KR102455414B1 - Method and system for providing online payment service - Google Patents

Abstract

A method for providing an online payment service, which is performed in an environment including a buyer side communication terminal, a seller communication terminal, a payment management platform server, and a payment server according to an embodiment disclosed in the present document, comprises the steps in which: the seller communication terminal requests the generation of an SMS payment link from the payment management platform server, the request of the generation of a payment link including information on the buyer side communication terminal; the payment management platform server checks information on whether the seller communication terminal is a registered affiliate store from a manager platform; the payment management platform server transmits a purchase link SMS to the buyer side communication terminal if the seller communication terminal is a registered affiliate store; the buyer side communication terminal, which has received the purchase link SMS, accesses the received link and inputting the card number of a buyer into a web payment UI platform for buyers; the web payment UI platform for buyers transmits an SMS transaction information request including the card number of the buyer to the payment management platform server; the payment management platform server, which has received the SMS transaction information request, requests payment from the payment server; and if payment is completed by the payment server by receiving a response to the payment, the payment management platform server notifies the web payment UI platform for buyers of payment completion result and registering transaction result in the manager platform. Therefore, payment can be performed online in various and convenient ways.

Description

Method and system for providing online payment service

Embodiments disclosed in this document relate to a method and system for providing an online payment service.

In the conventional payment service, a method in which a customer directly visits a store offline and proceeds with payment through a magnetic or IC chip was used.

Recently, due to the improvement of the performance of mobile terminals such as smartphones and the development of wireless network technology, the mobile terminals are being used for various purposes beyond the conventional simple phone use, and payment services using the mobile terminals are also gradually increasing.

However, even if the payment is made through the mobile terminal, the corresponding mobile terminal directly proceeds with the payment in the seller's payment system, or payment is possible through a specific online payment platform.

1. Republic of Korea Patent Publication No. 10-2019-0120533 (published on October 24, 2019) 2. Republic of Korea Patent Publication No. 10-2020-0116389 (published on October 12, 2020) 3. Republic of Korea Patent Publication No. 10-1339651 (2013.12.04 Announcement)

Although the technology of payment service using a mobile terminal without a card has been developed and commercialized, payment can be made online in a variety of convenient ways without restrictions on non-business operators as well as business operators who require card payment through smartphone apps or the web. There is a lack of technology.

As such, there is an urgent need for a technology that can provide a simple payment service between a seller and a buyer in the process of payment service using a mobile terminal.

In particular, it is difficult for sellers to accept card payments in the case of non-business operators, and a technology that enables non-business operators (individuals) to use card payments is required.

The online payment service providing method performed in an environment including a buyer side communication terminal, a seller communication terminal, a payment management platform server, and a payment server according to an embodiment disclosed in this document is provided by a seller communication terminal to a payment management platform server requesting generation of an SMS payment link, the request for generating a payment link includes information of a communication terminal on the purchaser side; checking, by the payment management platform server, information on whether the seller communication terminal is a registered affiliate store to the manager platform; transmitting, by the payment management platform server, a purchase link SMS to the purchaser-side communication terminal when the seller communication terminal is a registered affiliate; accessing the received link by the purchaser-side communication terminal receiving the purchase link SMS, and inputting the purchaser's card number into a web payment UI platform for purchasers; transmitting, by the web payment UI platform for purchasers, an SMS transaction information request including the purchaser's card number to the payment management platform server; requesting payment to the payment server by the payment management platform server receiving the SMS transaction information request; When the payment is completed by receiving a response to the payment by the payment server, the payment management platform server may include the step of notifying the payment completion result to the web payment UI platform for the buyer and registering the transaction result in the manager platform .

In an embodiment, the method for providing an online payment service may further include, prior to the step of requesting generation of a payment link, requesting registration of SMS payment from the merchant mobile application platform by the seller communication terminal.

In an embodiment, the method of providing an online payment service, the payment management platform, when receiving an online payment request, may be configured to check data forgery using a hash key (HashKey).

In one embodiment, the online payment service providing method, the payment management platform, based on the transaction cancellation rate and civil complaint rate for each seller may be configured to select a defective merchant and automatically notify the merchant contract termination processing to the defective merchant.

In one embodiment, in the process of selecting a bad affiliated store, the transaction cancellation rate, civil complaint occurrence rate, and fee rate for each seller are input and stored in the storage, and the transaction cancellation rate, civil complaint occurrence rate and commission rate for each seller are transmitted to the deep learning server, and input from the server Analyzing the unstructured data to systematize and divide the characteristics into a certain classification; It is set as a training data set for systematically divided sets and transaction cancellation rate, civil complaint rate, and commission rate by seller, and uses an unsupervised feature extraction deep learning method for the training data set. learning the pattern; Refining data for analysis from text unstructured data; performing stem extraction and semantic analysis from the purified data; performing linguistic analysis from the preprocessed data to extract features; mapping the extracted characteristics to standard terms for each transaction cancellation rate, civil complaint rate, and commission rate by seller; It further includes an automatic learning step built through deep learning that reflects the standard transaction term, transaction cancellation rate by seller, complaint rate and transaction cancellation rate by seller generated by characteristics of the fee rate, civil complaint rate, and commission rate case data, The Unsupervised Deep Feature Learning method uses SDA (Stack of Denoising Autoencoders), SDA has the same dimension as the input layer and the output layer, and SDA is the hidden layer between the input and output layers. The number is smaller than the number of input and output layers, and in SDA, the encoding process from the input layer to the hidden layer and the decoding process from the heat layer to the output layer are performed, and features hidden in the input data are encoded in the encoding process. , and can be configured to reconstruct hidden features in the decoding process.

Payment (card payment) can be performed online in a variety of convenient ways without restrictions on non-business operators as well as business operators who require card payment through a smartphone app or the web.

We can provide a smart card payment solution that allows you to receive card payments simply by signing up anytime, anywhere.

In addition, through various payment methods, customers can conveniently make payments in a preferred manner, and selectively provide functions that facilitate risk management for each seller.

It can be managed collectively without the need for cumbersome contracts for each card company, transaction management, and settlement confirmation.

1A shows a schematic diagram of a handwritten payment or terminal payment system according to the present invention.
1B shows a flowchart of a handwritten payment method according to the present invention.
1c shows a flowchart of a terminal payment method according to the present invention.
Figure 2a shows a schematic diagram of an SMS payment or link payment system according to the present invention.
Figure 2b shows a flow chart of the SMS payment method according to the present invention.
2c illustrates a method of registering a payment link according to the present invention.
3 shows a schematic diagram of a QR payment system according to the present invention.

Hereinafter, various embodiments of the present invention will be described with reference to the accompanying drawings. However, this is not intended to limit the present invention to specific embodiments, and it should be understood that various modifications, equivalents, and/or alternatives of the embodiments of the present invention are included.

In this document, the singular form of a noun corresponding to an item may include one item or a plurality of items unless the context clearly dictates otherwise. As used herein, "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 "A; Each of the phrases "at least one of B, or C" may include any one of the items listed together in the corresponding one of the phrases, or all possible combinations thereof. Terms such as “first”, “second”, or “first” or “second” may simply be used to distinguish the component from other components in question, and may refer components to other aspects (e.g., importance or order) is not limited. It is said that one (eg, first) component is "coupled" or "connected" to another (eg, second) component, with or without the terms "functionally" or "communicatively". When referenced, it may mean that one component can be coupled to another component directly (eg, by wire), wirelessly, or through a third component.

Each component (eg, a module or a program) of components described in this document may include a singular or a plurality of entities. According to various embodiments, one or more components or operations among the corresponding components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (eg, a module or a program) may be integrated into one component. In this case, the integrated component may perform one or more functions of each component of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to integration. According to various embodiments, operations performed by a module, program, or other component are executed sequentially, in parallel, repeatedly, or heuristically, or one or more of the operations are executed in a different order, omitted, or , or one or more other operations may be added.

The term "platform" used in this document may be implemented in hardware or software, and may be a server that stores and processes data.

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, for example, logic, logic block, component, or circuit. A module may be an integrally formed part or a minimum unit of a part or a part thereof that performs one or more functions. For example, according to an embodiment, the module may be implemented in the form of an application-specific integrated circuit (ASIC).

Various embodiments of the present document may be implemented as software (eg, a program or an application) including one or more instructions stored in a storage medium (eg, memory) readable by a machine. For example, the processor of the device may call at least one of the one or more instructions stored from the storage medium and execute it. This may enable the device to be operated to perform at least one function according to the at least one command called. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The device-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' only means that the storage medium is a tangible device and does not include a signal (eg, electromagnetic wave), and this term is used in cases where data is semi-permanently stored in the storage medium and It does not distinguish between temporary storage cases.

Methods according to various embodiments disclosed in this document may be included and provided in a computer program product. Computer program products may be traded between sellers and buyers as commodities. The computer program product is distributed in the form of a machine-readable storage medium (eg, compact disc read only memory (CD-ROM)), or via an application store or between two user devices (eg, smartphones). It can be distributed directly, online (eg, downloaded or uploaded). In the case of online distribution, at least a part of the computer program product may be temporarily stored or temporarily created in a machine-readable storage medium such as a memory of a server of a manufacturer, a server of an application store, or a relay server.

1A shows a schematic diagram of a handwritten payment or terminal payment system according to the present invention.

The payment system according to the present invention is a payment system in which anyone, such as a business operator, a non-business operator, or an individual, who needs card payment can easily sign up using a smartphone app, and immediately receive a card payment using various types of payment methods.

In the payment system according to the present invention, non-business operators (individuals) who cannot contract with a card company can use card payment. The payment system according to the present invention can provide hand-written payment, SMS payment, link payment, and QR payment for non-face-to-face payment.

The payment system according to the present invention can be used in wireless (Bluetooth type, Android type, iOS type, etc.) terminals without space restrictions.

Moreover, in the case of card payment, the difference between the settlement date and the settlement date is often large, so the seller's cash liquidity is often lowered. However, the payment system according to the present invention can provide a variety of settlement forms from immediate settlement (immediate settlement), which facilitates securing cash flow of the seller, to general settlement (eg, 5-day deposit) with a low fee burden.

The payment system according to the present invention enables collective management without the need for cumbersome contracts for each card company, transaction management, and settlement confirmation. In addition, in the payment system according to the present invention, a card company interest installment benefit may be provided at all times according to a card company event.

Referring specifically to FIG. 1A , the buyer 110 requests the seller 120 to purchase goods or services. The seller 120 makes the purchaser 110 read the card through the terminal or requests a handwritten payment. In response, the purchaser 110 may read the card in the terminal or notify the seller 120 of the card number. In the case of handwritten payment, the seller 120 may input the payment amount and card number of the corresponding product or service into the mobile application platform 130 for the affiliated store.

The merchant mobile application platform 130 requests the merchant information request to the payment management platform 160, and the payment management platform 160 checks information on whether the merchant is a registered merchant to the manager platform 170 for merchant information. The mobile application platform 130 is notified of this. The merchant mobile application platform 130 may request a transaction from the payment service platform 140 , and the payment service platform 140 may request a transaction from the credit card company 150 . The credit card company 150 may notify the payment service platform 140 of a message for approving the transaction, and the payment service platform 140 may notify the mobile application platform 130 for a merchant of a message for approving the transaction. have. The merchant mobile application platform 130 may transmit the transaction result to the seller 120 and register the transaction result in the payment management platform 160 .

When the payment is completed, the seller 120 may pay the buyer 110 the goods.

1B shows a flowchart of a handwritten payment method according to the present invention.

In step S110, the seller 120 logs in to the application installed in the terminal. At this time, it is also possible to log in through a simple password.

In step S120, after login, select "manual payment" from the payment list (terminal payment, handwritten payment, SMS payment, cash receipt).

In step S130, hand-set payment information is input. You can enter the sales amount in won and choose whether to install or not. Then, the card information is received from the purchaser 110 and is input. At this time, if the payment amount is 100,000 won or more, the customer's mobile phone number is input. Meanwhile, by selecting a menu to inquire the payment limit before payment, it is possible to check in advance whether the sales amount is within the payment limit.

In step S140, card payment is performed.

In step S150, payment is confirmed, and payment details are confirmed.

In step S160, the receipt of the transaction may be transmitted via text message (eg, SMS message or messenger app (KakaoTalk, etc.)) or email.

1c shows a flowchart of a terminal payment method according to the present invention.

In step S111, the seller 120 logs in to the application installed in the terminal. At this time, it is also possible to log in through a simple password.

In step S121, after login, select "terminal payment" from the payment list (terminal payment, manual payment, SMS payment, cash receipt).

In step S131, card payment information is input. You can enter the sales amount in won and choose whether to install or not. At this time, if the payment amount is 100,000 won or more, the customer's mobile phone number is input. Meanwhile, by selecting a menu to inquire the payment limit before payment, it is possible to check in advance whether the sales amount is within the payment limit.

In step S141, the swipe connection is confirmed.

In step S151, a reader is connected and a card is inserted.

In step S161, the card payment is approved.

In step S171, payment is confirmed, and payment details are confirmed.

In step S181, the receipt of the transaction may be transmitted through a text message (eg, an SMS message or a messenger app (KakaoTalk, etc.)) or e-mail.

Figure 2a shows a schematic diagram of an SMS payment or link payment system according to the present invention.

Referring specifically to FIG. 2A , the buyer 210 requests the seller 220 to purchase goods or services.

The seller 220 requests to register the SMS payment with the mobile application platform 230 for the merchant. The merchant mobile application platform 230 requests the payment management platform 260 to generate an SMS payment link. The payment management platform 160 notifies the mobile application platform 230 for merchants by confirming information on whether the merchant is a registered merchant to the manager platform 270, and if it is a registered merchant, the payment management platform 260 is A purchase link SMS is transmitted to the purchaser 210 .

The purchaser 210 accesses the received link and inputs the card number into the web payment UI platform 235 for the purchaser. The web payment UI platform 235 for the buyer transmits the SMS transaction information request to the payment management platform 260 , and performs the transaction request to the payment service platform 240 . A payment service and a payment process with a credit card company are the same as the process of FIG. 1A . The payment management platform 260 checks the information, notifies the web payment UI platform 235 for the buyer, and registers the transaction result.

When the payment is completed, the seller 220 may pay the buyer 210 the goods.

Figure 2b shows a flow chart of the SMS payment method according to the present invention.

In step S210, the seller 220 logs in to the application installed in the terminal. At this time, it is also possible to log in through a simple password.

In step S220, after logging in, select "SMS payment" from the payment list (terminal payment, handwritten payment, SMS payment, cash receipt).

In step S230, SMS payment information is input. You can enter a product name, enter the sales amount in won, and enter an additional description.

In step S240, a shipping option may be selected. You can enter the shipping price and quantity.

In step S250 , the purchaser 210 may receive a text related to payment.

In step S260 , the purchaser 210 may check payment information and select whether to agree or not.

In step S270, the purchaser 210 proceeds with card payment.

In step S280, it is possible to check the payment details.

2c illustrates a method of registering a payment link according to the present invention.

In step S211, select "payment link" on the application.

In step S221, select "Register new" to register a payment link.

In step S231, the payment link is registered.

In step S241, it is possible to check the product list.

In step S251, the payment link may be copied from the product list.

3 shows a schematic diagram of a QR payment system according to the present invention.

Referring specifically to FIG. 3 , the buyer 310 requests the seller 320 to purchase goods or services.

The seller 320 requests product registration to the QR payment platform 330 . The purchaser 310 proceeds with a purchase request through a QR scan to the QR payment platform 330 .

The QR payment platform 330 responds to the transaction request of the purchaser 310, and proceeds with a transaction request to the web payment UI platform 340 for the purchaser, and the purchaser 310 provides a card to the web payment UI platform 340 for the purchaser. Enter the number.

A payment service and a payment process with a credit card company are the same as the process of FIG. 1A .

The web payment UI platform for the buyer 340 notifies the QR payment platform 330 of the response of the completion of the transaction after payment approval, and the QR payment platform 330 sends the transaction result to both the buyer 310 and the seller 320 . can notify.

In addition, the web payment UI platform 340 for the buyer may register the transaction result in the payment management platform 370 .

When the payment is completed, the seller 320 may pay the buyer 310 the product.

When a transaction is requested from the web payment UI for purchasers according to the present invention to the payment management platform, data forgery can be checked using HashKey.

The seller may receive a settlement of the sales amount after a certain period of time. On the other hand, in order to secure cash flow, affiliated stores may use the "immediate settlement service" that allows the settlement amount to be withdrawn immediately after payment. Through this, the merchant can secure cash flow while the payment management platform company can secure additional revenue by charging an additional fee for using the service.

For example, if the normal settlement service fee is 3 to 4%, when using the instant settlement service, the fee can be set higher at 6-7% instead of being deposited immediately.

On the other hand, the payment management platform according to the present invention may select a defective affiliated store based on the transaction cancellation rate and the civil complaint rate for each seller and terminate the affiliated store contract. For example, if the transaction cancellation rate for each seller exceeds 50% or the complaint rate exceeds 30%, the affiliated store can be selected as a defective affiliated store. Through this, the business risk of the payment management platform company can be reduced.

On the other hand, in the case of an online payment platform, when a transaction is canceled after a transaction is made and settlement is performed, the already paid settlement amount must be recovered from the affiliated store. If there is a malicious seller who only accepts settlement and cancels the transaction, the risk of not being able to properly recover the paid settlement remains. This is highly likely to act as a fatal risk for online payment platform companies.

Therefore, artificial intelligence learning can be applied based on the transaction cancellation rate, civil complaint rate, and commission rate for each seller.

An artificial neural network (ANN) may have a hierarchical structure including an input layer, an output layer, and at least one intermediate layer (or hidden layer) between the input layer and the output layer. The deep learning algorithm can derive reliable results as a result through learning to optimize the weight of the activation function between layers based on such a multi-layer structure. Here, the process of optimizing the weights includes quantizing the real weight values.

The deep learning algorithm applicable to the present invention may include a deep neural network (DNN) such as a convolutional neural network (CNN) and a recurrent neural network (RNN).

A deep neural network (DNN) is basically characterized by increasing the middle layer (or hidden layer) in the existing ANN model to improve the learning result. As an example, the above DNN is characterized in that the learning process is performed using two or more intermediate layers.

Accordingly, the computer can derive the optimal output value by repeating the process of creating a classification label by itself, distorting the space, and classifying the data.

A convolutional neural network (CNN) is characterized in that it has a structure in which a pattern of features is identified by extracting features of data, unlike a technique in which a learning process is performed by extracting knowledge from existing data. The above CNN can be performed through a convolution process and a pooling process. In other words, the above CNN may include an algorithm composed of a convolution layer and a pooling layer. Here, in the convolution layer, a process of extracting features of data (aka, a convolution process) is performed. The above convolution process is a process of examining the adjacent components of each component in the data, identifying the characteristics, and deriving the identified characteristics into one sheet. As a single compression process, the number of parameters can be effectively reduced. In the pooling layer, a process of reducing the size of the convolutional layer (so-called pooling process) is performed. The above pooling process can reduce the size of data, cancel noise, and provide consistent features in minute details. As an example, the CNN above can be used in various fields such as information extraction, sentence classification, and face recognition.

A recurrent neural network (RNN) is a type of artificial neural network specialized for repetitive and sequential data learning, and is characterized by having a cyclic structure inside. The above RNN uses the above cyclic structure to apply weights to the past learning contents and reflect them in the present learning, thereby enabling the connection between the present learning and the past learning and has the characteristic of being dependent on time. The above RNN is an algorithm that solves the limitations of the existing continuous, iterative, and sequential data learning, and can be used to identify speech waveforms or identify front and back components of text.

For example, when the nodes of the input layer and/or the intermediate layer are transferred to the next step, the value of the weight of the node of each layer may be quantized.

However, these are only examples of specific deep learning techniques applicable to the present invention, and other deep learning techniques may be applied to the present invention according to embodiments.

The system for inferring the degree of similarity using an artificial neural network technique with respect to the target settlement risk according to the present invention can generate a recommendation model by using it as input data of a deep neural network algorithm.

According to the present invention, in the process of selecting defective affiliated stores, the transaction cancellation rate, civil complaint occurrence rate, and fee rate for each seller are input and stored in the storage, and the transaction cancellation rate, civil complaint occurrence rate and commission rate by seller are transmitted to the deep learning server, and the input from the server By analyzing the unstructured data, the characteristics are systematically divided into a certain classification, and the systematically divided set and the training data set for the transaction cancellation rate, civil complaint rate, and commission rate by seller are set as the training data set, and the unsupervised method ( a data ETL (Extract, Transformation, Loading) module that learns patterns using an unsupervised feature extraction deep learning method and purifies data for analysis from text unstructured data; a preprocessing module that performs stem extraction and semantic analysis from the refined data; a feature extraction module for extracting features by performing language analysis from the preprocessed data; a data standardization module that maps the extracted characteristics to standard terms for each transaction cancellation rate, civil complaint rate, and commission rate by seller; And the standard transaction term, transaction cancellation rate by seller, complaint rate and transaction cancellation rate by seller generated by characteristics of fee rate, complaint rate and fee rate automatic learning built through deep learning that reflects case data The diagram-based Unsupervised Deep Feature Learning method uses SDA (Stack of Denoising Autoencoders), SDA has the same dimension as the input layer and the output layer, and SDA is a hidden layer between the input and output layers. In SDA, the encoding process proceeding from the input layer to the hidden layer and the decoding process proceeding from the heat layer to the output layer are performed in SDA, and features hidden in the input data are encoded in the encoding process. It can be configured to extract the form and reconstruct hidden features in the decoding process.

Even if noise is included in the input data through SDA, noise included in the input data is removed through the process of restoring encoded hidden features because the number of hidden layers between the input and output layers is smaller than the number of input and output layers. By doing so, learning is carried out so that the difference between input data and output data is minimized, and the feature representation data generated through pre-training learning that is converted into a vector through SDA is applied to the characteristics of transaction cancellation rate, civil complaint rate, and commission rate by seller. A system for generating a recommendation model is provided by using it as input data of a Deep Neural Network algorithm to predict the rating score of raw materials and the transaction cancellation rate, civil complaint rate, and commission rate for each seller. For example, the transaction cancellation rate for each seller, the civil complaint rate, the commission rate, the rancidity of raw materials, and the light stability can be used as factors in artificial intelligence. On the other hand, data mining using accumulated data including the movement of customers in the market and payment history in the market research of transaction cancellation rate, civil complaint rate, and commission rate by seller and various texts including keywords, inquiry contents, and documents searched on the web It is also possible to guide learning by selecting data as a factor of the deep layer.

Among various optimization techniques for deep learning model computation, quantization is widely used. Some forms of optimization can reduce latency, the amount of time it takes to run a single inference with a given model, by reducing the amount of computation required to run inference using the model, which can also affect the power consumption of the user's device. have.

Quantization can be used to reduce latency and power consumption in a way that simplifies calculations that occur during inference, potentially reducing accuracy. Specifically, quantization reduces the precision of a number used to represent a given model's weight and activation function value or input value, thereby reducing the model size and improving the computational speed in the inference or learning process. For example, quantization can contribute to reducing the computation cost of a node by converting the weight of a node expressed as a 32-bit floating point into an 8-bit integer.

For example, in TensorFlow Lite, an open source software for machine learning, it is known that the following types of post-learning quantization and quantization-aware learning techniques are being used.

In addition, the payment details of the online payment service are not stored on the server, but are stored through a computer network-based technology that secures the integrity and trust of the transaction records by a digitized public distributed ledger. can In other words, you can use a blockchain, a P2P network layer based on the gossip protocol, a consensus algorithm that agrees on common data between distributed nodes, and (3) a Merkle tree that stores the agreed state. It is composed of a data structure in the form of a Merkle tree, and (4) a digital encryption algorithm to ensure the identity of the account and the security of recorded information. Blockchain can be said to be an append-only infinite state machine that combines the above four elements and uses transactions to change state. A blockchain includes N blocks, each block includes a block header and a list of transactions, and the block header of a block includes a block number indicating the number of the block; and a parent hash including a hash value of the block header of the previous block, the parent hash configured to concatenate the block and the previous block based on the hash value of the block header of the previous block; a state root including state information of each block; and a transaction root including newly created transactions in each block, and the state root, name root, token root, and balance root may have a Merkle tree structure. The name root uses an account and an address as key values, and the token root uses the definition ID of the token of each node device and the hash value of the transaction as the key value. The definition ID includes the account's network ID, name, symbol, administrator, and total balance, and the transaction root may use the hash value of each transaction as a key value. The method for storing transaction details through the above block chain includes the steps of adding a new node device to a block chain consisting of a plurality of node devices; verifying, in the verification node device, whether or not the block creator's signature for the new block is valid based on the configuration file; if the verification of the new block is verified as valid, receiving, at the new node device, information on the latest block from the neighboring node device; and when the new node device receives a request for a new transaction, based on the latest block information, determining whether the UTXO (Unspent Transaction Outputs) to be used by the new transaction requested by the new node device is legal or not. In addition, the transaction details of the online payment service through the block chain may be configured to be distributed and stored in affiliated stores.

Additionally, the computer program according to the present invention may be stored in a computer-readable recording medium in combination with a computer to execute the various hardware accelerator control methods described above.

The above-mentioned program is a computer language such as C, C++, JAVA, machine language, etc. that the processor (CPU) of the computer can read through the device interface of the computer in order for the computer to read the program and execute the above methods implemented as the program. It may include a code (Code) coded as . Such code may include functional code related to functions defining functions necessary to execute the above methods, etc. can do. In addition, this code may further include additional information necessary for the processor of the computer to execute the above functions or code related to memory reference for where the media should be referenced in internal or external memory of the computer (address address). have. In addition, when the processor of the computer above needs to communicate with any other computer or server located remotely in order to execute the above functions, the code uses the communication module of the computer to determine how to communicate with any other computer or server remotely. It may further include a communication-related code for whether to communicate and what information or media to transmit and receive during communication.

The steps of the method or algorithm described in relation to the embodiment of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or implemented by a combination thereof. A software module may include random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or It may reside in any type of computer-readable recording medium well known in the art to which the present invention pertains.

As mentioned above, although embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art to which the present invention pertains can realize that the present invention can be embodied in other specific forms without changing its technical spirit or essential features. you will be able to understand

Accordingly, the embodiments disclosed in this document are for explanation rather than limiting the technical ideas disclosed in this document, and the scope of the technical ideas disclosed in this document is not limited by these embodiments. The scope of protection of the technical ideas disclosed in this document should be interpreted by the claims below, and all technical ideas within the equivalent range should be interpreted as being included in the scope of the present document.

Claims (5)

An online payment service providing method performed in an environment including a buyer side communication terminal, a seller communication terminal, a payment management platform server, and a payment server,
requesting registration of SMS payment to the mobile application platform for merchants by the merchant communication terminal;
requesting the payment management platform server to generate an SMS payment link by the seller communication terminal, the request for generating the payment link includes information of the communication terminal on the buyer side;
checking, by the payment management platform server, information on whether the seller communication terminal is a registered affiliate store to the manager platform;
transmitting, by the payment management platform server, a purchase link SMS to the purchaser-side communication terminal when the seller communication terminal is a registered affiliate;
accessing the received link by the purchaser-side communication terminal receiving the purchase link SMS, and inputting the purchaser's card number into a web payment UI platform for purchasers;
transmitting, by the web payment UI platform for purchasers, an SMS transaction information request including the purchaser's card number to the payment management platform server;
requesting payment to the payment server by the payment management platform server receiving the SMS transaction information request; and
When the payment is completed by receiving a response to the payment by the payment server, the payment management platform server notifies the payment completion result to the web payment UI platform for the buyer and registering the transaction result in the manager platform
including,
The method of providing the online payment service,
Selecting, by the seller communication terminal, a settlement method including a general settlement method and a direct settlement method
further comprising,
The step of selecting, by the seller communication terminal, a settlement method including a general settlement method and a direct settlement method,
depositing an amount excluding the first fee from the payment amount to the seller 5 days after the payment date when the general settlement method is selected by the seller communication terminal; and
When the direct settlement method is selected by the seller communication terminal, an amount excluding the second fee from the payment amount is directly deposited to the seller on the payment date
including,
In order for the seller to secure cash flow, the second fee when the direct settlement method is selected is determined to be 6 to 7% higher than the first fee in the general settlement method,
The payment management platform, when receiving an online payment request, is configured to verify data forgery using a hashkey,
The payment management platform is configured to select defective merchants based on the transaction cancellation rate and civil complaint rate for each merchant and automatically notify the merchant contract termination processing to the defective merchant,
The payment details of the online payment service are stored by a digitized public distributed ledger,
The public distributed ledger is a blockchain and is an append-only infinite state machine that uses transactions to change state,
The block chain includes N blocks, each block includes a block header and a transaction list, and the block header of the block includes a block number indicating the number of the block; and a parent hash including a hash value of the block header of the previous block, the parent hash configured to concatenate the block and the previous block based on the hash value of the block header of the previous block; a state root including state information of each block; and a transaction root including newly created transactions in each block, wherein the state root, name root, token root, and balance root are Merkle Tree structures,
The name root uses an account and an address as a key value, and the token root uses a token definition ID of each node device and a hash value of a transaction as a key value. wherein the definition ID includes the account's network ID, name, symbol, manager, and total balance, and the transaction root is used as the key value of each transaction's hash value,
The method is
adding a new node device to a blockchain composed of a plurality of node devices; verifying, in the verification node device, whether or not the block creator's signature for the new block is valid based on the configuration file;
if the verification of the new block is verified as valid, receiving, at the new node device, information on the latest block from the neighboring node device; and
When the new node device receives a request for a new transaction, based on the latest block information, determining whether UTXO (Unspent Transaction Outputs) to be used by the new transaction requested by the new node device is legal or not
further comprising,
The transaction details of the online payment service through the block chain are configured to be distributed and stored in affiliated stores,
The method is
In the process of selecting bad affiliates, the transaction cancellation rate, civil complaint rate, and commission rate by seller are input and stored in the storage, and the transaction cancellation rate, civil complaint rate and commission rate by seller are transmitted to the deep learning server, and the atypical data input from the server is analyzed. systematizing and dividing the characteristics into a certain classification;
It is set as a training data set for systematically divided sets and transaction cancellation rate, civil complaint rate, and commission rate by seller, and uses an unsupervised feature extraction deep learning method for the training data set. learning the pattern;
Refining data for analysis from text unstructured data;
performing stem extraction and semantic analysis from the purified data;
performing linguistic analysis from the preprocessed data to extract features;
mapping the extracted characteristics to standard terms for each transaction cancellation rate, civil complaint rate, and commission rate by seller;
Automatic learning stage built through deep learning that reflects standard transaction terms and transaction cancellation rate by seller, transaction cancellation rate by seller, complaint rate and commission rate case data generated by characteristics of complaint rate and commission rate
further comprising,
The unsupervised deep feature learning method uses SDA (Stack of Denoising Autoencoders),
In the SDA, the dimensions of the input layer and the output layer are the same, the number of hidden layers between the input and output layers is smaller than the number of input and output layers, and the encoding process proceeding from the input layer to the hidden layer in the SDA; A decoding process proceeding from the hidden layer to the output layer is performed, and in the encoding process, features hidden in the input data are extracted in an encoded form, and the features hidden in the decoding process are restored again.
When noise is included in the input data through the SDA, the noise included in the input data through the process of restoring encoded hidden features because the number of hidden layers between the input and output layers is smaller than the number of input and output layers Learning is carried out so that the difference between input data and output data is minimized by removing A recommendation model is generated using the input data of the Deep Neural Network algorithm to predict the characteristics of the transaction cancellation rate, civil complaint rate, and fee rate and the rating score of raw materials.
In the online payment service providing method, the input data of the deep neural network is data mining and web using accumulated data including transaction cancellation rate, civil complaint rate, and commission rate by seller, the movement of customers in the market, and payment details in the market research. contains various text data including keywords, inquiry contents, and documents retrieved from
By reducing the weight of the model of the deep neural network and the precision of numbers used to represent activation function values or input values, the model size of the deep neural network is reduced, and the calculation speed of the deep neural network is improved in the inference or learning process. In the model, the weights of nodes expressed as 32-bit floating-point are converted to 8-bit integers,
When the transaction cancellation rate for each seller exceeds 50%, the online payment service providing method is configured to select the affiliated store as a bad affiliate and automatically notify the bad affiliate of the affiliated store contract termination process. delete delete delete delete

Images