An automated pricing system for trading secondhand goods.

Abstract

The present application discloses an automatic pricing second-hand commodity trading system, including: an interactive interface for receiving user input information to verify the user identity, providing users with commodity information display and sales platform, and users include buyers and sellers; a sales application module for providing sellers with a commodity information filling interface for obtaining commodity-related information and submitting sales application information, and commodity-related information includes commodity images, commodity specification information and commodity usage information; a selling price generation module for using a preset classification network model to classify the target commodity in the sales application information according to the commodity-related information, obtain the classification result, and predict the selling price discount based on the classification result and commodity-related information based on the preset decision tree to obtain the selling price. The present application can alleviate the technical problem that the existing campus trading platform cannot reasonably price second-hand commodities, resulting in difficulty in trading.

Description

Technical Field

[0001] The present application relates to the field of e-commerce technology, and in particular to a second-hand commodity trading system with automatic pricing. Background Art

[0002] With the rapid development of the Internet and information technology, e-commerce has become particularly popular in recent years. Online shopping has become a normal part of life and has also been successfully applied to campus life. On college campuses, as students begin to achieve financial freedom, many students may buy items that they do not use at all or leave idle after using them a few times. If these items are not handled in time, it will cause waste in students' lives.

[0003] In order to alleviate the problem of waste among students, these items can be sold through the campus trading platform. However, whether the pricing is set by the seller or a third party, it is difficult to control the actual condition and price of the items, resulting in unreasonable transaction prices and making it difficult to proceed. Summary of the invention

[0004] The present application provides a second-hand commodity trading system with automatic pricing, which is used to alleviate the technical problem that the existing campus trading platform cannot reasonably price second-hand commodities, making transactions difficult.

[0005] In view of this, the present application provides a second-hand commodity trading system with automatic pricing, including:

[0006] Interactive interface, sales application module and selling price generation module;

[0007] The interactive interface is used to receive user input information to verify the user's identity and provide a commodity information display and sales platform for the user, the user includes buyers and sellers;

[0008] The sales application module is used to provide the seller with a product information filling interface, to obtain product-related information, and to submit sales application information. The product-related information includes product images, product specification information, and product usage information;

[0009] The selling price generating module is used to classify the target goods in the selling application information according to the relevant information of the goods by using a preset classification network model to obtain a classification result, and to predict the selling price discount according to the classification result and the relevant information of the goods based on a preset decision tree to obtain a selling price.

[0010] Preferably, the selling price generating module is specifically used for:

[0011] The preset classification network model includes an attribute classification network model and a wear classification network model, and the classification result includes an attribute classification result and a wear classification result;

[0012] Using the attribute classification network model to perform attribute classification according to the product image and the product specification information to obtain the attribute classification result;

[0013] The wear classification network model is used to classify the degree of wear according to the product image and the product usage information to obtain the wear classification result, wherein the wear classification result includes no wear, slight wear, medium wear and severe wear;

[0014] Based on a preset decision tree, a sales price discount is predicted according to the classification result and the product related information to obtain a predicted discount;

[0015] A discount calculation is performed based on the predicted discount and the preset market price to obtain a selling price.

[0016] Preferably, it also includes: a management module;

[0017] The management module is used to terminate the current transaction behavior when receiving the transaction question information from the user, and delete the product related information of the completed transaction product from the system.

[0018] Preferably, the management module is further used for:

[0019] Receive the goods for sale from the seller, conduct a quality review on the goods for sale, send the review result to the selling price generating module, and trigger the selling price generating module to update the selling price based on the review result.

[0020] Preferably, it also includes: a commodity receiving module;

[0021] The commodity receiving module is used to provide the buyer with an interface for selecting a commodity receiving method and to fill in the mailing information when the mail receiving method is selected. The mailing information includes the address, contact person and telephone number. The commodity receiving methods also include self-pickup and collection on behalf of others.

[0022] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0023] In the present application, a second-hand commodity trading system with automatic pricing is provided, including: an interactive interface, a sales application module and a sales price generation module; the interactive interface is used to receive user input information to verify the user's identity and provide users with a commodity information display and sales platform, and users include buyers and sellers; the sales application module is used to provide sellers with a commodity information filling interface for obtaining commodity-related information and submitting sales application information, and the commodity-related information includes commodity images, commodity specification information and commodity usage information; the sales price generation module is used to classify the target commodity in the sales application information according to the commodity-related information using a preset classification network model to obtain a classification result, and to predict the sales price discount based on the classification result and the commodity-related information based on a preset decision tree to obtain a selling price.

[0024] The application provides an automatic pricing second-hand goods trading system, which provides sellers with an information collection interface for the goods to be sold through the sales application module. The sellers can fill in the information according to the actual situation of the goods and apply for sale; then the price generation module will classify the goods according to the images and other information provided by the sellers, and make discount predictions based on the classification and product information, and automatically generate a reasonable selling price that is more in line with the actual situation, without the need for a third party and the seller to set the selling price; and the price setting based on the neural network is more scientific and reliable. Therefore, the application can alleviate the technical problem that the existing campus trading platform cannot reasonably price second-hand goods, making transactions difficult. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 A schematic diagram of the structure of a second-hand commodity trading system with automatic pricing provided in an embodiment of the present application;

[0026] Figure 2 A schematic diagram of the structure of a preset classification network model provided in an embodiment of the present application;

[0027] Figure 3 This is an example diagram of the pricing influencing factor determination process provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0029] For easier understanding, see Figure 1The present application provides an embodiment of an automatic pricing second-hand commodity trading system, including: an interactive interface 101, a sales application module 102 and a sales price generation module 103.

[0030] The interactive interface 101 is used to receive user input information to verify the user's identity and provide users with a commodity information display and sales platform. Users include buyers and sellers.

[0031] It should be noted that the user entering the system of this embodiment can be a buyer or a seller; as long as the user has pre-registered identity information on the system, the identity verification can be completed the next time the user enters the system. The identity verification method is not limited, and it can be an account password or a temporary verification code, which can be set as needed. Users can browse various second-hand goods on the interactive interface, or browse detailed information for a certain product of interest and make a purchase. In addition to the above interactive actions, interactive schemes can also be set as needed, and the specific ones are not limited.

[0032] The sales application module 102 is used to provide a product information filling interface for the seller to obtain product related information and submit sales application information. The product related information includes product images, product specification information and product usage information.

[0033] The seller can fill in the target product information through the sales application module, where product images can be set to be multi-angle images with a certain degree of clarity; product specification information refers to the size of a specific product, the power specifications of electrical appliances, the space volume of containers and other information, so that the buyer can select according to needs after clarifying the information; product usage information mainly describes the seller's ownership time, number of times used, and usage methods or scenarios of the product. It is understandable that the sales application information can only be successfully submitted after the product-related information is filled in in accordance with the requirements, otherwise the information needs to be further improved according to the instructions.

[0034] The selling price generating module 103 is used to classify the target goods in the selling application information according to the relevant information of the goods by using the preset classification network model to obtain the classification result, and to predict the selling price discount according to the classification result and the relevant information of the goods based on the preset decision tree to obtain the selling price.

[0035] Furthermore, the selling price generating module 103 is specifically used for:

[0036] The preset classification network model includes an attribute classification network model and a wear classification network model, and the classification results include an attribute classification result and a wear classification result;

[0037] Using the attribute classification network model to classify attributes according to the product image and product specification information, the attribute classification result is obtained;

[0038] The wear classification network model is used to classify the degree of wear according to the product image and product usage information to obtain the wear classification results, which include no wear, slight wear, medium wear and severe wear;

[0039] Based on the preset decision tree, the sales price discount is predicted according to the classification results and product related information to obtain the predicted discount;

[0040] The discount is calculated based on the predicted discount and the preset market price to obtain the selling price.

[0041] It should be noted that the preset classification network model uses a convolutional neural network. The network structure of the convolutional neural network can better adapt to the image structure, extract features and complete classification. The convolution layer and pooling layer of the hidden layer in the convolutional neural network are the core modules for realizing the feature extraction function. The network model reversely adjusts the weight parameters in the network layer by layer by minimizing the loss function through the gradient descent method, and improves the accuracy of the network through frequent iterative training.

[0042] The preset classification network model or decision tree in this embodiment is a model trained with transaction commodity images, which can be directly used in commodity classification and prediction tasks; and the classification network model in this embodiment includes 2 convolutional layers, a pooling layer and a fully connected layer, please refer to Figure 2 The training of the model is the process of optimizing the error between the model result and the real label calculation. The decision tree represents the mapping relationship between a product attribute and an object value. Each internal node is an attribute, and each branch can get a prediction result.

[0043] In this embodiment, two different classification network models are configured to perform attribute classification and wear classification respectively; attribute classification can include categories such as daily necessities, school supplies and household appliances, and more detailed classification can be set, and the specific ones are not limited; attribute classification can affect the price setting according to the size of the market share. For example, the market for school supplies on campus is good and the sales prospects are promising, so it will help to improve the pricing after comprehensive consideration of various pricing factors. Wear classification mainly evaluates and classifies the degree of wear of the target product, which in turn affects the pricing; this embodiment defines 4 levels of wear: no wear, slight wear, medium wear and severe wear. The degree of wear can be quantified by percentage, and the specific details are not repeated; different degrees of wear will result in different levels of selling prices. Generally, the smaller the degree of wear, the higher the price can be set, and vice versa, the lower the price.

[0044] In addition to the influence of category and degree of wear, there are some other influencing factors in the process of discount prediction by decision tree. In summary, there are three points. The first is whether the packaging bag of the product is removed, the second is the degree of wear of the product, and the last is the usage time of the product. All of these can be reflected in the decision tree and used to specify the selling price of the product. The preset market price can be defined according to the average price of the same product in the market or according to the seller's purchase price. As long as it is reasonable, it is not limited here.

[0045] See also Figure 3 , the discount of the product can be roughly determined based on the packaging removal, wear and tear, and usage time. The first layer determines whether the packaging bag of the product has been removed. If the packaging has not been removed, the discount of the product is 98%. If the packaging bag of the product has been removed, it will proceed to the next layer of judgment; the second layer is to judge the degree of wear of the product. The result obtained by the convolutional network model is used to judge the wear of the product. If the wear result of the product is serious, the discount is 38%. If the wear result of the product is slight, the discount is 10%. If the wear result of the product is medium, the last judgment will be made; the last layer is to judge the usage time of the product. The system calculates the usage time of the product based on the purchase time of the product filled in by the user. If the usage time of the product is within one year, the discount of the product is 15%. If the usage time exceeds 1 year, the discount is 23%.

[0046] Furthermore, it also includes: a management module 104;

[0047] The management module 104 is used to terminate the current transaction behavior when receiving the transaction question information from the user, and delete the commodity-related information of the completed transaction commodity from the system.

[0048] When receiving transaction question information from users, the current transaction can be intervened and terminated immediately. Later, the buyer and seller can arrange for negotiations under the witness of a third party to resolve the transaction problem. If it is a system problem, the management staff will be notified to handle it in time. The relevant information of the goods that have been traded needs to be deleted to give space for new goods to be displayed and reduce the redundant information storage in the system.

[0049] Furthermore, the management module 104 is also used for:

[0050] Receive the goods for sale from the seller, conduct a quality review on the goods for sale, send the review results to the selling price generation module, and trigger the selling price generation module to update the selling price based on the review results.

[0051] Scientific and reasonable rules can be formulated for product audits, and the audits can be comprehensive, including the completeness of product attributes, normal performance, and appearance wear and tear; these audits can be quantified into indicators, sent to the selling price generation module, and affect the selling price.

[0052] Furthermore, it also includes: a commodity receiving module 105;

[0053] The product receiving module is used to provide the buyer with an interface for selecting the product receiving method and to fill in the mailing information when the mailing method is selected. The mailing information includes the address, contact person and telephone number. The product receiving methods also include self-pickup and collection on behalf of others.

[0054] If a front-end buyer wants to place an order for a product, he can select the receiving method through the product receiving module. For self-pickup and agency pick-up, he only needs to select the specific pickup address and identity authentication information, while the mailing method requires filling in the specific delivery information. If there are other information requirements during the product receiving process, this module can also be used to obtain information, and there is no specific limitation.

[0055] The embodiment of the present application provides an automatic pricing second-hand goods trading system, which provides the seller with an information collection interface for the goods to be sold through the sales application module. The seller can fill in the information according to the actual situation of the goods and apply for sale; then the price generation module will classify the goods according to the images and other information provided by the seller, and make discount predictions based on the classification and the product information, and automatically generate a reasonable selling price that is more in line with the actual situation, without the need for a third party and the seller to set the selling price; and the price setting based on the neural network is more scientific and reliable. Therefore, the embodiment of the present application can alleviate the technical problem that the existing campus trading platform cannot reasonably price second-hand goods, making it difficult to conduct transactions.

[0056] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0057] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0058] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or software functional units.

[0059] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for executing all or part of the steps of the method described in each embodiment of the present application through a computer device (which can be a personal computer, a server, or a network device, etc.). The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (full name in English: Read-Only Memory, English abbreviation: ROM), random access memory (full name in English: Random Access Memory, English abbreviation: RAM), disk or optical disk and other media that can store program codes.

[0060] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A second-hand commodity trading system with automatic pricing, characterized in that: include: Interactive interface, sales application module and selling price generation module; The interactive interface is used to receive user input information to verify the user's identity and provide a commodity information display and sales platform for the user, the user includes buyers and sellers; The sales application module is used to provide the seller with a product information filling interface, to obtain product-related information, and to submit sales application information. The product-related information includes product images, product specification information, and product usage information; The selling price generating module is used to classify the target commodity in the selling application information according to the commodity related information using a preset classification network model to obtain a classification result, and to predict the selling price discount according to the classification result and the commodity related information based on a preset decision tree to obtain a selling price. The selling price generating module is specifically used to: The preset classification network model includes an attribute classification network model and a wear classification network model, and the classification result includes an attribute classification result and a wear classification result; Using the attribute classification network model to perform attribute classification according to the product image and the product specification information to obtain the attribute classification result; The wear classification network model is used to classify the degree of wear according to the product image and the product usage information to obtain the wear classification result, wherein the wear classification result includes no wear, slight wear, medium wear and severe wear; Based on a preset decision tree, a sales price discount is predicted according to the classification result and the product related information to obtain a predicted discount; A discount calculation is performed based on the predicted discount and the preset market price to obtain a selling price.

2. The automatic pricing second-hand commodity trading system according to claim 1 is characterized in that: Also includes: Management module; The management module is used to terminate the current transaction behavior when receiving the transaction question information from the user, and delete the product related information of the completed transaction product from the system.

3. The automatic pricing second-hand commodity trading system according to claim 2 is characterized in that: The management module is further used for: Receive the goods for sale from the seller, conduct a quality review on the goods for sale, send the review result to the selling price generating module, and trigger the selling price generating module to update the selling price based on the review result.

4. The automatic pricing second-hand commodity trading system according to claim 1, characterized in that: Also includes: Commodity receiving module; The commodity receiving module is used to provide the buyer with an interface for selecting a commodity receiving method and to fill in the mailing information when the mail receiving method is selected. The mailing information includes the address, contact person and telephone number. The commodity receiving methods also include self-pickup and collection on behalf of others.

Images