S51 can be executed.

[0085] That is, a step of receiving a signal from the second terminal to inquire about the sales conditions of a specific product prior to S51 may be further included.

[0086] The control module creates a chat room for transaction consultation between the first client and the second client. (S52)

[0087] More specifically, when a chat room requesting the purchase of a specific product is called from the second terminal, the control module creates a chat room for transaction consultation between the first client and the second client.

[0088] In an embodiment of the present disclosure, when a link calling a chat room at a second terminal is executed, the control module can create a chat room and provide a service regardless of the connection means used at the second terminal.

[0089] For example, it means that a chat room is created and a service is provided regardless of the type of web browser or application that executed the link on the second terminal.

[0090] The control module can provide a service that allows the client to use the chat room even when the function to call and enter the chat room is executed after logging in via email or other communication means, rather than the chat room being launched through the server's homepage.

[0091] If the connection means of the second terminal is not a connection through a server, the control module may permit the use of the chat room after the authentication of the second client is completed using a pre-configured authentication method.

[0092] For example, the control module can perform a process of verifying the client's email address.

[0093] In an embodiment of the present disclosure, the chat room may input text, and may upload or download voice data, documents, and images.

[0094] The control module checks whether the second client has enabled the negotiation function using the chatbot. (S53)

[0095] For example, a client using a service provided by a server can choose whether to enable or disable an AI-based chatbot response function for each product being sold or each chat room.

[0096] Referring to FIG. 10, a server according to an embodiment of the present disclosure can execute various functions using an artificial intelligence model, one of which is an embodiment utilizing the artificial intelligence model as a chatbot. A control module can have a pre-trained artificial intelligence model participate in a chat room as a chatbot, input sales conditions and conversation content as input, and obtain an output as a result.

[0097] If the second client has enabled the negotiation function using a chatbot, the control module proceeds with transaction negotiation with the second client using the chatbot. (S54)

[0098] The control module uses a chatbot to recognize the requirements of the second client for each item included in the conversation based on the currently set sales conditions. (S55)

[0099] For example, an AI-based chatbot can determine the requirements of a second client based on the type and item of the product that the second client wants to purchase in the current chat room and the content of the second client's conversation.

[0100] Next, with reference to FIG. 6, the processes of S61 to S63 will be explained.

[0101] The control module determines whether the requirements of the second client recognized through S55 match the product sales conditions of the first client. (S61)

[0102] The sales conditions of the first client may be numerically defined or defined as a numerical range. Additionally, among the sales conditions, there may be negotiable sales conditions and non-negotiable sales conditions.

[0103] For example, sales conditions regarding the minimum selling price can be set based on the purchase quantity of the product, and a threshold for the lead time based on physical limitations may be determined.

[0104] If the requirements recognized in S61 for all items for the product transaction contract meet the sales conditions, the control module generates a transaction condition confirmation form with these as the transaction conditions and provides it to the second terminal. (S62)

[0105] The control module determines that a contract has been concluded when it receives confirmation from the second client regarding the transaction condition confirmation transmitted in S62. (S63)

[0106] Next, the control module generates an invoice and a contract regarding the transaction conditions and provides them to the second terminal.

[0107] Detailed information regarding embodiments related to the contract will be described later.

[0108] In the chat room (110) of Fig. 11, the chatbot (140) provided information about the sales conditions of the product sold by the first client, and the second client recorded a conversation stating that they would enter into a contract under the said sales conditions.

[0109] In this case, the chatbot determines in the process of S61 that the requirements of the second client meet the sales conditions of the first client and proceeds to the next process.

[0110] In the chat room (1200) of Fig. 12, the chatbot (140) provided information on the sales conditions of the product sold by the first client, and the second client provided information on the purchase conditions they wanted.

[0111] And, the chatbot (140) reviews the sales conditions of the first client and determines that it is possible to proceed with the purchase conditions. In this case, the chatbot determines in the process of S61 that the requirements of the second client meet the sales conditions of the first client and proceeds to the next process.

[0112] With reference to FIG. 7, the processes of S71 to S73 will be explained.

[0113] In S61, if the control module determines that the second client's requirements do not meet the sales conditions, it performs the process of S71.

[0114] The control module controls the chatbot to send a message to the chat room indicating that the second client's request cannot be accepted. (S72)

[0115] An embodiment of performing S72 without presenting negotiation conditions regarding the second client's requirements may be performed when the second client's requirements exceed the threshold of the sales conditions or are conditions where negotiation is impossible.

[0116] In S61, if the control module determines that the second client's requirements are within a negotiable range, it derives negotiation conditions based on an artificial intelligence model and proposes negotiation conditions to the second client. (S73)

[0117] If the second client accepts the negotiation conditions proposed in S73, the control module generates a transaction condition confirmation and provides it to the second terminal. (S74)

[0118] The control module proceeds with the conclusion of the contract when it receives confirmation of the transaction conditions from the second terminal. (S75)

[0119] In an embodiment of the present disclosure, an artificial intelligence model can learn the types of products handled by the service platform, the minimum order quantity per product type, the lead time per type, and the sales price based on the order quantity per type. In this case, the training data may be generated based on information provided by the service platform or based on information provided by each client. That is, training data for common use may be applied, or training data optimized for use by each client may be applied.

[0120] In one embodiment, the control module can use an artificial intelligence model to recognize a product that a second client intends to purchase based on the conversation content within a chat room.

[0121] In one embodiment, the AI-based chatbot (140) can determine the negotiation conditions included in the negotiation proposal based on the previous transaction history of the second client, the type of product the second client intends to purchase, and the conversation content within the chat room, as a result of learning. At this time, the chatbot (140) can determine the negotiation conditions by further considering the sales conditions set by the first client.

[0122] S74 and S75 can proceed in the same way as the processes of S62 and S63.

[0123] In the chat room (1300) of Fig. 13, the chatbot (140) provided information on the sales conditions of the product sold by the first client, and the second client provided information on the purchase conditions they wanted.

[0124] And, the chatbot (140) reviewed the sales conditions of the first client and derived new sales conditions for negotiation and proposed them to the chat room. The aforementioned negotiation conditions and the new sales conditions for negotiation described in FIG. 13 have the same meaning.

[0125] Next, if the second client accepts the chatbot's negotiation conditions, the process of S74 is executed, and if it does not accept them and presents new requirements, the previous processes may be executed again.

[0126] An example is shown in which a second client accepts the sales conditions of product A presented by the chatbot (140) in the chat room (1400) of FIG. 14, and the chatbot (140) generates a transaction condition confirmation form as in S62 and provides it to the second terminal, and then the confirmation from the second client is received.

[0127] An example is shown in which a second client presents the purchase conditions (requirements) they want regarding the sales conditions of product A presented by the chatbot (140) in the chat room (1500) of FIG. 15, and the chatbot determines that the conditions are possible. After that, a process is performed in which the chatbot generates a transaction condition confirmation document.

[0128] In one embodiment, the server may provide a function to modify the contract even after the invoice and contract have been transmitted.

[0129] When the control module receives a request for modification regarding at least one item of the contract concluded from the second terminal, it can determine whether the requested modification can be made based on the sales conditions, invoice, and contract.

[0130] Additionally, if the control module determines that modification is possible based on the judgment result, it derives the changes to the transaction conditions resulting from the modification, provides them to the second terminal, and inquires for consent. If the control module receives consent regarding the changes to the transaction conditions from the second terminal, it may regenerate the invoice and contract corresponding to the changes in the transaction conditions and provide them to the second terminal.

[0131] We will describe additional embodiments related to setting sales conditions and negotiation conditions using an artificial intelligence model, which is a control module.

[0132] In one embodiment, the control module can control the communication module to collect news related to the country of origin of products handled on the service platform at preset intervals.

[0133] The control module can identify negative news related to the origin of products handled on the service platform.

[0134] In one embodiment, the control module can extract the aforementioned negative news from news related to disputes, wars, natural disasters, trade regulations, exchange rate fluctuations, logistics system failures, and pandemics concerning the country of origin of the product.

[0135] The control module requests an explainable artificial intelligence model (XAI) to summarize and explain the identified negative news, and inputs the results obtained from the explainable artificial intelligence model into a pre-trained impact calculation model to calculate the market price impact and lead time impact caused by the identified negative news.

[0136] The control module is characterized by training the AI-based chatbot with the calculated market price influence and lead time influence for the product in question, and controlling the AI-based chatbot to set the sales conditions or negotiation conditions.

[0137] For example, if an AI model expects the selling price to rise due to negative news related to the country of origin, it can modify the selling price among the sales conditions.

[0138] For example, if an AI model anticipates that the shipping period will increase due to negative news related to the country of origin, it can modify the lead time in the sales conditions.

[0139] An example related to calculating the impact of market prices using an artificial intelligence model will be described.

[0140] In one embodiment, the control module may extract a first keyword corresponding to content affecting the market price of the product in the negative news using a pre-trained keyword extraction model. The control module may create a first command prompt to request the calculation of the market price impact based on the extracted first keyword.

[0141] Additionally, the control module may request the calculation of the market price influence by inputting the first command prompt into the pre-learned influence calculation model. The control module may calculate the sales price of the sales conditions based on the market price of the product during a recently set period and the market price influence obtained from the influence calculation model.

[0142] An example related to calculating lead time using an artificial intelligence model will be described.

[0143] In one embodiment, the control module can extract a second keyword corresponding to content affecting the lead time of the product in the negative news using a pre-trained keyword extraction model. Then, the control module can create a second command prompt to request the calculation of the lead time impact based on the extracted second keyword.

[0144] The control module inputs the second command prompt into the pre-learned impact calculation model to request the calculation of the lead time impact, and can calculate the lead time of the sales condition based on the lead time trend of the product during a recently set period and the lead time impact obtained from the impact calculation model.

[0145] With reference to Fig. 8, the processes of S81 to S84 will be explained.

[0146] The server provides an online trading service platform for goods including B2B-based raw materials and industrial goods, and can provide at least one of a seller mode and a buyer mode to corporate clients.

[0147] In other words, the client can use this service to sell, buy only, or sell and buy simultaneously.

[0148] The control module provides a UI (User Interface) containing a seller page and a buyer page to the first terminal of the first client. (S81)

[0149] When the control module executes the seller page from the first terminal, it provides a UI for sales management that allows the first client to manage products currently on sale. (S82)

[0150] More specifically, when a seller page is executed / clicked from a first terminal, the control module provides a function that allows the first client to manage at least one of a list of products being sold, a list of chat rooms with customers, a sales term sheet, an invoice, and a contract through a user interface so that the first client can manage products being sold.

[0151] When the control module receives information about a product being sold from the first terminal, it displays sales conditions including at least one of the country of origin, minimum order quantity, sales price, and lead time of the product being sold to the first client.

[0152] When the control module executes the buyer page from the first terminal, it provides a UI for purchase management so that the first client can manage products purchased or products being considered for purchase. (S83)

[0153] More specifically, when a buyer page is executed / clicked from a first terminal, the control module provides a function to manage at least one of a list of products purchased by the first client, a list of chat rooms with customers, a sales term sheet, an invoice, and a contract through a user interface so that the first client can manage products purchased by the first client.

[0154] Additionally, when the buyer page is executed or clicked from the first terminal, the control module may provide various information to enable the first client to check information about the product being considered for purchase. For example, the control module may provide the price trend of the product being considered for purchase. More specifically, the first client may set conditions for deciding to purchase the product of interest, and the control module may provide information related to said conditions to the first terminal. In some embodiments, the control module may automatically proceed with the purchase if the sales conditions match the conditions set by the first client.

[0155] In an embodiment of the present disclosure, the server does not distinguish between corporate clients as buyers or sellers, and can provide a function to manage products sold by corporate clients on a sales page and a function to manage products purchased by corporate clients on a purchase page by logging into the server with a single ID.

[0156] In one embodiment, the control module can be configured to use the chatbot to automatically respond to a chat received from the second terminal in a chat room among the chat room list on the seller page where the automatic response mode is set.

[0157] In addition, if the chatbot is configured to respond to inquiries regarding pre-configured general items, it can automatically respond according to the content received in the chat and provide notifications to the first terminal for other inquiries, and if it is configured to respond to all inquiries, it can automatically respond to the content received in the chat.

[0158] With reference to FIG. 9, the processes S91 to S96 will be explained.

[0159] When the control module calls a chat window requesting the purchase of a product from the second terminal of the second client, it creates a chat room for transaction consultation between the first client and the second client. (S91)

[0160] Since the process of creating a chat room can be performed in the same way as S52, redundant explanations will be omitted.

[0161] The control module controls the transaction negotiation to proceed based on the conversation content within the chat room created in S91 using an AI-based chatbot. (S92)

[0162] The control module determines whether the second client's requirements meet the sales conditions based on the conversation content within the chat room. (S93)

[0163] In one embodiment, the process of S93 can be performed in the same manner as the process of S61, in which the control module determines whether the second client has accepted the sales conditions presented by the chatbot based on the conversation content within the chat room. That is, if the requirements in S93 do not meet the sales conditions, the process after S61 can be performed.

[0164] If the requirement in S93 meets the sales condition, the control module generates a transaction condition confirmation form with this as the transaction condition and provides it to the second terminal. (S94)

[0165] When confirmation from the second client regarding the above transaction conditions is received, it is determined that a contract has been concluded, and based on the above transaction conditions, a sales contract between the server operating the service platform and the first client and a purchase contract between the server and the second client are generated. (S95)

[0166] Provide the sales contract to the first terminal of the first client and provide the purchase contract to the second terminal of the second client. (S96)

[0167] In an embodiment of the present disclosure, the storage module may store a mirror contract drafting model in which a basic contract drafting method, a contract drafting method for a seller, and a contract drafting method for a buyer have been learned.

[0168] In an embodiment of the present disclosure, the server uses at least one artificial intelligence model, which may include an AI-based chatbot, a generative model, an explainable model, a mirror contract drafting model, etc.

[0169] In embodiments of the present disclosure, a mirror contract means that a sales contract and a purchase contract are symmetrical. However, this does not mean that the sales contract and the purchase contract are identical, but are created to be symmetrical while being formed to include the characteristics of each contract.

[0170] Referring to FIG. 16, the control module inputs at least one of the first information of the first client (200), the second information of the second client (300), the information of the server operating the service platform, and the transaction conditions into the artificial intelligence model (140), and requests the creation of a mirror contract in which the first information and the second information regarding the conclusion of the contract are reflected, respectively, and requests the output of a sales contract (1620) and a purchase contract (1610).

[0171] As shown in Fig. 16, the control module proceeds with a purchase contract between the second client (300) and the server through a purchase contract (1610), and proceeds with a purchase contract between the first client (200) and the server through a sales contract (1620).

[0172] A server according to an embodiment of the present disclosure allows a server operating a platform to participate as a party to an intermediary transaction for the transaction safety and reliability of the platform.

[0173] In other words, the conclusion is that there is a contract for the sale of the first client (200) and the purchase of the second client (300), but the server operating the platform service enters into a sales contract with the first client (200) and proceeds with a purchase contract with the second client (300), thereby ensuring that reliability is reliably secured.

[0174] Referring to FIG. 17, the control module can divide the contract concluded using an artificial intelligence model (140) into a first contract (1710) for a sales contract and a second contract (1720) for a purchase contract.

[0175] Specifically, the control module determines that a contract has been concluded when it receives confirmation from the second client regarding the transaction conditions confirmation, and can separate the concluded contract into multiple contracts, such as a first contract with a server operating a service platform for the first client's product sales and a second contract with a server operating a service platform for the second client's product purchases.

[0176] In addition, the control module can generate a sales contract for the first contract and a purchase contract for the second contract.

[0177] Next, the control module can proceed with a sales contract between the first client (200) and the server through the first contract (1710), and a purchase contract between the second client (300) and the server through the second contract (1720).

[0178] In one embodiment, the control module may input at least one of first information of a first client, second information of a second client, information of a server operating a service platform, and transaction conditions into an explainable artificial intelligence model to request the generation of first explanation content explaining a sales contract to the first client and second explanation content explaining a purchase contract to the second client.

[0179] In one embodiment, when a control module receives a first inquiry regarding a sales contract from a first terminal, it may request an explainable artificial intelligence model to output an explanation regarding the received first inquiry. Additionally, when a control module receives a second inquiry regarding a purchase contract from a second terminal, it may request an explainable artificial intelligence model to output an explanation regarding the received second inquiry.

[0180] In one embodiment, the control module inputs first information, second information, transaction conditions, a sales contract, and a purchase contract into a generative model, requests a review of whether the sales contract and the purchase contract are written to have symmetry according to the transaction conditions, and if there are parts in the sales contract and the purchase contract that are judged to be written insufficiently compared to the pre-set symmetry, it may request notification of such parts.

[0181] The method according to one embodiment of the present disclosure described above may be implemented as a program (or application) and stored on a medium to be executed in combination with a server, which is hardware.

[0182] The aforementioned program may include code encoded in a computer language such as C, C++, JAVA, or machine language, which can be read by the computer's processor (CPU) through the computer's device interface, in order for the computer to read the program and execute the methods implemented in the program. Such code may include functional code related to functions that define the necessary functions for executing the methods, and may include control code related to execution procedures necessary for the computer's processor to execute the functions according to a predetermined procedure. Additionally, such code may further include memory reference code regarding where (address) additional information or media necessary for the computer's processor to execute the functions should be referenced in the computer's internal or external memory. In addition, if the processor of the computer needs to communicate with any other computer or server located remotely in order to execute the above functions, the code may further include communication-related code regarding how to communicate with any other computer or server located remotely using the communication module of the computer, and what information or media to transmit or receive during communication.

[0183] The above-mentioned storage medium refers to a medium that stores data semi-permanently and is readable by a device, rather than a medium that stores data for a short period of time, such as a register, cache, or memory. Specifically, examples of the above-mentioned storage medium include, but are not limited to, ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage device. That is, the above-mentioned program may be stored on various recording media on various servers that the computer can access, or on various recording media on the user's computer. Additionally, the above-mentioned medium may be distributed across networked computer systems, and computer-readable code may be stored in a distributed manner.

[0184] The steps of the method or algorithm described in connection with the embodiments of the present disclosure may be implemented directly in hardware, implemented as a software module executed by hardware, or implemented by a combination thereof. The software module may reside in RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), Flash Memory, a hard disk, a removable disk, a CD-ROM, or any form of computer-readable recording medium well known in the art to which the present disclosure belongs.

[0185] Although embodiments of the present disclosure have been described above with reference to the attached drawings, those skilled in the art will understand that the present disclosure may be implemented in other specific forms without altering its technical concept or essential features. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. Explanation of the symbols

[0186] 10: System 100: Server 110: Control Module 120: Communication module 130: Storage Module 140: Artificial Intelligence Model

Claims

Claim 1 A server providing an online trading service platform for goods including raw materials and industrial goods, comprising: a storage module storing an artificial intelligence-based chatbot; and a communication module communicating with a first terminal of a first client and a second terminal of a second client. It includes a control module, wherein the control module collects news related to the country of origin of the product at preset intervals to identify negative news related to at least one of disputes, wars, natural disasters, trade regulations, exchange rate fluctuations, logistics system failures, and pandemics related to the country of origin, requests an explainable artificial intelligence model (XAI) to summarize and explain the identified negative news, inputs the results obtained from the explainable artificial intelligence model into a pre-trained impact calculation model to calculate the market price impact and lead time impact caused by the negative news, and trains the chatbot with the calculated market price impact and lead time impact to control the chatbot to set sales conditions or negotiation conditions, provides sales conditions including the country of origin, minimum order quantity, sales price, and lead time of the product sold by the first client on the service platform to the second client's second terminal, and when a chat window requesting the purchase of the product is called from the second client terminal, creates a chat room for transaction negotiation between the first client and the second client, and uses the chatbot to control the conversation within the created chat room. Control the transaction negotiation to proceed based on the content, and recognize the requirements of the second client for each item included in the conversation content based on the currently set sales conditions, determine whether the recognized requirements meet the sales conditions, and if the recognized requirements meet the sales conditions for all items for the contract, generate a transaction condition confirmation form with these as transaction conditions and provide it to the second terminal, and if the second client's confirmation of the transaction condition confirmation form is received, determine that the contract has been concluded.A server providing an online trading service platform for raw materials and industrial goods, which separates the above-mentioned contract into multiple contracts: a first contract with a server operating the service platform regarding the sale of goods by the first client and a second contract with a server operating the service platform regarding the purchase of goods by the second client; generates a sales contract for the first contract and a purchase contract for the second contract; inputs the first information of the first client, the second information of the second client, the transaction conditions, the sales contract, and the purchase contract into a generative model to request a review of whether the sales contract and the purchase contract are written to have a pre-set symmetry according to the transaction conditions; controls the system to notify if there are parts in the sales contract and the purchase contract that are judged to be insufficient compared to the symmetry; provides the sales contract to the first terminal and the purchase contract to the second terminal; and stores the conversation content, the transaction condition confirmation, the invoice, and the contract in the storage module. Claim 2 A server providing an online trading service platform for raw materials and industrial goods, wherein, in claim 1, the control module creates the chat room and provides the service regardless of the connection means used by the second terminal when a link calling the chat room is executed on the second terminal, and permits the use of the chat room after the second client authentication is completed using a pre-configured authentication method when the connection means is not a connection through the server. Claim 3 A server providing an online trading service platform for raw materials and industrial goods, wherein, in claim 1, the AI-based chatbot learns the types of products handled by the service platform, the minimum order quantity for each type, the lead time for each type, and the sales price based on the order quantity for each type; recognizes the product that the second client intends to purchase based on the conversation content within the chat room; if the recognized requirements do not meet the sales conditions, determines whether the recognized requirements fall within a negotiable range based on the learned results; if the determination result is not within a negotiable range, sends a message indicating that the transaction cannot proceed through the chat room; and if the determination result is determined to be within a negotiable range, outputs a negotiation proposal based on the learned results, and determines the negotiation conditions included in the negotiation proposal based on the learned results, the second client's previous transaction history, the type of product that the second client intends to purchase, and the conversation content within the chat room. Claim 4 A server providing an online trading service platform for raw materials and industrial goods, wherein, in the first paragraph, the control module determines whether the requested modification is possible based on the sales conditions, the invoice, and the contract when a modification request is received from the second terminal for at least one item of the contract concluded, and if it is determined that modification is possible, derives changes to the transaction conditions resulting from the modification and provides them to the second terminal to inquire about consent, and if consent to the changes to the transaction conditions is received from the second terminal, regenerates the invoice and the contract according to the changes to the transaction conditions and provides them to the second terminal. Claim 5 delete Claim 6 A server providing an online trading service platform for raw materials and industrial goods, wherein, in claim 1, the control module extracts a first keyword corresponding to content affecting the market price of the product in the negative news using a pre-trained keyword extraction model, creates a first command prompt to request the calculation of the market price influence based on the extracted first keyword, inputs the first command prompt into the pre-trained influence calculation model to request the calculation of the market price influence, and calculates the sales price of the sales conditions based on the market price of the product during a recently pre-set period and the market price influence obtained from the influence calculation model. Claim 7 A server providing an online trading service platform for raw materials and industrial goods, wherein, in claim 1, the control module extracts a second keyword corresponding to content affecting the lead time of the product in the negative news using a pre-trained keyword extraction model, creates a second command prompt to request the calculation of the lead time impact based on the extracted second keyword, inputs the second command prompt into the pre-trained impact calculation model to request the calculation of the lead time impact, and calculates the lead time of the sales conditions based on the lead time trend of the product during a recently pre-set period and the lead time impact obtained from the impact calculation model. Claim 8 delete Claim 9 A method for providing a service platform for online trading of goods including raw materials and industrial goods performed by a server, comprising the steps of: collecting news related to the country of origin of said goods at preset intervals to identify negative news related to at least one of disputes, wars, natural disasters, trade regulations, exchange rate fluctuations, logistics system failures, and pandemics related to said country of origin; requesting an explainable artificial intelligence model (XAI) to summarize and explain said negative news; inputting the results obtained from said explainable artificial intelligence model into a pre-trained impact calculation model to calculate the market price impact and lead time impact caused by said negative news; and training an AI-based chatbot with said calculated market price impact and lead time impact to control said chatbot to set sales conditions or negotiation conditions; providing sales conditions including the country of origin, minimum order quantity, sales price, and lead time of a product sold by a first client on said service platform to a second terminal of a second client; and when a chat window requesting the purchase of said product is called from said second terminal, creating a chat room for transaction negotiation between said first client and said second client, and said A step of controlling the transaction negotiation to proceed based on the conversation content within the chat room created above using a chatbot; a step of recognizing the requirements of the second client for each item included in the conversation content based on the currently set sales conditions; a step of determining whether the recognized requirements meet the sales conditions; and a step of generating a transaction condition confirmation document with these as transaction conditions and providing it to the second terminal if, for all items for the contract, the recognized requirements meet the sales conditions.When confirmation from the client regarding the above transaction condition confirmation is received, the method determines that a contract has been concluded, separates the concluded contract into multiple contracts, namely a first contract with the server operating the service platform regarding the sale of goods by the first client and a second contract with the server operating the service platform regarding the purchase of goods by the second client, and generates a sales contract for the first contract and a purchase contract for the second contract; inputs the first information of the first client, the second information of the second client, the transaction conditions, the sales contract, and the purchase contract into a generative model to request a review of whether the sales contract and the purchase contract have been written to have a pre-set symmetry according to the transaction conditions, controls the method to notify the relevant parts if there are parts in the sales contract and the purchase contract that are judged to be insufficient compared to the symmetry, and provides the sales contract to the first terminal and provides the purchase contract to the second terminal. A method for providing an online trading service platform for raw materials and industrial goods, comprising the step of storing the above conversation content, the above transaction condition confirmation, the invoice, and the contract. Claim 10 A computer-readable recording medium on which a computer program for performing the method of paragraph 9 is recorded.

Citation Information

Patent Citations

  • System and method for cyber-contacting over network

    KR1020020023104A

  • Method for processing request of user by using chatbot

    KR102017541B1

  • Apparatus for predicting stock price of company by analyzing news and operating method thereof

    KR1020190116590A

  • Automatic second-hand sales service providing system using chatbot

    KR1020230026706A

  • System and Method for Providing Electronic Contract Service Mediation based on AI

    KR1020230056420A