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

Abstract

To provide an information processing device capable of predicting spread of the trend of a transaction object between electronic malls, an information processing method, and an information processing program.SOLUTION: An information processing device comprises an acquisition unit and a generation unit. The acquisition unit acquires first purchase-related information, which is information on purchase of a transaction object in a first electronic mall, and second purchase-related information, which is information on purchase of a transaction object in a second electronic mall. The generation unit generates an estimation model for estimating a mode of spread to the second electronic mall of a trend on purchase in the first electronic mall on the basis of the first purchase-related information and second purchase-related information acquired by the acquisition unit.SELECTED DRAWING: Figure 3

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, transactions of products and other trade objects using electronic shopping malls including virtual stores that sell products on the Internet have become common. In such electronic shopping malls, when an order for a trade object is received from a user, the seller delivers the trade object to the user by requesting a delivery company to deliver the product to the user.

[0003] Patent document 1 describes an online shopping mall server that searches for products etc. based on keywords. The online shopping mall server determines the popularity of keywords used for product searches etc., and predicts demand for products based on the results of this determination. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2013-250677 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, the technology described in Patent Document 1 is merely a technology for predicting trends of trade items in an online shopping mall based on information within the online shopping mall, and there is room for improvement.

[0006] The present application has been made in consideration of the above, and aims to provide an information processing device, an information processing method, and an information processing program that make it possible to predict the spread of trends in trading items between online shopping malls. [Means for solving the problem]

[0007] The information processing device of the present application includes an acquisition unit that acquires first purchasing-related information, which is information regarding purchases of a transaction object in a first electronic shopping mall, and second purchasing-related information, which is information regarding purchases of a transaction object in a second electronic shopping mall, and a generation unit that generates an estimation model that estimates the manner in which a purchasing trend in the first electronic shopping mall will spread to the second electronic shopping mall based on the first purchasing-related information and the second purchasing-related information acquired by the acquisition unit. Effect of the Invention

[0008] According to one aspect of the embodiment, it is possible to predict the spread of trends in trading objects between online shopping malls. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of the configuration of an information processing system according to the embodiment. [Diagram 3] FIG. 3 is a diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of an online shopping mall information table stored in the online shopping mall information storage unit according to the embodiment. [Diagram 5] FIG. 5 is a diagram illustrating an example of an inflow number information table stored in the inflow number information storage unit according to the embodiment. [Figure 6] FIG. 6 is a flowchart showing an example of information processing by the processing unit of the information processing device 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 according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, the information processing device, the information processing method, and the 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. In addition, each embodiment can be appropriately combined as long as the processing contents are not contradictory. In addition, the same parts in each of the following embodiments are given the same reference numerals, and duplicated explanations will be omitted.

[0011] [1. An example of information processing] First, an example of information processing according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of information processing according to the embodiment, which is executed by an information processing device 1.

[0012] 1, the information processing device 1 acquires first and second purchase-related information from an internal storage unit or an external server (step S1). The first purchase-related information is information related to the purchase of a transaction target in the first online shopping mall 4A, and the second purchase-related information is information related to the purchase of a transaction target in the second online shopping mall 4B.

[0013] The first online shopping mall 4A and the second online shopping mall 4B are operated by different operators, but may be operated by a common operator. In the following, when the first online shopping mall 4A and the second online shopping mall 4B are not individually distinguished from each other, they may be referred to as the online shopping mall 4.

[0014] The first purchasing-related information includes, for example, first purchase quantity information for each trading object, first inventory quantity information for each trading object, first ranking information, first sell-out timing information for each sold-out trading object, first sell-out period information for each sold-out trading object, and first inflow quantity information.

[0015] The first purchase quantity information includes information on the purchase quantity of a transaction object in the first electronic shopping mall 4A. The first stock quantity information includes information on the stock quantity of a transaction object in the first electronic shopping mall 4A. The first ranking information includes ranking information of purchases of multiple transaction objects in the first electronic shopping mall 4A. A purchase of a transaction object in the first electronic shopping mall 4A is a purchase of the transaction object by a user U of the first electronic shopping mall 4A, and can also be said to be a sale of the transaction object in the first electronic shopping mall 4A.

[0016] The first sold-out timing information includes information indicating a first sold-out timing, which is the timing when the transaction object is sold out in the first online shopping mall 4A. The first sold-out period information includes information indicating a first sold-out period, which is the period until the transaction object, which has been put on sale in the first online shopping mall 4A, is sold out. The first inflow number information includes information indicating the number of users U who have inflowed into the first online shopping mall 4A.

[0017] The second purchasing-related information includes, for example, second purchase quantity information for each trading object, second inventory quantity information for each trading object, second ranking information, second sell-out timing information for each sold-out trading object, second sell-out period information for each sold-out trading object, and second inflow quantity information.

[0018] The second purchase quantity information includes information on the purchase quantity of a trading object in the second electronic shopping mall 4B. The second inventory quantity information includes information on the inventory quantity of a trading object in the second electronic shopping mall 4B. The second ranking information includes ranking information on purchases of multiple trading objects in the second electronic shopping mall 4B. A purchase of a trading object in the second electronic shopping mall 4B is a purchase of the trading object by a user U of the second electronic shopping mall 4B, and can also be said to be a sale of the trading object in the second electronic shopping mall 4B.

[0019] The second sold-out timing information includes information indicating a second sold-out timing, which is the timing when the transaction object is sold out in the second online shopping mall 4B. The second sold-out period information includes information indicating a second sold-out period, which is the period until the transaction object, whose sale has started in the second online shopping mall 4B, is sold out. The second inflow number information includes information indicating the number of users U who have inflowed into the second online shopping mall 4B.

[0020] Each of the first purchase quantity information and the second purchase quantity information includes information on the purchase quantity of each transaction object for each predetermined period (e.g., one day or one week). Each of the first stock quantity information and the second stock quantity information includes information on the stock quantity of each transaction object for each predetermined period (e.g., one day or one week).

[0021] Each of the first ranking information and the second ranking information includes information on rankings of purchases of multiple transaction objects for each predetermined period (e.g., one day or one week). The purchase ranking is, for example, a ranking of purchase numbers or purchase amounts. Note that the purchase ranking may be a ranking of purchase numbers or purchase amounts corrected using a correction value for each attribute (e.g., category or specification) of the transaction objects, and may be a ranking not based on category.

[0022] Each of the first inflow number information and the second inflow number information includes information indicating the number of users U who inflow to the online shopping mall 4 per predetermined period (e.g., one day or one week). The inflow number is estimated, for example, based on a search result on a search site by the user U. For example, the number of users U who inflow to each online shopping mall 4 is estimated based on a search keyword included in a search query by the user U.

[0023] For example, if a keyword identifying the first online shopping mall 4A (e.g., the name of the first online shopping mall 4A) is included in the search query, it is presumed that the user U is flowing into the first online shopping mall 4A. Also, if a keyword identifying the second online shopping mall 4B (e.g., the name of the second online shopping mall 4B) is included in the search query, it is presumed that the user U is flowing into the second online shopping mall 4B.

[0024] The number of users U flowing into the online shopping mall 4 may be an estimated value for each attribute of a transaction object (e.g., category or specification) or for each transaction object. For example, the number of users U flowing into the online shopping mall 4 is estimated for each attribute of a transaction object (e.g., category or specification) or for each transaction object based on other search keywords (e.g., keywords indicating the category of the transaction object or keywords indicating the transaction object) included in a search query in which a keyword identifying the online shopping mall 4 is included as a search keyword.

[0025] In addition, the number of users U flowing into the electronic shopping mall 4 may be the number of users U who actually accessed the electronic shopping mall 4. In this case, the information processing device 1 obtains, for example, the number of users U flowing into the electronic shopping mall 4 from an electronic commerce site that includes the electronic shopping mall 4.

[0026] In addition, each of the first sold-out timing information and the second sold-out timing information includes information on the timing of selling out of each transaction object that has sold out within a predetermined period since the start of sales. The information on the timing of selling out is, for example, information indicating the date and time when the transaction object sold out or the date when the transaction object sold out, but is not limited to such examples.

[0027] Next, the information processing device 1 generates an estimation model that estimates the spread of the trend regarding purchases in the first online shopping mall 4A to the second online shopping mall 4B based on the first purchase-related information and the second purchase-related information acquired in step S1 (step S2). Such an estimation model is a model generated by machine learning.

[0028] A trend in purchases is, for example, a situation in which demand is increasing. Whether or not the situation is one in which demand is increasing is determined, for example, by whether or not at least one of the following is satisfied: the rate of increase in the number of purchases is equal to or greater than a predetermined threshold, and the number of purchases in a predetermined period is equal to or greater than a predetermined threshold.

[0029] Whether or not the demand is high is not limited to the above example, and may be determined, for example, by whether or not the sold-out state continues for a preset period or more, or may be determined by other criteria. The preset threshold value and the preset period are set for each attribute of the transaction object (e.g., category or specification), but may also be set for each transaction object.

[0030] The estimation model estimates the manner in which a trend spreads with respect to purchases for each transaction object, but can also estimate the manner in which a trend spreads with respect to purchases for each attribute (eg, category or specification) of the transaction object.

[0031] The information processing device 1 generates, for example, an estimation model that estimates whether a trend regarding purchases in the first online shopping mall 4A will spread to the second online shopping mall 4B. For example, the information processing device 1 generates the estimation model based on the difference between the fluctuation of the first ranking information and the fluctuation of the second ranking information.

[0032] In this case, the estimation model is a model in which, for example, information indicating changes in the first ranking information for the transaction object to be judged is input as a feature, and information indicating whether or not there is a spillover of purchases from the first online shopping mall 4A to the second online shopping mall 4B for the transaction object to be judged is output.

[0033] The features used in the estimation model are, for example, information up to the time when it is estimated that it became popular in the first online shopping mall 4A, and are information for a predetermined period, but may also include information after the time when it is estimated that it became popular in the first online shopping mall 4A.

[0034] For example, the feature amount used in the estimation model may be, but is not limited to, information on a predetermined period until the transaction object is sold out in the first online shopping mall 4A, information on a predetermined period until the transaction object reaches a predetermined rank or higher in the ranking in the first online shopping mall 4A, etc. For example, the feature amount used in the estimation model may be information on a predetermined period until the increase rate of the purchase number of the transaction object in the first online shopping mall 4A reaches a threshold or higher.

[0035] The information indicating the change in the first ranking information of the transaction object to be judged is information indicating the change in the ranking of the transaction object to be judged in the first online shopping mall 4A, and is time-series data.

[0036] In addition, the estimation model may be a model in which one or more of the first purchase quantity information, the second purchase quantity information, the first inventory quantity information, the second inventory quantity information, the first ranking information, the second ranking information, the first sell-out timing information, the first sell-out period information, the first inflow quantity information, and the second inflow quantity information are further input as features.

[0037] For example, if a transaction object that has risen to a high, predetermined ranking in the first ranking information subsequently rises to a high, predetermined ranking in the second ranking information, the information processing device 1 determines that there is a spread of a trend from the first electronic shopping district 4A to the second electronic shopping district 4B for that transaction object, and if not, determines that there is no spread of a trend from the first electronic shopping district 4A to the second electronic shopping district 4B for that transaction object.

[0038] In addition, if a trading object whose ranking in the first ranking information rises subsequently rises in the second ranking information, the information processing device 1 can determine that a trend has spread from the first electronic shopping district 4A to the second electronic shopping district 4B for that trading object, and if this is not the case, can determine that a trend has not spread from the first electronic shopping district 4A to the second electronic shopping district 4B for that trading object.

[0039] When the information processing device 1 determines that there is a trend spreading, it performs annotation to add a label indicating that there is a trend spreading, and when it determines that there is no trend spreading, it performs annotation to add a label indicating that there is no trend spreading. In this way, the information processing device 1 can perform annotation based on the difference between the change in the first ranking information and the change in the second ranking information for the transaction object to be determined.

[0040] The information processing device 1 can also generate, as an estimation model, a model for estimating a first propagation delay period, which is a period until a trend regarding purchases in the first online shopping mall 4A propagates to the second online shopping mall 4B.

[0041] In this case, the estimation model is a model that receives information indicating the first sell-out timing of the trading object to be determined as a feature amount and outputs information indicating the first propagation delay period.

[0042] In addition, the estimation model may be a model in which one or more of the first purchase quantity information, the second purchase quantity information, the first inventory quantity information, the second inventory quantity information, the first ranking information, the second ranking information, the first visitor quantity information, and the second visitor quantity information, etc. are further input as features.

[0043] In addition, the information processing device 1 can determine that a trend has spread to a trading object if the trading object that has reached the first sell-out timing subsequently rises to a high predetermined ranking in the second ranking information, and can determine that a trend has not spread to the trading object if this is not the case.

[0044] For example, the information processing device 1 can determine that a trading object for which the period from the first sold-out time to the second sold-out time is within a predetermined period is experiencing trend spread, and can also determine that a trading object for which the period from the first sold-out time to the second sold-out time is not within the predetermined period is not experiencing trend spread.

[0045] The information processing device 1 generates an estimation model using information indicating the period from the first sell-out timing to the second sell-out timing for a trading object determined to have a trend spread as a label. In this way, the information processing device 1 can perform annotation based on the fluctuation in the first sell-out timing and the second ranking information for the trading object to be determined, the difference between the first sell-out timing and the second sell-out timing for the trading object to be determined, etc.

[0046] In this case, the estimation model is a model that inputs one or more pieces of information as features, such as first purchase quantity information, second purchase quantity information, first inventory quantity information, second inventory quantity information, first ranking information, second ranking information, first sold-out period information, first inflow number information, and second inflow number information, and outputs the period from the first sold-out timing to the second sold-out timing.

[0047] In addition, the information processing device 1 can also determine whether a purchasing trend in the first online shopping mall 4A will spread to the second online shopping mall 4B based on the difference in timing when the number of visitors to the online shopping mall 4 peaks.

[0048] For example, the information processing device 1 determines a first peak timing, which is a timing when the number of visitors to the first online shopping mall 4A peaks, based on the first visitor number information. Also, the information processing device 1 determines a second peak timing, which is a timing when the number of visitors to the second online shopping mall 4B peaks, based on the second visitor number information.

[0049] Then, the information processing device 1 determines that the purchasing trend in the first online shopping mall 4A will spread to the second online shopping mall 4B for transaction objects for which the period from the first peak timing to the second peak timing is within a predetermined period range, and determines that the trend will not spread if this is not the case.

[0050] The information processing device 1 generates an estimation model using information indicating the determined spread of the trend as a label. In this case, the estimation model is a model that inputs, as a feature, one or more pieces of information among the first purchase number information, the second purchase number information, the first stock number information, the second stock number information, the first ranking information, the second ranking information, the first sold-out timing information, the first sold-out period information, the first inflow number information, and the second inflow number information, and outputs information indicating the spread of the trend from the first online shopping mall 4A to the second online shopping mall 4B.

[0051] The information processing device 1 generates an estimation model using information indicating the period from the first peak timing to the second peak timing for a transaction object determined to have a trend spread as a label. In this way, the information processing device 1 can perform annotation based on the difference in fluctuation of the number of inflows between the first online shopping mall 4A and the second online shopping mall 4B. Note that the peak timing is the timing of the peak in the number of inflows per online shopping mall 4, but it may also be the timing of the peak in the number of inflows for each attribute of the transaction object to be determined.

[0052] In this case, the estimation model is a model that inputs one or more pieces of information as features, such as the first purchase quantity information, the second purchase quantity information, the first stock quantity information, the second stock quantity information, the first ranking information, the second ranking information, the first sell-out timing information, the first sell-out period information, the first inflow number information, and the second inflow number information, and outputs information indicating the period until the trend spreads from the first online shopping mall 4A to the second online shopping mall 4B.

[0053] Next, the information processing device 1 receives a propagation estimation request from the terminal device 2 (step S3). A user U of the terminal device 2 can cause the terminal device 2 to transmit a propagation estimation request to the information processing device 1 by operating the terminal device 2.

[0054] When the information processing device 1 receives a spread estimation request in step S3, it uses the estimation model described above to estimate the manner in which the purchasing trend in the first online shopping mall 4A will spread to the second online shopping mall 4B (for example, whether there will be a spread and the period until the spread) for each transaction object (step S4).

[0055] The spread estimation request includes information indicating whether the trading objects for which the spread of the trend is to be judged are to be all trading objects, trading objects in a specific category, or specific trading objects, and the information processing device 1 estimates the pattern of spread of the trend for the trading objects identified in the spread estimation request.

[0056] Next, the information processing device 1 transmits epidemic spread estimation result information indicating the result of the estimation in step S4 to the terminal device 2 (step S5). Upon receiving the epidemic spread estimation result information transmitted from the information processing device 1, the terminal device 2 displays the received epidemic spread estimation result information. In this way, the information processing device 1 can predict the popularity of transaction objects in the second online shopping mall 4B using the estimation model.

[0057] In addition, the information processing device 1 can also generate an estimation model that estimates the manner in which a purchasing trend in the second online shopping mall 4B will spread to the first online shopping mall 4A based on the first purchasing-related information and the second purchasing-related information, using a method similar to the method for generating the estimation model described above.

[0058] In addition, for example, when there are three or more electronic shopping malls 4, the information processing device 1 can generate an estimation model for each different combination of two electronic shopping malls 4, and when there are four or more electronic shopping malls 4, the information processing device 1 can generate an estimation model for each different combination of three electronic shopping malls 4.

[0059] The information processing device 1 can also generate the above-mentioned estimation model for each attribute of the trading object (e.g., category or specification). The information processing device 1 can also use the above-mentioned estimation model for generation and estimation using the estimation model by limiting, for example, information on trading objects with a predetermined number of stocks or more or information on trading objects of manufacturer's products.

[0060] Furthermore, the information processing device 1 can also exclude information on transaction objects that have flowed in after a search from only one of the first online shopping mall 4A and the second online shopping mall 4B from the data set used to generate the above-mentioned estimation model.

[0061] The configuration of an information processing system including the information processing device 1 and terminal device 2 that perform such processing will be described in detail below.

[0062] 2. Configuration of the Information Processing System 2 is a diagram showing an example of a configuration of an information processing system according to an embodiment. As shown in FIG. 2, an information processing system 100 according to an embodiment includes an information processing device 1 and a plurality of terminal devices 2.

[0063] The multiple terminal devices 2 are used by different users U. The terminal devices 2 are, for example, a notebook PC (Personal Computer), a desktop PC, a smartphone, a tablet PC, or a wearable device. The wearable device is, for example, smart glasses or a smart watch, but is not limited to such examples. The user U is a user who uses a service provided by the information processing device 1 or the like.

[0064] The information processing device 1 and the terminal device 2 are connected to each other so as to be able to communicate with each other by wire or wirelessly via a network N. Note that the information processing system 100 shown in FIG.

[0065] The network N includes, for example, a Wide Area Network (WAN) such as the Internet and mobile communication networks such as Long Term Evolution (LTE), 4th Generation (4G), and 5th Generation (5G: fifth generation mobile communication system).

[0066] The terminal device 2 can connect to the network N via short-range wireless communication such as a mobile communication network, Bluetooth (registered trademark), or a wireless LAN (Local Area Network), and communicate with the information processing device 1.

[0067] 3. Configuration of information processing device 1 3 is a diagram showing an example of the configuration of the information processing device 1 according to the embodiment. As shown in FIG. 3, the information processing device 1 includes a communication unit 10, a storage unit 11, and a processing unit 12.

[0068] [3.1. Communication unit 10] The communication unit 10 is realized by, for example, a communication module or a NIC (Network Interface Card). The communication unit 10 is connected to a network N by wire or wirelessly, and transmits and receives information to and from various other devices. For example, the communication unit 10 transmits and receives information to and from the terminal device 2 via the network N.

[0069] [3.2. Storage section 11] The storage unit 11 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. The storage unit 11 has an online shopping mall information storage unit 20 and a visitor number information storage unit 21.

[0070] [3.2.1. Electronic shopping mall information storage unit 20] The online shopping mall information storage unit 20 stores purchase-related information, which is various information related to purchases in each online shopping mall 4. Fig. 4 is a diagram showing an example of an online shopping mall information table stored in the online shopping mall information storage unit 20 according to the embodiment.

[0071] In the example shown in Figure 4, the user information table stored in the electronic shopping mall information storage unit 20 includes information on items such as "electronic shopping mall ID (Identifier)," "purchase quantity information," "inventory quantity information," "ranking information," "sold out timing information," and "sold out period information."

[0072] The "electronic shopping mall ID" is an identifier for identifying the electronic shopping mall 4, and is information assigned to each electronic shopping mall 4. In the example shown in Fig. 4, the electronic shopping mall ID "EC1" is the identifier of the first electronic shopping mall, and the electronic shopping mall ID "EC2" is the identifier of the second electronic shopping mall.

[0073] "Purchase quantity information" includes information on the purchase quantity of a trading object in the electronic shopping mall 4 associated with an "electronic shopping mall ID" for each predetermined period, and such purchase quantity information of the trading object is included for each trading object sold in the electronic shopping mall 4 associated with an "electronic shopping mall ID." A purchase of a trading object in the electronic shopping mall 4 is a purchase of the trading object by a user U of the electronic shopping mall 4, and can also be said to be a sale of the trading object in the electronic shopping mall 4.

[0074] "Stock quantity information" includes information on the stock quantity of trading objects in the electronic shopping mall 4 associated with the "electronic shopping mall ID" for each predetermined period, and such information on the stock quantity of trading objects is included for each trading object sold in the electronic shopping mall 4 associated with the "electronic shopping mall ID." "Ranking information" includes ranking information of purchases of multiple trading objects in the electronic shopping mall 4 associated with the "electronic shopping mall ID" for each predetermined period.

[0075] "Sold out timing information" includes information indicating the timing of the sale of a trading item that has sold out in the online shopping mall 4 associated with the "online shopping mall ID." "Sold out period information" includes information indicating the sell out period (the period from the start of sales to the sale) that is the period until the trading item that has started to go on sale in the online shopping mall 4 associated with the "online shopping mall ID" is sold out.

[0076] [3.2.2. Inflow number information storage unit 21] The visitor number information storage unit 21 stores various information related to the number of visitors to the online shopping mall 4. Fig. 5 is a diagram showing an example of a visitor number information table stored in the visitor number information storage unit 21 according to the embodiment.

[0077] 5, the user information table stored in the visitor count information storage unit 21 includes information on items such as "electronic shopping mall ID" and "visitor count information." The "visitor count information" includes information indicating the number of users U visiting the electronic shopping mall 4 associated with the "electronic shopping mall ID" for each predetermined period (e.g., one day or one week).

[0078] The "number of visitors information" is an estimate of the number of users U visiting the online shopping mall 4 associated with the "online shopping mall ID," but it may also be an estimated value for each attribute of the transaction object (e.g., category or specifications) or for each transaction object.

[0079] For example, based on other search keywords (e.g., keywords indicating the category of the transaction object or keywords indicating the transaction object) included in a search query that includes a keyword identifying the electronic shopping mall 4 as a search keyword, the processing unit 12 estimates the number of users U flowing into the electronic shopping mall 4 for each attribute of the transaction object (e.g., category or specification) or for each transaction object.

[0080] [3.3. Processing section 12] The processing unit 12 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs stored in a storage device inside the terminal device 2 using the RAM as a working area.

[0081] The processing unit 12 may be partially or entirely realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

[0082] 3, the processing unit 12 has an acquisition unit 30, a reception unit 31, a generation unit 32, an estimation unit 33, and a provision unit 34, and realizes or executes the functions and actions of information processing described below. Note that the internal configuration of the processing unit 12 is not limited to the configuration shown in FIG. 3, and may be other configurations as long as they perform the information processing described below.

[0083] [3.3.1. Acquisition part 30] The acquisition unit 30 acquires various pieces of information from an external information processing device, the terminal device 2, or the like via the communication unit 10, and causes the storage unit 11 to store the acquired information.

[0084] For example, the acquisition unit 30 acquires purchase-related information from an external information processing device or the like via the communication unit 10, and adds the acquired purchase-related information to the electronic shopping mall information table in the electronic shopping mall information storage unit 20. Also, the acquisition unit 30 acquires visitor number information from an external information processing device or the like via the communication unit 10, and adds the acquired visitor number information to the visitor number information table in the visitor number information storage unit 21.

[0085] The acquisition unit 30 also acquires various types of information from the storage unit 11. For example, the acquisition unit 30 acquires purchase-related information from the online shopping mall information storage unit 20, etc. The purchase-related information acquired by the acquisition unit 30 includes, for example, a part or all of at least one of the above-mentioned purchase number information, inventory number information, ranking information, sell-out timing information, and sell-out period information.

[0086] For example, the acquisition unit 30 acquires first purchase-related information, which is information regarding the purchase of a transaction object in a first online shopping mall 4A, and second purchase-related information, which is information regarding the purchase of a transaction object in a second online shopping mall 4B, from the online shopping mall information storage unit 20.

[0087] [3.3.2. Reception Unit 31] The reception unit 31 receives various requests and information from the terminal device 2 via the communication unit 10. For example, the reception unit 31 receives a trend estimation request transmitted from the terminal device 2 of the user U.

[0088] The spread estimation request includes information indicating whether the transaction subjects for which the spread of the epidemic is to be judged are to be all transaction subjects, transaction subjects in a specific category, or specific transaction subjects, for example.

[0089] [3.3.3. Generation unit 32] The generation unit 32 generates an estimation model that estimates the manner in which purchasing trends in the first online shopping mall 4A will spread to the second online shopping mall 4B based on the first purchasing-related information and the second purchasing-related information acquired by the acquisition unit 30.

[0090] A trend in purchases is, for example, a situation in which demand is increasing. Whether or not the situation is one in which demand is increasing is determined, for example, by whether or not at least one of the following is satisfied: the rate of increase in the number of purchases is equal to or greater than a predetermined threshold, and the number of purchases in a predetermined period is equal to or greater than a predetermined threshold.

[0091] Whether or not the demand is high is not limited to the above example, and may be determined, for example, by whether or not the sold-out state continues for a preset period or more, or may be determined by other criteria. The preset threshold value and the preset period are set for each attribute of the transaction object (e.g., category or specification), but may also be set for each transaction object.

[0092] The estimation model estimates the manner in which a trend spreads with respect to purchases for each transaction object, but can also estimate the manner in which a trend spreads with respect to purchases for each attribute (eg, category or specification) of the transaction object.

[0093] The generation unit 32 generates, for example, an estimation model that estimates whether a trend regarding purchases in the first online shopping mall 4A will spread to the second online shopping mall 4B. For example, the generation unit 32 generates the estimation model based on the difference between the fluctuation of the first ranking information and the fluctuation of the second ranking information.

[0094] In this case, the estimation model is a model in which, for example, information indicating changes in the first ranking information for the transaction object to be judged is input as a feature, and information indicating whether or not there is a spillover of purchases from the first online shopping mall 4A to the second online shopping mall 4B for the transaction object to be judged is output.

[0095] The features used in the estimation model are, for example, information up to the time when it is estimated that it became popular in the first online shopping mall 4A, and are information for a predetermined period, but may also include information after the time when it is estimated that it became popular in the first online shopping mall 4A.

[0096] For example, the feature amount used in the estimation model may be, but is not limited to, information on a predetermined period until the transaction object is sold out in the first online shopping mall 4A, information on a predetermined period until the transaction object reaches a predetermined rank or higher in the ranking in the first online shopping mall 4A, etc. For example, the feature amount used in the estimation model may be information on a predetermined period until the increase rate of the purchase number of the transaction object in the first online shopping mall 4A reaches a threshold or higher.

[0097] The information indicating the change in the first ranking information of the transaction object to be judged is information indicating the change in the ranking of the transaction object to be judged in the first online shopping mall 4A, and is time-series data.

[0098] In addition, the estimation model may be a model in which one or more of the first purchase quantity information, the second purchase quantity information, the first inventory quantity information, the second inventory quantity information, the first ranking information, the second ranking information, the first sell-out timing information, the first sell-out period information, the first inflow quantity information, and the second inflow quantity information are further input as features.

[0099] For example, if a transaction object that has risen to a high, predetermined ranking in the first ranking information subsequently rises to a high, predetermined ranking in the second ranking information, the generation unit 32 determines that there is a spread of popularity from the first electronic shopping district 4A to the second electronic shopping district 4B for that transaction object, and if not, determines that there is no spread of popularity from the first electronic shopping district 4A to the second electronic shopping district 4B for that transaction object.

[0100] In addition, if a trading object whose ranking in the first ranking information rises subsequently rises in the second ranking information, the generation unit 32 determines that there is a spread of popularity for that trading object from the first electronic shopping district 4A to the second electronic shopping district 4B, and if this is not the case, it can also determine that there is no spread of popularity for that trading object from the first electronic shopping district 4A to the second electronic shopping district 4B.

[0101] When the generation unit 32 determines that there is a trend spreading, it performs annotation to add a label indicating that there is a trend spreading, and when it determines that there is no trend spreading, it performs annotation to add a label indicating that there is no trend spreading. In this way, the generation unit 32 can perform annotation based on the difference between the change in the first ranking information and the change in the second ranking information for the transaction object to be determined.

[0102] The generating unit 32 can also generate, as an estimation model, a model for estimating a first propagation delay period, which is a period until a trend regarding purchases in the first online shopping mall 4A propagates to the second online shopping mall 4B.

[0103] In this case, the estimation model is a model that receives information indicating the timing from the first sell-out timing of the trading object to be determined as a feature amount, and outputs information indicating the first propagation delay period.

[0104] In addition, the estimation model may be a model in which one or more of the first purchase quantity information, the second purchase quantity information, the first inventory quantity information, the second inventory quantity information, the first ranking information, the second ranking information, the first visitor quantity information, and the second visitor quantity information are further input as features.

[0105] In the estimation model, the first purchase quantity information, the second purchase quantity information, the first inventory quantity information, the second inventory quantity information, the first ranking information, and the second ranking information are information on the transaction object to be judged, and are information for each predetermined period.

[0106] In addition, the generation unit 32 can determine that a trend has spread with respect to a trading object that has experienced a first sell-out timing if that trading object subsequently rises to a higher predetermined ranking in the second ranking information, and can also determine that a trend has not spread with respect to that trading object if that is not the case.

[0107] The generation unit 32 can, for example, determine that a trading object for which the period from the first sold-out time to the second sold-out time is within a predetermined period is experiencing trend influence, and can also determine that a trading object for which the period from the first sold-out time to the second sold-out time is not within the predetermined period is not experiencing trend influence.

[0108] The generation unit 32 generates an estimation model using information indicating the period from the first sell-out timing to the second sell-out timing for a trading object determined to have a trend spread as a label. In this way, the generation unit 32 can perform annotation based on the fluctuation in the first sell-out timing and the second ranking information for the trading object to be determined, the difference between the first sell-out timing and the second sell-out timing for the trading object to be determined, and the like.

[0109] The estimation model is a model that inputs one or more pieces of information as features, such as first purchase quantity information, second purchase quantity information, first inventory quantity information, second inventory quantity information, first ranking information, second ranking information, first sell-out period information, first inflow number information, and second inflow number information, and outputs the period from the first sell-out timing to the second sell-out timing.

[0110] In addition, the generation unit 32 can also determine whether a purchasing trend in the first online shopping mall 4A will spread to the second online shopping mall 4B based on the difference in timing when the number of visitors to the online shopping mall 4 peaks.

[0111] For example, the generation unit 32 determines a first peak timing, which is a timing when the number of visitors to the first online shopping mall 4A peaks, based on the first visitor number information. Also, the generation unit 32 determines a second peak timing, which is a timing when the number of visitors to the second online shopping mall 4B peaks, based on the second visitor number information.

[0112] Then, the generation unit 32 determines that the purchasing trend in the first online shopping mall 4A will spread to the second online shopping mall 4B for transaction objects for which the period from the first peak timing to the second peak timing is within a predetermined period range, and determines that the trend will not spread if this is not the case.

[0113] The generating unit 32 generates an estimation model using the information indicating the determined spread of the trend as a label. In this case, the estimation model is a model that inputs, as a feature, one or more pieces of information among the first purchase number information, the second purchase number information, the first stock number information, the second stock number information, the first ranking information, the second ranking information, the first sold-out timing information, the first sold-out period information, the first inflow number information, and the second inflow number information, and outputs information indicating the spread of the trend from the first online shopping mall 4A to the second online shopping mall 4B.

[0114] The generating unit 32 generates an estimation model using information indicating the period from the first peak timing to the second peak timing for a transaction object determined to have a trend spread as a label. In this way, the generating unit 32 can perform annotation based on the difference in fluctuation of the number of inflows between the first online shopping mall 4A and the second online shopping mall 4B. Note that the peak timing is the timing of the peak in the number of inflows per online shopping mall 4, but it may also be the timing of the peak in the number of inflows for each attribute of the transaction object to be determined.

[0115] In this case, the estimation model is a model that inputs one or more pieces of information as features, such as the first purchase quantity information, the second purchase quantity information, the first stock quantity information, the second stock quantity information, the first ranking information, the second ranking information, the first sell-out timing information, the first sell-out period information, the first inflow number information, and the second inflow number information, and outputs information indicating the period until the trend spreads from the first online shopping mall 4A to the second online shopping mall 4B.

[0116] In addition, the generation unit 32 can also generate an estimation model that estimates the manner in which a purchasing trend in the second online shopping mall 4B will spread to the first online shopping mall 4A based on the first purchasing-related information and the second purchasing-related information, using a method similar to the method for generating the estimation model described above.

[0117] In addition, for example, when there are three or more electronic shopping malls 4, the generation unit 32 can generate an estimation model for each different combination of two electronic shopping malls 4, and when there are four or more electronic shopping malls 4, the generation unit 32 can generate an estimation model for each different combination of three electronic shopping malls 4.

[0118] The generating unit 32 can also generate the above-mentioned estimation model for each attribute of the trading object (e.g., category or specification). The generating unit 32 can use the above-mentioned estimation model for generation and estimation using the estimation model by limiting, for example, information on trading objects with a predetermined number of stocks or more or information on trading objects of manufacturer's products.

[0119] The generation unit 32 can also exclude information on transaction objects that have flowed in after a search from only one of the first online shopping mall 4A and the second online shopping mall 4B from the data set used to generate the above-mentioned estimation model.

[0120] The above-mentioned estimation model is a model generated by machine learning, for example, generated by machine learning using a neural network such as a convolutional neural network, a recurrent neural network, or a deep neural network, but is not limited to such examples.

[0121] For example, the estimation model may be generated using machine learning with a learning algorithm such as a gradient boosting decision tree (GBDT), linear regression, or logistic regression instead of a neural network.

[0122] [3.3.4. Estimation part 33] When a spread estimation request is received by the receiving unit 31, the estimation unit 33 uses the above-mentioned estimation model to estimate the manner in which a purchasing trend in the first online shopping mall 4A will spread to the second online shopping mall 4B (for example, whether there will be a spread and the period until the spread, etc.) for each transaction object.

[0123] The spread estimation request includes information indicating whether the trading objects for which the spread of the trend is to be judged are to be all trading objects, trading objects in a specific category, or specific trading objects, and the estimation unit 33 estimates the manner in which the trend is spreading for the trading objects identified in the spread estimation request.

[0124] For example, the estimation unit 33 inputs the purchasing-related information acquired by the acquisition unit 30 into the above-mentioned estimation model, thereby estimating the manner in which a purchasing trend in the first online shopping mall 4A will spread to the second online shopping mall 4B (for example, whether or not there will be a spread and the period until the spread, etc.) for each transaction object.

[0125] [3.3.5.Providing Department 34] The providing unit 34 transmits epidemic spread estimation result information indicating the result of the estimation by the estimation unit 33 to the terminal device 2. Upon receiving the epidemic spread estimation result information transmitted from the information processing device 1, the terminal device 2 displays the received epidemic spread estimation result information. This allows the user U to predict the popularity of the transaction object in the second online shopping mall 4B.

[0126] 4. Processing Procedure Next, a procedure of information processing by the processing unit 12 of the information processing device 1 according to the embodiment will be described. Fig. 6 is a flowchart showing an example of information processing by the processing unit 12 of the information processing device 1 according to the embodiment.

[0127] 6, the processing unit 12 of the information processing device 1 determines whether or not it is time to generate an estimated model (step S10). The timing to generate an estimated model is, for example, a timing that arrives at a predetermined cycle, but is not limited to this example.

[0128] When the processing unit 12 determines that it is time to generate an estimation model (step S10: Yes), the processing unit 12 acquires the first purchasing related information and the second purchasing related information (step S11). Then, the processing unit 12 generates an estimation model based on the first purchasing related information and the second purchasing related information acquired in step S11 (step S12).

[0129] When the processing of step S12 is completed, or when it is determined that it is not time to generate an estimation model (step S10: No), the processing unit 12 determines whether or not a spillover estimation request has been received (step S13).

[0130] When the processing unit 12 determines that the spread estimation request has been received (step S13: Yes), it estimates the spread of the trend regarding purchases in the first online shopping mall to the second online shopping mall using the estimation model generated in step S12 (step S14).Then, the processing unit 12 provides the user U who made the spread estimation request with trend spread estimation result information, which is information indicating the estimation result in step S14 (step S15).

[0131] When the process of step S15 is completed or when it is determined that the spread estimation request has not been received (step S13: No), the processing unit 12 determines whether or not the operation end timing has arrived (step S16). The processing unit 12 determines that the operation end timing has arrived when, for example, the power supply of the information processing device 1 is turned off.

[0132] If the processing unit 12 determines that the operation end time has not arrived (step S16: No), it transitions to step S10, and if the processing unit 12 determines that the operation end time has arrived (step S16: Yes), it terminates the processing shown in FIG. 6.

[0133] 5. Modifications In the above-described example, the providing unit 34 transmits epidemic spread estimation result information indicating the result of the estimation by the estimating unit 33 to the terminal device 2, but the present invention is not limited to this example.

[0134] For example, when the estimation unit 33 estimates the manner in which a purchasing trend in the first electronic shopping mall 4A will spread to the second electronic shopping mall 4B for each transaction object at a predetermined period, the providing unit 34 can transmit trend spread estimation result information indicating the result of the estimation by the estimation unit 33 to the terminal device 2 at the time it is estimated that the spread will occur, for each transaction object for which the purchasing trend in the first electronic shopping mall 4A is estimated to have spread to the second electronic shopping mall 4B.

[0135] In addition, the providing unit 34 can also transmit information about a transaction object that is estimated to have a ripple effect to a device of a virtual store operator selling such transaction object in the online shopping mall 4 at the time when the ripple effect is estimated to occur.

[0136] [6. Hardware Configuration] The information processing device 1 according to the embodiment described above is realized by a computer 80 having a configuration as shown in Fig. 7. Fig. 7 is a hardware configuration diagram showing an example of the computer 80 that realizes the functions of the information processing device 1 according to the embodiment. The computer 80 has a CPU 81, a RAM 82, a ROM (Read Only Memory) 83, a HDD (Hard Disk Drive) 84, a communication interface (I / F) 85, an input / output interface (I / F) 86, and a media interface (I / F) 87.

[0137] The CPU 81 operates and controls each part based on a program stored in the ROM 83 or the HDD 84. The ROM 83 stores a boot program executed by the CPU 81 when the computer 80 is started up, and programs that depend on the hardware of the computer 80.

[0138] The HDD 84 stores programs executed by the CPU 81, data used by such programs, etc. The communication interface 85 receives data from other devices via the network N (see FIG. 2) and sends it to the CPU 81, and transmits data generated by the CPU 81 to other devices via the network N.

[0139] The CPU 81 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 86. The CPU 81 acquires data from the input devices via the input / output interface 86. The CPU 81 also outputs data generated via the input / output interface 86 to the output devices.

[0140] The media interface 87 reads a program or data stored in a recording medium 88 and provides it to the CPU 81 via the RAM 82. The CPU 81 loads the program from the recording medium 88 onto the RAM 82 via the media interface 87 and executes the loaded program. The recording medium 88 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.

[0141] For example, when the computer 80 functions as the information processing device 1 according to the embodiment, the CPU 81 of the computer 80 executes a program loaded onto the RAM 82 to realize the function of the processing unit 12. In addition, the HDD 84 stores data in the storage unit 11. The CPU 81 of the computer 80 reads and executes these programs from a recording medium 88, but as another example, these programs may be obtained from another device via the network N.

[0142] [7. Other] In addition, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

[0143] In addition, each component of each device shown in the figure is a functional concept, and does 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 according to various loads, usage conditions, etc.

[0144] For example, the above-mentioned information processing device 1 may be realized by a terminal device and a server computer, or may be realized by multiple server computers. Also, depending on the functions, the configuration can be flexibly changed, such as by calling an external platform using an API or network computing.

[0145] Furthermore, the above-described embodiments and modifications can be appropriately combined as long as the processing contents are not contradictory.

[0146] 8. Effects As described above, the information processing device 1 according to the embodiment includes an acquisition unit 30 that acquires first purchase-related information, which is information related to purchases of transaction objects in the first online shopping mall 4A, and second purchase-related information, which is information related to purchases of transaction objects in the second online shopping mall 4B, and a generation unit 32 that generates an estimation model that estimates the spread of a trend related to purchases in the first online shopping mall 4A to the second online shopping mall 4B, based on the first purchase-related information and the second purchase-related information acquired by the acquisition unit 30. This enables the information processing device 1 to predict the spread of a trend of transaction objects between online shopping malls.

[0147] The generating unit 32 generates an estimation model that estimates whether a trend regarding purchases in the first online shopping mall 4A will spread to the second online shopping mall 4B. This enables the information processing device 1 to more accurately predict the spread of a trend regarding transaction objects between online shopping malls.

[0148] The generating unit 32 generates, as an estimation model, a model for estimating a period until a trend regarding a purchase in the first online shopping mall 4A spreads to the second online shopping mall 4B. This enables the information processing device 1 to more accurately predict the spread of a trend of a transaction object between online shopping malls.

[0149] The first purchase-related information includes first ranking information which is ranking information of purchases of transaction objects in the first online shopping mall 4A, and the second purchase-related information includes second ranking information which is ranking information of purchases of transaction objects in the second online shopping mall 4B, and the generation unit 32 generates an estimation model based on the difference between the fluctuation of the first ranking information and the fluctuation of the second ranking information. This enables the information processing device 1 to more accurately predict the spread of a trend of a transaction object between online shopping malls.

[0150] The first purchase-related information includes information indicating a first sell-out timing when the transaction object is sold out in the first online shopping mall 4A, and the second purchase-related information includes information indicating a second sell-out timing when the transaction object is sold out in the second online shopping mall 4B, and the generation unit 32 generates an estimation model based on a period from the first sell-out timing to the second sell-out timing. This enables the information processing device 1 to more accurately predict the spread of a trend of the transaction object between online shopping malls.

[0151] The first purchase-related information includes information indicating a first sell-out timing when the transaction object is sold out in the first online shopping mall 4A, and the second purchase-related information includes information indicating a second sell-out timing when the transaction object is sold out in the second online shopping mall 4B, and the generation unit 32 generates an estimation model assuming that a trend regarding purchases in the first online shopping mall 4A will spread to the second online shopping mall 4B if the period from the first sell-out timing to the second sell-out timing is within a predetermined period. This enables the information processing device 1 to more accurately predict the spread of a trend regarding transaction objects between online shopping malls.

[0152] The first purchase-related information includes information indicating a first sell-out timing when the transaction object is sold out in the first online shopping mall 4A, and the second purchase-related information includes information indicating a second sell-out timing when the transaction object is sold out in the second online shopping mall 4B, and the generation unit 32 generates an estimation model in which the period from the first sell-out timing to the second sell-out timing is the period until a trend regarding purchases in the first online shopping mall 4A spreads to the second online shopping mall 4B. This enables the information processing device 1 to more accurately predict the spread of a trend of a transaction object between online shopping malls.

[0153] Furthermore, the generating unit 32 generates an estimation model for each attribute of the transaction object, which enables the information processing device 1 to more accurately predict the spread of a trend of the transaction object between online shopping malls.

[0154] In addition, the generation unit 32 generates an estimated model for each combination of the first online shopping mall 4A and the second online shopping mall 4B. This enables the information processing device 1 to predict the spread of a trend of a trade object between online shopping malls.

[0155] The above describes the embodiment of the present application in detail based on the drawings, but this is merely an example, and the present invention can be implemented in other forms that include various modifications and improvements based on the knowledge of those skilled in the art, including the forms described in the Disclosure of the Invention section.

[0156] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit", etc. For example, an acquisition section can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0157] 1. Information processing device 2 Terminal Device 4 Electronic shopping street 4A 1st Electronic Shopping Street 4B Second electronic shopping street 10. Communications Department 11 Storage section 12 Processing section 20 Electronic shopping mall information storage section 21 Inflow number information storage unit 30 Acquisition Department 31 Reception 32 Generation part 33 Estimation part 34 Providing Department 100 Information Processing Systems N Network

Claims

1. an acquisition unit that acquires first purchase-related information, which is information regarding a purchase of a transaction object in the first online shopping mall, and second purchase-related information, which is information regarding a purchase of a transaction object in the second online shopping mall; a generation unit that generates an estimation model for estimating a manner in which a trend regarding the purchase in the first online shopping mall will spread to the second online shopping mall based on the first purchase-related information and the second purchase-related information acquired by the acquisition unit.

23. An information processing apparatus comprising:

2. The generation unit is A model for estimating whether or not the trend regarding the purchase in the first online shopping mall will spread to the second online shopping mall is generated as the estimation model.

2. The information processing apparatus according to claim 1,

3. The generation unit is A model for estimating a period until the trend regarding the purchase in the first online shopping mall spreads to the second online shopping mall is generated as the estimation model.

2. The information processing apparatus according to claim 1,

4. The first purchase-related information is First ranking information is ranking information of purchases of the transaction object in the first online shopping mall, The second purchase-related information is Second ranking information is ranking information of purchases of the transaction object in the second online shopping mall, The generation unit is The estimation model is generated based on a difference between the fluctuation of the first ranking information and the fluctuation of the second ranking information.

4. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

5. The first purchase-related information is information indicating a first sell-out timing, which is a timing when the transaction object is sold out in the first online shopping mall; The second purchase-related information is information indicating a second sell-out timing, which is a timing when the transaction object in the second online shopping mall is sold out; The generation unit is The estimation model is generated based on a period from the first sell-out timing to the second sell-out timing.

4. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

6. The first purchase-related information is information indicating a first sell-out timing, which is a timing when the transaction object is sold out in the first online shopping mall; The second purchase-related information is information indicating a second sell-out timing, which is a timing when the transaction object in the second online shopping mall is sold out; The generation unit is When the period from the first sold-out timing to the second sold-out timing is within a predetermined period, it is determined that the trend regarding the purchase in the first online shopping mall has spread to the second online shopping mall, and the estimation model is generated.

3. The information processing apparatus according to claim 2.

7. The first purchase-related information is information indicating a first sell-out timing, which is a timing when the transaction object is sold out in the first online shopping mall; The second purchase-related information is information indicating a second sell-out timing, which is a timing when the transaction object in the second online shopping mall is sold out; The generation unit is Generate the estimation model in which the period from the first sold-out timing to the second sold-out timing is the period until the trend regarding the purchase in the first online shopping mall spreads to the second online shopping mall.

4. The information processing apparatus according to claim 3.

8. The generation unit is The estimation model is generated for each attribute of the trading object.

4. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

9. The generation unit is The estimation model is generated for each combination of the first online shopping mall and the second online shopping mall.

4. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

10. 1. A computer-implemented information processing method, comprising: an acquiring step of acquiring first purchase-related information which is information regarding a purchase of a transaction object in the first online shopping mall and second purchase-related information which is information regarding a purchase of a transaction object in the second online shopping mall; and generating an estimation model for estimating a manner in which a trend regarding the purchase in the first online shopping mall will spread to the second online shopping mall based on the first purchase-related information and the second purchase-related information acquired by the acquiring step.

23. An information processing method comprising:

11. an acquisition step of acquiring first purchase-related information which is information relating to a purchase of a transaction object in the first online shopping mall, and second purchase-related information which is information relating to a purchase of a transaction object in the second online shopping mall; a generating step of generating an estimation model for estimating a manner in which a trend regarding the purchase in the first online shopping mall will spread to the second online shopping mall based on the first purchase-related information and the second purchase-related information acquired by the acquiring step, 2. An information processing program comprising:

Images