KR102384786B1 - Aluminum ingot transaction integrated management system - Google Patents

Abstract

The present invention relates to an integrated management system for aluminum ingot transactions, which can perform mass transactions between transaction targets which are sensitive to market price but limited, can increase transparency in aluminum ingot transactions in which it is difficult to predict and respond to defects, and can enhance transaction convenience and reliability. The integrated management system for aluminum ingot transactions can collect information on transactions based on aluminum ingots, can broker products through auctions or reverse auctions for the products and information provision services, can perform integrated settlement and accounting for product prices, can normalize feedback information after product purchase, and can store all the collected information in a blockchain unit, so that the reliability between transaction parties can be confirmed based on transparent shared information, and can provide reliability evaluation information through transaction histories and feedback, thereby increasing satisfaction with the transactions between sellers and buyers.

Description

Aluminum ingot transaction integrated management system

The present invention relates to an integrated aluminum ingot transaction management system. In particular, it is possible to increase the transparency of aluminum ingot transactions that are difficult to predict and respond to defects, as well as increase the transaction convenience and reliability, as well as mass transactions between market-sensitive but limited transaction targets. It relates to an integrated aluminum ingot transaction management system.

In general, aluminum processing companies supply aluminum, the raw material, in the form of ingots. The price of aluminum changes according to the London Metal Exchange (LME) price and exchange rate. Sensitive to price trends.

Therefore, according to the price trend, when the price is low, it is not easy to immediately check the quality of the aluminum ingots purchased at a time because many aluminum ingots are purchased to secure inventory. In particular, buyers must measure the weight at an authorized institution when making a transaction, but since the ingredient inspection is not done for reasons such as cost, the transaction is made based on the ingredient inspection information provided by the melter. may be sold or purchased.

Depending on the country of origin, aluminum ingots have a lot of differences between the component analysis table provided by the melter and the actual component. The origin of aluminum ingots is largely divided into non-Western products, and in particular, the component analysis table for non-Western ingots (mainly from India, China, and Turkey) is very unreliable.

Therefore, after the actual transaction is completed, the purchaser can use the aluminum ingots in stock for production, and then understand the quality of the aluminum ingots through the product status or occurrence of defects. However, in the actual market, since there is no quantified refund/compensation system for defective products due to different quality differences from the presented ingredient analysis table, buyers bear all the damages for defective products.

Until now, most domestic aluminum ingot transactions are offline direct transactions, so buyers cannot predict the quality of the supplier's products. .

In addition, aluminum ingots have a difference in weight depending on humidity and temperature due to the characteristics of the product. The transaction price is calculated in units of ton, so for the difference in weight of 1 ton or less, the contracted weight and actual transaction are separately negotiated with the seller. The inconvenience of having to settle for the difference in weight occurs. Since the settlement method is different for each seller, the buyer spends a lot of time and labor in this settlement process. In particular, if the buyer gets money back due to underweight, the seller often delays settlement or does not fulfill the promise.

In the end, the current aluminum ingot transaction is a large amount of transactions within a short time without checking samples or analyzing components according to the variable market price, but it is difficult to accurately determine reliability because most of the offline transactions are done. There is an unreasonable problem in that the purchaser has to bear all the responsibilities in the case of purchasing a defective product because the ingredient analysis table cannot be trusted.

Therefore, it is necessary to understand the reliability of the transaction target in advance, to solve the inconvenience of settlement due to the weight difference, and to be able to predict the possibility of the occurrence of defects in the transaction to some extent in advance to reduce the risk of purchasing aluminum ingots in large quantities. However, to date, there has been no adequate solution to this problem.

Korean Patent Registration No. 10-2207993 [Title of the invention: Transaction management system and method using block chain] Korean Patent Registration No. 10-2216122 [Title of Invention: Smart integrated transaction system for industrial metal materials including aluminum and steel]

An object of the present invention to solve the above problems is to collect information on transactions based on aluminum ingots, and settling and accounting for product prices while brokering products through auctions, reverse auctions, and information provision services. , and at the same time normalizes feedback information after product purchase, stores all collected information in the block chain unit so that trustworthiness between transaction parties can be verified based on transparent shared information, and reliability evaluation through transaction history and feedback The purpose of providing information is to provide an integrated aluminum ingot transaction management system to increase the satisfaction of the transaction between the seller and the buyer.

Another object of the present invention is to record information on the weight difference measured by checking the weight during actual product delivery in the aluminum ingot transaction in which tens of tons are the basic transaction level and the weight difference of 1 ton or less is separately settled. In addition, by automatically processing the settlement process at a specific point in time based on the blockchain smart contract, it occurs for every transaction, but instead of the settlement processing method that is different for each company, it enables safe, simple, and reliable weight difference settlement, so that the accounting of the parties to the transaction is possible. It is to provide an integrated aluminum ingot transaction management system to reduce the load and increase transaction reliability.

Another object of the present invention is to reflect all of the ingredient analysis table, product information, seller and buyer information provided by melters of various reliability as inputs to a neural network, and quantify feedback information with high subjectivity as quality information through a separate neural network model. By using it as learning data, it is possible to predict quality through multiple inputs, and by applying price volatility as well as weight difference information on transactions as additional learning subjects, trends on quality problems that may occur when the market price is large It is to provide an integrated aluminum ingot transaction management system that allows for a more realistic quality prediction by reflecting the

The aluminum ingot transaction integrated management system according to an embodiment of the present invention includes a block chain unit for storing seller, product, buyer and transaction information related to ingot transaction so that it cannot be modified, and a service server interworking with the block chain unit As an aluminum ingot transaction integrated management system, the service server collects information about the seller and the product from the seller terminal, collects purchase information from the buyer terminal, and stores the collected information in the block chain unit; Provides stored product information, collects transaction information from seller and buyer terminals, collects information on transaction progress, stores it in the block chain unit, checks the transaction process, and collects transaction information stored in the block chain unit The contract management unit that performs automatic settlement with a smart contract prepared in advance according to the transaction process, requests feedback information on the purchased product from the purchaser terminal where the transaction has been completed, and converts the text and image included in the received feedback information into information on the block chain. A reliability management unit that stores, sets the trust level of buyers, sellers, and products based on feedback information and settlement information, and then stores them in the block chain unit, seller, product and purchaser information for completed transactions stored in the block chain unit, and the corresponding Through a neural network quality prediction model that is trained by matching the quality information generated based on the feedback information stored in the block chain after the transaction, quality prediction information about the product to be traded is generated through seller, product and buyer information, and it is A prediction unit provided to at least one of the terminals is provided.

As an example, the contractor management unit receives information about the vendor information from the vendor terminal and records and searches the transaction history and the trust level of the company in the block chain unit, and at least aluminum as product information received from the vendor terminal A product management unit that receives ingot specifications, melter information, and ingredient analysis table information, records and searches in the block chain unit, and receives information on purchasing company information from a purchaser terminal and records the transaction history and the trust rating of the company in the block chain unit It may include a purchaser management department that records and searches in the .

As an example, the contract management unit provides product information and seller information registered from the seller terminal and stored in the block chain unit, reliability information about the seller, product or buyer, and market price information for aluminum ingots to the buyer and seller terminal. Study, register the transaction details including information about the seller, buyer, product, price, and settlement received from at least one of the seller terminal and the buyer terminal in the block chain unit, and measure the weight of the product during the transportation of the seller terminal, the buyer terminal and the product The transaction management unit that confirms the transaction progress with information received from the metering terminal, manages the cost according to the transaction details registered in the transaction management unit through the escrow account, and the contents of the weighing certificate received from the authorized metering terminal is stored in the block chain unit, and may include a settlement unit that automatically settles the cost according to the weight difference based on the information on the weight and the transaction contents stored in the block chain unit.

Furthermore, the settlement unit calculates the weight difference based on the transaction details stored in the block chain unit and information received from the authorized weighing station terminal, and performs the settlement of the weight difference through the escrow account, but the settlement of the weight difference is performed in the block chain Based on the information stored in the department, it can be automatically performed according to the contents of the smart contract set in advance and disclosed.

As an example, the reliability management unit receives quantified feedback information including a quality rating and non-quantified feedback information including text and images from the purchaser terminal on which the transaction is completed, separates and preprocesses the text and image information, respectively, and then matches the transaction information a feedback management unit that determines the feedback grade based on the buyer history and the amount of information in the informatized feedback, evaluates the product quality through the quality rating among the buyer feedbacks for the seller and the product, and setstling information between the seller and the buyer Recommendation ranking adjustment information to a trust rating management unit that evaluates the reliability rating according to settlement processing based on the trust rating management unit to adjust the trust rating for sellers, buyers, and products, and the contract management unit that exposes product information according to the rating of the trust rating management unit; It may include a limit management unit for each grade that provides at least one of warning content display information and preferential policy application information.

As an example, the prediction unit includes a price information collection unit that collects market price information and exchange rate information for an aluminum ingot and provides it to the contract management unit, and calculates price volatility of an aluminum ingot with the information collected by the price information collection unit, and predicts neural network quality The learning data management unit collects learning data to be applied to the model or input data for prediction from the block chain unit, and the feedback information and arithmetic quality information in the form of text and images stored in the block chain unit are learned through the feedback analysis neural network model. After providing arithmetic quality information on feedback information in text and image form, and after learning the weight difference information or the price volatility information in addition to seller, product, and buyer information to the neural network quality prediction model, the neural network quality prediction model It may include a learning and predicting unit that generates quality prediction information on products to be traded through.

The aluminum ingot transaction integrated management system according to an embodiment of the present invention collects information on transactions based on aluminum ingots and brokers products through auctions, reverse auctions, and information providing services for products, while settlement and accounting for product prices It performs integrated processing and normalizes feedback information after product purchase, and stores all collected information in the block chain so that reliability between transaction parties can be verified based on transparent shared information. Reliability through transaction history and feedback By providing evaluation information, it has the effect of increasing satisfaction with the transaction between the seller and the buyer.

In addition, in the embodiment of the present invention, in the aluminum ingot transaction in which tens of tons are the basic transaction level and the weight difference of 1 ton or less is separately settled, information on the weight difference measured by checking the weight during actual product delivery is stored in the block chain unit It occurs for every transaction by automatically processing the settlement process at a specific point in time based on the blockchain smart contract, but instead of the settlement processing method that differs for each company, it enables safe, simple, and reliable settlement of weight difference between the parties to the transaction. It has the effect of lowering the accounting load and increasing transaction reliability.

Furthermore, by reflecting all of the ingredient analysis tables, product information, seller and buyer information provided by melters of various reliability as inputs to the neural network, and quantifying the highly subjective feedback information as quality information through a separate neural network model, it is used as learning data. In addition to making it possible to predict quality through input, it also reflects trends in quality problems that may occur when market price changes are large by applying price volatility as an additional learning target as well as weight difference information on transactions. It has the effect of lowering the risk of purchasing defective products through quality prediction.

1 is a block diagram of an aluminum ingot transaction integrated management system according to an embodiment of the present invention.
2 is a block diagram of a service server according to an embodiment of the present invention;
3 is a configuration example of a contractor management unit according to an embodiment of the present invention.
4 is a configuration example of a contract management unit according to an embodiment of the present invention.
5 is a configuration example of a reliability management unit according to an embodiment of the present invention.
6 is a configuration example of a prediction unit according to an embodiment of the present invention.
8 is an example of a measurement certificate according to an embodiment of the present invention.
9 is an example of a component analysis table according to an embodiment of the present invention.
10 is an example of input information for basic information of a buyer, a seller, and a product according to an embodiment of the present invention;
11 is an example of feedback information according to an embodiment of the present invention.

It should be noted that the technical terms used in the present invention are only used to describe specific embodiments, and are not intended to limit the present invention. In addition, the technical terms used in the present invention should be interpreted as meanings generally understood by those of ordinary skill in the art to which the present invention belongs, unless otherwise defined in the present invention, and excessively comprehensive It should not be construed as meaning or in an excessively reduced meaning. In addition, when the technical term used in the present invention is an incorrect technical term that does not accurately express the spirit of the present invention, it should be understood by being replaced with a technical term that can be correctly understood by those skilled in the art. In addition, general terms used in the present invention should be interpreted as defined in the dictionary or according to the context before and after, and should not be interpreted in an excessively reduced meaning.

Also, the singular expression used in the present invention includes the plural expression unless the context clearly dictates otherwise. In the present invention, terms such as “consisting of” or “comprising” should not be construed as necessarily including all of the various components or various steps described in the invention, and some components or some steps may not be included. It should be construed that it may further include additional components or steps.

In addition, terms including ordinal numbers such as first, second, etc. used in the present invention may be used to describe the components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, a first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component.

Hereinafter, a preferred embodiment according to the present invention will be described in detail with reference to the accompanying drawings, but the same or similar components are assigned the same reference numerals regardless of reference numerals, and redundant description thereof will be omitted.

In addition, in the description of the present invention, if it is determined that a detailed description of a related known technology may obscure the gist of the present invention, the detailed description thereof will be omitted. In addition, it should be noted that the accompanying drawings are only for easy understanding of the spirit of the present invention, and should not be construed as limiting the spirit of the present invention by the accompanying drawings.

The service server, the buyer terminal, the seller terminal, and the authorized metering terminal mentioned in the embodiment of the present invention include a storage unit such as a memory, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, and a microcomputer. , hardware such as a field programmable array (FPA), a programmable logic unit (PLU), a microprocessor, software including an instruction set, or any combination thereof or any other device capable of executing and responding to instructions; It may be configured based on the above general-purpose computer or special-purpose computer, or may be configured based on a network such as a cloud.

Furthermore, communication between the seller terminal, the authorized metering station terminal, the purchaser terminal, the service server, the block chain linkage unit, and the block chain unit may include a wired/wireless communication network, and an example of such a wireless communication network is a wireless LAN: WLAN), DLNA (Digital Living Network Alliance), WiBro (Wireless Broadband: Wibro), Wimax (World Interoperability for Microwave Access: Wimax), GSM (Global System for Mobile communication), CDMA (Code Division Multi Access), CDMA2000 (Code Division Multi Access 2000), Enhanced Voice-Data Optimized or Enhanced Voice-Data Only (EV-DO), Wideband CDMA (WCDMA), High Speed Downlink Packet Access (HSDPA), High Speed Uplink Packet Access (HSUPA), IEEE 802.16, Long Term Evolution (LTE), Long Term Evolution-Advanced (LTE-A), Wireless Mobile Broadband Service (WMBS), 5G mobile communication service, Bluetooth (Bluetooth), Long Range (LoRa) ), RFID (Radio Frequency Identification), Infrared Data Association (IrDA), UWB (Ultra Wideband), ZigBee, Near Field Communication (NFC), Ultrasound Communication (Ultra Sound Communication: USC) , Visible Light Communication (VLC), Wi-Fi, Wi-Fi Direct network (Wi-Fi Direct), etc. may be included. In addition, wired communication networks include wired LAN (Local Area Network), wired WAN (Wide Area Network), Power Line Communication (PLC), USB communication, Ethernet, serial communication, optical/coaxial Cables and the like may be included.

Hereinafter, embodiments of the present invention will be described with reference to FIGS. 1 to 11 .

First, Figure 1 shows the configuration of the aluminum ingot transaction integrated management system 10 according to an embodiment of the present invention.

As shown, the information collected while managing the price and exchange rate of aluminum ingots, information on registered products, transaction information made according to auction, reverse auction or mutual coordination, and accounting information on the transaction, etc. The service server 100 managed in such a way as to be stored in the unit 300, and the service server 100 after signing up as a member to provide company information, and information about the product to be sold (origin, melter, ingredient, sales) weight, transaction conditions, etc.) providing transaction or contract information for a specific product through sales-related information after signing up as a member to the seller terminal 20 and service server 100 The purchaser terminal 30 that provides the product, and the authorized weighing station terminal 40 that provides information about the product and a weighing certificate to the service server 100 when the seller must visit and measure the weight of the product in the process of delivering the product ), a block chain unit 300 that stores information provided by interworking with the service server 100 and shares the stored information, and a block chain unit 300 by linking the block chain unit 300 and the service server 100 ) to provide and store information, disclose necessary information according to preset conditions, and when certain conditions are met according to preset smart contract contents, smart contract contents are displayed based on the information stored in the block chain unit 300 It includes a block chain linkage 200 to be performed.

Here, the block chain interworking unit 200 may be substantially configured together with the service server 100 , and the block chain unit 300 may also be configured together with the service server, but to increase the reliability of the block chain unit 300 . To this end, the block chain unit 300 can increase transparency and reliability by interworking with at least a known public block chain. If necessary, the block chain unit 300 and the block chain link unit 200 may be systems of a third block chain service specialized company different from the subject operating the service server 100 .

For example, when a seller and a buyer conclude a transaction for a specific product, information about the transaction is stored in the block chain unit 300 through the service server 100, and when the transaction is completed according to the transaction progress, the service server 100 According to the contents of the smart contract set in advance and disclosed to the seller and the buyer, the settlement of the payment according to the transaction can be made automatically.

The illustrated service server 100 basically provides the market price for the aluminum ingot to the seller terminal 20 and the buyer terminal 30 or provides auction/reverse auction/exposure information for a transaction, and performs cost settlement upon completion of the product transaction It includes a configuration that replaces it, but further includes a function for automatic settlement of weight difference, which is a problem in the prior art, and reliability for quality.

To this end, the service server 100 collects information about the seller and the product from the seller terminal 20 as shown, collects purchase information from the buyer terminal 30, and collects the collected information from the block chain linkage unit 200 ) provides the product information stored in the block chain unit 300 through the contract management unit 100 stored in the block chain unit 300 and the block chain link unit 200 through the seller terminal 20 and the buyer terminal Collect information about the transaction from (40), collect information about the transaction progress, store it in the block chain unit 300 through the block chain link unit 200, check the transaction process, and then check the block chain unit 300 ), the contract management unit 120 that performs automatic settlement with a smart contract prepared in advance according to the transaction information stored in the transaction process, and the purchaser terminal 30 on which the transaction has been completed, request feedback information on the purchased product and respond to the received feedback information. The included text and images are converted into information and stored in the block chain unit 300 through the block chain link unit 200, and the trust level of the buyer, seller and product is set based on the feedback information and settlement information, and then the block chain link unit The reliability management unit 130 stored in the block chain unit 300 through 200, the seller, product and buyer information for the completed transaction stored in the block chain unit 300, and the block chain unit 300 after the transaction Through a neural network quality prediction model trained by matching the quality information generated based on the feedback information stored in the 40) includes a prediction unit 40 that provides it to at least one.

Here, the contract management unit 120 receives the weighing certificate information from the authorized weighing station terminal 40 that always visits and measures the weight when delivering products other than the seller terminal 20 and the buyer terminal 40 to check the contract progress. It can be further understood, and the corresponding metering certificate information is stored in the block chain unit 300 through the block chain link unit 200 . The actual product weight information of the weighing certificate is information for confirming the difference from the weight set during the transaction, and the cost change according to the weight difference is automatically settled by the contract management unit 120 .

The prediction unit 40 learns a neural network quality prediction model by matching various information about the completed product transaction and quality information according to the feedback information, and inputs various information about the product to be traded into the learned neural network quality prediction model. After calculating the quality information is configured to provide it to at least the purchaser terminal (30). The purchaser can estimate the possibility of occurrence of defects in the corresponding product based on the quality prediction information for the specific product provided through the corresponding purchaser terminal 30 .

FIG. 2 shows a more detailed configuration of the service server 100 according to an embodiment of the present invention, and shows the contract management unit 100 , the contract management unit 120 , the reliability management unit 130 , and the prediction unit 140 . The detailed components are shown.

The illustrated configuration logically divides the functional parts in order to explain the operation and operation of each structural part, and the location or classification of the corresponding configuration may be changed if necessary, and some parts may be omitted or a plurality of configurations may be integrated.

First, the illustrated service server 100 provides data to be recorded by interworking with the block chain interworking unit 200 and searches for and receives desired data, a block chain information record and search unit 150 and the seller terminal 20 and It includes a smart contract management unit 160 that manages information about a smart contract that is transparently disclosed to the purchaser terminal 30 and provides it to the block chain linkage 200 and collects information about execution. This configuration corresponds to a basic configuration that can be utilized in all components.

Hereinafter, the functions of the contract management unit 100 , the contract management unit 120 , the reliability management unit 130 , and the prediction unit 140 as characteristic components according to an embodiment of the present invention will be described with detailed configuration.

FIG. 3 shows the configuration of the contractor management unit 110 shown in FIG. 2 in more detail. As shown, information on vendor information is received from the vendor terminal 20 and the transaction history and trust rating of the vendor are displayed. The block chain unit ( 300), the product management unit 112 that records and searches, and the buyer receives information about the purchasing company information from the purchaser terminal 30, and records and searches the transaction history and trust level of the company in the block chain unit 300 and a management unit 113 .

The seller management unit 111 and the purchaser management unit 113 may provide information for membership registration for each seller terminal 20 and purchaser terminal 30 and receive necessary information to register as a seller and a buyer, each terminal An interface (dedicated application or web) for connection to (20, 30) may be provided.

Information on the aluminum ingot product includes the product name of the aluminum, country of origin (from Western countries, non-Western production (country)), melter (producer who produced the aluminum ingot), and ingredient analysis table (pure aluminum for aluminum ingot) provided by the melter. type and content of impurities excluded).

9 shows an exemplary component analysis table, and the content of aluminum and impurities (such as silicon or iron) that cause defects can be confirmed.

Such seller information, buyer information, and product information may include member registration IDs, trade names, and business registration numbers of buyers and sellers as illustrated in FIG. , melter, production location information, etc. may be included.

4 is a view showing the configuration of the contract management unit 120 of FIG. 2, and has a configuration that provides information on products, mediates transactions, monitors the transaction process, and even automatically performs settlement for weight differences.

As shown, the contract management unit 120 registers from the seller terminal 20 and stores product information and seller information stored in the block chain unit 300, reliability information for the seller, product or buyer, and market price information for aluminum ingots. Transaction contents including information on the seller, buyer, product, price, and settlement received from the product information providing unit 121 provided to the buyer and the seller terminal, and at least one of the seller terminal 20 and the buyer terminal 30 . Transaction management unit that registers with the block chain unit 300 and checks the transaction progress with information received from the seller terminal 20, the buyer terminal 30, and the authorized weighing station terminal 40 that measures the weight of the product during product transportation 122 and the transaction management unit 122 manages the cost according to the registered transaction through an escrow account, and stores the contents of the weighing certificate received from the authorized weighing station 40 in the block chain unit 300, It includes a settlement unit 123 that automatically settles the cost according to the weight difference based on the information about the weight and the transaction contents stored in the block chain unit 300 .

In this way, the contract management unit 120 includes a configuration for collecting information about a transaction, registering it in the block chain unit, and tracking the transaction progress, as well as a basic configuration of providing product information / price information for a contract and brokering a transaction. In addition, additional costs or return costs according to the weight difference found during product delivery are automatically settled.

Here, the product information providing unit 121 includes a product information module for providing product information, a recommendation module for exposing a corresponding product first according to trust information of a seller or product, a market price of the London Metal Exchange for an aluminum ingot, exchange rate information, etc. Includes a price information module that provides

The transaction management unit 122 collects transaction details including seller information for the transaction, buyer information, product information, weight information, transaction price information, transaction payment method information, and the like, and registers it in the block chain unit 300 . A registration module, a transaction progress management module that collects information on product delivery from the seller terminal, information on the way through the weighing station through the authorized weighing station terminal 40 (weighing certificate), and information on product delivery completion to manage the transaction progress In addition, the pre-transferred purchase price is managed with an escrow account, and the seller and buyer’s expenses for weight difference settlement (costs for weight differences are equivalent to 1 ton) are managed with the escrow account, and the authorized weighing station terminal (40 ) and a weight settlement module that compares weight information among contract information stored in the block chain unit 300 to settle costs for a weight difference, and an accounting module that manages transaction details and fees.

8 shows an exemplary weighing proof table, and information about the shipper and weight is included as shown. Such information was provided one way through FAX, and since the certified weighing station does not reissue the relevant weighing certificate, there is a problem in that it is difficult to assert the weight difference if the relevant weighing certificate is lost. Therefore, in the embodiment of the present invention, the service server 100 that has received the corresponding weighing certificate information from the authorized weighing station terminal 40 stores it in the block chain unit 300, so that the settlement is automatically processed by the smart contract. By doing so, it is possible to fundamentally resolve conflicts of interest between sellers, buyers, and authorized weighing stations.

That is, the weight settlement module of the settlement unit 123 calculates the weight difference based on the transaction details stored in the block chain unit 300 and the information received from the authorized weighing station terminal 40, and calculates the weight difference through the escrow account. Settlement is performed, but the settlement of this weight difference is automatically performed by a smart contract set and published in advance based on information stored in the block chain unit 300 (that is, the smart contract unit of the block chain linkage unit 200). do.

5 is a reliability management unit 130 shown in FIG. 2 receives the quantified feedback information including the quality rating and the non-quantified feedback information including the text and image from the purchaser terminal on which the transaction is completed, and separates the text and image information, respectively. and the feedback management unit 131 that determines the feedback grade based on the amount of information of the buyer history and the informatized feedback, and performs the pre-processing to match the transaction information, and the product quality through the quality rating among the buyer feedbacks for the seller and the product. The rating of the trust rating management unit 132 and the trust rating management unit 132 for evaluating and adjusting the trust rating for the seller and the buyer and the product by evaluating the reliability rating according to the settlement processing based on the settlement information of the seller and the buyer A limit management unit 133 for each grade that provides at least one of recommendation ranking adjustment information, warning content display information, and preferential policy application information to the contract management unit 120 that exposes product information according to the above.

The feedback management unit 131 internally receives a feedback request and reception module for requesting and receiving non-quantified feedback information including preconfigured quantified feedback information and text and images input by the purchaser to the purchaser terminal 30 on which the transaction has been completed; It removes unnecessary characters or symbols from the text, extracts only meaningful sentences or words, quantifies the size of the image or performs pre-processing to remove unnecessary parts, and then matches the transaction information to learn through the neural network of the prediction unit 140 A feedback information module that informatizes information in a state where it is possible, and the amount of aluminum ingot purchase (whether it is a professional handling company) through the purchaser's previous purchase history, and the feedback grade is managed based on the amount of information of the informatized feedback (whether it is a faithful feedback) and a feedback rating management module that assigns weights to the corresponding feedback.

Such feedback information includes quantitative feedback information such as contract information, actual weight, actual transaction amount, quality satisfaction (quantitative value), product usage history, ingredient impurity, aluminum series number, etc. and free text, as in the example shown in FIG. 11 . and non-quantitative feedback information such as defect reports and feedback supplements that can be registered with defective photos.

The trust rating management unit 132 is a product quality evaluation module that evaluates product quality through a quantified quality rating among buyer feedbacks for sellers and products, and payment considering settlement delays or errors based on settlement information between sellers and buyers A settlement processing evaluation module that evaluates the reliability rating for includes

The rating limit management unit 133 includes a recommendation ranking adjustment module that provides recommendation ranking adjustment information to the contract management unit 120 that exposes product information according to the rating of the trust rating management unit 132, and a warning content to be displayed when the confidence level is low A warning content management module to generate and provide to the contract management unit 120, and to generate preferential application information such as lowering the escrow fee or lowering the transaction brokerage fee in the case of a company with a high level of trust and providing it to the contract management unit 120 It may include a preferential application management module.

6 is a view showing the configuration of the prediction unit 140 shown in FIG. 2 , a price information collection unit 141 that collects price information and exchange rate information for an aluminum ingot and provides it to the contract management unit 120 , and market price information A learning data management unit 142 that calculates price volatility of aluminum ingots with the information collected by the collection unit 141 and collects learning data to be applied to the neural network quality prediction model or input data for prediction from the block chain unit, and feedback After learning the feedback information and arithmetic quality information in the form of text and images stored in the block chain unit through the analytic neural network model, arithmetic quality information for the feedback information in the form of text and images is provided, and the seller to the neural network quality prediction model; It includes a learning and predicting unit 143 for generating quality prediction information for a product to be traded through a neural network quality prediction model after learning the product weight difference information or the price volatility information in addition to product and purchaser information.

Here, the price information collection unit 141 may include a market price information collection module for collecting various price information such as the London Metal Exchange and the domestic public procurement service price, and an exchange rate information collection module for collecting exchange rate information.

The learning data management unit 142 blocks the price fluctuation line calculation module for calculating the price volatility of the aluminum ingot with the information collected by the market price information collection unit 141, and learning data to be applied to the neural network quality prediction model or input data for prediction. Includes a learning data collection module collected by the chain unit. Here, the input data for learning data or prediction includes seller company information, buyer company information, product information, such as country of origin, melter, ingredient analysis table information, information on transaction amount and transaction weight, price volatility information, and quantified quality information. .

The learning and prediction unit 143 is largely divided into a feedback analysis neural network model and a neural network quality prediction model, which will be described again with reference to FIG. 7 .

As shown in the figure, the learning and prediction unit shown in FIG. 7 may be configured in multiple stages of a plurality of neural network models, and information that the neural network quality prediction model must predict through various input information is quality information, which has to be quantified. From the point of learning, quantified quality information and various input information must be matched to form learning information.

Therefore, it is necessary to establish a standard for calculating quantified quality information from unstructured text and image feedback. In an embodiment of the present invention, numerical information on quality can be predicted using a feedback analysis neural network model.

Such a feedback analysis neural network model calculates primary information on arithmetic quality from words included in text feedback information, calculates secondary information on arithmetic quality from images and buyer information included in image feedback information, It can be configured to generate arithmetic quality information by weight combining. That is, a text-based neural network model and an image-based neural network model are configured in parallel, and a neural network model for learning weights for them can be configured. Here, the quality rating included in the quantitative feedback information and the text/image feedback may be matched to be used as learning data. However, since the deviation in the quality rating of each buyer is large, it may be necessary to reduce the deviation in the quality rating by applying a weight through the feedback rating for each buyer.

In the neural network quality prediction model of the learning and prediction unit 143 through this configuration, seller company information, buyer company information, and product information as the origin, melter, ingredient analysis table information, transaction amount and weight information, price volatility information If you provide some, you will be able to obtain quality prediction information (numeric information) for the products to be traded.

Through matching learning on the quality and the inputs applied to the learning and prediction unit 143, product quality patterns according to country of origin and melter, product quality patterns according to the analysis contents of the ingredient analysis table, product quality patterns according to transaction amount and weight, It is possible to provide quality prediction information by considering all product quality patterns according to price volatility, product quality patterns according to sellers, and subjective feedback patterns of buyers.

Accordingly, the contract management unit 110 may periodically calculate quality prediction information through the prediction unit 140 when exposing product information, and provide at least the purchaser terminal 30 for transacting the product.

In particular, the learning and prediction unit 143 may provide the quality prediction information to the purchaser terminal 30 only when the purchaser's confidence level is equal to or greater than the standard. The reliability management unit 130 that manages such a buyer trust rating may allocate and adjust the buyer's reliability in consideration of whether or not feedback from the buyer terminal 30 is provided, feedback accuracy, and a settlement pattern.

That is, quality prediction information can be selectively provided as a factor for inducing activation of the system by inducing the buyer to actively provide padback, provide accurate feedback, and smoothly proceed with settlement for the transaction.

Additionally, the quality prediction information for the product to be traded is stored in the block chain unit 300, and when the quality information according to the feedback information received after the transaction of the product is completed and the quality prediction information for the same product are different, the transaction is completed Based on the subsequent information, re-learning of the neural network quality prediction model can be performed. Furthermore, it is possible to reduce the deviation in the quality level by adjusting the feedback level of the purchaser through the feedback of the purchaser on the transaction completed product and the quality level set by the purchaser.

Such a configuration of the present invention may be implemented through physical means such as a terminal, a server, a measurement equipment of a metering station, a physical configuration of a block chain network node, etc., electrical and electronic devices, an electrical device, a circuit board, an integrated circuit chip, and these Some of them may be configured in the form of software inside the programmable chip. Those of ordinary skill in the art to which the present invention pertains may modify and modify the above-described contents without departing from the essential characteristics of the present invention. Accordingly, the embodiments disclosed in the present invention are not intended to limit the technical spirit of the present invention, but to explain, and the scope of the technical spirit of the present invention is not limited by these embodiments. The protection scope of the present invention should be construed by the following claims, and all technical ideas within the scope equivalent thereto should be construed as being included in the scope of the present invention.

10: Aluminum Ingot Trading Integrated Management System
20: seller terminal 30: buyer terminal
40: authorized weighing station terminal 100: service server
110: contract management unit 120: contract management unit
130: reliability management unit 140: prediction unit
200: block chain linkage unit 300: block chain unit

Claims (10)

An aluminum ingot transaction integrated management system comprising: a block chain unit for storing seller, product, buyer and transaction information related to ingot transaction in a non-modifiable manner; and a service server interworking with the block chain unit,
the service server
a contractor management unit that collects information about the seller and the product from the seller terminal, collects purchase information from the buyer terminal, and stores the collected information in the block chain unit;
Provides product information stored in the block chain unit, collects transaction information from the seller terminal and buyer terminal, collects information on the transaction progress process, stores it in the block chain unit, checks the transaction process, and stores it in the block chain unit a contract management unit for performing automatic settlement with a smart contract prepared in advance according to the stored transaction information and transaction progress;
Request feedback information about the purchased product from the purchaser terminal where the transaction has been completed, convert the text and image included in the received feedback information into information, and store it in the block chain unit. Based on the feedback information and settlement information, the trust rating of the buyer, seller and product a reliability management unit that is set and then stored in the block chain unit;
Seller, product, and purchaser information through a neural network quality prediction model that is trained by matching seller, product, and buyer information about the completed transaction stored in the block chain and quality information generated based on the feedback information stored in the block chain after the transaction and a prediction unit that generates quality prediction information for a product to be traded through and provides it to at least one of a seller terminal and a buyer terminal,
The contract management department
a product information providing unit that provides product information and seller information registered from the seller terminal and stored in the block chain unit, reliability information about the seller, product or buyer, and market price information on the aluminum ingot to the buyer and the seller terminal;
Authorization that registers transaction details including information about the seller, buyer, product, price, and settlement received from at least one of the seller terminal and the buyer terminal in the block chain unit, and measures the weight of the product during the transportation of the seller terminal, the buyer terminal and the product a transaction management unit for checking a transaction progress state with information received from the metering terminal;
Manages the cost according to the transaction details registered in the transaction management unit through an escrow account, stores the contents of the weighing certificate received from the authorized weighing station terminal in the block chain unit, and stores the transaction contents and weight information stored in the block chain unit Includes a settlement unit that automatically settles costs according to weight differences based on
The settlement unit calculates the weight difference based on the transaction details stored in the block chain unit and information received from the authorized weighing station terminal, and performs the settlement of the weight difference through the escrow account, but the settlement of the weight difference is performed by the block chain unit Aluminum ingot transaction integrated management system, characterized in that it is automatically performed based on the information stored in the preset and disclosed smart contract contents.
The method according to claim 1, The contractor management unit
a seller management unit for receiving information about the seller information from the seller terminal and recording and searching the transaction history and the trust level of the corresponding business in the block chain unit;
a product management unit for receiving at least the aluminum ingot standard, melter information, and component analysis table information as product information received from the seller terminal, and recording and searching the block chain unit;
An aluminum ingot transaction integrated management system comprising a buyer management unit that receives information on purchasing company information from a purchaser terminal and records and searches the transaction history and the trust level of the company in the block chain unit.
delete delete The method according to claim 1, The reliability management unit
Receives quantified feedback information including quality rating and non-quantified feedback information including text and image from the purchaser terminal on which the transaction is completed, separates and pre-processes text and image information, respectively, matches the transaction information to informatize it, and purchases history And a feedback management unit for determining a feedback grade based on the information amount of the informational feedback;
Evaluating product quality through quality rating among buyer feedback on the seller and the product, and evaluating the reliability rating according to the settlement process based on the settlement information of the seller and buyer to adjust the trust rating for the seller and the buyer and the product a trust level management unit;
Aluminum ingot transaction, characterized in that it comprises a limit management unit for each grade that provides at least one of recommendation ranking adjustment information, warning content display information, and preferential policy application information to the contract management unit that exposes product information according to the grade of the trust rating management unit Integrated management system.
The method according to claim 1, wherein the prediction unit
a market price information collection unit that collects price information and exchange rate information on aluminum ingots and provides them to the contract management unit;
a learning data management unit that calculates price volatility of an aluminum ingot with the information collected by the price information collection unit, and collects learning data to be applied to a neural network quality prediction model or input data for prediction from the block chain unit;
After learning the feedback information and arithmetic quality information in the form of text and images stored in the block chain unit through the feedback analysis neural network model, arithmetic quality information for the feedback information in the form of text and images is provided, and the seller in the neural network quality prediction model , aluminum ingot comprising a learning and predicting unit for generating quality prediction information for a product to be traded through a neural network quality prediction model after learning the product weight difference information or the price volatility information in addition to product and buyer information Transaction Integration Management System.
The method according to claim 6, The feedback analysis neural network model of the learning and prediction unit calculates primary information about arithmetic quality from words included in text feedback information, and calculates primary information about arithmetic quality from images and buyer information included in image feedback information An aluminum ingot transaction integrated management system, characterized in that the secondary information is calculated and then combined by weight to generate arithmetic quality information.
The method according to claim 6, The input provided to the neural network quality prediction model of the learning and prediction unit is seller company information, buyer company information, product information, such as country of origin, melter, ingredient analysis table information, transaction amount and weight information, price volatility information Including, through at least one of the inputs, the aluminum ingot transaction integrated management system, characterized in that for generating the quality prediction information for the product to be traded.
The method according to claim 8, wherein the learning and prediction unit is a product quality pattern according to country of origin and melter, a product quality pattern according to the analysis contents of the ingredient analysis table, a product quality pattern according to the transaction amount and weight, a product quality pattern according to price volatility, to the seller Aluminum ingot, characterized in that when product information is exposed through the contract management unit in consideration of both the product quality pattern and the buyer's subjective feedback pattern according to Transaction Integration Management System.
The method according to claim 9, wherein the learning and prediction unit provides quality prediction information to the purchaser terminal when the confidence level of the purchaser is greater than or equal to the standard, and the reliability management unit for managing the confidence level of the purchaser determines whether or not feedback from the purchaser terminal is provided and feedback accuracy , an aluminum ingot transaction integrated management system, characterized in that allocating and adjusting the buyer's trust in consideration of all settlement patterns.

Images