Information processing device, information processing method, and information processing program

Abstract

An appropriate purchase price will be determined based on the user. [Solution] The information processing device of the present application is characterized by having an estimation unit that estimates, based on information about a user (information about products that the user has offered as items for purchase), whether the user is a good user who offers products that meet specified conditions as items for purchase, a determination unit that determines the purchase price of the products offered by the user based on the estimation result by the estimation unit, and a presentation unit that presents the purchase price determined by the determination unit to the user.

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] Conventionally, there are known technologies for supporting the purchase of secondhand goods. One example of such a technology is a technology that calculates the supply and demand balance in the market based on the distribution status of the goods and determines an appropriate selling price for a secondhand product of the same goods that was previously sold. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2001-134635 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the above-mentioned techniques do not necessarily allow for determining an appropriate purchase price according to the user.

[0005] For example, the above-mentioned technology merely determines the selling price of a used item based on the distribution status of the item, and does not necessarily determine an appropriate purchase price depending on the user.

[0006] The present application has been made in view of the above, and aims to determine an appropriate purchase price according to the user. [Means for solving the problem]

[0007] The information processing device of the present application is characterized by having an estimation unit that estimates, based on information about the user, whether the user is a good user who offers products that meet specified conditions as items to be purchased, a determination unit that determines a purchase price for the products offered by the user based on the estimation result by the estimation unit, and a presentation unit that presents the purchase price determined by the determination unit to the user. [Effects of the Invention]

[0008] According to one aspect of the embodiment, it is possible to obtain an effect that an appropriate purchase price can be determined according to the user. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of an information processing system 1 according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of information processing according to the embodiment. [Figure 3] FIG. 3 is a diagram showing an example of the configuration of the information processing device 10 according to the embodiment. [Figure 4] FIG. 4 is a diagram showing an example of the product information database 31 according to the embodiment. [Figure 5] FIG. 5 is a diagram showing an example of the user information database 32 according to the embodiment. [Figure 6] FIG. 6 is a flowchart illustrating an example of a procedure for information processing according to the embodiment. [Figure 7] FIG. 7 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 10. As shown in FIG. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, an information processing device, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to these embodiments. Furthermore, the same components in the following embodiments will be denoted by the same reference numerals, and duplicated descriptions will be omitted.

[0011] (Embodiment) [1. Information Processing System Configuration] First, an information processing system 1 according to an embodiment will be described. FIG. 1 is a diagram showing an example of the configuration of the information processing system 1 according to an embodiment. As shown in FIG. 1, the information processing system 1 includes an information processing device 10 and a user terminal 100. The information processing device 10 and the user terminal 100 are connected to each other via a predetermined communication network (network N) so as to be able to communicate with each other via wired or wireless communication. Note that the information processing system 1 shown in FIG. 1 may include a plurality of information processing devices 10 and a plurality of user terminals 100.

[0012] The information processing device 10 is an information processing device that estimates whether a user is a good user who will offer (send, sell) products that meet predetermined conditions as purchase targets, and performs information processing according to the estimation result, and is realized, for example, by a server device, a cloud system, etc. For example, the information processing device 10 provides an e-commerce service #1 that offers (sells) products (fashion items). Here, fashion items include various items related to clothing, such as clothes, footwear (also called shoes), headwear (e.g., caps, hats, etc.), ornaments (also called accessories), bags, cosmetics, etc.

[0013] Furthermore, the information processing device 10 purchases products (hereinafter referred to as "owned products") that the user has purchased and owns through e-commerce service #1 (or another e-commerce service or store, etc.), and offers (sells) the purchased products (hereinafter referred to as "used products") via the e-commerce service #1. For example, the information processing device 10 manages information about the user's owned products (e.g., identification information (product ID) that identifies the owned products, category, brand, selling price of new products, selling price of used products, price range, corresponding era (e.g., 2024 items), corresponding season (e.g., spring / summer items, fall / winter items), etc.) in a storage unit of the device. The information processing device 10 then presents information about offers to purchase the owned products (e.g., information indicating products (hereinafter referred to as "designated products") designated by the administrator #1 of the e-commerce service #1, etc., and the purchase price of the designated products) to the user via the user terminal 100. Here, if the user wishes to sell their possessions (sends a request to sell the possessions from the user terminal 100), the information processing device 10 will grant the user a profit (for example, points that can be used in the e-commerce service #1) corresponding to the purchase price of the possessions via the user terminal 100. The user then provides (sends, sells) to administrator #1 the items that correspond to the purchase request (for example, designated products and products other than designated products (in other words, bundled items)). The information processing device 10 then provides (sells) the used items (in other words, the items to be purchased) provided (sent, sold) by the user via electronic commerce service #1. For example, the information processing device 10 provides (sells) the used items provided (sent, sold) by the user at a selling price based on the appraisal results of the used items provided (sent, sold) by administrator #1, etc. As an example, the information processing device 10 provides (sells) the used items provided (sent, sold) by the user at a selling price based on the appraisal results regarding the storage condition (for example, one of five assessment levels: "Condition #1 (Like New)", "Condition #2 (No Signs of Use)", "Condition #3 (No Signs of Noticeable Use)", "Condition #4 (Some Signs of Use)", or "Condition #5 (Scratches, Stained)").

[0014] The information processing device 10 may have a function as a web server that provides a website related to the e-commerce service #1. The information processing device 10 may also be a device that distributes information to be displayed in applications related to various services installed in the user terminal 100 to the user terminal 100. The information processing device 10 may also be a device that distributes the application data itself.

[0015] Furthermore, the information processing device 10 may function as a distribution device that distributes control information to the user terminal 100. Here, the control information is written in, for example, a script language such as JavaScript (registered trademark) or a style sheet language such as CSS (Cascading Style Sheets). Note that the application itself distributed from the information processing device 10 may be regarded as the control information.

[0016] The user terminal 100 is an information processing device used by a user. The user terminal 100 is realized, for example, by a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. The user terminal 100 displays information distributed by the information processing device 10 using a web browser or an application. Note that the example shown in FIG. 2 shows a case where the user terminal 100 is a smartphone.

[0017] [2. An example of information processing] Next, an example of information processing realized by an information processing device etc. according to this embodiment will be described with reference to FIG. 2. FIG. 2 is a diagram showing an example of information processing according to this embodiment. In the following description, it is assumed that the user terminal 100 is used by a user (user U1) identified by the user ID "UID#1". In addition, in the following description, the user terminal 100 may be considered to be the same as the user U1. In other words, in the following, user U1 can also be read as the user terminal 100.

[0018] First, the information processing device 10 purchases a product (possession) owned by user U1 (step S1). For example, when user U1 purchases a new product in e-commerce service #1, the information processing device 10 presents information regarding a proposal to purchase the possessed item via the user terminal 100. Note that even when user U1 does not purchase a new product in e-commerce service #1, the information processing device 10 presents information regarding a proposal to purchase the possessed item via the user terminal 100. Here, if user U1 wishes to purchase the possessed item (sends a purchase request for the possessed item from the user terminal 100), the information processing device 10 sells the newly purchased product to the user at a selling price obtained by subtracting the purchase price of the possessed item from the selling price of the product. Thereafter, user U1 provides (sends, sells) the possessed item corresponding to the purchase request to administrator #1 of the information processing device 10. Then, the information processing device 10 offers (sells) the used items provided (sent, sold) by user U1 to other users via the electronic commerce service #1. For example, the information processing device 10 offers (sells) the used items provided (sent, sold) by user U1 at a selling price based on the appraisal results regarding the condition of the used items. The information processing device 10 also manages the appraisal results of the owned items provided (sent, sold) by user U1 in a memory unit of the device itself.

[0019] In the example of FIG. 2, it is assumed that the above-described process for buying back user U1's belongings (hereinafter referred to as "buy-back process") has been performed five or more times. In other words, it is assumed that user U1 has requested to buy back his / her belongings (sent a buy-back request for the belongings from the user terminal 100) five or more times in the past. In the following explanation, the buy-back process for user U1 that was last performed at the current time (in other words, the buy-back process performed one time before the current time) will be referred to as buy-back process #1. The buy-back process performed one time before buy-back process #1 (in other words, the buy-back process performed two times before the current time) will be referred to as buy-back process #2. The buy-back process performed one time before buy-back process #2 (in other words, the buy-back process performed three times before the current time) will be referred to as buy-back process #3. The buy-back process performed one time before buy-back process #3 (in other words, the buy-back process performed four times before the current time) will be referred to as buy-back process #4. Also, the resale transaction performed immediately before resale transaction #4 (in other words, the resale transaction performed five times before the current time) is described as resale transaction #5.

[0020] Next, the information processing device 10 estimates, based on the information about user U1, whether user U1 is a good user who will offer possessions that meet predetermined conditions as purchase items in the next buy-back process (step S2). For example, based on the information about user U1 at each point in time when buy-back processes #1 to #5 were performed, the information processing device 10 estimates whether user U1 is a good user who will offer (send, sell) possessions in good condition (e.g., condition #1 or condition #2) as purchase items in the next buy-back process (including estimating the probability that user U1 is a good user). As a specific example, the information processing device 10 estimates whether a predetermined threshold or more (e.g., 80% or more) of the possessions that user U1 will offer (send, sell) as purchase items in the next buy-back process are target goods (including estimating the probability that items above the predetermined threshold are target goods). For example, if user U1 offers (sends, sells) five possessions, it is estimated whether four or more of them are target products.

[0021] For example, the information processing device 10 trains (constructs) model #1 so that when information about user U1 (in other words, explanatory variables x1 to x4) at each point in time when buyback processes #2 to #5 were performed (for example, the point in time immediately before the user U1 provided (sent, sold) the owned item to be bought) is input, the information processing device 10 outputs information indicating whether user U1 is a good user in buyback process #1 (in other words, objective variable y). For example, when the information processing device 10 determines that user U1 is a good user in buyback process #1 based on the appraisal results of the used items provided (sent, sold) by user U1 in buyback process #1 (the used items provided (sent, sold) by user U1 in buyback process #1 that are equal to or greater than a predetermined threshold are target items), the information processing device 10 trains model #1 so that the information about user U1 at each point in time when buyback processes #2 to #5 were performed outputs a score of "1" indicating that user U1 is a good user. In addition, if the information processing device 10 determines that user U1 is not a good user in purchase process #1 based on the appraisal results of the used items provided (sent, sold) by user U1 in purchase process #1, it trains model #1 so that it outputs a score of "0" indicating that user U1 is not a good user based on information about user U1 at each point in time when purchase processes #2 to #5 were performed.

[0022] Then, the information processing device 10 inputs information about user U1 at each point in time when buyback processes #1 to #4 were performed (in other words, explanatory variables x1 to x4) into model #1, and estimates whether user U1 will be a good user in the next buyback process based on the output score (in other words, objective variable y). For example, if the score output from model #1 is equal to or greater than a predetermined threshold (e.g., 0.8 or greater), the information processing device 10 estimates that user U1 will be a good user in the next buyback process.

[0023] The information about user U1 at the time of the buyback process (in other words, the explanatory variables) may be, for example, the number of owned items at that time, the total price of the owned items (e.g., the selling price in e-commerce service #1), the number of owned items that are the target item, the total price of the owned items that are the target item, the number of owned items other than the target item, the total price of the owned items other than the target item, the average number of owned items (hereinafter referred to as "items to be bought") that were the subject of buyback processes prior to that time (n (n is any natural number) times ago), the average price of the items to be bought (e.g., buyback price), the average number of items to be bought that are the target item, the average price of items to be bought that are the target item, the average number of items to be bought other than the target item, the average price of items to be bought other than the target item, the presence or absence of the target item, etc. The buyback price may be a buyback price according to the storage state, or if it is simply desired to learn how many buyback processes have been performed, a buyback price assuming that the storage state is in a predetermined state (e.g., state #3) regardless of the storage state.

[0024] Furthermore, the information about user U1 at the time the buyback process was performed may be, for example, the number of days from that time to the time the previous buyback process was performed (recency), the number of times buyback processes were performed in a predetermined period from that time (e.g., the most recent year) (frequency), the total amount (monetary) of the prices (e.g., buyback amounts) of the possessions that were the subject of buyback processes performed in a predetermined period from that time to the time, the number of days from that time to the time when a buyback process that satisfies predetermined conditions was performed in the past (e.g., a buyback process in which a target product was the subject of buyback) was performed, the number of times buyback processes that satisfy predetermined conditions were performed in a predetermined period from that time to the time, the total amount of the prices of the target products that were the subject of buyback processes performed in a predetermined period from that time to the time, etc. Furthermore, the information about user U1 at the time the buyback process was performed may be the number of days from the purchase of the possessions or target products that were the subject of buyback to the provision (sending, selling) of the possessions or target products that were the subject of buyback, or the average number of days thereafter.

[0025] Any known technology can be applied to the training of Model #1, and a learning method appropriately selected depending on the information used as training data may be used. For example, Model #1 may be trained using various conventional machine learning technologies (e.g., supervised machine learning technologies such as SVM (Support Vector Machine)). Model #1 may also be trained using deep learning technologies. For example, Model #1 may be trained using various deep learning technologies such as RNN (Recurrent Neural Network) and CNN (Convolutional Neural Network).

[0026] Next, the information processing device 10 determines the resale price of the belongings of user U1 (step S3). In the example of FIG. 2, it is assumed that user U1 is estimated to be a good user in the next resale process. In this case, the information processing device 10 determines the resale price of user U1's belongings to be higher than the normal price offered if the user is estimated not to be a good user. For example, for a user who is estimated not to be a good user, the information processing device 10 assumes that the storage condition of the belongings is condition #3, and sets the resale price of such user's belongings to a price based on condition #3 (normal price). On the other hand, for user U1 who is estimated to be a good user, the information processing device 10 assumes that the storage condition of the belongings is better than condition #3, and sets the resale price of user U1's belongings to a price higher than the normal price (for example, a price based on condition #1 or #2).

[0027] Next, the information processing device 10 presents the purchase price determined in step S3 to the user U1 (step S4). For example, when the user U1 purchases a new product in the electronic commerce service #1, the information processing device 10 presents the purchase price determined in step S3 via the user terminal 100 as information regarding a proposal to purchase the owned item.

[0028] As described above, the information processing device 10 according to the embodiment estimates whether the user is a good user who will offer (send or sell) possessions in good condition as items to be repurchased in the next repurchase process, and determines the repurchase price to be offered to the user based on the estimation result. This allows the information processing device 10 according to the embodiment to determine an appropriate repurchase price according to the user.

[0029] Furthermore, in the past, when purchasing a user's belongings by offering a purchase price in advance, it was not possible to confirm the actual condition of the belongings, so the purchase price was sometimes offered to every user assuming that the belongings were in a certain condition (for example, condition #3). In such cases, even for good users who offer possessions in a better condition than condition #3, the purchase price based on condition #3 would be offered, which could reduce the motivation of good users to sell their possessions.

[0030] In contrast, the information processing device 10 of the embodiment can offer a higher purchase price than usual to good users who sell their belongings that are in good condition, thereby increasing the motivation of good users to sell their belongings.

[0031] [3. Other processing examples] The above-described process is merely an example, and the information processing device 10 may perform various processes using various information. In this regard, examples are listed below.

[0032] [3-1. About Good Users] In the example of FIG. 2, the information processing device 10 may estimate whether user U1 is a preferred user who will offer (send or sell) a product of a predetermined brand as a target for resale in the next resale process. In this case, the information processing device 10 sets the target product to be a product of the predetermined brand. Then, the information processing device 10 estimates whether or not a predetermined threshold or more of the owned items that user U1 will offer (send or sell) as a target for resale in the next resale process are target products (i.e., whether user U1 is a preferred user). For example, if the information processing device 10 determines that user U1 is a preferred user in resale process #1 based on the appraisal results (e.g., whether or not the used item is a product of a predetermined brand) of the used item offered (sent or sold) by user U1 in resale process #1, the information processing device 10 trains model #1 so as to output a score of "1" indicating that user U1 is a preferred user based on information about user U1 at each time point when resale processes #2 to #5 are performed. Furthermore, if user U1 is determined not to be a good user in repurchase process #1, model #1 is trained to output a score of "0" indicating that user U1 is not a good user based on information about user U1 at each point in time when repurchase processes #2 to #5 were performed. Then, the information processing device 10 inputs information about user U1 at each point in time when repurchase processes #1 to #4 were performed into model #1, and estimates whether user U1 is a good user in the next repurchase process based on the output score.

[0033] The information processing device 10 may also estimate whether user U1 is a preferred user who will offer (send or sell) products in a predetermined price range (e.g., a high price range) or a predetermined brand class (e.g., a high brand class) as items to be resold in the next resale transaction. In this case, the information processing device 10 sets the target products to be products in a predetermined price range or a predetermined brand class. Then, the information processing device 10 estimates whether, among the owned items that user U1 will offer (send or sell) as items to be resold in the next resale transaction, items equal to or greater than a predetermined threshold are target products (i.e., whether user U1 is a preferred user). For example, if the information processing device 10 determines that user U1 is a preferred user in resale transaction #1 based on the appraisal results (e.g., whether the products are in a predetermined price range or a predetermined brand class) of the used items offered (sent or sold) by user U1 in resale transaction #1, the information processing device 10 trains model #1 so as to output a score of "1" indicating that user U1 is a preferred user, based on information about user U1 at each time point when resale transactions #2 to #5 were performed. Furthermore, when it is determined in the repurchase process #1 that user U1 is not a good user, the information processing device 10 trains the model #1 so as to output a score of "0" indicating that user U1 is not a good user based on information about user U1 at each time point when the repurchase processes #2 to #5 were performed.The information processing device 10 then inputs information about user U1 at each time point when the repurchase processes #1 to #4 were performed into the model #1, and estimates whether user U1 is a good user in the next repurchase process based on the output score.

[0034] The information processing device 10 may also estimate whether user U1 is a good user who will offer a product corresponding to a predetermined era (e.g., a product from 1990) as a target for purchase in the next buy-back process. In this case, the information processing device 10 sets the target product to be a product corresponding to the predetermined era. Then, the information processing device 10 estimates whether, among the owned items that user U1 will offer (send, sell) as a target for purchase in the next buy-back process, items equal to or greater than a predetermined threshold are target products (i.e., whether user U1 is a good user). For example, if the information processing device 10 determines that user U1 is a good user in buy-back process #1 based on the appraisal results (e.g., whether the product is a product corresponding to a predetermined era) of the used item that user U1 offered (send, sell) in buy-back process #1, the information processing device 10 trains model #1 so as to output a score of "1" indicating that user U1 is a good user based on information about user U1 at each time point when buy-back processes #2 to #5 were performed. Furthermore, when it is determined in the repurchase process #1 that user U1 is not a good user, the information processing device 10 trains the model #1 so as to output a score of "0" indicating that user U1 is not a good user based on information about user U1 at each time point when the repurchase processes #2 to #5 were performed.The information processing device 10 then inputs information about user U1 at each time point when the repurchase processes #1 to #4 were performed into the model #1, and estimates whether user U1 is a good user in the next repurchase process based on the output score.

[0035] The information processing device 10 may also estimate whether user U1 is a preferred user who will offer products corresponding to a predetermined season (e.g., spring / summer items or fall / winter items) as items to be resold in the next resale process. In this case, the information processing device 10 sets the target products as products corresponding to the predetermined season. Then, the information processing device 10 estimates whether or not a predetermined threshold or more of the owned items that user U1 will offer (send or sell) as items to be resold in the next resale process are target products (i.e., whether user U1 is a preferred user). For example, if the information processing device 10 determines that user U1 is a preferred user in resale process #1 based on the appraisal results (e.g., whether or not the products are corresponding to a predetermined season) of the used items offered (sent or sold) by user U1 in resale process #1, the information processing device 10 trains model #1 so as to output a score of "1" indicating that user U1 is a preferred user based on information about user U1 at each time point when resale processes #2 to #5 were performed. Furthermore, when it is determined in the repurchase process #1 that user U1 is not a good user, the information processing device 10 trains the model #1 so as to output a score of "0" indicating that user U1 is not a good user based on information about user U1 at each time point when the repurchase processes #2 to #5 were performed.The information processing device 10 then inputs information about user U1 at each time point when the repurchase processes #1 to #4 were performed into the model #1, and estimates whether user U1 is a good user in the next repurchase process based on the output score.

[0036] The information processing device 10 may input a description of an item provided (sent or sold) by user U1 as a purchase target into model #2, which has been trained to output the season corresponding to the item when a description of the item (e.g., a description in e-commerce service #1) is input. The information processing device 10 may then determine the season corresponding to the item by inputting the description of the item. Based on the determination result, the information processing device 10 may estimate whether user U1 is a good user. For example, if the information processing device 10 determines that user U1 is a good user in buyback process #1 based on the determination result using model #2 of the used item provided (sent or sold) by user U1 in buyback process #1, the information processing device 10 trains model #1 to output a score of "1" indicating that user U1 is a good user, based on information about user U1 at each time point when buyback processes #2 to #5 were performed. Furthermore, when it is determined based on the discrimination result that user U1 is not a good user in repurchase process #1, the information processing device 10 trains model #1 so as to output a score of "0" indicating that user U1 is not a good user based on information about user U1 at each time point when repurchase processes #2 to #5 were performed. Then, the information processing device 10 inputs information about user U1 at each time point when repurchase processes #1 to #4 were performed into model #1, and estimates whether user U1 is a good user in the next repurchase process based on the output score.

[0037] Furthermore, the information processing device 10 may input a description of an item owned by user U1 into model #2, which has been trained to output the season corresponding to the item when a description of the item (e.g., a description in e-commerce service #1) is input, thereby determining the season corresponding to the item. Then, based on the determination result, the information processing device 10 may determine whether user U1 owns an item corresponding to a predetermined season (e.g., spring / summer items or fall / winter items). Then, if user U1 owns an item corresponding to a predetermined season, the information processing device 10 may determine and present a purchase price for the item that is higher than the normal price (e.g., a price based on condition #1 or #2).

[0038] Typically, e-commerce service #1 associates search tags with corresponding seasons to allow user U1 to search for desired products. However, search tags for the wrong season may be associated, or search tags for all seasons may be associated to increase the hit rate. Therefore, when attempting to determine whether user U1 owns a product corresponding to a specific season by referencing the associated season as a search tag, there is a risk that the user may mistakenly believe that the user owns a product corresponding to the specific season, even though they do not actually own the product. Therefore, as described above, by determining the season corresponding to user U1's possessions based on the product description, it is possible to more accurately determine whether user U1 owns a product corresponding to the specific season, thereby enabling more appropriate purchase proposals, etc.

[0039] The information processing device 10 may also estimate whether user U1 is a good user who will offer (send or sell) other personal items (hereinafter referred to as "bundled items") in addition to the designated items as items to be resold in the next resale process. In such a case, the information processing device 10 estimates whether the personal items to be offered (sent or sold) by user U1 as items to be resold in the next resale process include other personal items in addition to the designated items (i.e., whether user U1 is a good user). For example, if the information processing device 10 determines that user U1 is a good user in resale process #1 based on the appraisal results of the used items offered (sent or sold) by user U1 in resale process #1 (e.g., whether other personal items in addition to the designated items are included), the information processing device 10 trains model #1 so as to output a score of "1" indicating that user U1 is a good user based on information about user U1 at each time point when resale processes #2 to #5 are performed. Furthermore, when it is determined in the repurchase process #1 that user U1 is not a good user, the information processing device 10 trains the model #1 so as to output a score of "0" indicating that user U1 is not a good user based on information about user U1 at each time point when the repurchase processes #2 to #5 were performed.The information processing device 10 then inputs information about user U1 at each time point when the repurchase processes #1 to #4 were performed into the model #1, and estimates whether user U1 is a good user in the next repurchase process based on the output score.

[0040] In such a case, information about user U1 at the time the purchase process was carried out (in other words, explanatory variables) may include, for example, the number of items owned at that time, the total price of the items owned, the number of items owned that are designated products, the total price of items owned that are designated products, the number of items owned other than the designated products, the total price of items owned other than the designated products, the average number of items purchased in purchase processes prior to that time, the average price of items purchased, the average number of designated products purchased, the average price of designated products purchased, the average number of items purchased other than the designated products (included items), the average price of items purchased other than the designated products, whether or not there are any designated products purchased, whether or not there are any items purchased other than the designated products, etc.

[0041] Furthermore, information about user U1 at the time the purchase process was carried out may include, for example, the number of days from that time to the time the previous purchase process was carried out, the number of purchase processes carried out in a specified period from that time in the past (for example, the most recent year), the total price (for example, the purchase amount) of the owned items that were the subject of purchase in purchase processes carried out in a specified period from that time in the past, the number of days from that time to the time a purchase process that met specified conditions was carried out in the past (for example, a purchase process that purchased included items in addition to the specified product), the number of purchase processes that met specified conditions were carried out in a specified period from that time in the past, the total price of included items that were the subject of purchase in purchase processes carried out in a specified period from that time, etc.

[0042] In addition, the information processing device 10 may estimate whether user U1 is a good user who will offer (send, sell) possessions that meet specified conditions as items for purchase in the next purchase process based on multiple scores, including a score indicating whether user U1 is a good user who will offer (send, sell) possessions in good condition as items for purchase in the next purchase process, a score indicating whether user U1 is a good user who will offer (send, sell) products of a specified brand as items for purchase, a score indicating whether user U1 is a good user who will offer (send, sell) products in a specified price range as items for purchase, a score indicating whether user U1 is a good user who will offer (send, sell) products corresponding to a specified era (for example, items from 1990) as items for purchase, a score indicating whether user U1 is a good user who will offer (send, sell) products corresponding to a specified season (for example, spring / summer items or fall / winter items) as items for purchase, and a score indicating whether user U1 is a good user who will offer (send, sell) bundled items as items for purchase in addition to the specified items. For example, the information processing device 10 estimates whether user U1 is a good user who will offer (send, sell) possessions in good condition as items for purchase in the next purchase process, based on a score indicating whether user U1 is a good user who will offer (send, sell) possessions in good condition as items for purchase in the next purchase process, and a score indicating whether user U1 is a good user who will offer (send, sell) products of a specified brand as items for purchase.

[0043] [3-2. Determination of purchase price] In the example of Figure 2, when user U1 offers a purchase price higher than the normal price, the information processing device 10 determines whether or not the user will be a good user in the purchase process, and if it is determined that the user will be a good user (in other words, if it is determined that the user will offer a purchase price higher than the normal price), it may determine a purchase price higher than the normal price.

[0044] For example, the information processing device 10 trains model #3 so that if a user who offers a purchase price higher than the regular price in a resale process is a good user in the resale process (in other words, if offering a purchase price higher than the regular price is effective), the information processing device 10 outputs a score of "1" based on information about the user. Furthermore, the information processing device 10 trains model #3 so that if a user who offers a purchase price higher than the regular price in a resale process is not a good user in the resale process (in other words, if offering a purchase price higher than the regular price is ineffective), the information processing device 10 outputs a score of "0" based on information about the user. The information processing device 10 then inputs information about user U1 into model #3. Here, it is assumed that the output score is equal to or greater than a predetermined threshold (e.g., 0.8 or greater). In such a case, the information processing device 10 determines that user U1 is a good user in the resale process if he or she offers a purchase price higher than the regular price. The information processing device 10 then determines a purchase price higher than the regular price and presents it to user U1.

[0045] In addition, if the processing using model #1 predicts that user U1 will be a good user in the next buy-back process, and if the processing using model #3 determines that user U1 will not be a good user in the buy-back process when user U1 offers a buy-back price higher than the normal price, the information processing device 10 may determine the buy-back price of user U1's belongings to be the normal price and present it to user U1. In addition, if the processing using model #1 predicts that user U1 will be a good user in the next buy-back process, and if the processing using model #3 determines that user U1 will not be a good user in the buy-back process when user U1 offers a buy-back price higher than the normal price, the information processing device 10 may determine the buy-back price of user U1's belongings to be higher than the normal price and present it to user U1. Furthermore, if the processing using model #1 estimates that user U1 will not be a good user in the next buy-back process, and if the processing using model #3 determines that user U1 will be a good user in the buy-back process if he or she offers a buy-back price higher than the normal price, the information processing device 10 may determine the buy-back price of user U1's belongings to be higher than the normal price and present it to user U1. Furthermore, if the processing using model #1 estimates that user U1 will not be a good user in the next buy-back process, and if the processing using model #3 determines that user U1 will be a good user in the buy-back process if he or she offers a buy-back price higher than the normal price, the information processing device 10 may determine the buy-back price of user U1's belongings to be the normal price and present it to user U1.

[0046] [3-3. About Users] In the example of FIG. 2, the information processing device 10 may estimate whether user U2, who has performed the buy-back process less than five times (e.g., a user using a buy-back service for the first time or a cold-start user), will be a good user in the next buy-back process. For example, when information about the user, such as attribute information, browsing history in e-commerce service #1, purchase history in e-commerce service #1, and information about owned items, is input, the information processing device 10 inputs information about user U2 into model #4, which has been trained to output information (score) indicating whether the user will be a good user in the next buy-back process, thereby estimating whether user U2 will be a good user in the next buy-back process. In other words, model #4 can be said to be a model trained using information about users similar to user U2.

[0047] [3-4. About model learning] In the example of FIG. 2, the information processing device 10 trains the model #1 using the most recent five trade-in processes (trade-in processes #1 to #5) performed by user U1. However, the training of the model #1 is not limited to this example. For example, the information processing device 10 may train the model #1 using the most recent six or more trade-in processes performed by user U1. As a specific example, the information processing device 10 trains the model #1 so that, when information about user U1 at the time points of trade-in processes #2 to #5 and trade-in process #6, which is the trade-in process immediately before trade-in process #5, is input, the model #1 is trained so that the model #1 outputs information (score) indicating whether user U1 is a good user in trade-in process #1. The information processing device 10 then inputs information about user U1 at the time points of trade-in processes #1 to #5 into the model #1, and estimates whether user U1 is a good user in the next trade-in process based on the output score.

[0048] Furthermore, the information processing device 10 may train model #1 using the four or fewer most recent trade-in processes performed by user U1. For example, the information processing device 10 trains model #1 so that when information about user U1 at each time point when trade-in processes #2 to #4 were performed is input, the information processing device 10 outputs information indicating whether user U1 is a good user in trade-in process #1. Then, the information processing device 10 inputs information about user U1 at each time point when trade-in processes #1 to #3 were performed into model #1, and estimates whether user U1 is a good user in the next trade-in process based on the output score.

[0049] 4. Configuration of Information Processing Device Next, the configuration of the information processing device 10 will be described with reference to Fig. 3. Fig. 3 is a diagram showing an example of the configuration of the information processing device 10 according to an embodiment. As shown in Fig. 3, the information processing device 10 has a communication unit 20, a storage unit 30, and a control unit 40.

[0050] (Regarding the communication unit 20) The communication unit 20 is realized by, for example, a network interface card (NIC), etc. The communication unit 20 is connected to the network N by wire or wirelessly, and transmits and receives information to and from the user terminal 100, etc.

[0051] (Regarding the storage unit 30) The storage unit 30 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 3 , the storage unit 30 has a product information database 31, a user information database 32, and a model database 33.

[0052] (About Product Information Database 31) The product information database 31 stores various information related to products provided (sold) by the e-commerce service #1. An example of the information stored in the product information database 31 will now be described with reference to FIG. 4. FIG. 4 is a diagram showing an example of the product information database 31 according to the embodiment. In the example of FIG. 4, the product information database 31 has items such as "product ID," "brand," "price range," "description," and "seasonality."

[0053] "Product ID" indicates identification information for identifying a product. "Brand" indicates the brand of the product. "Price range" indicates the price range of the product. "Description" indicates the description of the product. "Seasonality" indicates the season corresponding to the product, and information such as spring / summer items, fall / winter items, all seasons, etc. is stored.

[0054] That is, Figure 4 shows an example in which the brand of the product identified by the product ID "CID#1" is "Brand #1", the price range is "Price range #1", the description is "Description #1", and the seasonality is "Seasonal #1".

[0055] (Regarding User Information Database 32) The user information database 32 stores various types of information related to users. Here, an example of the information stored in the user information database 32 will be described with reference to FIG. 5. FIG. 5 is a diagram showing an example of the user information database 32 according to the embodiment. In the example of FIG. 5, the user information database 32 has items such as "user ID," "attribute information," "browsing history," "purchase history," "owned item information," and "purchase history."

[0056] "User ID" indicates identification information for identifying a user. "Attribute information" indicates the attributes of a user. "Browsing history" indicates the user's browsing history in e-commerce service #1 and various other services. "Purchase history" indicates the user's purchase history in e-commerce service #1. "Owned item information" indicates information about items that the user has purchased and owns in e-commerce service #1, and stores information such as identification information for identifying the items and the date and time the items were purchased. "Purchase history" indicates information about the purchase of the user's owned items, and stores information such as identification information for identifying the items that were purchased, the date and time the purchase was made (for example, the date and time the purchase request was received from user terminal 100), and the appraisal results of the items.

[0057] (About Model Database 33) The model database 33 stores model #1, which has been trained to output, when information about a user is input, information (score) indicating whether the user will be a good user in the next resale transaction. The model database 33 also stores model #2, which has been trained to output, when a product description is input, the season corresponding to the product. The model database 33 also stores model #3, which has been trained to output, when information about a user is input, information (score) indicating whether the user will be a good user when a resale price higher than the regular price is offered. The model database 33 also stores model #4, which has been trained to output, when information about a user is input, information (score) indicating whether the user will be a good user in the next resale transaction.

[0058] (Regarding the control unit 40) The control unit 40 is a controller, and is realized by, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs stored in a storage device inside the information processing device 10 using RAM as a work area. The control unit 40 is also a controller, and is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). As shown in FIG. 2 , the control unit 40 according to the embodiment has a discrimination unit 41, an estimation unit 42, a determination unit 43, a decision unit 44, and a presentation unit 45, and realizes or executes the functions and actions of information processing described below.

[0059] (Regarding the discrimination unit 41) The discrimination unit 41 determines the season corresponding to the product offered by the user for resale by inputting the description of the product offered by the user for resale into a model trained to output the season corresponding to the product when a description of the product is input. For example, the discrimination unit 41 determines the season corresponding to the product offered by the user for resale or the user's belongings by inputting the description of the product offered by the user for resale (sent or sold) or the user's belongings into a model trained to output the season corresponding to the product when a description of the product is input. As a specific example, in the example of FIG. 2, the discrimination unit 41 refers to the storage unit 30 and inputs the description of the product offered by user U1 for resale or the user's belongings into model #2 trained to output the season corresponding to the product when a description of the product is input, thereby determining the season corresponding to the product.

[0060] (Regarding the estimation unit 42) The estimation unit 42 estimates, based on information about a user, whether the user is a good user who will offer (send, sell) possessions that meet predetermined conditions as items to be repurchased. For example, in the example of Fig. 2, the estimation unit 42 refers to the storage unit 30 and estimates, based on information about user U1, whether user U1 is a good user who will offer (send, sell) possessions that meet predetermined conditions as items to be repurchased in the next repurchase process.

[0061] The estimation unit 42 may also estimate whether a user is a good user based on information about belongings that the user has provided (sent, sold) as items for purchase in the past. For example, in the example of Fig. 2, the estimation unit 42 estimates whether user U1 will be a good user in the next purchase process based on information about belongings that user U1 has provided (sent, sold) as items for purchase.

[0062] Furthermore, the estimation unit 42 may estimate whether a user is a good user by inputting information about the user into a model that has been trained to output information (score) indicating whether the user will be a good user in the next resale transaction when information about the user is input. For example, in the example of Fig. 2, the estimation unit 42 inputs information about user U1 at each time point when resale processes #1 to #4 were performed into model #1, and estimates whether user U1 will be a good user in the next resale transaction based on the output score.

[0063] The estimation unit 42 may also estimate whether the user is a good user who offers (sends, sells) items in good condition for purchase. For example, in the example of Fig. 2, the estimation unit 42 estimates whether, among the possessions that user U1 offers (sends, sells) for purchase in the next purchase process, the possessions that are equal to or greater than a predetermined threshold are possessions in good condition.

[0064] The estimation unit 42 may also estimate whether the user is a good user who offers (sends, sells) products of a predetermined brand for purchase. For example, in the example of Fig. 2, the estimation unit 42 estimates whether a predetermined threshold or more of the owned items that user U1 offers (sends, sells) for purchase in the next purchase process are products of the predetermined brand.

[0065] The estimation unit 42 may also estimate whether the user is a good user who offers (sends, sells) products in a predetermined price range as items to be purchased. For example, in the example of Fig. 2, the estimation unit 42 estimates whether, in the next purchase process, among the owned items that user U1 offers (sends, sells) as items to be purchased, items priced at or above a predetermined threshold are in a predetermined price range.

[0066] The estimation unit 42 may also estimate whether the user is a good user who offers (sends, sells) products corresponding to a predetermined age group as items to be purchased. For example, in the example of Fig. 2, the estimation unit 42 estimates whether, in the next purchase process, among the owned items that user U1 offers (sends, sells) as items to be purchased, a predetermined threshold or more are products corresponding to a predetermined age group.

[0067] The estimation unit 42 may also estimate whether the user is a good user who offers (sends, sells) products corresponding to a predetermined season as items to be purchased. For example, in the example of Fig. 2, the estimation unit 42 estimates whether or not a predetermined threshold or more of the owned items that user U1 offers (sends, sells) as items to be purchased in the next purchase process are products corresponding to a predetermined season.

[0068] Furthermore, the estimation unit 42 may estimate whether or not the user is a good user who offers (sends or sells) products corresponding to a predetermined season as items to be purchased, based on the determination result by the determination unit 41. For example, in the example of Fig. 2, the estimation unit 42 estimates whether or not user U1 is a good user, based on the determination result of the user's owned items using model #2.

[0069] The estimation unit 42 may also estimate whether the user is a good user who offers (sends, sells) other products as targets for purchase in addition to the products designated as targets for purchase. For example, in the example of Fig. 2, the estimation unit 42 estimates whether, in the next purchase process, the owned items that user U1 offers (sends, sells) as targets for purchase include, in addition to the designated products, other owned items different from the designated products.

[0070] (Regarding the determination unit 43) The determination unit 43 inputs information about a user into a model that has been trained to output information (score) indicating whether or not the user is a good user when a purchase price higher than the normal price is offered, when information about the user is input, and thereby determines whether or not to set a purchase price higher than the normal price for the user. For example, in the example of Figure 2, the determination unit 43 refers to the storage unit 30 and inputs information about user U1 into model #3 that has been trained to output information (score) indicating whether or not the user is a good user when a purchase price higher than the normal price is offered, when information about the user is input, and thereby determines whether or not user U1 will be a good user in the purchase process when a purchase price higher than the normal price is offered.

[0071] (Regarding the decision unit 44) The determination unit 44 determines the purchase price of the product offered (sent or sold) by the user based on the estimation result by the estimation unit 42. For example, in the example of Fig. 2, the determination unit 44 determines the purchase price of the product owned by user U1 in the next purchase process based on whether user U1 is a good user or not.

[0072] Furthermore, if a user is estimated to be a good user, the determination unit 44 may determine a higher purchase price for the product offered by the user than the normal price offered if the user is estimated not to be a good user. For example, in the example of Fig. 2, if the user is estimated to be a good user in the next purchase process, the determination unit 44 determines a higher purchase price for the product owned by user U1 than the normal price offered if the user is estimated not to be a good user.

[0073] Furthermore, the determination unit 44 may determine the purchase price of the product offered (sent or sold) by the user based on the determination result by the determination unit 43 and the estimation result. For example, in the example of Fig. 2, if a purchase price higher than the normal price is offered and it is determined that the user U1 will be a good user in the purchase process, the determination unit 44 determines the purchase price of the product owned by the user U1 to be higher than the normal price that would be offered if it was estimated that the user was not a good user.

[0074] (Regarding presentation unit 45) The presentation unit 45 presents the purchase price determined by the determination unit 44 to the user. For example, in the example of FIG. 2, when purchasing a new product in the e-commerce service #1, the presentation unit 45 presents the purchase price determined by the determination unit 44 via the user terminal 100 as information regarding a proposal to purchase the owned item. The presentation unit 45 may present to the user via the user terminal 100 that the user is estimated to be a good user (or that the user is estimated not to be a good user) or that the purchase price has been determined to be higher than the normal price (or that the purchase price has been determined to be the normal price). Even if the user is estimated to be a good user and the purchase price has been determined to be higher than the normal price, the presentation unit 45 may present to the user via the user terminal 100 the normal price as the purchase price for a predetermined period of time. Then, the presentation unit 45 may present to the user via the user terminal 100 the price determined to be higher than the normal price as the purchase price based on the lapse of the predetermined period of time. The specified period may be a predetermined period, a period determined for each user, or the period from when the user confirmed the purchase price to when they requested a purchase (sent a purchase request), or the average of that period.

[0075] [5. Information Processing Flow] The procedure of information processing of the information processing device 10 according to the embodiment will be described with reference to Fig. 6. Fig. 6 is a flowchart showing an example of the procedure of information processing according to the embodiment.

[0076] 6, the information processing device 10 estimates, based on information about a user, whether the user is a preferred user who offers products that meet predetermined conditions as targets for purchase (step S101). If the user is estimated to be a preferred user (step S102; Yes), the information processing device 10 determines the purchase price of the products offered by the user to be higher than the normal price offered if the user is estimated not to be a preferred user (step S103). On the other hand, if the user is estimated not to be a preferred user (step S102; No), the information processing device 10 determines the purchase price of the products offered by the user to be the normal price (step S104).

[0077] Next, the information processing device 10 presents the determined purchase price to the user (step S105), and ends the process. [6. Modifications] The above-described embodiment is merely an example, and various modifications and applications are possible.

[0078] [6-1. Processing mode] Of the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, and conversely, all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information, including the processing procedures, specific names, various data, and parameters shown in the above text and drawings, can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0079] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0080] Furthermore, the above-described embodiments can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0081] [7. Effects] As described above, the information processing device 10 according to the embodiment includes a discrimination unit 41, an estimation unit 42, a determination unit 43, a decision unit 44, and a presentation unit 45. The estimation unit 42 estimates, based on information about a user, whether the user is a preferred user who offers products that meet certain conditions as items to be repurchased. The estimation unit 42 also estimates, based on information about products previously offered by the user as items to be repurchased, whether the user is a preferred user. The estimation unit 42 also estimates, by inputting information about the user into a model that has been trained to output information indicating whether the user was a preferred user in the previous repurchase, when the information about the user is input. The estimation unit 42 also estimates whether the user is a preferred user who offers products in good condition as items to be repurchased. The decision unit 44 determines the repurchase price of the products offered by the user based on the estimation result by the estimation unit 42. The presentation unit 45 presents the repurchase price determined by the decision unit 44 to the user.

[0082] As a result, the information processing device 10 according to the embodiment can estimate whether the user is a good user who sends possessions in good condition for purchase, and determine the purchase price to be offered to the user based on the estimation result, thereby determining an appropriate purchase price according to the user.

[0083] Furthermore, in the information processing device 10 according to the embodiment, for example, the estimation unit 42 estimates whether or not the user is a good user who offers products of a predetermined brand as targets for purchase.

[0084] As a result, the information processing device 10 of the embodiment can estimate whether the user is a good user who sends in items from high-quality brands for purchase, and based on the estimation results, can determine the purchase price to be offered to the user, thereby determining an appropriate purchase price according to the user.

[0085] Furthermore, in the information processing device 10 according to the embodiment, for example, the estimation unit 42 estimates whether or not the user is a good user who offers products in a predetermined price range as targets for purchase.

[0086] As a result, the information processing device 10 according to the embodiment can estimate whether the user is a good user who sends high-quality possessions in a high price range for purchase, and determine the purchase price to be offered to the user based on the estimation result, thereby determining an appropriate purchase price according to the user.

[0087] Furthermore, in the information processing device 10 according to the embodiment, for example, the estimation unit 42 estimates whether or not the user is a good user who offers products corresponding to a predetermined age group as targets for purchase.

[0088] As a result, the information processing device 10 of the embodiment can estimate whether a user is a good user who will send in possessions from a specified era for purchase, and based on the estimation results, can determine the purchase price to be offered to the user, thereby determining an appropriate purchase price according to the user.

[0089] In the information processing device 10 according to the embodiment, for example, the estimation unit 42 estimates whether a user is a preferred user who offers products corresponding to a predetermined season for purchase. The discrimination unit 41 inputs a description of the product offered by the user for purchase into a model trained to output the season corresponding to the product when a description of the product is input, thereby discriminating the season corresponding to the product offered by the user for purchase. Based on the discrimination result by the discrimination unit 41, the estimation unit 42 estimates whether the user is a preferred user who offers products corresponding to a predetermined season for purchase.

[0090] As a result, the information processing device 10 of the embodiment can estimate whether the user is a good user who will send in possessions that correspond to the current season (in other words, products that are currently in high demand) for purchase, and based on the estimation results, can determine the purchase price to be offered to the user, thereby determining an appropriate purchase price that suits the user.

[0091] Furthermore, in the information processing device 10 according to the embodiment, for example, the estimation unit 42 estimates whether the user is a good user who offers other products as purchase items in addition to the products designated as purchase items.

[0092] As a result, the information processing device 10 according to the embodiment can estimate whether the user is a good user who sends more possessions for purchase, and determine the purchase price to be offered to the user based on the estimation result, thereby determining an appropriate purchase price according to the user.

[0093] Furthermore, in the information processing device 10 according to the embodiment, for example, when a user is estimated to be a preferred user, the determination unit 44 determines a purchase price for the product offered by the user that is higher than the normal price offered when the user is estimated not to be a preferred user. Furthermore, when information about the user is input, the judgment unit 43 inputs information about the user into a model that has been trained to output information indicating whether the user is a preferred user when a purchase price higher than the normal price is offered, thereby determining whether to set a purchase price higher than the normal price for the user. Then, the determination unit 44 determines the purchase price for the product offered by the user based on the judgment result by the judgment unit 43 and the estimation result.

[0094] As a result, the information processing device 10 according to the embodiment can offer a higher purchase price than usual to good users, thereby increasing the motivation of good users to sell their belongings.

[0095] [8. Hardware Configuration] The information processing device 10 according to each of the above-described embodiments is realized, for example, by a computer 1000 configured as shown in Fig. 7. The information processing device 10 will be described below as an example. Fig. 7 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 10. The computer 1000 has a CPU 1100, a ROM 1200, a RAM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0096] The CPU 1100 operates and controls each unit based on programs stored in the ROM 1200 or the HDD 1400. The ROM 1200 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, programs that depend on the hardware of the computer 1000, and the like.

[0097] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a communication network 500 (corresponding to the network N in the embodiment) and sends the data to the CPU 1100, and also transmits data generated by the CPU 1100 to other devices via the communication network 500.

[0098] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600.

[0099] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1300. CPU 1100 loads the program or data from recording medium 1800 onto RAM 1300 via media interface 1700 and executes the loaded program. 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.

[0100] For example, when the computer 1000 functions as the information processing device 10, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1300 to realize the functions of the control unit 40. The HDD 1400 also stores various data in the storage device of the information processing device 10. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via a predetermined communication network.

[0101] [9. Other] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have undergone various modifications and improvements based on the knowledge of those skilled in the art.

[0102] Furthermore, the information processing device 10 described above can flexibly change its configuration, for example, by calling an external platform or the like using an API (Application Programming Interface) or network computing, depending on the function.

[0103] Furthermore, the term "unit" in the claims can be read as "means" or "circuit," etc. For example, a discrimination unit can be read as discrimination means or discrimination circuit. [Explanation of symbols]

[0104] 10. Information processing equipment 20 Communications Department 30 Storage section 31 Product Information Database 32 User Information Database 33 Model Database 40 Control Unit 41 Discrimination part 42 Estimation part 43 Judgment section 44 Decision Section 45 Presentation section 100 user terminals

Claims

1. an estimation unit that estimates whether the user is a good user who offers products that meet predetermined conditions as purchase targets based on information about the user's belongings; a determination unit that determines a purchase price of the product provided by the user based on the estimation result by the estimation unit; a presentation unit that presents the purchase price determined by the determination unit to the user; and The estimation unit When information about the possessions of a user similar to the user is input, the model is trained to output information indicating whether the user similar to the user was a good user in the previous purchase, and by inputting information about the possessions of the user, it is possible to estimate whether the user is a good user.

1. An information processing device comprising:

2. The estimation unit It is estimated whether the user is a good user based on information about products that the user has offered for purchase in the past.

2. The information processing apparatus according to claim 1, wherein:

3. The estimation unit When information about a user's belongings is input, the model is trained to output information indicating whether the user was a good user in the previous purchase. By inputting information about the user's belongings, the model estimates whether the user is a good user.

2. The information processing apparatus according to claim 1, wherein:

4. The estimation unit It is estimated whether the user is a good user who offers products in good condition as items to be purchased.

2. The information processing apparatus according to claim 1, wherein:

5. The estimation unit It is estimated whether the user is a good user who offers products of a predetermined brand as a target for purchase.

2. The information processing apparatus according to claim 1, wherein:

6. The estimation unit It is estimated whether the user is a good user who offers products in a predetermined price range as a target for purchase.

2. The information processing apparatus according to claim 1, wherein:

7. The estimation unit It is estimated whether the user is a good user who offers products corresponding to a predetermined age group as a target for purchase.

2. The information processing apparatus according to claim 1, wherein:

8. The estimation unit It is estimated whether the user is a good user who offers products corresponding to a predetermined season as items to be purchased.

2. The information processing apparatus according to claim 1, wherein:

9. A discrimination unit that determines the season corresponding to the product offered by the user as a purchase target by inputting a description of the product offered by the user to a model that has been trained to output the season corresponding to the product when a description of the product is input. and The estimation unit Based on the determination result by the determination unit, it is estimated whether the user is a good user who offers products corresponding to a predetermined season as items to be purchased.

9. The information processing apparatus according to claim 8,

10. The estimation unit It is estimated whether the user is a good user who offers other products as purchase targets in addition to the products designated as purchase targets.

2. The information processing apparatus according to claim 1, wherein:

11. The determination unit If the user is presumed to be a good user, the purchase price of the product provided by the user is determined to be higher than the normal price offered if the user is presumed not to be a good user.

2. The information processing apparatus according to claim 1, wherein:

12. A determination unit that, when information about a user's belongings is input, determines whether to set a purchase price for the user that is higher than the normal price by inputting information about the user's belongings to a model that has been trained to output information indicating whether the user is a good user when a purchase price higher than the normal price is offered. and The determination unit A purchase price of the product offered by the user is determined based on the determination result by the determination unit and the estimation result.

12. The information processing apparatus according to claim 11,

13. 1. A computer-implemented information processing method, comprising: an estimation step of estimating whether the user is a good user who offers products that meet predetermined conditions and are eligible for purchase, based on information about the user's possessions; a determination step of determining a purchase price for the product offered by the user based on the estimation result obtained by the estimation step; a presentation step of presenting the purchase price determined in the determination step to the user; Including, The estimation step includes: When information about the possessions of a user similar to the user is input, the model is trained to output information indicating whether the user similar to the user was a good user in the previous purchase, and by inputting information about the possessions of the user, it is possible to estimate whether the user is a good user.

1. An information processing method comprising:

14. an estimation procedure for estimating whether or not a user is a good user who offers products that meet predetermined conditions and are eligible for purchase, based on information about the user's possessions; a determination step for determining a purchase price of the product offered by the user based on the estimation result of the estimation step; a presentation step of presenting the purchase price determined by the determination step to the user; on the computer, The estimation procedure comprises: When information about the possessions of a user similar to the user is input, the model is trained to output information indicating whether the user similar to the user was a good user in the previous purchase, and by inputting information about the possessions of the user, it is possible to estimate whether the user is a good user. An information processing program characterized by:

Images