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

Abstract

To assist users in purchasing products at the desired price. [Solution] The information processing device 100 comprises an acquisition means for acquiring data on the selling prices of products at stores and data indicating the details of sales promotion measures implemented at the store as a training dataset, and a learning means for training a machine learning model using the training dataset acquired by the acquisition means so that when a user's desired purchase price data is input, data indicating the timing at which the user can purchase the product at the desired price is output.The information processing device 100 also comprises an input means for inputting the user's desired purchase price data into the trained machine learning model, and a notification means for performing processing to notify the user when data indicating the timing at which the user can purchase the product at the desired price is output from the trained machine learning model.

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] The following presentation device is known. This presentation device allows shoppers to grasp their savings status by outputting the amount of savings they have made on purchases within a specified period in an online marketplace where multiple stores are located (for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 5901864 Summary of the Invention [Problem to be solved by the invention]

[0004] Generally, users who shop at a store want to purchase products as cheaply as possible in order to save money, and to do so, they may set a desired purchase price for each product. In such cases, a system is needed to help users purchase products at their desired purchase price, but no technology for this purpose has been considered to date. [Means for solving the problem]

[0005] The information processing device according to the present invention includes an acquisition means for acquiring data on the selling prices of products in a store and data indicating the details of sales promotion measures implemented in the store as a training dataset, and a learning means for training a machine learning model using the training dataset acquired by the acquisition means so that when a user's desired purchase price data is input, data indicating the timing at which the user can purchase the product at the desired price is output. The desired purchase price data is data of a desired purchase price list including a plurality of products and the desired purchase price of each product, and the learning means is trained to determine that the product can be purchased at the price desired by the user when the selling price of each product included in the desired purchase price list is equal to or lower than the purchase price desired by the user, or when the total selling prices of the products included in the desired purchase price list is equal to or lower than the total desired purchase prices of the user included in the desired purchase price list. It is characterized by: The information processing device according to the present invention includes an input means for inputting a user's desired purchase price data into a trained machine learning model that has been trained to output data indicating a timing at which the user can purchase a product at the price desired by the user when the user inputs the desired purchase price data, and a notification means for performing processing to notify the user when the trained machine learning model outputs data indicating a timing at which the user can purchase a product at the price desired by the user. The notification method notifies the user of the date when the desired quantity is available for purchase at the desired price based on the output from the trained machine learning model, the product's inventory quantity, and the expected delivery quantity. It is characterized by: The information processing device according to the present invention comprises: The system includes an input means for inputting a user's desired purchase price data into a trained machine learning model that has been trained to output data indicating the timing at which the user can purchase the product at the price desired by the user when the user inputs the desired purchase price data, and a notification means for performing processing to notify the user when data indicating the timing at which the user can purchase the product at the price desired by the user is output from the trained machine learning model, and if the desired purchase price of the user is not reached, the notification means notifies the user of the timing at which the desired purchase price is closest within a predetermined period. It is characterized by: The information processing method according to the present invention is a method carried out by a computer, the method comprising: an acquisition step in which an acquisition means acquires data on the selling prices of products in a store and data indicating the details of sales promotion measures implemented in the store as a training dataset; and a learning step in which a learning means uses the training dataset acquired by the acquisition means to train a machine learning model so that, when a user's desired purchase price data is input, the machine learning model outputs data indicating the timing at which the user can purchase the product at the desired price. In the system, the desired purchase price data is data of a desired purchase price list including a plurality of products and the desired purchase price of each product, and the learning means is characterized by learning to determine that the product can be purchased at the price desired by the user when the selling price of a single product included in the desired purchase price list is equal to or lower than the purchase price desired by the user, or when the total selling prices of the products included in the desired purchase price list is equal to or lower than the total desired purchase price of the user included in the desired purchase price list. The information processing method according to the present invention includes: inputting a user's desired purchase price data into a trained machine learning model that has been trained to output data indicating a timing at which the user can purchase a product at the desired price; Registered by A method executed by a computer, comprising: a step of inputting desired purchase price data; and a step of notifying a user when data indicating a time when the user can purchase the product at the price desired by the user is output from the trained machine learning model by a notification means. The notification means is characterized by notifying the user of the date on which the product can be purchased at the desired purchase price and the quantity desired by the user is in stock, based on the output from the trained machine learning model, the product's inventory quantity, and the expected delivery quantity. The information processing method according to the present invention comprises: In an information processing method performed on a computer, the method includes the steps of: inputting desired purchase price data registered by a user into a trained machine learning model that has been trained so that, when input of the user's desired purchase price data is made, the model outputs data indicating the timing at which the user can purchase the product at the price desired by the user; and notifying the user when data indicating the timing at which the user can purchase the product at the price desired by the user is output from the trained machine learning model. The notifying means is characterized in that, if the user's desired purchase price is not reached, the notifying means notifies the user of the timing at which the price will come closest to the desired purchase price within a specified period. The information processing program according to the present invention is a program for causing a computer to execute an acquisition procedure for acquiring data on the selling prices of products in stores and data indicating the details of sales promotion measures implemented in the stores as a training dataset, and a learning procedure for training a machine learning model using the training dataset acquired in the acquisition procedure so that, when a user's desired purchase price data is input, data indicating the timing at which the user can purchase the product at the desired price is output. In the system, the desired purchase price data is data of a desired purchase price list including a plurality of products and the desired purchase price of each product, and the learning procedure is characterized in that when the selling price of a single product included in the desired purchase price list is equal to or lower than the purchase price desired by the user, or when the total selling prices of the products included in the desired purchase price list is equal to or lower than the total desired purchase price of the user included in the desired purchase price list, the learning procedure is characterized in that the system learns to determine that the product can be purchased at the price desired by the user. The information processing program according to the present invention is a program for processing a user's desired purchase price data into a trained machine learning model that has been trained to output data indicating the timing at which the user can purchase a product at the desired price. Registered by A program for causing a computer to execute an input procedure for inputting desired purchase price data and a notification procedure for notifying a user when data indicating the timing at which the user can purchase a product at the desired price is output from a trained machine learning model. In the method, the notification procedure is characterized by notifying the user of the date when the product can be purchased at the desired purchase price and the desired quantity is in stock, based on the output from the trained machine learning model, the product's inventory quantity, and the expected delivery quantity. The information processing program according to the present invention comprises: In an information processing program for causing a computer to execute an input procedure for inputting desired purchase price data registered by a user into a trained machine learning model that has been trained to output data indicating the timing at which the user can purchase the product at the price desired by the user when the user's desired purchase price data is input, and a notification procedure for performing processing to notify the user when data indicating the timing at which the user can purchase the product at the price desired by the user is output from the trained machine learning model, the notification procedure is characterized in that if the user's desired purchase price is not reached, the notification procedure notifies the user of the timing at which the price will come closest to the desired purchase price within a specified period. [Effects of the Invention]

[0006] According to the present invention, data indicating the timing when a user can purchase a product at the price they desire can be output, thereby assisting the user in purchasing the product at the desired purchase price. [Brief explanation of the drawings]

[0007] [Figure 1] 1 is a block diagram showing a configuration of an embodiment of an information processing device 100. FIG. [Figure 2] FIG. 1 is a flowchart illustrating the process flow in the learning stage of a machine learning model. [Figure 3] FIG. 1 is a flowchart showing the flow of processing using an AI agent. DETAILED DESCRIPTION OF THE INVENTION

[0008] 1 is a block diagram showing the configuration of an information processing device 100 according to the present embodiment. The information processing device 100 is, for example, a personal computer or a server, and includes a communication module 101, a control device 102, and a recording device 103.

[0009] The communication module 101 includes a module for connecting the information processing device 100 to a communication line such as a LAN or the Internet, wirelessly or by wire. In this embodiment, the information processing device 100 can communicate with other devices by connecting to the communication line via the communication module 101.

[0010] The control device 102 is configured with a CPU, memory, and other peripheral circuits, and controls the entire information processing device 100. The memory that configures the control device 102 is, for example, a volatile memory such as SDRAM. This memory is used as a work memory for the CPU to expand programs when the programs are executed, and as a buffer memory for temporarily recording data. For example, data received via the communication module 101 is temporarily recorded in the buffer memory.

[0011] The recording device 103 is a recording device for recording various data stored in the information processing device 100, program data to be executed by the control device 102, etc., and may be, for example, a hard disk drive (HDD) or a solid state drive (SSD). The program data recorded in the recording device 103 is provided by being recorded on a recording medium such as a CD-ROM or DVD-ROM, or provided via a network, and the user can install the acquired program data in the recording device 103, thereby enabling the control device 102 to execute the program.

[0012] The information processing device 100 in this embodiment provides a mechanism for notifying a user, who is a customer of a store, of the timing when the user can purchase the product at the desired price when the user registers the desired purchase price for the product in advance. To this end, the information processing device 100 in this embodiment accepts registration of data on the user's desired purchase price for the product, data on the selling price of the product at the store, and data indicating the details of sales promotion measures implemented by the store. Note that in this embodiment, the store includes both a physical store and a virtual store on the Internet. Furthermore, the virtual store on the Internet includes a marketplace where multiple sellers gather.

[0013] The data of the user's desired purchase price for each product is registered in advance by the user. For example, the user creates a list of desired purchase prices for each product, such as desired purchase price for product A is 500 yen, desired purchase price for product B is 500 yen, desired purchase price for product C is 200 yen, and desired purchase price for product D is 300 yen, and registers this as desired purchase price data in the information processing device 100.

[0014] There are no particular limitations on the method by which the user registers the desired purchase price data, but for example, the user may create a desired purchase price list on a user terminal such as a smartphone or a personal computer and transmit this via a communication line to the information processing device 100. In the information processing device 100, the control device 102 records the data of the desired purchase price list received from the user terminal in the recording device 103, thereby completing the registration of the desired purchase price data.

[0015] Data on the selling prices of products in a store and data indicating the details of sales promotion measures implemented in the store are registered in advance for each product by a store employee. For example, the store employee creates a sales price list in which the current selling price is set for each product, such as the selling price of product A being 600 yen, the selling price of product B being 500 yen, the selling price of product C being 300 yen, and the selling price of product D being 350 yen, and registers this in the information processing device 100. Furthermore, if there are plans to change the selling prices of products, the store employee registers the changed selling prices for each product along with information on the planned date of the price change. For example, a sales price list in which the changed selling prices are set for each product is created, such as from a certain date on a certain month, the selling price of product A will be changed to 500 yen and the selling price of product D will be changed to 380 yen, and this is registered in the information processing device 100 as selling price data.

[0016] The store clerk also creates a sales promotion list that records details of sales promotion measures, such as coupon information including the coupon usage date or coupon usage period and the coupon discount rate or discount price, point information including the point grant date or point grant period and the point grant rate or grant amount, or discount information including the discount date or discount period and the discount amount or discount rate for each product, and registers this as sales promotion data in the information processing device 100. For example, if there is a plan to distribute a 500 yen discount coupon that can be used from September 1st to September 10th, the store clerk will register the coupon information stating "Coupon usage period: September 1st to September 10th, coupon discount price: 500 yen" as sales promotion data.

[0017] The method by which the store clerk registers the sales price data and sales promotion data is not particularly limited, but for example, the store clerk may create the sales price list and sales promotion list data on a store terminal such as a smartphone or a personal computer, and register the data by transmitting it to the information processing device 100 via a communication line. In the information processing device 100, the control device 102 records the sales price list and sales promotion list data received from the store terminal in the recording device 103, thereby completing the registration of the sales price data and sales promotion data.

[0018] The control device 102 acquires the sales price data and sales promotion data recorded in the recording device 103 as a training dataset, and inputs the acquired training dataset into the machine learning model. The machine learning model is then trained so that when the desired purchase price data registered by the user is input, it outputs data indicating the timing at which the user can purchase the product at the desired price. This makes it possible to create a machine learning model that is trained so that when the desired purchase price data of the user is input as an explanatory variable, it outputs data indicating the timing at which the user can purchase the product at the desired price as a target variable.

[0019] In this embodiment, the machine learning model is trained to determine that a product can be purchased at the price desired by the user, for example, when the selling price of a single product is equal to or lower than the user's desired purchase price, or when the total selling prices of the products included in the list of desired purchase prices is equal to or lower than the user's total desired purchase prices included in the list of desired purchase prices. In this case, the machine learning model is trained to calculate the product selling price by taking into account the discount amount from a coupon, the amount of points redeemed, or the discount amount on the product price. Below, we will explain an example of when the trained machine learning model determines that a product can be purchased at the user's desired price.

[0020] Examples of cases where the selling price of a single product falls below the user's desired purchase price include the following: For each product included in the desired purchase price list registered by the user, the machine learning model compares the user's desired purchase price with the product's selling price based on sales price data and sales promotion data, and is trained to determine that if there is a product whose selling price is below the user's desired purchase price, the product can be purchased at the user's desired price.

[0021] For example, if a user's desired purchase price for Product A is 500 yen, and the sales price data contains data indicating that the sales price of Product A is 500 yen or less, it is determined that Product A can be purchased immediately at the price desired by the user. Also, if a user's desired purchase price for Product A is 500 yen, and the sales price data contains data indicating that the sales price of Product A will be changed to 500 yen or less in three days, it is determined that Product A can be purchased at the price desired by the user in three days. Alternatively, if a user's desired purchase price for Product B is 300 yen, and the sales price data contains data indicating that the sales price of Product B is 350 yen, and the sales promotion data contains data indicating that a 50 yen discount coupon will be distributed in five days, it is determined that Product B can be purchased at the price desired by the user in five days.

[0022] Furthermore, the following cases are examples of when the total selling price of the products included in the desired purchase price list is equal to or less than the total desired purchase price of the user included in the desired purchase price list: The machine learning model is trained to compare the total purchase price desired by the user for all products included in the desired purchase price list registered by the user with the total selling price of the products based on the selling price data and sales promotion data, and determine that the products can be purchased at the price desired by the user if the total selling price is equal to or less than the total desired purchase price.

[0023] For example, if the total desired purchase price of users included in the list of desired purchase prices is 1,500 yen, and it is determined based on the sales price data that the total selling price of the items included in the list is 1,500 yen or less, it is determined that the items can be purchased at the price desired by the user immediately. Also, if the total desired purchase price of users included in the list of desired purchase prices is 1,500 yen, and it is determined based on the sales price data that the total selling price of the items included in the list will be 1,500 yen or less in three days, it is determined that the items can be purchased at the price desired by the user in three days. Alternatively, if the total desired purchase price of users included in the list of desired purchase prices is 1,500 yen, and the sales price data includes data indicating that the total selling price of the items included in the list is 1,800 yen, and the sales promotion data includes data indicating that 500 yen points will be awarded starting five days later, it is determined that the items can be purchased at the price desired by the user in five days.

[0024] The trained machine learning model is trained to output data indicating the timing when the product can be purchased at the user's desired price, if it determines that the product can be purchased at the user's desired price. For example, if the trained machine learning model determines that the product can be purchased immediately at the user's desired price at the present time, it is configured to output data indicating that the product can be purchased at the user's desired price at the present time. Furthermore, if the trained machine learning model determines that the product can be purchased at the user's desired price three days from now, it is configured to output data indicating that the product will be available to purchase at the desired price three days from now.

[0025] This makes it possible to create a trained machine learning model that is configured to input the desired purchase price data registered by the user as an explanatory variable and output data indicating the timing at which the user can purchase the product at the price they desire as a target variable.

[0026] The control device 102 records data for using the created trained machine learning model. This allows the control device 102 to perform processing using the recorded trained machine learning model. Note that the recording destination of the trained machine learning model is not particularly limited. For example, the control device 102 may record the trained machine learning model in the recording device 103, or may record it in another device that can communicate via a communication line. In this embodiment, the following description will be given assuming that the trained machine learning model is recorded in the recording device 103.

[0027] The information processing device 100 in this embodiment uses this machine learning model to provide an AI agent that acts as a human representative (agent). In this embodiment, the AI ​​agent uses the trained machine learning model described above to execute a process for notifying the user of the timing when a product will become available for purchase at the price they desire. To this end, in this embodiment, a program for implementing the AI ​​agent is recorded in the recording device 103, and the control device 102 executes the program to execute the functions provided by the AI ​​agent.

[0028] Here, an AI agent is a system that acts as a human agent, has the ability to learn and make decisions on its own, and integrates various AI technologies to solve complex problems. For example, when a user gives an AI agent a question (prompt), the AI ​​agent searches for an answer to the question, generates an answer, and outputs the answer. Also, when a user gives an AI agent a task (prompt), the AI ​​agent searches for a solution to the task, generates an answer, and outputs the solution.

[0029] In this embodiment, an LLM (Large Scale Language Model) is assumed as an example of an AI agent, but the AI ​​agent according to the present invention is not limited to an LLM (Large Scale Language Model).

[0030] The AI ​​agent in this embodiment inputs the desired purchase price data recorded in the recording device 103 into the trained machine learning model. Based on the input desired purchase price data, the trained machine learning model determines, as described above, whether the product can be purchased at the price desired by the user, and if the product can be purchased at the price desired by the user, outputs data indicating the timing at which the product can be purchased at the price desired by the user as an inference result.

[0031] When the AI ​​agent determines that the trained machine learning model has output data indicating the timing at which the user can purchase the product at the price they desire, the AI ​​agent performs processing to notify the user of the output data. Note that the method of notifying the user is not particularly limited, and for example, the AI ​​agent may notify the user by displaying the data output from the trained machine learning model on a monitor (not shown), or by transmitting the data output from the trained machine learning model to a connected user terminal via a communication line.

[0032] 2 is a flowchart showing the flow of processing in the learning stage of a machine learning model executed by the information processing device 100 in this embodiment. The processing shown in FIG. 2 is executed by the control device 102 as a program that is activated when the machine learning model is trained. Note that there are no particular limitations on the timing when the machine learning model is trained.

[0033] In step S10, as described above, the control device 102 acquires the sales price data and sales promotion data recorded in the recording device 103 as a learning data set. Then, the process proceeds to step S20.

[0034] In step S20, the control device 102 inputs the acquired learning data set into the machine learning model, and causes the machine learning model to learn. Then, the process proceeds to step S30.

[0035] In step S30, the control device 102 determines whether learning of the machine learning model has finished. The control device 102 may determine that learning of the machine learning model has finished, for example, when an operator instructs the control device 102 to finish learning of the machine learning model. If the determination in step S30 is negative, the process returns to step S10. On the other hand, if the determination in step S30 is positive, the process proceeds to step S40.

[0036] In step S40, as described above, the control device 102 records data for using the trained machine learning model in a recording destination, for example, the recording device 103. Thereafter, the process ends.

[0037] 3 is a flowchart showing the flow of processing using an AI agent executed by information processing device 100 in this embodiment. The processing shown in FIG. 3 is executed by control device 102 as a program that is started when an operator issues an instruction to start the AI ​​agent.

[0038] In step S110, the control device 102 inputs the desired purchase price data recorded in the recording device 103 into the trained machine learning model. Then, the process proceeds to step S120.

[0039] In step S120, the control device 102 determines whether the trained machine learning model has output the inference result data, i.e., data indicating the timing at which the user can purchase the product at the desired price. If the determination in step S120 is affirmative, the process proceeds to step S130.

[0040] In step S130, the control device 102 performs a process to notify the user of the inference result output from the trained machine learning model, i.e., data indicating the timing when the user can purchase the product at the price desired by the user, as described above. Then, the process ends.

[0041] According to the embodiment described above, the following advantageous effects can be obtained. (1) The control device 102 acquires data on the selling prices of products at stores and data indicating the details of sales promotion measures implemented at the stores as a training dataset, and trains a machine learning model using the acquired training dataset so that when a user's desired purchase price data is input, data indicating the timing at which the user can purchase the product at the desired price can be output. This makes it possible to create a machine learning model that supports users in purchasing products at their desired prices.

[0042] (2) The desired purchase price data is data of a desired purchase price list including a plurality of products and the desired purchase price of each product, and the control device 102 trains the machine learning model to determine that a product can be purchased at the price desired by the user when the selling price of a single product included in the desired purchase price list is equal to or lower than the purchase price desired by the user, or when the total selling prices of the products included in the desired purchase price list is equal to or lower than the total desired purchase prices of the user included in the desired purchase price list. This makes it possible to notify the user that the time when the product can be purchased at the price desired by the user is when the selling prices of one or more products included in the desired purchase price list are equal to or lower than the desired purchase price, or when the selling prices of the products in the desired purchase price list as a whole are equal to or lower than the desired purchase price.

[0043] (3) The sales price data for products in stores is data showing the current sales price for each product or data showing the changed sales price for each product. This allows users to determine when they can purchase a product at their desired price based on the current sales price or the future planned sales price.

[0044] (4) The data indicating the details of sales promotion measures implemented at the store is assumed to be coupon information including the coupon validity date or validity period and the coupon discount rate or discount price, point information including the point grant date or point grant period and the point grant rate or amount, or discount information including the discount date or discount period and the discount amount or discount rate for each product.The machine learning model is then trained to calculate the product sales price taking into account the coupon discount amount, the point redemption amount, or the product price discount amount.This makes it possible to determine the timing when a user can purchase a product at their desired price by taking into account the coupon discount amount, the point redemption amount, or the product price discount amount.

[0045] (5) The control device 102 inputs the user's desired purchase price data into a trained machine learning model that has been trained to output data indicating the timing at which the user can purchase the product at the price desired by the user when the user inputs the desired purchase price data, and performs processing to notify the user when the trained machine learning model outputs data indicating the timing at which the user can purchase the product at the price desired by the user. This makes it possible to notify the user of the timing at which the user can purchase the product at the price desired by the user.

[0046] -Variation- The information processing device according to the above-described embodiment can be modified as follows. (1) In the above-described embodiment, an example was described in which the machine learning model is trained using sales price data and sales promotion data registered by a store employee as a training dataset, and is trained to output data indicating when a product will be available for purchase when the desired purchase price data is input. However, if data from other chain stores is available, the machine learning model may be trained by including sales price data and sales promotion data from other chain stores in the training dataset. The machine learning model may also be configured to output, as an inference result, products that are better purchased at the store and products that are better purchased at other chain stores when the desired purchase price data is input. This makes it possible to provide information that is beneficial to the user, such as, for example, that products A and B can be purchased at the desired price at the store, and product C can be purchased at the desired price at another chain store.

[0047] (2) In the above-described embodiment, the control device 102 acquires data on the selling prices of products at a store and data indicating the details of promotional measures implemented at the store as a training dataset, and uses the acquired training dataset to train a machine learning model so that, when a user's desired purchase price data is input, data indicating the timing at which the user can purchase the product at the desired price is output. The user's desired purchase price data is then input to the trained machine learning model, and processing is performed to notify the user when the trained machine learning model outputs data indicating the timing at which the user can purchase the product at the desired price. However, the present invention can be realized without using a machine learning model. For example, the control device 102 may identify planned price changes, coupons, or other promotional measures based on the selling price data of products at the store and the data indicating the details of promotional measures implemented at the store, and calculate and notify the user of the timing at which the user can purchase the product at the desired purchase price.

[0048] (3) In the above-described embodiment, the control device 102 acquires data on the selling price of a product at a store and data indicating details of sales promotion measures implemented at the store as a training dataset, and uses the acquired training dataset to train a machine learning model so that, when a user's desired purchase price data is input, data indicating the timing at which the user can purchase the product at the desired price is output. The user's desired purchase price data is then input to the trained machine learning model, and processing is performed to notify the user when the trained machine learning model outputs data indicating the timing at which the user can purchase the product at the desired price. However, the control device 102 may also notify the user of the date on which the user can purchase the product at the desired purchase price and the desired quantity is in stock, based on the output from the trained machine learning model and the product inventory and planned delivery quantity. Furthermore, if the user's desired purchase price is not reached, the control device 102 may also notify the user of the timing at which the desired purchase price will be closest within a predetermined period. In addition, when future price forecasts are known and there are multiple times when the product can be purchased at the user's desired purchase price, the control device 102 may notify the user of a time when the product can be purchased at a lower price, or may notify the user that there is a time when the product can be purchased at a lower price.

[0049] (4) In the above-described embodiment, the control device 102 acquires data on the selling prices of products at stores and data indicating details of sales promotion measures implemented at the stores as training datasets. Using the acquired training datasets, the control device 102 trains a machine learning model so that, when a desired purchase price data registered by a user is input, the machine learning model outputs data indicating when the user can purchase the product at the desired price. The desired purchase price data registered by the user is input to the trained machine learning model. When the trained machine learning model outputs data indicating when the user can purchase the product at the desired price, the control device 102 performs processing to notify the user. However, the desired purchase price data input to the machine learning model is not limited to data registered by the user. For example, based on the user's purchase history, the control device 102 inputs data on products previously purchased by the user and the purchase prices at those times into the machine learning model as the user's desired purchase price data. The trained machine learning model then outputs data indicating when the user can purchase the product at the desired price. This allows the control device 102 to notify the user of when the user can purchase the product previously purchased at the same price or a lower price.

[0050] (5) In the above-described embodiment, the control device 102 acquires data on the selling prices of products at stores and data indicating the details of sales promotion measures implemented at the stores as training datasets, and uses the acquired training datasets to train a machine learning model so that, when a user's desired purchase price data is input, data indicating the timing at which the user can purchase the product at the desired price is output. The user's desired purchase price data is then input into the trained machine learning model, and processing is performed to notify the user when the trained machine learning model outputs data indicating the timing at which the user can purchase the product at the desired price. However, the user may also be notified of the timing at which the user can purchase the product at the desired price, as well as the store where the product can be purchased at that price, or the store and sales area within the store where the product can be purchased at that price.

[0051] For this purpose, the sales price data and sales promotion data include store information, and management information data including information such as store allocation, display position, layout, and zoning is also prepared. The control device 102 then acquires the sales price data, sales promotion data, and management information data recorded in the recording device 103 as a training dataset and inputs the acquired training dataset into the machine learning model. The machine learning model can then be trained to output data indicating the timing and store at which the product can be purchased at the user's desired price, or data indicating the timing and store and sales floor at which the product can be purchased, when the desired purchase price data registered by the user is input. This makes it possible to create a machine learning model that is trained to output data indicating the timing and store at which the product can be purchased at the user's desired price, as the objective variable, when the desired purchase price data of the user is input as the explanatory variable. Furthermore, it is possible to create a machine learning model that is trained to output data indicating the timing and store and sales floor at which the product can be purchased, as the objective variable, when the desired purchase price data of the user is input as the explanatory variable.

[0052] The AI ​​agent then inputs the desired purchase price data recorded in the recording device 103 into the trained machine learning model. Based on the input desired purchase price data, the trained machine learning model determines whether the product can be purchased at the user's desired price, as described above. If the product can be purchased at the user's desired price, the trained machine learning model outputs data indicating the timing at which the product can be purchased at the user's desired price and the store where the product can be purchased as an inference result. Alternatively, the AI ​​agent outputs data indicating the timing at which the product can be purchased at the user's desired price and the store and sales area where the product can be purchased as an inference result. When the AI ​​agent determines that an inference result has been output from the trained machine learning model, it performs processing to notify the user of the output data. That is, when the trained machine learning model outputs data indicating the timing at which the product can be purchased at the user's desired price and the store where the product can be purchased, the AI ​​agent notifies the user of the timing at which the product can be purchased at the user's desired price and the store where the product can be purchased. Furthermore, when the trained machine learning model outputs data indicating the timing at which the product can be purchased at the user's desired price and the store and sales area where the product can be purchased, the AI ​​agent notifies the user of the timing at which the product can be purchased at the user's desired price and the store and sales area where the product can be purchased.

[0053] It should be noted that the present invention is not limited to the configurations in the above-described embodiments, as long as the characteristic functions of the present invention are not impaired. [Explanation of symbols]

[0054] 100 Information processing device 101 Communication Module 102 Control device 103 Recording Device

Claims

1. an acquisition means for acquiring data on the sales prices of products in a store and data indicating the details of sales promotion measures implemented in the store as a learning dataset; a learning means for training a machine learning model using the learning dataset acquired by the acquisition means so that when a user's desired purchase price data is input, data indicating a time when the user can purchase the product at the price desired by the user is output; The desired purchase price data is data of a desired purchase price list including a plurality of products and the desired purchase price of each product, The information processing device is characterized in that the learning means is trained to determine that a product can be purchased at the price desired by the user when the selling price of a single product included in the desired purchase price list is lower than the purchase price desired by the user, or when the total selling prices of the products included in the desired purchase price list is lower than the total desired purchase price of the user included in the desired purchase price list.

2. 2. The information processing device according to claim 1, The information processing device is characterized in that the data on the selling prices of the products in the store is data indicating the current selling price of each product, or data indicating a changed selling price of each product.

3. 2. The information processing device according to claim 1, The information processing device is characterized in that the data indicating the content of sales promotion measures implemented at the store is coupon information including the coupon usage date or coupon usage period and the discount rate or discount price for the coupon, point information including the point award date or point award period and the point award rate or amount, or discount information including the discount date or discount period and the discount amount or discount rate for each product.

4. 4. The information processing device according to claim 3, The information processing device is characterized in that the learning means trains the machine learning model to calculate the selling price of a product by taking into account the discount amount due to a coupon, the amount of points returned, or the discount amount on the product price.

5. an input means for inputting the user's desired purchase price data into a trained machine learning model that has been trained to output data indicating the timing at which the user can purchase the product at the price desired by the user when the user's desired purchase price data is input; a notification means for notifying a user when data indicating a time when the user can purchase a product at a desired price is output from the trained machine learning model; The notification means notifies the user of the date on which the product can be purchased at the desired purchase price and the quantity desired by the user is in stock, based on the output from the trained machine learning model, the product's inventory quantity, and the planned delivery quantity.

6. An input means for inputting a user's desired purchase price data into a trained machine learning model that has been trained to output data indicating the timing at which the user can purchase a product at the price desired by the user when the user's desired purchase price data is input; a notification means for notifying a user when data indicating a time when the user can purchase a product at a desired price is output from the trained machine learning model; The information processing device is characterized in that, if the price is not reached at the user's desired purchase price, the notification means notifies the user of the timing when the price will come closest to the desired purchase price within a predetermined period.

7. 7. The information processing device according to claim 5, The information processing device is characterized in that, when there are multiple times when the product can be purchased at the user's desired purchase price, the notification means notifies the user of a time when the product can be purchased at a lower price, or notifies the user that there is a time when the product can be purchased at a lower price.

8. 7. The information processing device according to claim 5, The information processing device is characterized in that the notification means notifies the user of the timing when the product can be purchased at the price desired by the user and the store where the product can be purchased, or the timing when the product can be purchased at the price desired by the user and the store and sales area where the product can be purchased.

9. an acquisition step of acquiring data on the sales prices of products in a store and data indicating the details of sales promotion measures implemented in the store as a learning dataset; an information processing method performed by a computer, the information processing method comprising: a step in which a learning means uses the learning dataset acquired by the acquisition means to train a machine learning model so that, when a user's desired purchase price data is input, the machine learning model outputs data indicating a timing at which the user can purchase a product at the price desired by the user; The desired purchase price data is data of a desired purchase price list including a plurality of products and the desired purchase price of each product, An information processing method characterized in that the learning means is trained to determine that a product can be purchased at the price desired by the user when the selling price of a single product included in the desired purchase price list is lower than the purchase price desired by the user, or when the total selling prices of the products included in the desired purchase price list is lower than the total desired purchase prices of the user included in the desired purchase price list.

10. 10. The information processing method according to claim 9, The information processing method is characterized in that the data on the selling prices of the products in the store is data indicating the current selling price of each product, or data indicating a changed selling price of each product.

11. 10. The information processing method according to claim 9, An information processing method characterized in that the data indicating the content of sales promotion measures implemented at the store is coupon information including the coupon usage date or coupon usage period and the discount rate or discount price for the coupon, point information including the point award date or point award period and the point award rate or amount, or discount information including the discount date or discount period and the discount amount or discount rate for each product.

12. 12. The information processing method according to claim 11, The learning means may be configured to learn discounts by coupons, points redemption amounts, or discounts on product prices. An information processing method characterized by training the machine learning model to calculate the selling price of a product taking into account the above.

13. inputting the desired purchase price data registered by the user into a trained machine learning model that has been trained so that, when the input means inputs the desired purchase price data of the user, it outputs data indicating the timing at which the user can purchase the product at the price desired by the user; a notification means for notifying a user when data indicating a timing at which the user can purchase a product at a price desired by the user is output from the trained machine learning model, The information processing method is characterized in that the notification means notifies the user of the date on which the product can be purchased at the desired purchase price and the quantity desired by the user is in stock, based on the output from the trained machine learning model, the product's inventory quantity, and the planned delivery quantity.

14. A step of inputting the desired purchase price data registered by a user into a trained machine learning model that has been trained so that, when the user inputs the desired purchase price data, it outputs data indicating the timing at which the user can purchase the product at the desired price; a notification means for notifying a user when data indicating a timing at which the user can purchase a product at a price desired by the user is output from the trained machine learning model, The information processing method is characterized in that, if the price is not reached at the user's desired purchase price, the notification means notifies the user of the timing when the price will come closest to the desired purchase price within a predetermined period.

15. 15. The information processing method according to claim 13, The information processing method is characterized in that, when there are multiple times when the product can be purchased at the user's desired purchase price, the notification means notifies the user of a time when the product can be purchased at a lower price, or notifies the user that there is a time when the product can be purchased at a lower price.

16. 15. The information processing method according to claim 13, The information processing method is characterized in that the notification means notifies the user of the timing when the product can be purchased at the desired price and the store where the product can be purchased, or the timing when the product can be purchased at the desired price and the store and sales floor where the product can be purchased.

17. an acquisition step of acquiring data on the sales prices of products in a store and data indicating the details of sales promotion measures implemented in the store as a learning dataset; a learning procedure for training a machine learning model using the learning dataset acquired in the acquisition procedure so that, when a user's desired purchase price data is input, data indicating a timing at which the user can purchase a product at the price desired by the user is output, The desired purchase price data is data of a desired purchase price list including a plurality of products and the desired purchase price of each product, The information processing program is characterized in that the learning procedure is learned to determine that a product can be purchased at the price desired by the user when the selling price of a single product included in the desired purchase price list is lower than the user's desired purchase price, or when the total selling prices of the products included in the desired purchase price list is lower than the user's total desired purchase price included in the desired purchase price list.

18. 18. The information processing program according to claim 17, The information processing program is characterized in that the data on the selling prices of the products in the store is data indicating the current selling price of each product, or data indicating a changed selling price of each product.

19. 18. The information processing program according to claim 17, The information processing program is characterized in that the data indicating the content of sales promotion measures implemented at the store is coupon information including the coupon usage date or coupon usage period and the discount rate or discount price for the coupon, point information including the point award date or point award period and the point award rate or amount, or discount information including the discount date or discount period and the discount amount or discount rate for each product.

20. 20. The information processing program according to claim 19, The information processing program is characterized in that the learning procedure trains the machine learning model to calculate the selling price of a product by taking into account the discount amount due to a coupon, the amount of points returned, or the discount amount on the product price.

21. an input step of inputting the desired purchase price data registered by the user into a trained machine learning model that has been trained to output data indicating the timing at which the user can purchase the product at the desired price when the user inputs the desired purchase price data; a notification procedure for performing processing to notify a user when data indicating a timing at which the user can purchase a product at a desired price is output from the trained machine learning model, The information processing program is characterized in that the notification procedure notifies the user of the date on which the product can be purchased at the desired purchase price and the quantity desired by the user is in stock, based on the output from the trained machine learning model, the product's inventory quantity, and the planned delivery quantity.

22. An input step of inputting the desired purchase price data registered by a user into a trained machine learning model that has been trained to output data indicating the timing at which the user can purchase the product at the price desired by the user when the desired purchase price data is input; a notification procedure for performing processing to notify a user when data indicating a timing at which the user can purchase a product at a desired price is output from the trained machine learning model, The information processing program is characterized in that the notification step notifies the user of the timing when the price is closest to the user's desired purchase price within a predetermined period if the price is not reached.

23. 23. The information processing program according to claim 21, The information processing program is characterized in that the notification procedure notifies the user of a timing when the product can be purchased at a lower price when there are multiple timings when the product can be purchased at the user's desired purchase price, or notifies the user that there is a timing when the product can be purchased at a lower price.

24. 23. The information processing program according to claim 21, The information processing program is characterized in that the notification procedure notifies the user of the timing at which the product can be purchased at the desired price and the store where the product can be purchased, or the timing at which the product can be purchased at the desired price and the store and sales floor where the product can be purchased.

Images