JP7292362B2 - Decision device, decision method and decision program - Google Patents

Description

The present invention relates to a determination device, a determination method, and a determination program.

Conventionally, there has been known a technique for supporting purchase of second-hand goods. For example, there is known a technique of calculating the supply and demand balance in the market based on the distribution status of the product and determining an appropriate selling price for the same used product that has been sold in the past.

Japanese Patent Application Laid-Open No. 2001-134635

However, in the prior art, in pricing used goods, it was not possible to appropriately determine a fair price for sales according to the condition of the used goods such as scratches.

The present application has been made in view of the above, and an object of the present application is to improve the accuracy of pricing second-hand goods.

The determination device according to the present application includes an acquisition unit that acquires new product information of a target product and second-hand product information of a second-hand product that has been sold in the past, and the new product information and the second-hand product information acquired by the acquisition unit. and a determination unit that determines an estimated price for sales of the second-hand goods for each condition based on the condition.

According to one aspect of the embodiment, it is possible to improve the accuracy of pricing second-hand goods.

FIG. 1 is a diagram showing a configuration example of a decision system according to an embodiment. FIG. 2 is a diagram illustrating an example of determination processing according to the embodiment. FIG. 3 is a diagram illustrating a configuration example of a user terminal according to the embodiment; FIG. 4 is a diagram illustrating a configuration example of a determination device according to the embodiment; 5 is a diagram illustrating an example of a storage unit according to the embodiment; FIG. 6 is a diagram illustrating an example of a storage unit according to the embodiment; FIG. FIG. 7 is a flowchart illustrating an example of determination processing according to the embodiment. FIG. 8 is a hardware configuration diagram showing an example of a computer that implements the functions of the determination device.

Embodiments (hereinafter referred to as "embodiments") for implementing the determination device, determination method, and determination program according to the present application will be described in detail below with reference to the drawings. Note that the determination device, determination method, and determination program according to the present application are not limited to this embodiment. Also, in each of the following embodiments, the same parts are denoted by the same reference numerals, and overlapping descriptions are omitted.

(embodiment)
[1. Configuration of decision system]
The determination system 1 shown in FIG. 1 will be described. As shown in FIG. 1 , the decision system 1 includes a user terminal 10 and a decision device 100 . The user terminal 10 and the determination device 100 are communicably connected by wire or wirelessly via a predetermined communication network (network N). FIG. 1 is a diagram showing a configuration example of a determination system 1 according to an embodiment.

The user terminal 10 is an information processing device used by the user who requests the purchase and is on the parting side. The user terminal 10 may be any device as long as it can implement the processing in the embodiments. Also, the user terminal 10 may be a device such as a smart phone, a tablet terminal, a notebook PC, a desktop PC, a mobile phone, or a PDA. FIG. 2 shows a case where the user terminal 10 is a smart phone.

The user terminal 10 is, for example, a smart device such as a smartphone or a tablet, and is a mobile device capable of communicating with any server device via a wireless communication network such as 3G to 5G (Generation) or LTE (Long Term Evolution). It is a terminal device. The user terminal 10 has a screen such as a liquid crystal display and has a touch panel function, and the user can perform various operations on display data such as content by tapping, sliding, or scrolling with a finger or a stylus. operation may be accepted. In FIG. 2, user terminal 10 is used by user U11.

The determination device 100 is an information processing device intended to improve the accuracy of pricing second-hand goods, and may be any device as long as it can implement the processing in the embodiments. The decision device 100 is implemented by, for example, a server device, a cloud system, or the like. For example, the determination device 100 is realized by a server device, a cloud system, or the like for a predetermined service that buys and sells second-hand goods.

[2. Example of decision processing]
FIG. 2 is a diagram showing an example of determination processing of the determination system 1 according to the embodiment. In the following embodiments, second-hand clothes are used as an example of a product to be purchased.

First, let's talk about pricing used clothes. In general, when buying used clothes, clothes sent as used clothes do not have price tags attached to them, so they do not have a code such as a JAN code that allows individual items to be specified. In addition, although it is possible to identify a single item by searching for the brand's unique model number included in the quality label tag, it is time-consuming and costly to check and search for middle-to-low price used clothing item by item. is also impractical.

In addition, it is common practice to treat all products as single items without considering that there are products with the same model number, and to price them using a price table based on at least one combination of brand, category, and condition. However, in this method, for example, the most recent sales record for each model number, depletion of value, etc. cannot be reflected in the price, and the accuracy of pricing may be low.

In addition, in order to improve the accuracy of pricing, the model number of a new product of the same product in a predetermined online shopping mall is predetermined, and the model number is linked in advance with second-hand product information and new product information. shall be

In the following embodiment, it is assumed that the user U11 who requests the purchase requests the purchase of the used clothes P11. Specifically, it is assumed that the user terminal 10 transmits information for requesting the purchase of the used clothes P11 to the determination device 100 by the user U11's operation.

The determination device 100 acquires the information for requesting the purchase of the used clothes P11 transmitted from the user terminal 10 (step S101). Then, based on the information for requesting the purchase of the used clothes P11, the determining apparatus 100 determines, for example, the business operator information of the predetermined service for which the purchase of the used clothes P11 is requested, and the fact that the user U11 has purchased the same new product. acquire business information of a predetermined electronic shopping mall;

(Identification based on purchase history)
Based on the acquired information, the determining apparatus 100 determines that the predetermined service for which the purchase of the second-hand clothes P11 is requested has a predetermined relationship (for example, a business operator are the same). If the determination device 100 determines that the predetermined service requested to purchase the used clothes P11 has a predetermined relationship with the predetermined online shopping mall where the user U11 purchased the same new product, the predetermined relationship is established. Acquire the purchase history at a predetermined online shopping mall that is determined to have a certain relationship, and based on the acquired purchase history, the model number of a new product of the same product at a predetermined online shopping mall that is determined to have a predetermined relationship is specified (step S102). For example, the user U11 requests the purchase of the used clothes P11 through the predetermined online shopping mall where the new item was purchased.

(Specification based on tag information)
Further, when the determining apparatus 100 determines that the predetermined service requested to purchase the used clothes P11 does not have a predetermined relationship with the predetermined online shopping mall where the user U11 purchased the same new product, For example, based on the tag information attached to the used clothes P11 (for example, information on the model number unique to the brand included in the quality display tag) sent to the store that provides the predetermined service where the purchase is requested, the used clothes P11 can be purchased. A model number of a new product of the same product in a predetermined electronic shopping mall having a predetermined relationship with the requested service is specified. For example, the second-hand clothes P11 may have been purchased at a predetermined online shopping mall that does not have a predetermined relationship with the predetermined service for which purchase is requested.

(model generation)
The determination device 100 determines a price (selling price) as a basis for calculating an estimated price for sales of each condition of a used product based on new product information and second-hand product information of a product that has been sold. A model to be output for each condition is generated (step S103). For example, the determination device 100 uses new product information of products with a sales record and second-hand product information up to the previous sale as explanatory variables, and uses the previous sales price as an objective variable to create a model based on XGBoost (eXtreme Gradient Boosting) or the like. to generate Here, the new article information includes, for example, information such as the normal price of the same article as the used article P11 (the initial fixed price at the time of sale of the new article), the start of sales, the brand, the category, and the like. In addition, second-hand product information includes, for example, the sales price of second-hand products that have been sold in the past, the off rate at the time of sale, increase or decrease in sales price, the period from listing to sale (e.g., number of days elapsed), purchase (trade-in) price, Includes information such as purchase (trade-in) year. Of these, the second-hand product information includes information on the period from exhibition to sale.

Here, the inside out of the selling price may occur. For example, it is assumed that the condition ranks are (S, A, B, C, D) and the reference condition is the rank (B) condition. In addition, it is assumed that the sales price of the condition of rank (C) becomes higher than the sales price of the condition of higher rank (B), and the inside out occurs. In this case, the decision device 100 trains the model using the selling price of the condition of rank (B) as a positive example, but in reality, the selling price of the condition of rank (B) may be erroneous. In this way, when the selling price is reversed, it cannot be determined which of the selling price of the condition of rank (B) and the selling price of the condition of rank (C) is actually wrong. If the information does not include information on the period from listing to sale, in the event of such a reversal of the selling price, the selling price of each condition will be adjusted to an appropriate selling price. Can not do it.

On the other hand, if the second-hand product information, which is the input information of the model, includes information on the period from listing to sale, if the selling price is reversed, one of the periods from listing to sale will be very long. Since the sales price of each condition becomes shorter (the sales price of the condition of rank (B) is lower than that of rank (B), it sells immediately because of the lower sales price), even if the sales price of the condition of rank (B) is really an error, the sales price of each condition is Price correction can be performed so as to converge to an appropriate selling price.

The determination device 100 acquires new product information and second-hand product information predetermined in association with the model number of the new product specified based on the purchase history or tag information (step S104). In FIG. 2, the determination device 100 acquires new product information and second-hand product information transmitted from an information providing device 200 that manages a predetermined online shopping mall Q11. Then, the determining device 100 inputs the acquired new product information and second-hand product information to the generated model to calculate the sales price for each condition of the second-hand product (step S105). At this time, the model outputs the sales price of each condition according to the second-hand product information of each condition.

Then, the determining device 100 multiplies the calculated sales price for each condition by the correction coefficient to calculate an estimated price for sales for each condition (step S106). For example, the determination device 100 multiplies the sales price of each condition by the same correction factor to calculate the estimated price for the sale of each condition. For example, the decision device 100 calculates the estimated price for the sale of the rank (A) condition by multiplying the sale price of the rank (A) condition by the same correction factor for all conditions.

Note that, for example, if the condition ranks are (S, A, B, C, D), and the second-hand product information for some of the conditions is insufficient, the determining device 100 determines the reference condition By multiplying the sales price of the standard condition output from the model based on the second-hand product information, by the correction coefficient corresponding to some conditions for which the second-hand product information is lacking, the second-hand product information is insufficient. Calculate an estimated price for some condition sales. For example, if the reference condition is a rank (B) condition and the second-hand product information of the rank (A) condition is insufficient, the determination device 100 adds the sales price of the rank (B) condition to By multiplying by a correction coefficient according to the rank (A) condition, an estimated price for sales of the rank (A) condition is calculated. As a result, the determination device 100 can set an appropriate price even when second-hand product information is insufficient due to the condition.

Also, for example, when the estimated price for sales of some conditions is higher than the estimated price for sales of higher conditions than some conditions, and a flip occurs, the determination device 100 determines the price of the reference condition. By multiplying the sales price of the standard condition, which is output from the model based on the second-hand product information, by the correction coefficient corresponding to the part of the condition where the inside-out occurred, the sales price of the part of the condition where the inside-out occurred Calculate an estimated price. For example, it is assumed that the condition ranks are (S, A, B, C, D) and the reference condition is the rank (B) condition. Then, when the estimated price for the sale of the condition of rank (C) becomes higher than the estimated price for the sale of the condition of the higher rank (B), and a flip occurs, the decision device 100 determines the condition of the rank (B). By multiplying the sales price of the condition by a correction coefficient corresponding to the condition of rank (C), an estimated price for the sale of the condition of rank (C) is calculated.

In addition, if the estimated price for the sale of the condition of rank (A) is lower than the estimated price for the sale of the condition of the lower rank (B), and a flip occurs, the decision device 100 By multiplying the sales price of the condition by a correction factor corresponding to the condition of rank (A), an estimated price for the sale of the condition of rank (A) is calculated. As a result, the decision device 100 can appropriately correct the price when an estimated price is reversed due to some error in model learning.

The correction coefficient by which the sales price is multiplied will be described below. The correction coefficient is assumed to decrease as the period (e.g., the number of days elapsed) from the start of sales of new products to the latest purchase of second-hand products increases. Note that the correction coefficient may be increased as the period is shortened. In this case, the faster the second-hand product sells, the larger the correction coefficient will be, depending on the sales performance. Also, the degree to which the correction coefficient becomes smaller or larger depending on the period may differ for each condition.

Then, the determining device 100 determines the calculated estimated price as an estimated price for sales for each condition (step S107). In this way, the determination device 100 determines an estimated price for sales for each condition based on new product information and second-hand product information. As a result, the determination device 100 can estimate the price based on both the new product information and the second-hand product information, so that it is possible to set an appropriate price with high accuracy. Moreover, since the determination device 100 can estimate the price for each condition, it is possible to set an appropriate price.

Also, a maximum price may be set. Here, the coefficient for setting the upper limit price by multiplying the sales price is defined as the specific coefficient. For example, the specific coefficient is predetermined for each product class (for example, a combination of brand and category). The determination device 100 compares the corrected price obtained by multiplying the selling price by a correction coefficient and the upper limit price obtained by multiplying the selling price by a specific coefficient, and if the corrected price exceeds the upper limit price, the upper limit price may be used as the estimated price. As a result, the determination device 100 can optimize price setting so that second-hand products are premium products and do not deviate significantly from the list price of new products. In addition, the determination device 100 can set the upper limit price according to each product class by using a predetermined specific coefficient for each product class.

(Variation 1 of decision processing)
In the above embodiment, the determination device 100 may determine the purchase price based on the estimated sales price for each determined condition. Then, the determining device 100 may provide the user U11 with the purchase price determined based on the estimated price related to the sale of the reference condition as the trade-in price by transmitting information for displaying on the user terminal 10. Good (step S108). In addition, the determination device 100 transmits information to the seller of second-hand goods for displaying the purchase price determined based on the estimated price for sale for each condition on the terminal device of the seller for each condition. and may be provided for each condition.

(Variation 2 of decision processing)
In the above-described embodiment, when the product is exhibited in consideration of the demand in the market, the pricing process according to the above-described embodiment may be performed when the demand in the market is high. For example, seasonal products (seasonal products) are determined in advance, and if the purchased second-hand product is a seasonal product, it can be put up until the time of high demand in the market before listing it. , the pricing process according to the above embodiment may be performed. For example, if a summer item is purchased in winter, the item may be put on the market after being laid out until summer, so that the pricing process according to the above-described embodiment may be performed during a period of high demand in the market. The decision device 100 decides an estimated price for sales for each condition during a period of high market demand, when the product is put up for sale in consideration of the demand in the market. This allows the decision device 100 to set prices in consideration of market demand.

(Variation 3 of decision processing)
In the above-described embodiment, when the user U11 requests the purchase of the used clothes P11, the sales price for each condition of the used item is estimated based on the information for requesting the purchase of the used clothes P11 transmitted from the user terminal 10. Although the case of determining the price and trade-in price has been described, the present invention is not limited to this example. For example, for all (or some) products sold in a predetermined electronic shopping mall, after determining the sales price, estimated price, and trade-in price for each condition of the used product, the trade-in price is presented to the user U11. You may In this case, the user U11 may check the trade-in price, select the product, and request the purchase of the used clothes P11. Details of the processing will be described below.

The determination device 100 acquires new product information and used product information for each product for all (or some) products sold on a predetermined online shopping mall. In addition, the determination device 100 determines the sales price, estimated price, and trade-in price for each condition of the second-hand product for each product by inputting new product information and second-hand product information into the model for each product. Then, the determining device 100 determines whether or not there is an item for sale at the predetermined online shopping mall among the belongings of the user U11, and determines that there is an item for sale at the predetermined online shopping mall. In this case, information for displaying the trade-in price of the product on the user terminal 10 is transmitted. For example, if the user U11's belongings include a plurality of products to be sold at a predetermined online shopping mall, the determining device 100 causes the user terminal 10 to display the trade-in price for each of the plurality of products. send information about It should be noted that the user U11's property is specified based on the purchase history of the user U11 at a predetermined electronic shopping mall, for example. In addition, when the user U11's property is specified based on the purchase history of the user U11 at a predetermined online shopping mall, the determining device 100, for example, , information for displaying the trade-in price of the product purchased by the user U11 at a predetermined online shopping mall is transmitted. Then, the user terminal 10 transmits information for requesting purchase of a second-hand product of the product selected by the user U11 from the products whose trade-in prices are displayed. For example, when the user U11 selects a product corresponding to the used clothes P11, the user terminal 10 transmits information for requesting purchase of the used clothes P11.

[3. Configuration of User Terminal]
Next, the configuration of the user terminal 10 according to the embodiment will be described using FIG. FIG. 3 is a diagram showing a configuration example of the user terminal 10 according to the embodiment. As shown in FIG. 3 , the user terminal 10 has a communication section 11 , an input section 12 , an output section 13 and a control section 14 .

(Communication unit 11)
The communication unit 11 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 11 is connected to a predetermined network N by wire or wirelessly, and transmits and receives information to and from the determining device 100 and the like via the predetermined network N.

(Input unit 12)
The input unit 12 receives various operations from the user. In FIG. 2, various operations from the user U11 are accepted. For example, the input unit 12 may receive various operations from the user through the display surface using a touch panel function. The input unit 12 may also receive various operations from buttons provided on the user terminal 10 or from a keyboard or mouse connected to the user terminal 10 .

(Output unit 13)
The output unit 13 is a display screen of a tablet terminal realized by, for example, a liquid crystal display or an organic EL (Electro-Luminescence) display, and is a display device for displaying various information. For example, the output unit 13 displays information transmitted from the decision device 100 .

(control unit 14)
The control unit 14 is, for example, a controller, and a CPU (Central Processing Unit), MPU (Micro Processing Unit) or the like transfers various programs stored in a storage device inside the user terminal 10 to a RAM (Random Access Memory). ) as a work area. For example, these various programs include application programs installed in the user terminal 10 . For example, these various programs include an application program that transmits information for requesting purchase to the determining device 100 . Also, the control unit 14 is implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 3, the control unit 14 has a receiving unit 141 and a transmitting unit 142, and implements or executes the information processing operation described below.

(Receiver 141)
The receiving unit 141 receives various information from an external information processing device. The receiving unit 141 receives various information from other information processing devices such as the determining device 100 . For example, the receiving unit 141 receives information for displaying a trade-in price.

(Sending unit 142)
The transmission unit 142 transmits various types of information to an external information processing device. The transmission unit 142 transmits various types of information to other information processing devices such as the determination device 100 . For example, the transmission unit 142 transmits information for requesting purchase received from the user.

[4. Configuration of Decision Device]
Next, the configuration of the determination device 100 according to the embodiment will be described using FIG. FIG. 4 is a diagram illustrating a configuration example of the determination device 100 according to the embodiment. As shown in FIG. 4 , the determination device 100 has a communication section 110 , a storage section 120 and a control section 130 . The decision making device 100 has an input unit (for example, keyboard, mouse, etc.) for receiving various operations from the administrator of the decision making device 100, and a display unit (for example, liquid crystal display, etc.) for displaying various information. good too.

(Communication unit 110)
The communication unit 110 is implemented by, for example, a NIC. The communication unit 110 is connected to the network N by wire or wirelessly, and exchanges information with the exhibitor terminal 10 or the like via the network N.

(storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM or flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 4 , the storage unit 120 has a new product information storage unit 121 and a used product information storage unit 122 .

The new product information storage unit 121 stores predetermined new product information (for example, new product list price, sales start time, brand, category, etc.) linked to the model number. Here, FIG. 5 shows an example of the new product information storage unit 121 according to the embodiment. As shown in FIG. 5, the new product information storage unit 121 has items such as "model number" and "new product information".

"Model number" indicates a model number for identifying a product on a predetermined online shopping mall. “New product information” indicates new product information of the product.

That is, in FIG. 5, the new product information of the product identified by the model number "YYXX11" is "regular price: 5,000 yen, sales start date: January 1, 2000, brand: AABB, category: T-shirt (white)". Here is an example.

The second-hand product information storage unit 122 stores predetermined second-hand product information linked to the model number (for example, the sales price of n times before, the off rate at the time of the previous sale, the sales price increase/decrease from the time before last, the sales price from the previous exhibition to the sale number of days, purchase (trade-in) price, purchase (trade-in) year). Here, FIG. 6 shows an example of the used product information storage unit 122 according to the embodiment. As shown in FIG. 6, the second-hand product information storage unit 122 has items such as "model number" and "second-hand product information".

"Model number" indicates identification information for identifying a product on a predetermined online shopping mall. “Second-hand product information” indicates second-hand product information of the product.

That is, in FIG. 6, the second-hand product information of the product identified by the model number “YYXX11” is “previous sales price: 3,000 yen; × 〇 yen; Sales price 4 times ago: 〇〇 XX yen, Off rate at the time of previous sale: 10%, Increase/decrease in sales price from the time before last to the previous time: 5% increase, Number of days from last listing to sale: 2 weeks, Purchase price: 1,000 yen, year of purchase: 2021”.

(control unit 130)
The control unit 130 is a controller, and is implemented, for example, by executing various programs stored in a storage device inside the determination device 100 using a RAM as a work area by a CPU, MPU, or the like. Also, the control unit 130 is a controller, and is implemented by an integrated circuit such as an ASIC or FPGA, for example.

As shown in FIG. 4, the control unit 130 includes an acquisition unit 131, an identification unit 132, a generation unit 133, a determination unit 134, a calculation unit 135, a determination unit 136, and a provision unit 137. It implements or performs the information processing operations described below. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 4, and may be another configuration as long as it performs information processing described later.

(Acquisition unit 131)
Acquisition unit 131 acquires various types of information. Acquisition unit 131 acquires various types of information from an external information processing device. The acquisition unit 131 acquires various types of information from other information processing devices such as the user terminal 10 .

Acquisition unit 131 acquires various types of information from storage unit 120 . The acquisition unit 131 acquires various types of information from the new product information storage unit 121 and the second-hand product information storage unit 122 . The acquisition unit 131 also stores the acquired various information in the storage unit 120 . The acquisition unit 131 stores various types of information in the new product information storage unit 121 and the used product information storage unit 122 .

The acquisition unit 131 acquires, for example, information for requesting purchase of a product, which is transmitted from the user terminal 10 . Then, based on the information for requesting the purchase of the product, the acquisition unit 131 obtains, for example, the business operator information of the predetermined service for which the purchase of the product is requested, and the predetermined electronic Acquire business operator information of the shopping district.

(Specifying unit 132)
For example, based on the information acquired by the acquisition unit 131, the specifying unit 132 determines whether the predetermined service requested to purchase the product has a predetermined relationship with the predetermined online shopping mall where the user purchased the same new product. It is determined whether or not there is For example, the identifying unit 132 determines whether or not they are the same provider, or whether the provider of one service belongs to the provider of the other service. If the identifying unit 132 determines that the predetermined service requested to purchase the product has a predetermined relationship with the predetermined online shopping mall where the user purchased the same new product, the specifying unit 132 determines the predetermined relationship. Acquire the purchase history at a predetermined online shopping mall that is determined to have a certain relationship, and specify the model number of a new product of the same product at the predetermined online shopping mall that is determined to have a predetermined relationship based on the acquired purchase history. do.

Further, when the specifying unit 132 determines that the predetermined service requested to purchase the product does not have a predetermined relationship with the predetermined electronic shopping mall where the user purchased the same new product, for example Predetermined online shopping mall having a predetermined relationship with the predetermined service requested to purchase the product based on the tag information attached to the actual product sent to the store of the predetermined service requested to purchase to specify the model number of a new product of the same product.

(Generating unit 133)
The generation unit 133 generates a model for outputting a sales price for each condition of a second-hand product, based on the new product information and the second-hand product information of products that have been sold. For example, the generation unit 133 generates a model based on XGBoost or the like, using new product information of products with a sales record and second-hand product information up to the previous sale as explanatory variables, and using the previous sales price as an objective variable. In this way, the generation unit 133 uses the second-hand product information up to the time of the previous sale as an explanatory variable, thereby generating a model that outputs the previous sales price, for example, the sales price from two to five times before. It should be noted that the product with a sales record may be the same product as the product requested to purchase, or may be a different product from the product requested to purchase. In addition, the generation unit 133 learns the model by using, as a positive example, the sales price of a predetermined condition that is predetermined as a reference condition among the conditions of second-hand goods.

(Determination unit 134)
The determination unit 134 determines whether or not the second-hand product information of some conditions is insufficient. If the determining unit 134 determines that the second-hand product information is insufficient for some conditions, it identifies the partial conditions for which the second-hand product information is lacking.

The determination unit 134 determines whether or not the estimated price for sales of some conditions is higher than the estimated price for sales of higher conditions than the part of conditions, and a turnover has occurred. If the determining unit 134 determines that the estimated price for sales of a condition higher than the part of the condition is higher than the estimated price and the inside-out has occurred, the part of the condition in which the inside-out has occurred is specified.

(Calculation unit 135)
The calculation unit 135 acquires predetermined new product information and used product information in association with the model number of the new product specified by the specifying unit 132 . That is, the calculation unit 135 acquires new product information and used product information to be input to the model generated by the generation unit 133 . Then, the calculation unit 135 inputs the acquired new product information and used product information to the model generated by the generation unit 133 to calculate the selling price of the used product for each condition. In this way, the generation unit 133 generates a model that outputs the previous sales price, for example, at the sales price two to five times before, and the calculation unit 135 outputs the future sales price at the sales price from the previous time to the fourth time before. Calculate the price.

The calculation unit 135 multiplies the calculated sales price for each condition by a correction coefficient to calculate an estimated price for sales for each condition. For example, the calculation unit 135 multiplies the sales price of each condition by the same correction coefficient to calculate the estimated price for the sale of each condition.

The calculation unit 135 adds the second-hand product information specified by the determination unit 134 to the sales price of the reference condition output from the model based on the second-hand product information of the reference condition. By multiplying by the corresponding correction factor, an estimated price for sales of some conditions for which second-hand product information is lacking is calculated.

The calculation unit 135 adds a correction coefficient corresponding to the part of the condition in which the inside-out occurred specified by the determination unit 134 to the sales price in the reference condition output from the model based on the second-hand product information in the reference condition. Multiply by to get an estimated price for the sale of the part of the condition where the inside-out occurred.

(Determination unit 136)
The determining unit 136 determines the estimated price calculated by the calculating unit 135 as an estimated price for sales for each condition. In addition, the calculation unit 135 compares, for example, a corrected price obtained by multiplying the selling price by a correction coefficient and an upper limit price obtained by multiplying the selling price by a specific coefficient, and determines whether the corrected price exceeds the upper limit price. judge. Then, when the calculation unit 135 determines that the correction price exceeds the upper limit price, the calculation unit 135 sets the upper limit price as the estimated price.

(Providing unit 137)
The providing unit 137 transmits information for displaying on the user terminal 10 the purchase price determined based on the estimated price for the sale of the reference condition as the trade-in price. The providing unit 137 also transmits information for displaying the purchase price determined based on the estimated price for the sale for each condition on the terminal device of the seller for each condition.

[5. Decision processing flow]
Next, the procedure of decision processing by the decision system 1 according to the embodiment will be described with reference to FIG. FIG. 7 is a flow chart showing the procedure of determination processing by the determination system 1 according to the embodiment.

As shown in FIG. 7, the determination device 100 acquires new product information of a product that the user has requested to buy and used product information of the same product that has been sold in the past (step S201).

The determination device 100 calculates the selling price of the second-hand product for each condition based on the acquired new product information and second-hand product information (step S202).

The determination device 100 determines an estimated price for sales of the second-hand product for each condition based on the calculated sales price for each condition (step S203).

[6. effect〕
As described above, the determination device 100 according to the embodiment has the acquisition unit 131 and the determination unit 136 . The acquiring unit 131 acquires new product information of the target product and second-hand product information of the target product that has been sold in the past. The determination unit 136 determines, for each condition, an estimated price for the second-hand product sold for each condition, based on the new product information and the second-hand product information acquired by the acquisition unit 131 .

As a result, the determination device 100 according to the embodiment can estimate the price based on both the new product information and the second-hand product information, so that it is possible to set an appropriate price with high accuracy. Moreover, since the determination device 100 according to the embodiment can estimate the price for each condition, it is possible to set an appropriate price. In other words, the determination device 100 according to the embodiment can appropriately determine a fair price for sales according to the condition of the second-hand product, thereby improving the accuracy of pricing the second-hand product.

Further, the determination device 100 according to the embodiment determines whether or not second-hand product information corresponding to a part of the condition different from a predetermined condition predetermined as a reference condition is lacking in the second-hand product information. It further has a determination unit 134 . Further, when the determination unit 134 determines that the second-hand product information corresponding to some conditions is insufficient, the determination unit 136 determines part of the second-hand product information corresponding to predetermined conditions. determine the estimated price for the sale of the condition of

As a result, the determination device 100 according to the embodiment can set an appropriate price even when second-hand product information is insufficient depending on the condition.

In addition, if the estimated price for sales of some conditions is higher than the estimated price for sales of higher conditions than the part of conditions, the determination unit 136 determines the second-hand product information according to the predetermined conditions. determines the estimated price for the sale of some condition.

As a result, the determination device 100 according to the embodiment can appropriately perform price correction when an estimated price is reversed due to some error.

In addition, when inputting the new product information of the product and the second-hand product information of the second-hand product that has been sold in the past, the determination unit 136 determines the estimated price for each condition of the second-hand product. An estimated price is determined by inputting new product information of the target product and second-hand product information of the target product that has been sold in the past to a model that outputs a certain sales price for each condition. Also, the second-hand product information includes information on the period from exhibition to sale of the second-hand product.

As a result, even if the sales price of a predetermined condition that is a positive example is incorrect, the determination device 100 according to the embodiment corrects the sales price of each condition so that it converges to an appropriate sales price. can be done.

In addition, the determination unit 136 determines an estimated price for sales of second-hand goods for each condition based on the sales price for each condition.

Thereby, the determination device 100 according to the embodiment can set an appropriate price.

Further, the determining unit 136 determines an estimated price related to the sale of the condition of the second-hand product by multiplying the sales price of the condition by a correction coefficient according to the condition.

Thereby, the determination device 100 according to the embodiment can set an appropriate price.

Also, the determination unit 136 determines an estimated price for sales of a part of condition by multiplying the sales price of a predetermined condition by a correction coefficient corresponding to the part of condition.

As a result, the determination device 100 according to the embodiment can set an appropriate price even when second-hand product information is insufficient depending on the condition.

Also, the correction coefficient becomes smaller as the period from the start of sales of a new product to the latest used purchase becomes longer.

Thereby, the determination device 100 according to the embodiment can set an appropriate price according to the sales of second-hand goods.

In addition, the determining unit 136 compares the corrected price obtained by multiplying the selling price by the correction coefficient and the upper limit price obtained by multiplying the selling price by the specific coefficient, and determines that the corrected price is higher than the upper limit price. , the ceiling price is the estimated price.

As a result, the determination device 100 according to the embodiment can optimize the price setting so as not to greatly deviate from the list price of a new product when the second-hand product sells quickly and becomes a premium product.

Further, the specific coefficient is a coefficient predetermined for each product class.

Thereby, the determination device 100 according to the embodiment can set the maximum price according to each product class.

In addition, the determination device 100 according to the embodiment provides the user with a purchase price based on the estimated price for sales of a predetermined condition as a trade-in price, and also provides the second-hand product seller with an estimated sales price for each condition. It further has a providing unit 137 that provides a purchase price based on the price for each condition.

Thereby, the determination device 100 according to the embodiment can present a purchase price based on appropriate pricing.

[7. Hardware configuration]
Also, the user terminal 10 and the determination device 100 according to the above-described embodiments are implemented by a computer 1000 configured as shown in FIG. 8, for example. FIG. 8 is a hardware configuration diagram showing an example of a computer that implements the functions of the user terminal 10 and the decision device 100. As shown in FIG. Computer 1000 has CPU 1100 , RAM 1200 , ROM 1300 , HDD 1400 , communication interface (I/F) 1500 , input/output interface (I/F) 1600 and media interface (I/F) 1700 .

The CPU 1100 operates based on programs stored in the ROM 1300 or HDD 1400 and controls each section. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, a program depending on the hardware of the computer 1000, and the like.

The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. Communication interface 1500 acquires data from another device via a predetermined communication network, sends the data to CPU 1100, and transmits data generated by CPU 1100 to another device via a predetermined communication network.

The CPU 1100 controls output devices such as displays and printers, and input devices such as keyboards and mice, through an input/output interface 1600 . CPU 1100 acquires data from an input device via input/output interface 1600 . CPU 1100 also outputs the generated data to an output device via input/output interface 1600 .

Media interface 1700 reads programs or data stored in recording medium 1800 and provides them to CPU 1100 via RAM 1200 . CPU 1100 loads such a program from recording medium 1800 onto RAM 1200 via media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. etc.

For example, when the computer 1000 functions as the user terminal 10 and the determination device 100 according to the embodiment, the CPU 1100 of the computer 1000 implements the functions of the control units 14 and 130 by executing programs loaded on the RAM 1200. . CPU 1100 of computer 1000 reads these programs from recording medium 1800 and executes them, but as another example, these programs may be obtained from another device via a predetermined communication network.

[8. others〕
Further, among the processes described in the above embodiments, all or part of the processes described as being automatically performed can be manually performed, or the processes described as being performed manually can be performed manually. All or part of this can also be done automatically by known methods. In addition, information including processing procedures, specific names, various data and parameters shown in the above documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

Also, each component of each device illustrated is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution and integration of each device is not limited to the one shown in the figure, and all or part of them can be functionally or physically distributed and integrated in arbitrary units according to various loads and usage conditions. Can be integrated and configured.

Further, the embodiments described above can be appropriately combined within a range that does not contradict the processing contents.

As described above, some of the embodiments of the present application have been described in detail based on the drawings. It is possible to carry out the invention in other forms with modifications.

Also, the above-mentioned "section, module, unit" can be read as "means" or "circuit". For example, the acquisition unit can be read as acquisition means or an acquisition circuit.

1 determination system 10 user terminal 11 communication unit 12 input unit 13 output unit 14 control unit 100 determination device 110 communication unit 120 storage unit 121 new product information storage unit 122 second-hand product information storage unit 130 control unit 131 acquisition unit 132 identification unit 133 generation unit 134 determination unit 135 calculation unit 136 determination unit 137 provision unit 141 reception unit 142 transmission unit N network

Claims (12)

New product information of the target product, including at least price information, and second-hand product information of the target product that has been sold in the past , including at least price information and condition information, and information on the period from listing to sale of the above-mentioned second-hand product an acquisition unit that acquires second-hand product information including
Acquired by the acquisition unit to a model trained to output a sales price for calculating an estimated price of sales for each condition of a second-hand product when new product information and second-hand product information of the product are input a determination unit that inputs new product information and second-hand product information to determine an estimated price for sales of each condition of the second-hand product for each condition;
A decision device, comprising: a determination unit for determining whether or not second-hand product information corresponding to a part of the second-hand product information that differs from a predetermined condition as a reference condition is lacking;
further having
The decision unit
When it is determined by the determination unit that the second-hand product information corresponding to the part of the condition is insufficient, sales of the part of the condition are based on the second-hand product information corresponding to the predetermined condition. 2. The apparatus of claim 1, wherein the apparatus determines an estimated price for a. The decision unit
If the estimated price for the sale of a part of the condition that differs from the predetermined condition that is predetermined as the standard condition is higher than the estimated price for the sale of a higher condition than the part of the condition, the predetermined condition 3. The determination device according to claim 1 or 2, wherein an estimated price for sale of said partial condition is determined based on second-hand goods information corresponding to said condition. The decision unit
4. The determination device according to claim 2, wherein an estimated price for sales of the second-hand goods for each condition is determined based on the sales price for each condition. The decision unit
5. The determination device according to claim 4 , wherein the estimated price for the sale of the used condition is determined by multiplying the sale price of the condition by a correction factor according to the condition. The decision unit
5. The method of claim 4 , wherein the estimated price for the sale of the partial condition is determined by multiplying the selling price of the predetermined condition by a correction factor according to the partial condition. decision device. 7. The determination device according to claim 5 , wherein the correction coefficient becomes smaller as the period from the start of sales of new products to the latest purchase of second-hand products becomes longer. The decision unit
8. The estimated price is determined based on a comparison between a corrected price based on the selling price and the correction coefficient and a maximum price based on the selling price and a specific coefficient . 2. The determination device according to item 1. The determination device according to claim 8 , wherein the specific coefficient is a coefficient predetermined for each product class. Providing the user with a purchase price as a trade-in price based on an estimated price for the sale of a predetermined condition determined in advance as a reference condition, and providing the second-hand product seller with an estimated price for the sale for each of the conditions. 10. The determination device according to any one of claims 1 to 9 , further comprising a providing unit that provides a purchase price based on the condition for each condition. A computer implemented method of determination comprising:
New product information of the target product, including at least price information, and second-hand product information of the target product that has been sold in the past , including at least price information and condition information, and information on the period from listing to sale of the above-mentioned second-hand product an acquisition step of acquiring second-hand product information including
When the new product information and the second-hand product information of the product are input, the model learned to output the sales price for calculating the estimated price for the sales of each condition of the second-hand product of the product acquired by the acquisition step a determination step of determining an estimated sales price for each condition of the second-hand product by inputting new product information and second-hand product information;
A determination method comprising: New product information of the target product, including at least price information, and second-hand product information of the target product that has been sold in the past , including at least price information and condition information, and information on the period from listing to sale of the above-mentioned second-hand product an acquisition procedure for acquiring second-hand product information including
When new product information and second-hand product information of a product are input, a model trained to output a sales price for calculating an estimated price for sales of each condition of the second-hand product of the product acquired by the acquisition procedure a determination procedure for determining, for each condition, an estimated price for sales of the second-hand product for each condition by inputting new product information and second-hand product information;
A decision program characterized by causing a computer to execute

Images