Information-symmetric ordering platform for steel products and its operation method

Abstract

A method of operation of an electronic device constituting an order platform for steel products according to one embodiment may include: receiving quotation request data for at least one steel product; extracting detailed specifications for each of the at least one steel product from the quotation request data; classifying an order type for each of the at least one steel product based on the detailed specifications for the quotation request—the order type includes a Standard Order and a Custom Order—; and generating a quotation for the at least one steel product based on the order type and the detailed specifications for the quotation request.

Description

Technology Field

[0001] The following disclosure relates to an ordering platform for steel products, and more specifically, to an information-symmetric ordering platform for steel products and a method of operation thereof. Background Technology

[0002] The steel industry has traditionally been structured around suppliers, such as large steel mills and distributors. In this structure, a small number of suppliers tend to hold market dominance and lead pricing and transaction conditions. Consequently, buyers rely on the unilateral terms of suppliers without substantial bargaining power, and small and medium-sized manufacturers as well as secondary and tertiary processors find it difficult to secure stable supply sources and are exposed to high price volatility.

[0003] Furthermore, the supplier-centric structure acts as a major factor exacerbating price asymmetry and transaction opacity in the steel distribution process. During distribution, steel product prices are determined differentially based on the size or bargaining power of the buyers; consequently, prices for the same product often vary depending on the supplier. Moreover, because steel transaction information is shared informally within limited networks, overall market transparency is undermined, making it difficult for new entrants or small and medium-sized buyers to obtain fair trading opportunities.

[0004] This structure ultimately has a negative impact on the stability of steel supply. Steel supply and demand at any given time can fluctuate rapidly depending on suppliers' production schedules, logistics conditions, and internal circumstances, making it difficult for consumers to predict or respond to these changes in advance. This instability becomes particularly pronounced during global supply chain issues or surges in raw material prices, negatively affecting production planning and cost structures across the manufacturing sector. Prior art literature

[0005] Korean Registration No. 10-2780900 (March 10, 2025) Korean Publication No. 10-2022-0041806 (April 1, 2022) The problem to be solved

[0006] It is necessary to resolve issues such as price asymmetry, transaction opacity, and supply instability arising from the supplier-centric structure of the steel industry. To this end, an environment must be created where demanders can accurately grasp market information and make rational decisions by transparently providing key transaction data—such as real-time steel product prices, delivery schedules, and supply availability—on a platform. Furthermore, it is necessary to enhance transaction reliability and quality assurance levels, and prevent the distribution of counterfeit or defective products, by digitally integrating and managing historical information such as production certificates, quality reports, and distribution histories.

[0007] However, these tasks are exemplary and do not limit the scope of the present disclosure. means of solving the problem

[0008] A method of operation of an electronic device constituting an order platform for steel products according to one embodiment may include: receiving quotation request data for at least one steel product; extracting detailed specifications for each of the at least one steel product from the quotation request data; classifying an order type for each of the at least one steel product based on the detailed specifications for the quotation request—the order type includes a Standard Order and a Custom Order—; and generating a quotation for the at least one steel product based on the order type and the detailed specifications for the quotation request.

[0009] According to one embodiment, the detailed specifications of the quotation request include information regarding the material, specifications, quantity, country of origin, alternative specifications, and allowable specifications in case of error of at least one steel product, and the step of extracting the detailed specifications of the quotation request may be characterized by selectively performing at least one of OCR (Optical Character Recognition), STT (Speech-To-Text), and Text Parsing in response to receiving a quotation request email, quotation request image, quotation request document, or quotation request call as the quotation request data.

[0010] According to one embodiment, the step of extracting the detailed specifications of the quotation request is performed by an artificial intelligence model, wherein the artificial intelligence model may include: a preprocessing layer that converts the quotation request data into a standardized form; a data classification module that receives the preprocessed quotation request data and classifies the data type; a data type-specific data extraction module that performs data extraction on the original quotation request data based on the data type to extract specification data in the form of parsed Key-Value pairs; and a specification data integration extraction module that integrates the specification data extracted by data type to extract the detailed specifications of the quotation request.

[0011] According to one embodiment, the step of generating the quotation may include: deriving a base price for each of the at least one steel product based on the detailed specifications of the quotation request and real-time external variables by utilizing an internal price database; evaluating the difficulty of the work of the steel product based on the order type and the detailed specifications of the quotation request; and deriving production availability parameters based on the order type and factory schedule data.

[0012] According to one embodiment, the base price can be derived by considering real-time external variables including steel raw material prices, logistics costs, tax rates, exchange rates, and oil prices, based on the internal price database including the shipment price of a steel manufacturer, the price of an intermediate processor, and the market offer price of an imported product.

[0013] According to one embodiment, the step of generating the quotation may further include: a step of deriving a final quotation amount for each of the at least one steel product by reflecting the production availability parameter and a surcharge according to the work difficulty to the base price; and a step of generating the quotation including the final quotation amount, wherein the production availability parameter may be derived by evaluating the production availability time and the expected waiting time of the steel product based on the production line operating status, production schedule data, and raw material inventory data.

[0014] According to one embodiment, the difficulty of the work may be quantified by evaluating whether there is a requirement for a change in physical properties, whether there are non-standard specifications, and whether there is a special use for the custom order.

[0015] According to one embodiment, the method of operation further comprises the steps of: performing grouping for the order of at least one steel product; setting a Quality Assurance (QA) policy (e.g., range, standard) for the grouped at least one steel product; and providing a quality control guide according to the Quality Assurance policy, wherein the QA policy may further include an additional QC policy for the custom order. Effects of the invention

[0016] The present invention creates an environment where demanders can accurately grasp market information and make rational decisions by transparently providing key transaction data, such as real-time prices, delivery information, and supply availability ranges of steel products, on a platform. In addition, by digitally integrating and managing historical information such as product manufacturing certificates, quality reports, and distribution history, it improves the reliability of transactions and the level of quality assurance, and prevents the distribution of counterfeit or defective products.

[0017] Furthermore, the present invention utilizes AI and machine learning technologies to collect and analyze external variables, such as market trends, raw material prices, transportation costs, and exchange rates, in real time, and provides a function to automatically calculate optimal prices and supply conditions tailored to the needs of consumers based on this analysis. This prediction and optimization function offers higher accuracy and speed compared to traditional human-based intuition-dependent trading methods, and contributes to preventing price irrationality or supply inefficiency in advance.

[0018] Furthermore, this invention provides a foundation for small and medium-sized manufacturers to compete on equal terms with large corporations through supply chain management functions that consider integration with ERP and SCM systems. Throughout the transaction process, automated procedures and the collaboration of professional personnel are harmoniously combined to minimize the possibility of human error and fraudulent intervention, while maintaining standardized transaction quality. This enables the resolution of structural problems in the steel industry and the realization of a fair and sustainable digital steel distribution ecosystem. Brief explanation of the drawing

[0019] FIG. 1 is a block diagram of a system according to an exemplary embodiment of the present disclosure. FIG. 2 is a block diagram of an electronic device according to an exemplary embodiment of the present disclosure. FIG. 3 is a drawing for explaining the function of a steel platform management module according to an exemplary embodiment of the present disclosure. FIG. 4 is a flowchart illustrating the operation of a steel platform management module according to an exemplary embodiment of the present disclosure. FIGS. 5 to 7 are quotation request data according to exemplary embodiments of the present disclosure. FIG. 8 is a drawing for explaining the operation of generating an estimate according to an exemplary embodiment of the present disclosure. FIG. 9 is a flowchart illustrating additional operations of a steel platform management module according to an exemplary embodiment of the present disclosure. FIG. 10 is a drawing for explaining the operation of providing a quality control guide according to an exemplary embodiment of the present disclosure. Specific details for implementing the invention

[0020] Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only and may be modified and implemented in various forms. Accordingly, actual implementations are not limited to the specific embodiments disclosed, and the scope of this specification includes modifications, equivalents, or substitutions included in the technical concept described by the embodiments.

[0021] Terms such as "first" or "second" may be used to describe various components, but these terms should be interpreted solely for the purpose of distinguishing one component from another. For example, the first component may be named the second component, and similarly, the second component may be named the first component.

[0022] When it is stated that a component is "connected" to another component, it should be understood that it may be directly connected to or coupled with that other component, or that there may be other components in between.

[0023] Singular expressions include plural expressions unless the context clearly indicates otherwise. In this document, phrases such as “A or B,” “at least one of A and B,” “at least one of A or B,” “A, B or C,” “at least one of A, B and C,” and “at least one of A, B, or C” may each include any one of the items listed together with the corresponding phrase, or all possible combinations thereof. In this specification, terms such as “comprising” or “having” are intended to designate the existence of the described feature, number, step, action, component, part, or combination thereof, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0024] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this specification.

[0025] As used herein, the term "module" may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be a component formed integrally, or a minimum unit of said component or a part thereof that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0026] As used in this document, the term "part" refers to a software or hardware component, such as an FPGA or ASIC, that performs certain roles. However, "part" is not limited to software or hardware. "Part" may be configured to reside in an addressable storage medium or configured to operate one or more processors. For example, "part" may include components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and "parts" may be combined into a smaller number of components and "parts" or further separated into additional components and "parts." Furthermore, components and "parts" may be implemented to operate one or more CPUs within a device or secure multimedia card. Additionally, '~part' may include one or more processors.

[0027] Hereinafter, embodiments will be described in detail with reference to the attached drawings. In the description with reference to the attached drawings, identical components are given the same reference numeral regardless of the drawing number, and redundant descriptions thereof will be omitted.

[0028] FIG. 1 is a block diagram of a system according to an exemplary embodiment of the present disclosure.

[0029] Referring to FIG. 1, the system (100) may include an electronic device (100), a plurality of user terminals (201, ..., 20N), a steel database (300), and a network (11). The components (or elements) shown in FIG. 1 are exemplary, and additional components may exist or some of the components shown in FIG. 1 may be omitted. The plurality of user terminals (201, ..., 20N) and the electronic device (100) of the present disclosure may transmit and receive data for the system according to embodiments of the present disclosure through the network (11).

[0030] Multiple user terminals (201, ..., 20N) can transmit various data to the electronic device (100). Multiple user terminals (201, ..., 20N) may refer to any form of entity(s) in a system having a mechanism for communication with the electronic device (100). Multiple user terminals (201, ..., 20N) are wireless communication devices that ensure portability and mobility, and may include all types of handheld-based wireless communication devices such as the aforementioned PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), smartphones, etc., as well as wearable devices such as watches, rings, etc. The number of multiple user terminals (201, ..., 20N) may be one or more. At this time, each of the different users can perform communication with the electronic device (100) using their respective multiple user terminals (201, ..., 20N). For example, a general user using an application program provided by an electronic device (100) may use a plurality of user terminals (201, ..., 20N) to use the services provided by the application program. Additionally, the plurality of user terminals (201, ..., 20N) may include any server implemented by at least one of an agent, an API (Application Programming Interface), and a plug-in. Additionally, the plurality of user terminals (201, ..., 20N) and the administrator terminal (11) may include an application source and / or a client application. The application program may be referred to as an application platform.

[0031] The network (11) can use various wired communication systems such as a Public Switched Telephone Network (PSTN), xDSL (x Digital Subscriber Line), RADSL (Rate Adaptive DSL), MDSL (Multi Rate DSL), VDSL (Very High Speed ​​DSL), UADSL (Universal Asymmetric DSL), HDSL (High Bit Rate DSL), and a Local Area Network (LAN). The network (11) can use various wireless communication systems such as CDMA (Code Division Multi Access), TDMA (Time Division Multi Access), FDMA (Frequency Division Multi Access), OFDMA (Orthogonal Frequency Division Multi Access), SCFDMA (Single Carrier-FDMA), and other systems. The network (11) can be configured regardless of the mode of communication, such as wired or wireless, and can be configured as various communication networks such as a Personal Area Network (PAN) and a Wide Area Network (WAN). In addition, the above network may be the known World Wide Web (WWW) and may also utilize wireless transmission technologies used for short-range communication, such as Infrared Data Association (IrDA) or Bluetooth.

[0032] The steel database (300) can store various data related to steel products. Steel products refer to metal materials manufactured by adding various components with iron (Fe) as the main component, and may refer to products such as plates, bars, structural steel, and steel pipes used as structural materials or component materials in various industrial fields such as construction, machinery, automobiles, shipbuilding, and plants. There may be one or more steel databases (300). For example, the steel database (300) may include a customer database and a processing database. However, the present disclosure is not limited to the examples described above.

[0033] The electronic device (100) can communicate with a plurality of user terminals (201, ..., 20N) and can execute a program of program data. In this specification, the term "device according to the present disclosure" includes all various devices capable of performing computational processing and providing results to a user. For example, the device according to the present disclosure may be a computing device and may include all of a computer, a server device, and a portable terminal, or may be in the form of any one of them. Here, the computer may include, for example, a notebook, desktop, laptop, tablet PC, slate PC, etc. equipped with a web browser. The 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.The above portable terminal may include, for example, all types of handheld-based wireless communication devices such as PCS (Personal Communication System), GSM (Global System for Mobile communications), PDC (Personal Digital Cellular), PHS (Personal Handy-phone 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).

[0034] The electronic device (100) may include a communication interface (110), a network interface (120), a processor (130), a memory (140), and a database (150). The communication interface (110) may interface with input data and / or output data. The network interface (120) may interface with the network (11). The processor (130) may control various operations of the electronic device (100) overall. The processor (130) may include a steel platform management module (131). The database (150) may store various data.

[0035] The memory (140) can store data for an algorithm or a program that reproduces the algorithm for controlling the operation of components within the device, and can be implemented as at least one processor (130) that performs the aforementioned operation using the data stored in the memory (140). Here, the memory (140) and the processor (130) can each be implemented as separate chips. Additionally, the memory (140) and the processor (130) can be implemented as a single chip.

[0036] The memory (140) can store data supporting various functions of the device and programs for the operation of the processor (130), and can store input / output data, and can store a number of application programs (or applications) running on the device, data for the operation of the device, instructions, and one or more instructions. At least some of these application programs may be downloaded from an external server via wireless communication.

[0037] Such memory (140) 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 memory, etc.), RAM (random access memory; RAM), SRAM (static random access memory), ROM (read-only memory; ROM), EEPROM (electrically erasable programmable read-only memory), PROM (programmable read-only memory), magnetic memory, magnetic disk, and optical disk. Additionally, the memory (140) may be a database that is separated from the device but connected via wired or wireless connection.

[0038] The memory (140) can temporarily store data and can provide the stored data to the processor (130) under the control of the processor (130). The database (150) can store various data sets.

[0039] FIG. 2 is a block diagram of an electronic device according to an exemplary embodiment of the present disclosure.

[0040] Referring to FIG. 2, the electronic device (100) may be an electronic device such as a mobile phone, a smartphone, a laptop computer, a digital broadcasting terminal, a PDA (personal digital assistants), a PMP (portable multimedia player), a navigation device, a slate PC, a tablet PC, an ultrabook, a wearable device (e.g., a smartwatch, a smart glass, a head-mounted display (HMD)), a workstation, a server, a cloud server, etc., but is not limited thereto, and is a general term for an electronic processing device or a combination of electronic processing devices that provides computing functions for processing data.

[0041] The communication interface (110) may be configured to receive requests from the outside. The communication interface (110) may communicate with an external device. Accordingly, the electronic device (100) may transmit and receive information with an external device through the communication interface (110). The communication interface (110) may include at least one of a WiFi chip, a Bluetooth chip, a wireless communication chip, a Near Field Communication (NFC) chip, and a Radio Frequency Identification (RFID) chip. Descriptions that overlap with FIG. 1 will be omitted.

[0042] The network interface (120) may include an API (Application Programming Interface) interface (121) and a web interface (122). The API interface (121) may provide a programming interface. Through the API interface (121), web clients and mobile clients within the platform environment can be run as applications. An API refers to a language format used for communication between an operating system and an application. An API is implemented by having a program module or routine and calling a function that provides a connection to a specific subroutine for execution within the program.

[0043] The web interface (122) provides an interface with the web. Using the web interface (122), the web crawling module (143) can access the World Wide Web.

[0044] The API interface (121) and the Web interface (122) are connected to one or more application servers, and as an exemplary embodiment, the processor (130) can function as an application server.

[0045] The processor (130) is configured to control the overall organic operation of various functional units, such as processing one or more commands required for the control of the electronic device (100), performing calculations according to the commands, and making judgments according to program logic. The processor (130) can provide or process appropriate information or functions to the user by processing signals, data, information, etc. input or output through the communication interface (110) or by running an application program stored in the memory (140). The processed data may be stored in the memory (140), used to build a database (150), or transmitted externally through the communication interface (110). Such a processor (130) may be implemented as a general-purpose processor, a dedicated processor, or an application processor. In an exemplary embodiment, the processor (130) may be implemented as a computational processor (e.g., CPU (Central Processing Unit), GPU (Graphic Processing Unit), AP (Application Processor), etc.) including a dedicated logic circuit (e.g., FPGA (Field Programmable Gate Array), ASICs (Application Specific Integrated Circuits), etc.), but is not limited thereto. In an exemplary embodiment, the processor (130) is not excluded from being implemented as a DSP (Digital Signal Processor), MCU (Micro Controller Unit), or NPU (Neural Processing Unit), which is specialized for processing artificial neural networks, capable of converting analog signals into digital signals for high-speed processing.

[0046] If the processor (130) functions as an application server, it can host an artificial neural network processing module (145). The processor (130) can, in turn, be coupled to one or more databases (150) that enable access to one or more information storage stores or databases (150).

[0047] In addition to operations related to applications executed by the electronic device (100), the processor (130) can perform learning for building an artificial intelligence learning model, repetitive arithmetic operations necessary for learning, and inference on learning data using artificial intelligence with the built learning model applied, and control various modules for artificial intelligence processing.

[0048] In addition to operations related to applications executed by the electronic device (100), the processor (130) can execute learning for building an artificial intelligence learning model, repetitive arithmetic operations necessary for learning, and inference on learning data using artificial intelligence applied to the built learning model, and control various modules for artificial intelligence processing. In this case, in addition to the artificial intelligence operating inside the processor (130), an artificial neural network processing module (145), which is a processing device specialized for artificial intelligence learning and computation, may be provided in the electronic device (100). This refers to an artificial intelligence-dedicated processor implemented physically separately from the processor (130), or a processing module of a logical concept executed inside the processor (130). The artificial neural network processing module (145) may refer to a logical functional part implemented by the processor (130), or a physical implementation part based on an ASIC or FPGA provided separately for artificial intelligence learning, and there are no restrictions on the form of implementation.

[0049] The memory (140) may be a local storage medium that supports various functions of the processor (130). The memory (140) may store applications that can be run on the processor (130), data for the operation of the processor (130), and instructions. At least some of these applications may be downloaded from an external source via wireless communication. The applications may be stored and installed in the memory (140) and run to perform operations (or functions) by the processor (130).

[0050] The memory (140) may be a volatile memory including dynamic random access memory (DRAM), such as DDR SDRAM (Double Data Rate Synchronous Dynamic Random Access Memory), LPDDR (Low Power Double Data Rate) SDRAM, GDDR (Graphics Double Data Rate) SDRAM, RDRAM (Rambus Dynamic Random Access Memory), DDR2 SDRAM, DDR3 SDRAM, DDR4 SDRAM, etc.

[0051] However, the embodiments of the present disclosure are not limited thereto. In an exemplary embodiment, the memory (140) may be provided as a writable non-volatile memory so that data remains even when the power supplied to the processor (130) is cut off and changes can be reflected. However, the memory (140) may be a flash memory or EPROM or EEPROM, resistive memory cells such as ReRAM (resistive RAM), PRAM (phase change RAM), MRAM (magnetic RAM), MRAM (Spin-Transfer Torque MRAM), Conductive Bridging RAM (CBRAM), FeRAM (Ferroelectric RAM), and various other types of memory. Alternatively, the memory (140) may be implemented as various types of devices such as an embedded multimedia card (eMMC), universal flash storage (UFS), or CF (Compact Flash), SD (Secure Digital), Micro-SD (Micro Secure Digital), Mini-SD (Mini Secure Digital), xD (Extreme Digital), or Memory Stick. For convenience of explanation in this disclosure, it is described that all instruction information is stored in a single memory (140), but this is not limited thereto, and the memory (140) may be equipped with multiple memories.

[0052] According to an exemplary embodiment of the present disclosure, the memory (140) may include a steel data management module (141), a web crawling module (143), and an artificial neural network processing module (145). In the present disclosure, the steel data management module (141), the web crawling module (143), and the artificial neural network processing module (145) provided in the memory (140) may be fetched by a processor (130).

[0053] The steel data management module (141) can collect, store, and manage major transaction-related data such as the price, inventory, delivery date, quality certificate, production history, and distribution channel of steel products, thereby supporting the securing of reliability, transparency, and efficiency of transactions.

[0054] The web crawling module (143) can mechanically collect and index information related to steel products through the world wide web.

[0055] According to an exemplary embodiment of the present disclosure, the artificial neural network processing module (145) can implement artificial intelligence. Artificial intelligence refers to a machine learning method based on an artificial neural network that mimics human biological neurons to enable a machine to learn. The methodology 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 answer (output data) to the problem (input data) is determined; unsupervised learning, where only input data is provided without output data and the answer (output data) to the problem (input data) is not determined; and reinforcement learning, where a reward is given from an external environment whenever an action is taken in the current state, and learning proceeds in a direction that maximizes such reward. In addition, artificial intelligence methodologies can 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 (CNN), Recurrent Neural Networks (RNN), Transformers, and Generative Adversarial Networks (GAN).

[0056] The artificial neural network processing module (145) can generate a neural network, train (or learn) a neural network, perform operations based on received input data, generate an information signal based on the results of the operation, or retrain the neural network. The neural network models may include, but are not limited to, various types of models such as CNN (Convolutional Neural Network), R-CNN (Region with Convolutional Neural Network), RPN (Region Proposal Network), RNN (Recurrent Neural Network), S-DNN (Stacking-based Deep Neural Network), S-SDNN (State-Space Dynamic Neural Network), Deconvolution Network, DBN (Deep Belief Network), RBM (Restructured Boltzmann Machine), Fully Convolutional Network, LSTM (Long Short-Term Memory) Network, Classification Network, Transformer, BERT, GPT-3, GPT-4, etc. The artificial neural network processing module (145) may include one or more processors for performing operations according to the models of the neural network.

[0057] A database (150) refers to a collection of data that is integrated and managed for the purpose of being shared and used by storing various information. The database (150) can store data temporarily or semi-permanently. For example, the database (150) may store an operating system (OS) for operating at least one device, data for hosting a website, or data regarding an application (e.g., a web application). Additionally, the database may store modules in the form of computer code as described above. The database (150) is managed through middleware that is separate from the application.

[0058] Examples of databases (150) may include a hard disk drive (HDD), a solid state drive (SSD), flash memory, ROM (Read-Only Memory), and RAM (Random Access Memory). These databases may be provided as built-in or detachable types.

[0059] The database (150) includes a relational database (RDB; relational database), a key-value database, an object database, a document database, a memory database, etc.

[0060] FIG. 3 is a drawing for explaining the function of a steel platform management module according to an exemplary embodiment of the present disclosure.

[0061] The steel platform management module (131) is a system that systematically manages the entire process from receiving orders for steel products to delivering them, and integrates product-related data digitally to increase the transparency and reliability of transactions.

[0062] First, the order interface (I / F) can provide an environment where administrators can easily manage order sequences (e.g., general orders and custom orders). The order processing unit can distinguish whether an order is a general order or a custom order based on received order data, perform appropriate processing procedures, and transparently manage the progress status of the order.

[0063] The Product Management Department maintains detailed specifications, standard information, and real-time inventory status of steel products to immediately determine supply availability and promptly deliver it to the orderer. As mentioned above, steel products refer to metallic materials manufactured with iron (Fe) as the main component and various added components, and may refer to products such as plates, bars, structural steel, and steel pipes used as structural or component materials in various industrial fields such as construction, machinery, automobiles, shipbuilding, and plants.

[0064] The delivery interface (I / F) shares logistics information, such as the dispatch schedule and delivery progress of ordered products, in real time to enhance predictability for the customer and support smooth product receipt.

[0065] The Quality Assurance department may be intended to establish quality standards and assurance procedures from the pre-production stage to continuously manage whether quality standards are met during the manufacturing process and to ensure product quality reliability.

[0066] The Quality Control department can strictly guarantee the quality of products ultimately delivered to customers by conducting thorough quality verification and standard compliance inspections on finished products.

[0067] In the delivery sequence, even after the product is delivered to the customer, it supports customer trust by digitally providing quality assurance documentation (medium quality assurance, high quality assurance), product specification verification results, certificates of distribution history, and consumer evaluation information. Furthermore, it transparently manages and shares distribution costs and tax information incurred during the delivery process, helping customers receive products in a reasonable and efficient transaction environment.

[0068] Through this process, the steel platform management module (131) transparently provides key transaction data, such as real-time prices, delivery information, and supply availability of steel products, thereby creating an environment where users can accurately grasp market information and make rational decisions. At the same time, detailed history information, such as production certificates, quality certificates, and distribution history, is digitally integrated and managed to improve the reliability of transactions and prevent the distribution of counterfeit or defective products. Below, the operation of generating an estimate during the operation of the steel platform management module will be explained in detail through FIG. 4.

[0069] FIG. 4 is a flowchart illustrating the operation of a steel platform management module according to an exemplary embodiment of the present disclosure. FIGS. 5 to 7 are quotation request data according to an exemplary embodiment of the present disclosure.

[0070] In FIG. 4, steps S410 through S440 can be understood as being performed by a processor (130) of the electronic device (100) (e.g., a steel platform management module (131)). Steps S410 through S440 may be performed sequentially or in parallel.

[0071] In step S410, the steel platform management module (131) may receive quotation request materials for at least one steel product. The quotation request materials may include a quotation request email (e.g., FIG. 5), a quotation request document (e.g., FIG. 6), a quotation request image (e.g., FIG. 7), and / or a quotation request call.

[0072] Various forms of quotation requests (e.g., quotation request email (Fig. 5), document (Fig. 6), image (Fig. 7), and / or call, etc.) are mixed together, so it takes time to identify and respond to each request, and there is a possibility of omission. Therefore, the steel platform management module (131) can function as an integrated quotation management system that can immediately collect all quotation requests regardless of the request channel and manage them consistently.

[0073] In step S420, the steel platform management module (131) can extract detailed specifications for each of at least one steel product from the quotation request data. The detailed specifications for the quotation request may include the material of the steel product (e.g., 304, 316L, etc.), specifications (e.g., thickness, width, length), quantity (e.g., number of sheets), country of origin (e.g., whether domestic or imported), information regarding alternative specifications, and information regarding allowable specifications in case of error.

[0074] Since various types of quotation requests are mixed, the steel platform management module (131) can selectively perform at least one of OCR (Optical Character Recognition), STT (Speech-To-Text), and Text Parsing. At this time, the steel platform management module (131) can utilize an artificial intelligence model.

[0075] The artificial intelligence model may include a preprocessing layer, a data classification module, a data extraction module by data type, and a specification data integration extraction module.

[0076] The preprocessing layer can convert quotation request data (e.g., FIGS. 5 to 7) into a standardized form. The output of the preprocessing layer may include preprocessed quotation request data (e.g., text data, image data, and / or voice data).

[0077] The data classification module can receive preprocessed quotation request data and classify data types. The data classification module may be a multi-modal classifier. The output of the data classification module may be a data type class (e.g., text, image, speech). The data classification module may include a CNN such as Transformer, ResNet, or EfficientNet fine-tuned based on BERT, and / or a spectrogram-based CNN.

[0078] The data extraction module by data type can perform data extraction on the source of the quotation request data based on the data type (e.g., data type class). The output of the data extraction module by data type may be specification data in the form of parsed Key-Value pairs. The specification data in the form of Key-Value pairs may be structured in the format shown in Table 1.

[0080] texture 304 thickness 2mm width 1219mm length 2438mm quantity 50 pages origin domestic Alternative standards impossibility tolerance ±0.5mm

[0082] The data extraction module by data type may include a NER model fine-tuned from a Transformer-based model (e.g., BERT, RoBERTa, etc.) for processing text data (e.g., email, document).

[0083] The data extraction module by data type may include CNN-based OCR models (e.g., PaddleOCR, EasyOCR) and Transformer-based Text Parsing models for image data processing.

[0084] The data extraction module by data type may include CNN (Spectrogram) and Transformer (e.g., Whisper) based STT for speech data processing.

[0085] The specification data integration extraction module can extract detailed specifications for a quotation request by integrating specification data extracted by data type. The detailed specifications for a quotation request may be JSON data in which specification data in the form of Key-Value pairs is integrated.

[0086] In other words, the operation of the AI ​​model can be exemplarily explained as follows: 1) Receive quotation request image -> Classify as image -> Extract text from image using modulo -> Extract detailed specifications using parsing modulo -> Output in the form. 2) Receive quotation request audio file -> Classify as speech -> Convert speech to text using modulo -> Extract detailed specifications using parsing modulo -> Output in the form.

[0087] The AI ​​model may be configured such that the output of the preprocessing layer is primarily utilized by a data classification module for classifying data types, while data extraction modules for each data type (OCR, STT, etc.) that extract actual detailed specifications operate based on raw data rather than the preprocessed data.

[0088] In other words, in an AI model, the input data for classification and the input data for extracting detailed specifications are different. Since the primary purpose of the data classification module (Classifier module) is to accurately distinguish data types (images, text, voice, etc.), it is sufficient to clearly reflect only the features (embeddings, etc.) representing the data type, rather than the minute details of the data. Therefore, using standardized and simplified preprocessed data can be more efficient.

[0089] On the other hand, the primary purpose of data extraction modules for specific data types (OCR, STT, Parsing) is to extract precise information, such as exact numbers, units, and names, from the data. In this case, it may be more effective to directly input and process the raw data to avoid potential information loss or distortion during the preprocessing stage and to preserve the maximum amount of information.

[0090] In step S430, the steel platform management module (131) can classify order types for each of at least one steel product based on the detailed specifications of the quotation request. Order types may include Standard Order and Custom Order. The classification of order types may be performed by an order classification algorithm. The order classification algorithm may be intended to effectively manage accurate cost estimation and production schedules by automatically classifying the order based on whether the detailed specifications of the quotation request fall within preset standard product criteria.

[0091] The order classification algorithm is a rule-based algorithm that considers an order a standard order if all of the following conditions are met, and classifies it as a custom order otherwise.

[0093] [Order Classification Algorithm]

[0094] IF (Material == exists in the material list of the standard DB)

[0095] AND (thickness (List of thicknesses of the corresponding material in the standard DB)

[0096] AND (width (List of widths for the corresponding material in the standard DB)

[0097] AND (length (List of lengths of the corresponding material in the standard DB)

[0098] AND (Origin == exists in the origin list of the standard DB)

[0099] AND (tolerance range (Tolerance defined in standard DB)

[0100] AND (Alternative specifications are not required or are allowed)

[0101] THEN "Standard Order"

[0102] ELSE "Custom Order"

[0104] Additionally, the order classification algorithm can perform additional weight-based classification, which may be intended to classify cases that differ slightly from the standard but can be processed similarly to standard products during production.

[0105] In step S440, the steel platform management module (131) can generate a quotation for at least one steel product based on the order type and the detailed specifications of the quotation request. The operation of generating a quotation will be explained in detail through FIG. 8.

[0106] FIG. 8 is a drawing for explaining the operation of generating an estimate according to an exemplary embodiment of the present disclosure.

[0107] The steel platform management module (131) can collect detailed specifications of steel products from the orderer's request and use this data to generate a sophisticated and reasonable price quotation. To this end, the steel platform management module (131) performs the following operations.

[0108] First, the steel platform management module (131) utilizes an internal price database to derive the base price of each steel product based on detailed specifications extracted from a quotation request and real-time external variables (first element: external environment) (e.g., Pricing Type 1). The real-time external variables may be crawled in real-time from a web crawling module (143).

[0109] The base price may be derived based on an internal price database including the shipment price of steel manufacturers, the price of intermediate processors, and the market offer price of imported products, while considering the above-mentioned real-time external variables including steel raw material prices, logistics costs, tax rates, exchange rates, and oil prices.

[0110] This configuration offers the advantage of reflecting market conditions and cost changes in real time during the steel product pricing process. In particular, since key external variables such as steel raw material prices, exchange rates, and logistics costs are automatically reflected in real time via a web crawling module, it enables rapid and accurate price responsiveness even in a rapidly changing market environment. Furthermore, by managing steel manufacturers' ex-factory prices, intermediate processor prices, and import market offer prices within an internal database, it ensures price competitiveness across various suppliers. Consequently, it offers the benefits of providing reasonable and competitive prices to customers, enhancing transparency, and minimizing potential errors in the pricing process.

[0111] Second, the steel platform management module (131) can evaluate the difficulty of working on steel products based on the order type (standard order or custom order) and the detailed specifications of the quotation request (second factor: difficulty of working). At this stage, detailed work environment data such as the size, scale, physical properties, raw material characteristics, and supply status of the product can be taken into account to classify it as Pricing Type 2 and reflect it in the price.

[0112] In other words, the difficulty of the work may be quantified by evaluating whether there is a requirement for changes in physical properties, whether there are non-standard specifications, and whether there is a special application for the custom order.

[0113] This configuration offers the advantage of accurately reflecting the complexity and additional workload associated with custom orders in the price. By objectively and quantitatively evaluating the difficulty of tasks—such as requirements for changes in product properties, non-standard specifications, and special applications—factories can effectively manage the risks of additional labor costs or time delays. Furthermore, customers can understand the reasons for additional costs based on clear criteria, enabling them to make more rational decisions. Consequently, this enhances the transparency and rationality of pricing during the custom order process, thereby improving trust between both customers and suppliers.

[0114] Third, the steel platform management module (131) can derive production availability parameters based on order types and current factory production schedule data (third element: Capacity). Here, internal conditions affecting actual production capacity, such as the factory's production capacity, delivery availability, workforce status, schedule, and holidays, are comprehensively evaluated and defined as Pricing Type 3, and reflected.

[0115] In other words, the production availability parameter may be derived by evaluating the production feasibility and estimated waiting time of the steel product based on production line operating status, production schedule data, and raw material inventory data. This configuration has the advantage of realistically reflecting the actual production conditions of the steel product in the calculation of price and delivery time. By evaluating the accurate production feasibility and estimated waiting time based on production availability information such as the factory's production capacity, schedule, and raw material inventory status, it becomes possible to provide the customer with reliable delivery information and fair pricing. Furthermore, it can increase production efficiency by efficiently utilizing internal factory resources and preventing schedule delays or resource waste. Consequently, it has the effect of simultaneously increasing customer satisfaction and the producer's operational efficiency.

[0116] Fourth, the steel platform management module (131) can derive a final estimate for each of at least one steel product by reflecting production availability parameters and a markup based on work difficulty in the base price. Subsequently, the steel platform management module (131) can generate an estimate including the final estimate.

[0117] The above price calculation process is carried out by the Pricing Management Department, which determines a reasonable price by comprehensively evaluating each element (first element, second element, and third element), and finally, through a process of verifying the optimal price and quality (QA / QC) of the consumer's finished product, can be transparently provided to the orderer.

[0118] The pricing management department may determine the price by considering the aforementioned factors, international raw material prices, market formation prices, supply volume status relative to demand (domestic manufacturing / import), shipment prices of domestic manufacturers (POSCO), inventory availability, delivery dates, designated suppliers, raw material prices (nickel, molybdenum, pure iron, chromium), market conditions, exchange rates, market conditions of demand industries, payment terms of customers, creditworthiness of customers, usage volume of customers, competitor prices, customer future value, product complexity, and sales costs.

[0119] In addition, the steel platform management module (131) supports the orderer in specifically presenting special requests requiring additional work through a custom management interface, and confirms whether production is possible through a separate factory environment review and reflects this in the final estimate calculation.

[0120] Finally, the platform management department can enhance the trading efficiency of steel products by providing users with all such price evaluation and production feasibility data, as well as quality assurance information, to support rational and reliable decision-making.

[0121] FIG. 9 is a flowchart illustrating additional operations of a steel platform management module according to an exemplary embodiment of the present disclosure. FIG. 10 is a diagram illustrating a quality management guide provision operation according to an exemplary embodiment of the present disclosure.

[0122] In FIG. 9, steps S450 through S470 can be understood as being performed by a processor (130) of the electronic device (100) (e.g., a steel platform management module (131)). Steps S450 through S470 may be performed sequentially or in parallel.

[0123] In step S450, the steel platform management module (131) can perform grouping for at least one order of steel products. The steel platform management module (131) performs grouping according to specific criteria for efficient management and quality inspection of steel product orders. This grouping can be done to distinguish between general orders (e.g., standard orders) and custom orders (e.g., custom orders), or to optimize the quality control period of similar orders by utilizing criteria such as material, specifications, and similarity of production processes. As a result, production schedule management and quality inspection schedules are optimized, thereby achieving improved productivity and reduced quality inspection costs.

[0124] In step S460, the steel platform management module (131) can set a Quality Assurance (QA) policy for at least one grouped steel product. The Quality Assurance policy may be defined to include the period of quality inspection, the frequency of inspection, acceptable defects, and detailed criteria for quality inspection (e.g., measurement of physical and chemical properties, visual inspection). Additionally, for custom orders, which are more difficult to work on than standard orders, additional Quality Control (QC) policies may be set to manage quality more strictly. The QC policy includes additional inspection items and detailed evaluation criteria, thereby minimizing the possibility of product defects and maximizing the reliability of quality control.

[0125] In step S470, the steel platform management module (131) can provide a quality management guide in accordance with the quality assurance policy. The quality management guide is provided including the timing of QA and QC verification, detailed criteria for quality evaluation, and the measuring equipment and inspection methods used when performing quality evaluation, thereby supporting production and quality management personnel in performing clear and consistent quality management tasks. This can raise the overall quality management level and maintain consistency in the production process, thereby improving customer satisfaction and product reliability.

[0126] Referring to Fig. 10, the specific timing and method of performing quality control (Quality Assurance, QA and Quality Control, QC) during the order processing process of steel products in the steel platform management module (131) can be identified.

[0127] Orders for steel products are classified into general orders (e.g., standard orders) and custom orders (e.g., bespoke orders), and multiple orders are grouped by specific period.

[0128] When orders are grouped by a certain number or period, QA verification is performed based on this grouping. For example, the first QA verification (period 1) is conducted on a group including general orders #1, #3, and #4, and custom order #2. Special orders, such as custom orders, undergo additional QC verification (QC verification 1) after QA to ensure stricter quality control.

[0129] In the same way, the following groups (general orders #5, #7 and custom order #6, etc.) also undergo QA verification (period 2), and orders with customized requirements also undergo additional QC verification (QC verification 2).

[0130] These periodic QA and, when necessary, additional QC verifications are repeated at regular intervals to maintain a consistent quality level throughout the entire order processing process. Furthermore, the results of these periodic quality verifications are ultimately linked to consumer evaluation data to ensure product quality reliability and contribute to increasing customer satisfaction.

[0131] A collection device according to the embodiments disclosed in this document may be of various forms. A collection device may include, for example, a portable communication device (e.g., a smartphone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a consumer electronics device. A collection device according to the embodiments of this document is not limited to the aforementioned devices.

[0132] The embodiments of this document and the terms used therein are not intended to limit the technical features described in this document to specific embodiments, and should be understood to include various modifications, equivalents, or substitutions of said embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of said items unless the relevant context clearly indicates otherwise. In this document, phrases such as "A or B," "at least one of A and B," "at least one of A or B," "A, B or C," "at least one of A, B and C," and "at least one of A, B, or C" may each include any one of the items listed together in the corresponding phrase, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used simply to distinguish said components from other said components and do not limit said components in any other aspect (e.g., importance or order). Where any (e.g., 1st) component is referred to as "coupled" or "connected" to another (e.g., 2nd) component, with or without the terms "functionally" or "communicationly," it means that said any component may be connected to said other component directly (e.g., via a wire), wirelessly, or through a third component.

[0133] The term “module” as used in the embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit, for example. A module may be a component formed integrally, or a minimum unit of said component or a part thereof that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0134] One embodiment of the present document may be implemented as software (e.g., a program) comprising one or more instructions stored in a storage medium (e.g., internal memory or external memory) readable by a machine (e.g., an electronic device). For example, a processor (e.g., a processor) of the machine (e.g., an electronic device) may call at least one of the one or more instructions stored from the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code that can be executed by an interpreter. The storage medium readable by the machine may be provided in the form of a non-transitory storage medium. Here, "non-transitory" simply means that the storage medium is a tangible device and does not contain a signal (e.g., electromagnetic waves), and this term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily in the storage medium.

[0135] According to one embodiment, the method according to the embodiments disclosed herein may be provided by being included in a computer program product. The computer program product may be traded between a seller and a buyer as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)), or distributed online (e.g., download or upload) through an application store (e.g., Play Store™) or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily created on a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0136] According to one embodiment, each component (e.g., module or program) of the components described above may include a singular or multiple entities, and some of the multiple entities may be separated and placed in other components. According to one embodiment, one or more of the components or operations among the aforementioned components may be omitted, or one or more other components or operations may be added. Generally or additionally, multiple components (e.g., module or program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the multiple components in the same or similar manner as those performed by the corresponding component among the multiple components prior to integration. According to one embodiment, operations performed by the module, program, or other components may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added. Explanation of the symbols

[0138] 100: Electronic device

Claims

Claim 1 A method of operation of an electronic device constituting an order platform for steel products comprises: receiving quotation request data for at least one steel product; extracting detailed specifications for each of the at least one steel product from the quotation request data; classifying an order type for each of the at least one steel product based on the detailed specifications for the quotation request—the order type includes a Standard Order and a Custom Order—; and generating a quotation for the at least one steel product based on the order type and the detailed specifications for the quotation request, wherein the step of generating the quotation comprises: deriving a base price for each of the at least one steel product based on the detailed specifications for the quotation request and real-time external variables by utilizing an internal price database; and evaluating the work difficulty of the steel product based on the order type and the detailed specifications for the quotation request. A method of operation comprising the step of deriving production availability parameters based on the above order type and factory schedule data, wherein the base price is derived by considering real-time external variables including steel raw material prices, logistics costs, tax rates, exchange rates, and oil prices, based on the above internal price database including the steel manufacturer's shipment price, the price of the intermediate processor, and the market offer price of the imported product, and wherein the production availability parameters are derived by evaluating the production possible time and expected waiting time of the steel product based on the production line operating status, production schedule data, and raw material inventory data. Claim 2 A method of operation according to claim 1, wherein the detailed specification of the quotation request includes information regarding the material, specifications, quantity, country of origin, alternative specifications, and allowable specifications in case of error of at least one steel product, and the step of extracting the detailed specification of the quotation request is characterized by selectively performing at least one of OCR (Optical Character Recognition), STT (Speech-To-Text), and Text Parsing in response to receiving a quotation request email, quotation request image, quotation request document, or quotation request call as the quotation request data. Claim 3 A method of operation according to claim 1, wherein the step of extracting the detailed specifications of the quotation request is performed by an artificial intelligence model, wherein the artificial intelligence model comprises: a preprocessing layer that converts the quotation request data into a standardized form; a data classification module that receives the preprocessed quotation request data and classifies the data type; a data type-specific data extraction module that performs data extraction on the original of the quotation request data based on the data type to extract specification data in the form of parsed Key-Value pairs; and a specification data integration extraction module that integrates the specification data extracted by data type to extract the detailed specifications of the quotation request. Claim 4 delete Claim 5 delete Claim 6 A method of operation according to claim 1, wherein the step of generating the above-mentioned estimate further comprises: a step of deriving a final estimate amount for each of the at least one steel product by reflecting the production availability parameter and the work difficulty-related markup on the base price; and a step of generating the above-mentioned estimate including the final estimate amount. Claim 7 A method of operation according to claim 1, characterized in that the difficulty of the work is quantified by evaluating whether there is a requirement for a change in physical properties, whether there are non-standard specifications, and whether there is a special use for the custom order. Claim 8 A method of operation according to claim 1, further comprising: a step of performing grouping on orders for at least one steel product; a step of setting a Quality Assurance (QA) policy for at least one grouped steel product; and a step of providing a quality control guide according to the Quality Assurance policy, wherein the QA policy further comprises an additional QC policy for the custom order. Claim 9 A computer program stored on a storage medium to execute the method of claim 1 in combination with hardware. Claim 10 In an electronic device, a memory in which instructions are stored; The processor includes a processor, wherein when the instructions are executed, the processor causes the electronic device to receive quotation request data for at least one steel product, extract detailed specifications for each of the at least one steel product from the quotation request data, classify an order type for each of the at least one steel product—the order type includes Standard Order and Custom Order—based on the detailed specifications for the quotation request, and generate a quotation for the at least one steel product based on the order type and the detailed specifications for the quotation request. When the instructions are executed, the processor causes the electronic device to utilize an internal price database to derive a base price for each of the at least one steel product based on the detailed specifications for the quotation request and real-time external variables, evaluate the work difficulty of the steel product based on the order type and the detailed specifications for the quotation request, and derive production availability parameters based on the order type and factory schedule data. The base price is based on the internal price database including the steel manufacturer's shipment price, the intermediate processor's price, and the market offer price of imported products, steel raw material price, An electronic device characterized by being derived by considering the above-mentioned real-time external variables including logistics costs, tax rates, exchange rates, and oil prices, and the above-mentioned production availability parameter being derived by evaluating the production possible time and expected waiting time of the steel product based on the production line operating status, production schedule data, and raw material inventory data.

Images