KR20230160612A - Flower wholesale and retail management service based on business to customer and business to business - Google Patents

Abstract

A B2C and B2B based flower wholesale and retail management service provision system is provided, a user terminal for ordering at least one type of flower product, receiving guidance on ordering and delivery of flower products, and transmitting reviews and ratings, and at least one type of flower product. Registering at least one flower gardener terminal and at least one flower gardener terminal that places orders for products, receives and places orders and deliveries of flower products, uploads evaluations of ordering services between flower gardeners, and registers at least one flower gardener terminal, and registers at least one flower gardener terminal. A register that divides terminals into orders, orders, and sub-orders and creates a database, an order management department that lists the order data of the user terminal in the order details when the order is received from at least one flower shop terminal, and order details are collected from at least one flower shop terminal. order management department that updates the order details, an information department that guides the user to the user terminal if order reception and delivery processing is uploaded from at least one flower shop terminal, and ordering information if evaluation data is uploaded from the flower shop terminal that uploaded the order details. It includes a management service providing server including an evaluation unit that maps and stores the details with the flower shop terminal that received the order.

Description

Ｂ２Ｃ and ＢＢＢ based flower wholesale and retail management service provision system {FLOWER WHOLESALE AND RETAIL MANAGEMENT SERVICE BASED ON BUSINESS TO CUSTOMER AND BUSINESS TO BUSINESS}

The present invention relates to a B2C and B2B based flower wholesale and retail management service provision system. When an order is received from a user and the order details are received, a platform is provided to broker the order details to accept and deliver the order.

The distribution of flower products has developed into a unique form, unlike other product distribution channels. The development of information technology and the Internet has not simplified the distribution channel by connecting producers and consumers directly, but rather strengthened the influence of flower wholesalers and retailers by streamlining the distribution channel and activating transactions. Due to the nature of flower products, it was difficult to deliver them via courier, so the volume of transactions between flower retailers increased and associations that brokered products emerged. In addition, the distribution channel used to be a distribution structure in which producing farms supplied products through auctions or wholesale stores and delivered them to retail stores, but large retail stores began to contract with producers to receive supplies directly from farmers. Flower products are distributed through two places: the Agro-Fisheries Trade Corporation's flower market and the flower wholesale and retail market. At the Yangjae flower market, flower products are supplied through auctions, and middlemen who can participate in the auction conduct the auction using an automated auction system. .

At this time, a method for brokering and managing flower wholesale and retail distribution was researched and developed. In relation to this, the prior art, Korea Patent Publication No. 2020-0065548 (published on June 9, 2020) and Korea Patent Publication No. 2020-0044421 (2020) (Published on April 29, 2008), when order information is transmitted from the order terminal, it is transmitted to the member store terminal, and the type and quantity of flowers are managed, and the user, who is the customer, directly selects the flower shop terminal that performs the order reception and places the order. We provide a direct transaction order brokerage platform between users and flower gardeners to place orders, and when ordering amount, photo, delivery time, and delivery availability information are registered from the flower gardener's terminal, the user can search for the painter on the terminal and place an order. A system is provided, and a configuration for transmitting the order confirmation and delivery completion messages to the user terminal upon receiving the order confirmation and delivery completion messages from the Hwawonsa terminal is disclosed.

However, the former and latter configurations only disclose the B2C configuration and do not disclose the configuration of transaction processes between member companies such as B2B brokerage process, order placement management, and settlement management. In flower distribution, there is a distribution process between flower farms, auction houses, associations, and wholesalers. If this is not processed, the functions for account receivables and product inventory management will not be properly reflected in the information system, and automation will occur without establishing transaction and work processes. When an information system is introduced as a concept, the workload resulting from the inconsistency between the information system and the work process only increases. Accordingly, by intermediating between ordering and ordering painters and performing ordering management, sales can be handled transparently through immediate processing and settlement of trade receivables, and the quality of products and services can be managed by establishing a system to evaluate ordering and ordering painters. Platform research and development is required.

One embodiment of the present invention is based on B2C (Business-to-Consumer), which receives orders from the user terminal of a user who is a customer and delivers them to the customer, and B2B (Business-to-Business), which brokers and manages between suppliers and orderers. ), a B2C- and B2B-based florist that can transparently process sales through immediate processing and settlement of trade receivables, and manage the quality of products and services by establishing a system to evaluate flower gardens that place orders. A wholesale and retail management service provision system can be provided. However, the technical challenge that this embodiment aims to achieve is not limited to the technical challenges described above, and other technical challenges may exist.

As a technical means for achieving the above-described technical problem, one embodiment of the present invention includes a user terminal for ordering at least one type of flower product, receiving guidance on ordering and delivery of the flower product, and transmitting reviews and ratings; Registering at least one flower shop terminal and at least one flower gardener terminal that places orders for at least one type of flower product, receives and places orders and deliveries of flower products, and uploads evaluations of the order service between flower gardeners; , a register that divides at least one flower shop terminal into orders, orders, and received orders and forms a database, an order management unit that lists the order data of the user terminal in the order details when the order is received from at least one flower shop terminal, and at least one flower shop terminal. An order management department that updates the order details when order details are received from a terminal; an information department that guides the user to the user terminal when order reception and delivery processing is uploaded by at least one flower shop terminal; and an evaluation from the flower shop terminal that uploaded the order details. When data is uploaded, it includes a management service providing server that includes an evaluation unit that maps and stores the order details with the flower shop terminal that received the order.

According to one of the above-described means for solving the problems of the present invention, B2B is a B2B system that brokers and manages orders between buyers and sellers based on B2C (Business-to-Consumer), which receives orders from the user terminal of a user who is a customer and delivers them to the customer. (Business-to-Business) management process is provided, sales can be processed transparently through immediate processing and settlement of trade receivables, and the quality of products and services can be managed by establishing a system to evaluate potential buyers. .

Figure 1 is a diagram for explaining a B2C and B2B based flower wholesale and retail management service provision system according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating a management service providing server included in the system of FIG. 1.
Figures 3 and 4 are diagrams for explaining an embodiment in which a B2C and B2B based flower wholesale and retail management service is implemented according to an embodiment of the present invention.
Figure 5 is an operation flowchart illustrating a method of providing B2C and B2B-based flower wholesale and retail management services according to an embodiment of the present invention.

Below, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention in the drawings, parts that are not related to the description are omitted, and similar parts are given similar reference numerals throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected," but also the case where it is "electrically connected" with another element in between. . In addition, when a part is said to "include" a certain component, this does not mean excluding other components unless specifically stated to the contrary, but may further include other components, and one or more other features. It should be understood that it does not exclude in advance the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

The terms "about", "substantially", etc. used throughout the specification are used to mean at or close to that value when manufacturing and material tolerances inherent in the stated meaning are presented, and are used to enhance the understanding of the present invention. Precise or absolute figures are used to assist in preventing unscrupulous infringers from taking unfair advantage of stated disclosures. The term “step of” or “step of” as used throughout the specification of the present invention does not mean “step for.”

In this specification, 'part' includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more pieces of hardware, and two or more units may be realized using one piece of hardware. Meanwhile, '~ part' is not limited to software or hardware, and '~ part' may be configured to reside in an addressable storage medium or may be configured to reproduce one or more processors. Therefore, as an example, '~ part' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and 'parts' may be combined into a smaller number of components and 'parts' or may be further separated into additional components and 'parts'. Additionally, components and 'parts' may be implemented to regenerate one or more CPUs within a device or a secure multimedia card.

In this specification, some of the operations or functions described as being performed by a terminal, apparatus, or device may instead be performed on a server connected to the terminal, apparatus, or device. Likewise, some of the operations or functions described as being performed by the server may also be performed in a terminal, apparatus, or device connected to the server.

In this specification, some of the operations or functions described as mapping or matching with the terminal mean mapping or matching the terminal's unique number or personal identification information, which is identifying data of the terminal. It can be interpreted as

Hereinafter, the present invention will be described in detail with reference to the attached drawings.

Figure 1 is a diagram for explaining a B2C and B2B based flower wholesale and retail management service provision system according to an embodiment of the present invention. Referring to FIG. 1, the B2C and B2B based flower wholesale and retail management service providing system 1 may include at least one user terminal 100, a management service providing server 300, and at least one florist terminal 400. You can. However, since the B2C and B2B based flower wholesale and retail management service providing system 1 of FIG. 1 is only an embodiment of the present invention, the present invention is not limitedly interpreted through FIG. 1.

At this time, each component of FIG. 1 is generally connected through a network (Network, 200). For example, as shown in FIG. 1, at least one user terminal 100 may be connected to the management service providing server 300 through the network 200. In addition, the management service providing server 300 may be connected to at least one user terminal 100 and at least one Hwawonsa terminal 400 through the network 200. Additionally, at least one Hwawonsa terminal 400 may be connected to the management service providing server 300 through the network 200.

Here, the network refers to a connection structure that allows information exchange between each node, such as a plurality of terminals and servers. Examples of such networks include a local area network (LAN) and a wide area network (WAN). Wide Area Network, Internet (WWW: World Wide Web), wired and wireless data communication network, telephone network, wired and wireless television communication network, etc. Examples of wireless data communication networks include 3G, 4G, 5G, 3rd Generation Partnership Project (3GPP), 5th Generation Partnership Project (5GPP), Long Term Evolution (LTE), World Interoperability for Microwave Access (WIMAX), and Wi-Fi. , Internet, LAN (Local Area Network), Wireless LAN (Wireless Local Area Network), WAN (Wide Area Network), PAN (Personal Area Network), RF (Radio Frequency), Bluetooth network, NFC ( It includes, but is not limited to, Near-Field Communication (Near-Field Communication) network, satellite broadcasting network, analog broadcasting network, and DMB (Digital Multimedia Broadcasting) network.

In the following, the term at least one is defined as a term including singular and plural, and even if the term at least one does not exist, each component may exist in singular or plural, and may mean singular or plural. This should be self-explanatory. In addition, whether each component is provided in singular or plural form may be changed depending on the embodiment.

At least one user terminal 100 may be a terminal of a customer, that is, a user, who orders and pays for flower products using a web page, app page, program, or application related to B2C and B2B-based flower wholesale/retail management service.

Here, at least one user terminal 100 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc. At this time, at least one user terminal 100 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one user terminal 100 is, for example, a wireless communication device that guarantees portability and mobility, and includes navigation, personal communication system (PCS), global system for mobile communications (GSM), personal digital cellular (PDC), PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband Internet) ) It may include all types of handheld-based wireless communication devices such as terminals, smartphones, smartpads, and tablet PCs.

The management service providing server 300 may be a server that provides a B2C and B2B based flower wholesale/retail management service web page, app page, program, or application. In addition, the management service providing server 300 may be a terminal that receives and registers categories such as order receipt, order placement, and receipt of order from at least one flower gardener terminal 400. In addition, the management service providing server 300 uploads the order reception from the user terminal 100 from the flower shop terminal 400 that places the order, uploads it to the order list, and places the order in the flower shop terminal 400 that places the order. Once received, it may be a server that changes the status and updates the status of order reception, product preparation, delivery preparation, and delivery completion in real time. In addition, the management service providing server 300 receives and registers ratings and reviews when the user terminal 100 confirms receipt or makes a purchase decision, and the hwawonsa terminal 400 that places an order and the hwawonsa terminal 400 that places an order. (400) It may be a server that allows mutual evaluation. Additionally, the management service providing server 300 may be a server that shares real-time details of accounts receivable and provides a withdrawal service to enable settlement on a weekly basis.

Here, the management service providing server 300 may be implemented as a computer that can connect to a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc.

At least one florist terminal 400 may be a florist terminal that places, receives, and receives orders using web pages, app pages, programs, or applications related to B2C and B2B-based flower wholesale/retail management services.

Here, at least one Hwawonsa terminal 400 may be implemented as a computer capable of accessing a remote server or terminal through a network. Here, the computer may include, for example, a laptop equipped with a navigation system and a web browser, a desktop, a laptop, etc. At this time, at least one Hwawonsa terminal 400 may be implemented as a terminal capable of accessing a remote server or terminal through a network. At least one Hwawonsa terminal 400 is, for example, a wireless communication device that guarantees portability and mobility, and is used for navigation, personal communication system (PCS), global system for mobile communications (GSM), and personal digital cellular (PDC). , PHS (Personal Handyphone System), PDA (Personal Digital Assistant), IMT (International Mobile Telecommunication)-2000, CDMA (Code Division Multiple Access)-2000, W-CDMA (W-Code Division Multiple Access), Wibro (Wireless Broadband) It may include all types of handheld-based wireless communication devices such as Internet) terminals, smartphones, smartpads, and tablet PCs.

Figure 2 is a block diagram for explaining the management service providing server included in the system of Figure 1, and Figures 3 and 4 are an implementation of the B2C and B2B based flower wholesale and retail management service according to an embodiment of the present invention. This is a drawing to explain an example.

Referring to FIG. 2, the management service providing server 300 includes a registration unit 310, an order management unit 320, an order management unit 330, an evaluation unit 340, a fact verification unit 350, and an interactive unit 360. , it may include a real-time sales confirmation unit 370, a weekly settlement unit 380, a certificate issuance unit 390, a notification obligation performance unit 391, and an administrator mode unit 393.

The management service providing server 300 or another server (not shown) operating in conjunction with an embodiment of the present invention operates on a B2C and B2B basis with at least one user terminal 100 and at least one Hwawonsa terminal 400. When transmitting a flower wholesale/retail management service application, program, app page, web page, etc., at least one user terminal 100 and at least one florist terminal 400 are configured to transmit a B2C and B2B-based flower wholesale/retail management service application, program, etc. , you can install or open app pages, web pages, etc. Additionally, a service program may be run on at least one user terminal 100 and at least one Hwawonsa terminal 400 using a script executed in a web browser. Here, a web browser is a program that allows the use of web (WWW: World Wide Web) services and refers to a program that receives and displays hypertext written in HTML (Hyper Text Mark-up Language), for example, Netscape. , Explorer, Chrome, etc. Additionally, an application refers to an application on a terminal and includes, for example, an app running on a mobile terminal (smartphone).

Referring to FIG. 2, the registration unit 310 may register at least one flower gardener terminal 400 and divide the at least one flower gardener terminal 400 into a database by dividing it into orders received, orders placed, and received orders. At this time, the ordering company may be a flower shop that receives the order received from the user terminal 100 placed by the ordering company and prepares and delivers the product. The ordering company may be a terminal of the ordering company that receives an order from a user who is a customer and requests product preparation and delivery, that is, placing an order. A flower shop that is capable of receiving and placing orders may be of a certain size or may be a flower shop that can handle both orders and orders. At this time, in one embodiment of the present invention, the contracting company and the ordering company are all collectively referred to as flower gardeners without distinction, and their roles are distinguished by adding ordering or ordering, etc. according to their roles.

The order management unit 320 may list the order data of the user terminal 100 in the order details when the order is received from at least one flower shop terminal 400. The order management unit 330 may update the order details when an order is received from at least one flower shop terminal 400. At least one flower shop terminal 400 can place orders for at least one type of flower product, and receive and place orders for flower product delivery. By dividing orders into unreceived details, rejected order details, and details with recent status changes, ordering companies, ordering companies, and platform managers can quickly identify each status change situation and respond to the situation.

The guidance unit 340 may provide guidance to the user terminal 100 when order reception and delivery processing are uploaded from at least one flower shop terminal 400. The user terminal 100 can order at least one type of flower product, receive guidance on ordering and delivery of the flower product, and transmit reviews and ratings.

When evaluation data is uploaded from the Hwawon company terminal 400 that uploaded the order details, the evaluation unit 350 may map the order details with the Hwawon company terminal 400 that received the order and store it. At least one flower gardener terminal 400 can upload an evaluation of the service ordering between flower gardeners. Evaluation data can be divided into items for product quality, delivery time, and overall service and stored.

When a photo of a flower product is uploaded from the user terminal 100, the fact confirmation unit 360 measures the similarity between the photo of the flower product and the photo of the already registered flower product, and the flower shop terminal that uploaded the order details ( 400) can be compared with the evaluation data. In general, statistical process control (SPC) procedures have been used in various fields such as design, service, and sales as well as manufacturing processes. The field where statistical process management is most widely used is the manufacturing field, and control charts are the most frequently used tool to manage processes efficiently. In general, the quality characteristics of the product to apply the control chart are specified, measured with the naked eye or using a measuring instrument, and the process is managed using these measured values. These methods may take a lot of time to be used in practice, or in some cases, it may be difficult to accurately determine the condition of the product, and in the case of destructive testing, etc., may involve a lot of cost. Accordingly, in recent industrial production processes, machine vision systems (MVS) are used to provide information on the geometric structure of the product, surface defects, surface finish, and other product quality characteristics. There are a lot.

Accordingly, one embodiment of the present invention is an object in a photo uploaded as a flower product, an object in a photo taken just before shipment at the flower garden terminal 400, which is the contract recipient, and an object uploaded by the user terminal 100. Differences between photos can be compared using MVS, and if there are differences such as different types of flowers, reduced numbers, or changes in auxiliary materials, it is possible to check whether the above-mentioned evaluation is true. User satisfaction is subjective, but at least it can be measured objectively whether it is similar to the product announced for sale. For example, if a photo with 20 carnations is uploaded, it must meet at least a 10% margin of error, but if the number is reduced to 5, for example, no matter how satisfied the user is by giving a rating of 5, the evaluation value must be adjusted. It can act as a factor. At this time, MVS analyzes the characteristics of objects based on images, including an image capture step, an image analysis step, and tasks performed based on image analysis, such as noise reduction, image compression, Contrast enhancement, etc. can be performed.

<Flower Product Recognition>

Generally, flower baskets or bouquets are products that contain a mixture of various flowers. At this time, the similarity can be confirmed by comparing the type, number, and color of flowers included in the flower product introduction image with the type, number, and color of flowers included in the image uploaded by the user of the flower product received. At this time, in order to identify the type of flower, the object must first be identified. In order to distinguish multiple objects in an image containing multiple objects, such as a bouquet or flower basket, a segmentation model or object detection model is used. Available. These models have common limitations when applied directly. First, they require a large data set for learning, and second, each time a new plant is added, it is inefficient to recollect and retrain the new plant data set. It means doing it. Accordingly, an embodiment of the present invention can use an object detection model that does not distinguish between classes for object detection and a class search model for object classification.

First, in the object detection model that does not distinguish between classes, a camera screen containing objects is received as input and all objects in the screen are detected as one class. In the class search model, each detected object image is received and its class is classified by comparing it with a small number of reference images. This process was previously well known as the Retrieval Process. When using this, since it does not distinguish between first classes, it is possible to detect even untrained objects. Using this model, semi-automatic data set generation is possible and saves time in building the initial training data set. Second, because a class search model is used, even untrained objects can be classified. Therefore, even if a new object is added, there is no need to add data or retrain, and it is enough to add a few simple reference images.

In order to explain the above-described configuration, the basic concept behind it will be briefly explained below.

<Basic concept>

Research on recognizing and classifying objects can be divided into two categories: segmentation and object detection. Segmentation is the process of classifying pixels in an image, and object detection is the process of recognizing the object area using a bounding box and classifying the objects within the box. Both approaches showed successful results in recognition and classification of learned object classes when there was sufficient data. However, both did not perform well on objects of different classes than the training data. For these objects, additional data collection and retraining are required. Recently, in order to solve this problem, a method has been researched and developed to select and place unknown objects using image search without re-learning them. This method compares the object's reference images (Reference Images) to the existing object. and recognize new objects, and as a result, can pick up and match new objects when there are obstacles in the way. However, this method has the limitation of having to select, photograph, and classify objects one by one, so it is not efficient when taking pictures.

The goal of image search is to find the image that is most similar to a given query image among reference images. This is because the query and reference images are not always included in the learned class, so identifying the similarity between the two images is important. One of the most useful approaches for this is distance learning (metric learning). If an appropriate embedding vector for an image can be found through distance learning, the corresponding embedding vectors for similar images are located close together. This can be used to perform image retrieval tasks and can classify any image only given a reference image of the class.

One of the well-known loss functions used in distance learning is Triplet Loss. Triple loss minimizes the distance between same classes and maximizes the distance between different classes. A triplet tuple in the data set consists of an anchor, a positive sample that is one of the samples of the same class, and a negative sample that is one of the samples of a different class. Therefore, the total number of data increases in proportion to the cube of the number of samples. In other words, it is important to sample only useful triple tuples. To solve this sampling problem, semi-hard sampling and distance weighted sampling were introduced. Recently, the problem was solved with a small number of proxies that approximate the original data set. This method uses the Neighborhood Component Analysis (NCA) loss function to optimize the proxy. Furthermore, the results are further improved by using the normalized Softmax loss instead of the NCA loss.

<Multiple object distinction>

To distinguish multiple objects, when an image containing plants including various types of flowers on one screen is input to an object detection model that does not distinguish between classes, bounding box information for all plants in the photo is output. Based on this bounding box information, images of plants inside the photo are cut out and input into the class search model. The class search model embeds each plant image, compares the distance with vectorized references using the same embedding model, and classifies it into the class of the reference with the closest distance among the references. At this time, even if the class learned during learning and the class of the reference do not match, the plants detected in the photo can be classified into the reference class with the closest distance.

<Object detection model without class distinction>

The class-agnostic object detection model can be based on the Tiny version of YOLO v3, one of the well-known object detection networks. This has the advantage of being relatively faster, more accurate, and lighter than other object detection models. When an image is input into the model, a V vector with three anchors for a grid (cell) of size 26 × 26 is obtained as follows.

Here, xk, yk, wk, hk, ck, and vk are the x value, y value, width, height, confidence level, and class vector for the kth anchor, respectively. Since the goal of this model is to estimate the bounding box of plants regardless of their class, all plants are labeled with one class. That is, the length of all v vectors is 1. This removes the classification loss from the loss function of the YOLO v3 Tiny network, and thus the model is trained by the loss for bounding boxes and confidence. As a result, a class-agnostic object detection model is trained with a focus on accurate estimation of bounding boxes for all products.

<Class Search Model>

The class detection model is based on the DenseNet-121 model and is initialized with weights pre-trained using the ImageNet dataset. When each product image obtained from a class-insensitive object detection model is sequentially input to the class search model, a vector of size 1024 used for loss function evaluation is output. The learning process of this model can be based on the Softmax-NCA method, which has recently been evaluated as the state-of-the-art in the image retrieval field. The core of this method is Softmax-NCA loss, which is a loss function that combines the existing NCA loss and Softmax concept. The proxy concept is used to train efficiently when training a model with Softmax-NCA loss. Under the proxy concept, Euclidean distance can be used to express the distance between two vectors, and the final loss function L is given in Equation 2 below.

Here, x is the target image vector, py and pz are positive and negative proxy vectors for x, respectively, and σ is a parameter for temperature scaling. After training of the class search model is completed, classification work using the class search model is performed using the list of given reference classes. For each reference class in the list, a small number of reference images are selected to become reference images representing that class. Then, all selected reference images are converted to vectors through a class search model. After that, each time a query image is input, the Euclidean distance between the vector of the query image and the vectors of the reference images is calculated. Finally, the closest reference image is found and the class to which this reference image corresponds is assigned as the class of the query image.

<Semi-automatic data set creation>

This process can be designed to save time for generating training data sets for both models. First, in the initial state without learning data, bounding boxes for several plants must be annotated, and each plant's class must be labeled by a human. Afterwards, a class-insensitive object detection model and a class search model are trained with a small amount of data. This model allows new data to be created semi-automatically. As new data comes in, you can use the trained models to create a draft of the object's bounding box annotation and class label. The object detection model detects objects without class distinction, and the class search model classifies the class by comparing the distance between the object's vector and the image vector in the reference. To minimize inaccurate data, only bounding boxes with a certain level of confidence are used to generate data for class-insensitive object detection. Similarly, for class search models, the distance between the input image vector and the expected result image vector is used as the confidence level. As a result, this process effectively reduces the work that people and data sets must perform, allowing deep learning models to be trained in a short period of time.

When evaluation data is uploaded from the Hwawon company terminal 400 that received the order details, the interactive unit 360 can store the order details by mapping them with the Hwawon company terminal 400 that uploaded the order details.

When managing sales details in at least one painter terminal 400, the real-time sales confirmation unit 370 outputs the sales amount for real-time orders in the form of a balance for each painter account of each painter terminal 400. can do. The weekly settlement unit 380 can withdraw and settle the sales amount on a weekly basis from at least one flower shop terminal 400. The certificate issuing unit 390 may automatically issue a cash receipt for orders placed between at least one Hwawonsa terminal 400.

If there is a change in the price of flowers included in at least one flower product, the notification obligation performance department 391 can update in real time notification of the change in type and increase or decrease in quantity due to the change in flower price. If there is a change or increase or decrease in auxiliary materials according to the inventory of auxiliary materials included in the flower product, the notification obligation performance department 391 can update the notification of the change in auxiliary materials in real time. Since flower delivery began, the most reported cases of consumer damage are cases where the variety or type of flowers has changed or the number has decreased. If the flowers in question are sold out or run out at the florist receiving the order for flower delivery, they have no choice but to deliver with other flowers, or if only high-quality flowers of the same type are left, the number is reduced, and they are not delivered without prior notice to the consumer. Consumer damage will increase rapidly.

Korea's Act on Fair Labeling and Advertising defines four types of unfair labeling and advertising practices: false and exaggerated labeling and advertising, deceptive labeling and advertising, unfairly comparative labeling and advertising, and defamatory labeling and advertising. I am judging. Deceptive labeling and advertising practices that involve concealing or minimizing facts are expected to give rise to more and more cases and legal controversies in the future. A business operator's behavior that misleads the other party to a transaction must be divided into actions such as active false statements and omissions such as omission of facts, but even in the latter case, customer complaints do not disappear.

At this time, during the flower distribution process, auctions have the advantage of allowing one to select the product they want and bid on it, but it is difficult to win the bid for high-quality products because there are many bidders. As the number of bidders increases, the winning bid price may increase. The production site can ensure fairness in that products delivered to auction are sold according to the market price, but when the quality is lower compared to other products, the price of the product decreases, and if the product is not auctioned, there is a risk of having to bear the cost of garbage disposal. It also exists. In auctions, prices fluctuate so drastically that it is difficult to guarantee a consistent profit. For example, in the case of carnations, the price fluctuation increases up to five times around Mother's Day. This is because the consumption of carnations decreases sharply after Parents' Day. Also, it is difficult to release high-quality carnations right before Mother's Day. From the producer's perspective, it is difficult to determine whether it will be profitable to supply to the auction or flower wholesale/retail market, so products are mainly supplied to both the auction market and the flower wholesale/retail market. This is a way to obtain the best profit in a polarized market.

However, consumers who are unaware of this situation may, if the image of the flower product they selected and paid for and the flower product they actually received are different due to a difference in the number of flowers or a change in type, etc., even though the change is due to a change in circumstances. If the product violates notice or is different from the detailed description, you may return it or file a complaint. Accordingly, when circumstances change, such as the inventory of subsidiary materials being exhausted and replaced with other subsidiary materials, the price of cut flowers rising sharply and being changed to other cut flowers, or the number decreasing, each market price is uploaded in real time to monitor the changing situation. We can guide you in advance.

The administrator mode unit 393 displays the listed order details by dividing them into order rejection, not received, and recent status change tabs, and the latest status change includes order receipt, product preparation, delivery start, and delivery completion. You can display it so that it is sorted in the order of change.

<Demand Forecast>

In addition, the platform according to an embodiment of the present invention can further perform demand forecasting for individual flower products in order to determine the ordering time and order quantity of the flower product. Sales trends for each flower product are very different outside of designated days such as mid-February for Valentine's Day, late February for graduation ceremonies, and May for Parents' Day and Teacher's Day. Therefore, for optimal demand forecasting, individual flower product It is essential to build a demand forecasting model for. However, since there is inefficiency in building and training multiple models, in one embodiment of the present invention, transfer learning can be used to predict multiple flower products with the minimum number of models. At this time, transfer learning is a concept that represents techniques that utilize knowledge about other fields or tasks related to the purpose of the model when learning a model with a specific purpose. Additionally, when there is little data for the problem you want to solve, you can use a supervised learning method that utilizes a model that has already been learned with related data.

After creating a model by pre-training the sales data of currently distributed flower products, this can be used to predict sales volume of other flower products. After creating a sales forecast model using the TCN model, transfer learning can be applied and the learned weights can be used to predict demand for the top 10 flower products in sales. For prediction, trend, seasonality, and residual data obtained by decomposing flower product sales data into time series can be used. R2, RMSE, and MAPE can be used to evaluate flower product sales forecast performance, and verification can be done by conducting experiments with the MLP (Multi-Layer Perceptron) model and the TCN model without transfer learning to compare performance.

<Supplier risk management>

Supply chain management reduces unnecessary costs by integrating and managing all value chains related to the entire process from manufacturing goods to reaching customers by executing processes such as balance between supply and demand, demand forecasting, cycle time improvement, and customer management. The purpose is to implement efficient logistics management. In these supply chains, uncertain phenomena that cannot be controlled often occur between each value chain. As supply chains become longer and wider, risks in the supply chain gradually increase and management becomes necessary. This is called Supply Chain Risk Management. Losses resulting from an imbalance between supply and demand are sometimes defined as supply chain risk management, and are also defined as a potential phenomenon related to mistakes made by individual suppliers in the supply chain or mistakes made by purchasing companies in contact with customer demand.

For example, various risks and factors caused by risks in the areas of strategy, operations, supply chain, customers, assets, damage, competition, media, finance, accounting, regulation, and law in the supply chain are measured in terms of financial, performance, material, and risk factors. A list of major losses can be defined by social, psychological, and time, and the importance of supplier risk factors between logistics companies and outsourcing companies can be divided into transportation, inventory forecasting, information, market, and suppliers. The platform according to an embodiment of the present invention further includes the platform of the present invention and the ordering company between the user, who is the customer, and the ordering company, which is the seller. In other words, the order and logistics flow of [user-ordering painter-platform-ordering painter-user] is created, which means that there are many participants who generate external factors that cannot be directly controlled by the platform of the present invention. Accordingly, in one embodiment of the present invention, a supply chain risk management system can be established to actively respond to various unexpected risks in the supply chain network by classifying risks and verifying validity, as shown in Table 1 below. A further classification system could be provided.

Main Category Middle classification Detailed risk factors Enterprise
interior
risk operational risk
(Operation Risk) Human errors, breakdowns and failures, failure to convey information management risk
(Management Risk) Failure to predict, fail to plan, exceed capacity, fail to manage schedule, fail to manage suppliers, lack of flexibility. product risk
(Product Risk) Risks due to product characteristics, production disruption, quality deterioration, cargo theft and destruction financial risk
(Financial Risk) Delay in expense processing, deterioration of financial soundness, excess of financial capacity, accounting failure Supply Chain Risk Freight transportation risk
(Transport Risk) Transportation lead time error, occurrence of product loss, route interruption, route change, traffic congestion, physical damage to transportation means, physical form of cargo, misdelivery, error in recognizing dangerous cargo. information risk
(Information Risk) Data defects, communication defects, information system damage, security issues, information system service failure, information sharing failure, changes in systems and regulations reliability risk
(Reliability Risk) Failure to agree on service requirements, failure to manage logistics service quality, poor data reliability, and sabotage Risks external to the company environmental risk
(Environmental Risk) Temperature rise, marriage decline, pests and diseases natural disaster risk
(Natural Risk) Natural disasters such as earthquakes, volcanoes, storms, heavy snow, and floods political risk
(Political Risk) Regulations based on political issues

① Internal risk is a risk that occurs in the nodes of the network, and is mainly a risk that arises from the perspective of the orderer or platform. ② Supply Chain Risk: This is a risk that occurs in the arc of the network and mainly occurs in the logistics supply chain. ③ External risk is a risk caused by environmental changes outside the logistics network that affect the supply chain. Among the middle classifications, ① Operation Risk is a risk that causes time delays and increased costs due to exceptional situations or malfunction errors, etc., and ② Management Risk is a risk that causes losses and unexpected losses due to resource limitations or failure of plans. It is a risk that causes poor results. ③ Product Risk is the risk that losses in production and sales are expected due to the characteristics and quality of the products being produced, deterioration in quality, and theft or destruction of cargo. ④ Financial Risk is a risk that has a negative impact on continuous management due to delays in processing logistics costs, deterioration of corporate financial soundness, and accounting failures. ⑤ Transport Risk is a risk that has a negative impact on continuous management due to delays in processing logistics costs, deterioration of corporate financial soundness, and accounting failures. ⑤ Transportation Risk is a risk that occurs due to time delays that occur during the cargo transportation process. This is a risk where time and cost increase due to physical damage to the cargo. ⑥ Information risk is a risk that arises from errors in the information or information system required in the supply chain, communication defects, and data defects. ⑦ Reliability Risk is a risk that causes the partnership to collapse due to a decrease in reliability between the ordering company and the ordering company, causing a decrease in the competitiveness of the overall supply chain. ⑧ Environmental risk is the risk of failing to respond to CO2 reduction policies due to greenhouse gas regulations or increasing logistics costs due to new transportation policies, exchange rate changes, and tariff policy changes. ⑨ Natural disaster risk is the risk that normal logistics services cannot be provided due to natural disasters such as earthquakes, volcanoes, storms, heavy snow, and floods.

<Feasibility Verification>

After conducting confirmatory factor analysis on the data collected to verify the validity of risk classification in the supply chain network, the convergent validity and discriminant validity of each variable can be verified. In summary, first, confirmatory factor analysis to confirm the unidimensionality of supply chain risk classification is more preferable than exploratory factor analysis to test the unidimensionality of variables. In order to test the statistical suitability of each concept, χ2, GFI, AGFI, CFI, IFI, RMR, and RMSEA values can be used as standards. The general fit index criteria for adopting a model are Goodness of Fit Index (GFI), Adjusted Good of Fit Index (AGFI), Comparative Fit Index (CFI), and Incremental Fit Index. The Incremental Fit Index (IFI) is considered to be 0.9 or higher, the Root Mean Square Residual (RMR) is 0.05 or lower, and the Root Mean Square Error of Approximation (RMSEA) is 0.08 or lower. Confirmatory factor analysis can be conducted for each variable, such as internal corporate risk, supply chain risk, and external corporate risk, focusing on major categories.

Specifically, in the case of internal corporate risks, the mid-categories of operational risk, management risk, product risk, and financial risk can be set as potential variables, and analysis can be performed by inputting each item as a measurement variable. Supply chain risks and corporate risks can also be set as potential variables. External risks can also be set as latent variables in the same way: cargo transportation risk, information risk, reliability risk, environmental risk, natural disaster risk, and political risk. Then, analysis can be performed after inputting each item as a measurement variable.

Second, concentrated validity can be investigated to test first validity based on a confirmatory factor analysis model in which unidimensionality has been confirmed. Convergent validity tests the extent to which multiple items measuring the same concept are consistent. In other words, it can be said that concentrated validity is secured only when there is a high correlation between the questions measuring internal company risks, supply chain risks, and company external risks. Concept reliability values, which are the most rigorous way to evaluate convergent validity, can be used. The standard for concept reliability is 0.7 or higher, and convergent validity is considered to have been secured. Third, discriminant validity can be investigated to test the second validity based on the confirmatory factor analysis model in which unidimensionality has been confirmed. Discriminant validity means that there must be a clear difference in the measurements of different variables. Here, the clear difference is based on the correlation coefficient value, that is, the correlation between one variable and another variable must be low to ensure discriminant validity. In other words, discriminant validity can be said to be secured only when the correlation value between company internal risks, supply chain risks, and company external risks is low. The average variance extracted (AVE) value, which is the most rigorous method for evaluating discriminant validity, can be used.

Hereinafter, the operation process according to the configuration of the management service providing server of FIG. 2 described above will be described in detail using FIGS. 3 and 4 as an example. However, it will be apparent that the embodiment is only one of various embodiments of the present invention and is not limited thereto.

<Management of subcontractors>

Figure 3a is an administrator login page of a platform (Menconet) according to an embodiment of the present invention, and although not described in the present invention, it may be a screen of an administrator terminal (not shown) that manages the platform of the present invention. As shown in Figure 3b, it may include sub-order management, member management (order-receiving florist, ordering florist, sub-order florist), association settings, information management, deposit/withdrawal management, bulletin board management, text, fax management, log statistical analysis, administrator management, etc. You can. Figure 3c is the order details manager page.

<Membership Management>

The platform according to an embodiment of the present invention is currently building a system that allows approximately 400 member companies to evaluate the product production ability and service quality of the ordering flower shop that processes orders in the process of processing orders from the ordering flower shop and its own company. It is done. That is, as shown in FIGS. 3D and 3E , it is a system in which the ordering painter evaluates the ordering painter, and participation is activated through the benefit of receiving accumulated points operated by Menconet, the platform of the present invention. Figure 3f is a member management screen of Menconet.

<Deposit/withdrawal management>

As shown in Figure 3g, you can check the withdrawal details of each member company on the administrator screen. The platform of the present invention breaks away from the existing monthly and customer settlement method operated by competitors, etc., and sets the sales amount for each order in real time in the form of a balance for each account, and can estimate the sales amount of each flower shop. We are increasing the satisfaction of each painter by allowing the balance to be withdrawn in units. In order to operate a real-time monetary transaction like this, it is necessary to issue legal certificates for each order transaction, but Menconet has an advantage over competitors in the accuracy and speed of monetary transactions between business partners through the automatic cash receipt issuance function. Both the administrator account and each member company can check settlement details and proof details on their respective pages, and the corresponding deposit/withdrawal details, i.e. settlement details, can also be quickly checked. Figure 3h is the cash receipt issuance details on the manager screen, and Figure 3i is the settlement details for monetary transactions such as orders and orders between hwawon companies. At this time, in the above-mentioned screen capture, all personal information is not shown because it has been deleted, and each information is missing or It is stated that this is not because there is no function to display it on the screen.

FIGS. 4A to 4G are screens of a user of the user terminal 100, that is, a customer, and FIGS. 4H to 4L are images introducing the Hwawonsa application. Each user and flower shop can process orders, orders, and deliveries based on the application, and can also perform settlement, deposit/withdrawal, and evaluation.

Matters that are not explained about the method of providing B2C and B2B-based flower wholesale and retail management services in Figures 2 to 4 are the same as or explained in detail about the method of providing B2C and B2B-based flower wholesale and retail management services through Figure 1. Since it can be easily inferred from the content, the description below will be omitted.

FIG. 5 is a diagram illustrating a process in which data is transmitted and received between components included in the B2C and B2B based flower wholesale and retail management service provision system of FIG. 1 according to an embodiment of the present invention. Hereinafter, an example of the process of transmitting and receiving data between each component will be described with reference to FIG. 5, but the present application is not limited to this embodiment, and the process shown in FIG. 5 according to the various embodiments described above It is obvious to those skilled in the art that the process of transmitting and receiving data can be changed.

Referring to FIG. 5, the management service providing server registers at least one flower gardener terminal, divides the at least one flower gardener terminal into order receipt, order placement, and receiving order, and forms a database (S5100).

And, the management service providing server lists the order data of the user terminal in the order details when the order is received from at least one flower shop terminal (S5200), and lists the order details when the order data is received from at least one flower shop terminal. Update (S5300).

In addition, the management service providing server guides the user terminal when order reception and delivery processing are uploaded from at least one flower shop terminal (S5400), and when evaluation data is uploaded from the flower shop terminal that uploaded the order details, the order details are uploaded. It is mapped to the Hwawonsa terminal that received the order and stored (S5500).

The sequence between the above-described steps (S5100 to S5500) is only an example and is not limited thereto. That is, the order between the above-described steps (S5100 to S5500) may be changed, and some of the steps may be executed simultaneously or deleted.

Matters that are not explained about the method of providing B2C and B2B-based flower wholesale and retail management services in Figure 5 are the same as or explained above with respect to the method of providing B2C and B2B-based flower wholesale and retail management services through Figures 1 to 4. Since it can be easily inferred from the content, the description below will be omitted.

The method of providing B2C and B2B flower wholesale and retail management services according to an embodiment described in Figure 5 is also implemented in the form of a recording medium containing instructions executable by a computer, such as an application or program module executed by a computer. It can be. Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and non-volatile media, removable and non-removable media. Additionally, computer-readable media may include all computer storage media. Computer storage media includes both volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data.

The method of providing B2C and B2B-based flower wholesale and retail management services according to an embodiment of the present invention described above includes applications installed by default on a terminal (this may include programs included in the platform or operating system, etc., which are installed by default on the terminal). It may be executed by, or may be executed by an application (i.e., program) installed by the user directly on the master terminal through an application providing server such as an application store server, an application, or a web server related to the service. In this sense, the method of providing B2C and B2B-based flower wholesale and retail management services according to an embodiment of the present invention described above is implemented as an application (i.e., program) installed by default on the terminal or directly installed by the user, and is installed on the terminal by a computer, etc. It can be recorded on a readable recording medium.

The description of the present invention described above is for illustrative purposes, and those skilled in the art will understand that the present invention can be easily modified into other specific forms without changing the technical idea or essential features of the present invention. will be. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. For example, each component described as unitary may be implemented in a distributed manner, and similarly, components described as distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims described below rather than the detailed description above, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. do.

Claims (10)

A user terminal for ordering at least one type of flower product, receiving guidance on ordering and delivery of flower products, and transmitting reviews and ratings;
At least one flower shop terminal that places an order for at least one type of flower product, receives and places an order and delivery of the flower product, and uploads an evaluation of the order service between flower gardeners; and
A register that registers the at least one flower gardener terminal and divides the at least one flower gardener terminal into a database by dividing the at least one flower gardener terminal into orders placed, placed orders, and receiving orders; ordering when order data of the user terminal is ordered in the at least one flower gardener terminal An order management unit that lists the order details in the details, an order management unit that updates the order details when the order details are received from the at least one flower shop terminal, and the user terminal when the order reception and delivery processing are uploaded by the at least one flower shop terminal. A management service providing server including an information unit that guides the order details, and an evaluation unit that maps and stores the order details with the Hwawon company terminal that received the order when evaluation data is uploaded from the Hwawon company terminal that uploaded the order details;
A B2C and B2B based flower wholesale and retail management service provision system including.
According to claim 1,
The management service providing server is,
When a photo of a flower product is uploaded from the user terminal, a fact-checking unit measures the similarity between the photo of the flower product and the photo of the already registered flower product and compares it with the evaluation data of the flower shop terminal that uploaded the order details. ;
A B2C and B2B based flower wholesale and retail management service provision system further comprising:
According to claim 1,
The management service providing server is,
When evaluation data is uploaded from the Hwawon company terminal that received the order details, an interactive unit that maps and stores the order details with the Hwawon company terminal that uploaded the order details;
A B2C and B2B based flower wholesale and retail management service provision system further comprising:
According to claim 1,
The evaluation data is,
A B2C and B2B based flower wholesale and retail management service provision system characterized by dividing and storing items about product quality, delivery time, and overall service.
According to claim 1,
The management service providing server is,
When managing sales details in the at least one flower shop terminal, a real-time sales confirmation unit that outputs the sales amount for real-time orders in the form of a balance for each flower shop account of each flower shop terminal;
A B2C and B2B based flower wholesale and retail management service provision system further comprising:
According to claim 5,
The management service providing server is,
a weekly settlement unit that withdraws and settles the sales amount on a weekly basis from the at least one Hwawonsa terminal;
A B2C and B2B based flower wholesale and retail management service provision system further comprising:
According to claim 1,
The management service providing server is,
A certificate issuance unit that automatically issues cash receipts for orders placed between the at least one Hwawonsa terminal;
A B2C and B2B based flower wholesale and retail management service provision system further comprising:
According to claim 1,
The management service providing server is,
When a change occurs in the price of flowers included in the at least one flower product, a notification obligation performance department that updates in real time notification of changes in type and increase or decrease in quantity due to the change in flower price;
A B2C and B2B based flower wholesale and retail management service provision system further comprising:
According to claim 8,
The notification obligation department said,
A B2C and B2B-based flower wholesale and retail management service provision system characterized by real-time updates of notices of changes in subsidiary materials when changes or increases or decreases in subsidiary materials occur due to the inventory of subsidiary materials included in the flower product.
According to claim 1,
The management service providing server is,
The listed order details are divided into the Order Rejected, Not Received, and Recent Status Change tabs, and the latest status change displays cases where the status is updated to order receipt, product preparation, delivery start, and delivery completion, and is sorted in the order of change. An administrator mode unit that displays as much as possible;
A B2C and B2B based flower wholesale and retail management service provision system further comprising:

Images