Information processing systems, information processing methods, information processing programs, and AI agents

Abstract

This invention provides an information processing system, information processing method, information processing program, and AI agent that can generate criteria for purchasing decisions by buyers in the retail industry and other sectors, and optimize the purchasing activities of buyers. [Solution] An information processing system configured with an AI agent which is a computer, wherein the AI ​​agent includes a learning means for learning the purchasing activities of multiple buyers of a certain product; an analysis means capable of analyzing the relationship between product sales information relating to the sale of a certain product and the purchasing activities of a specific buyer among the multiple buyers; and a generation means capable of generating criteria for the purchasing activities of a certain buyer for that product based on the relationship between the product sales information of a certain product and the purchasing activities of the specific buyer.

Description

Technical Field

[0001] The present invention relates to an information processing system, an information processing method, an information processing program using an AI agent, and an AI agent.

Background Art

[0002] Conventionally, there has been proposed a product demand prediction program that causes a computer to execute an information acquisition step of acquiring transaction history information regarding a user's product transactions, a reference transaction history information regarding past transaction histories for each product of the user acquired in advance, and a relevance of three or more levels including a demand degree corresponding to subsequent transaction actions for the product, and a determination step of determining the demand degree for the product based on the transaction history information acquired in the information acquisition step (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the conventional system, although it is possible to predict the demand for a product based on the consumption activities of consumers of the product, it has not been possible to predict the demand for a product based on the purchasing activities of buyers of the product.

[0005] In view of such circumstances, the present invention aims to provide an information processing system, an information processing method, an information processing program, and an AI agent that can generate criteria for determining the purchasing activities of buyers in retail and the like, and can optimize the purchasing activities of products by buyers.

Means for Solving the Problems

[0006] The information processing system according to the present invention is an information processing system configured to have an AI agent which is a computer, wherein the AI ​​agent comprises: a learning means for learning the purchasing activities of multiple buyers of a certain product; an analysis means capable of analyzing the relationship between product sales information relating to the sale of a certain product and the purchasing activities of a specific buyer among the multiple buyers; and a generation means capable of generating criteria for the purchasing activities of a buyer for a certain product based on the relationship between the product sales information of a certain product and the purchasing activities of the specific buyer.

[0007] The information processing method according to the present invention is an information processing method that is performed using an AI agent which is a computer, wherein the AI ​​agent performs at least the following steps: a learning step of learning the purchasing activities of multiple buyers of a certain product; an analysis step capable of analyzing the relationship between product sales information relating to the sale of a certain product and the purchasing activities of a specific buyer among the multiple buyers; and a generation step capable of generating criteria for the purchasing activities of a certain buyer for a certain product based on the relationship between the product sales information of a certain product and the purchasing activities of the specific buyer.

[0008] The information processing program according to the present invention is a program for an information processing system configured to have an AI agent, characterized in that the AI ​​agent, which is a computer, functions as: a learning means for learning the purchasing activities of multiple buyers of a certain product; an analysis means capable of analyzing the relationship between product sales information relating to the sale of a certain product and the purchasing activities of a specific buyer among the multiple buyers; and a generation means capable of generating criteria for the purchasing activities of a certain buyer for that product based on the relationship between the product sales information of a certain product and the purchasing activities of the specific buyer.

[0009] The AI ​​agent according to the present invention is an AI agent that acts as a substitute for a human and has the ability to learn and make decisions on its own, wherein the AI ​​agent, which is a computer, functions as a learning means for learning the purchasing activities of multiple buyers of a certain product; an analysis means capable of analyzing the relationship between product sales information relating to the sale of a certain product and the purchasing activities of a specific buyer among the multiple buyers; and a generation means capable of generating judgment criteria for the purchasing activities of a certain buyer based on the relationship between the product sales information of a certain product and the purchasing activities of the specific buyer, wherein the judgment criteria for purchasing activities are repeatedly provided as learning data and the judgment criteria for purchasing activities are acquired by machine learning. [Effects of the Invention]

[0010] The information processing system, information processing method, information processing program, and AI agent according to the present invention can generate criteria for purchasing activities of buyers in the retail industry, and can achieve the excellent effect of optimizing the purchasing activities of buyers. [Brief explanation of the drawing]

[0011] [Figure 1] This is a schematic diagram showing an overview of the information processing system 10 according to this embodiment. [Figure 2] This is a system configuration diagram showing an example of the configuration of the information processing system 10 according to this embodiment. [Figure 3] This diagram illustrates an example of the relationship between product sales information and buyer purchasing activity. [Modes for carrying out the invention]

[0012] The following describes an information processing system 10 according to an embodiment of the present invention with reference to the drawings.

[0013] <Overview of the Information Processing System> First, an overview of the information processing system 10 according to this embodiment will be described using Figure 1. Figure 1 is a schematic diagram showing an overview of the information processing system 10 according to this embodiment.

[0014] The information processing system 10 according to this embodiment is an information processing system configured to have an AI agent 12 which is a computer, wherein the AI ​​agent 12 comprises: a learning means 12a for learning the purchasing activities of multiple buyers of a certain product; an analysis means 12b capable of analyzing the relationship between product sales information relating to the sale of a certain product and the purchasing activities of a specific buyer among multiple buyers; and a generation means 12c capable of generating judgment criteria for a buyer's purchasing activity for a certain product based on the relationship between the sales information of a certain product and the purchasing activities of a specific buyer.

[0015] According to the information processing system of this embodiment, it is possible to generate criteria for purchasing activities of buyers in the retail industry, and to optimize the purchasing activities of buyers.

[0016] Here, "AI agent" refers to a system that acts as a substitute (agent) for a human, possessing the ability to learn and make decisions on its own, and integrating various AI technologies for solving complex problems.

[0017] AI agents can perform tasks based on external triggers (e.g., user prompts, sensor inputs) or internal triggers (e.g., activation by an internal scheduler, occurrence of anomalies).

[0018] For example, when a question (prompt) is given as a trigger from the outside, tasks such as searching for an answer to the question or generating an answer are executed, and the answer to the question is output. Also, for example, when a task (prompt) is given as a trigger from the outside, tasks such as searching for a solution to the task or generating a solution are executed, and the solution to the task is output.

[0019] Also, "prompt" refers to instructions or questions given by a user to the system, and includes, for example, an AI prompt given to a generative AI, a command prompt that gives instructions by a command sentence (command), etc. The data format of "prompt" is not particularly limited, and may be any of, for example, text data, voice data, still image data, moving image data, a file, etc.

[0020] Various processes executed by the AI agent can also be executed by "agent-type AI", "optical generation model", etc. Here, "agent-type AI" refers to a system in which a plurality of AI agents operate in cooperation. Agent-type AI is used to solve complex problems that cannot be solved by a single AI agent. Each AI agent plays a specialized role and outputs an answer to a question or a solution to a task while exchanging information with each other.

[0021] Also, "optical generation model" refers to a system that uses the physical properties of light, combines optical elements such as lenses, prisms, diffraction gratings, etc., and performs information processing by the light itself performing calculations. Since it can process countless light rays simultaneously, its processing speed is higher than that of an AI that uses electricity to process information sequentially. Also, its energy efficiency is high, and it can reduce power consumption compared to an AI that uses electricity.

[0022] In addition, the "buyer's purchasing activities" refer to various activities (actions) carried out by the buyer (purchaser) of goods during the process of purchasing and selling goods in a company such as retail. Examples of "buyer's purchasing activities" include, for example, procurement of goods (the work of placing an order for goods), sales promotion activities of goods (activities of promoting and advertising goods), search for goods (activities of looking for goods), selection of goods (activities of choosing goods), price negotiation of goods, price determination of goods, etc.

[0023] In addition, "product sales information" refers to information (marketing information) related to the sales of products. Examples of "product sales information" include, for example, purchase history information which is information on the history of goods purchased by customers (past performance data), demand prediction information which is information on the demand prediction of products (future prediction data), etc.

[0024] Examples of "purchase history information" include, for example, (1) customer information (customer ID, gender, age, membership rank, personal information, etc.), (2) product information (product ID, product name, category, brand, unit price, etc.), (3) purchase information (purchase date, purchase time, purchase quantity, total amount, payment method, questionnaire, staff response record, etc.), (4) store information (store ID, store name, sales channel (store / EC), etc.), (5) campaign information (implementation status of campaigns and events, coupon use, point use, discount rate, etc.), (6) purchase frequency (number of purchases, average purchase interval, most recent purchase date, etc.).

[0025] Examples of "demand prediction information" include information on predicting the demand for products by category, information on predicting the demand for products by store, information on predicting the demand for products on a monthly basis, information on predicting the demand for products in the short, medium, and long terms, information on predicting the demand for products based on the prediction of customers' purchasing intentions, information on predicting the demand for products from product trends, etc.

[0026] "Buyer's purchasing criteria" refers to information that serves as a basis (indicator) for buyers when making purchasing decisions. Examples of buyer's purchasing criteria include the timing of product procurement, the number of products to be procured and sold, the timing of product promotion activities, the methods of product promotion activities, the purchase price and selling price of products, newly launched products, and products to be discontinued.

[0027] Furthermore, the system may include a storage means 12d capable of storing management numerical information, which is numerical information that visualizes the company's management status through management indicators and financial indicators, and a verification means 12e capable of analyzing the management numerical information after a buyer has carried out a purchasing activity based on the criteria for making purchasing decisions, and verifying whether or not the management numerical information has improved.

[0028] With this configuration, it becomes possible to understand the effectiveness of purchasing activities and improve the accuracy of the purchasing activity criteria generated by verifying whether the criteria for purchasing activities generated based on management numerical information are appropriate.

[0029] Here, "management numerical information" refers to numerical information that visualizes a company's management status through management indicators and financial indicators, and is used to evaluate company performance. Examples of "management numerical information" include: (1) sales and profit-related data (e.g., sales data, profit data), (2) sales and product management-related data (e.g., product master data, specifications, shelf layout data, sales performance and promotional effectiveness), (3) inventory and purchasing-related data (e.g., inventory status, ordering and purchasing data), (4) customer and marketing-related data (e.g., customer ID data (ID-POS), marketing campaign results), (5) store operations and personnel management-related data (e.g., store performance, staff shifts), (6) expense and financial-related data (e.g., store and headquarters expenses, financial indicators), (7) external environment data (e.g., trade area / population data, competitor store location and pricing information, weather, temperature, and disaster information), (8) local event / school event information, and (9) instruction and communication-related data (e.g., work instructions and policies from superiors, reports and suggestions from the field, history of collaboration with headquarters).

[0030] Furthermore, within "management numerical information," (2) sales and product management-related data (e.g., product master data, specifications, shelf layout data, sales performance and promotional effects) may be referred to as "sales promotion data," and within "management numerical data," (4) customer and marketing-related data (e.g., customer ID data (ID-POS), marketing campaign results) may be referred to as "purchase history data (purchase history information)."

[0031] Furthermore, the management numerical information may include purchase history information, which is information about the history of a particular product purchased by a customer. The verification means 12e may be configured to analyze the purchase history information after the buyer has carried out a purchase activity based on the criteria for making a purchase, and to verify whether the purchase history information has improved.

[0032] With this configuration, by verifying whether the criteria for generating purchasing activities are appropriate based on purchase history information (past performance data), it is possible to grasp the effectiveness of purchasing activities and improve the accuracy of the criteria for generating purchasing activities.

[0033] Furthermore, a buyer's purchasing activities may include the procurement of certain goods and sales promotion activities for certain goods.

[0034] With this configuration, purchasing decision criteria can be generated based on the buyer's product procurement and sales promotion activities, and these purchasing decision criteria can be optimized.

[0035] Furthermore, product sales information for a certain product may include purchase history information, which is information about the history of a customer's purchase of that product, and demand forecast information, which is information about the forecast of demand for that product.

[0036] With this configuration, purchasing decision-making criteria can be generated based on both past performance data (purchase history information) and future forecast data (demand forecast information), thereby optimizing the purchasing decision-making criteria.

[0037] Furthermore, a specific buyer may be just one of several buyers.

[0038] With this configuration, for example, purchasing criteria can be generated based on the purchasing activities of a high-performing buyer (the subjective opinion of a single buyer), and these purchasing criteria can be optimized.

[0039] Furthermore, the aforementioned specific buyer may be two or more buyers from among the aforementioned group of buyers whose purchasing activities are the same or similar.

[0040] With this configuration, purchasing decision criteria can be generated based on the purchasing activities of buyers whose purchasing activities are the same or similar (public opinion from multiple buyers with similar purchasing activities), and these purchasing decision criteria can be optimized.

[0041] Furthermore, the criteria for purchasing decisions may be repeatedly provided as training data, and the system may be configured to acquire these purchasing decision criteria through machine learning.

[0042] With this configuration, purchasing decision-making criteria can be accumulated as training data, thereby improving the accuracy of those criteria.

[0043] <Example of system configuration> Next, an example of the configuration of the information processing system 10 according to this embodiment will be described using Figure 2. Figure 2 is a system configuration diagram showing an example of the configuration of the information processing system 10 according to this embodiment.

[0044] The information processing system 10 can be configured, for example, to include a system terminal 12 that controls the entire system, and an information storage terminal 12d and an external terminal 16 that are connected to the system terminal 12 via a network NW so that they can communicate with each other.

[0045] The system terminal 12 is a terminal that controls the entire information processing system 10, and is composed of conventionally known servers, personal computers, etc. In this example, the system terminal 12 is composed of one server, but it may be composed of multiple servers, personal computers, etc. The hardware configuration of the system terminal 12 and the programs that the system terminal 12 executes will be described later.

[0046] The information storage terminal 12d is a terminal (storage means) used by a retail store (e.g., a drugstore, retail store, convenience store, etc.) to store the store's management figures and the customer's purchase history information, and is composed of a POS terminal, a conventionally known server, a personal computer, etc.

[0047] In this example, the information storage terminal 12d is configured with a single server, but it may also be configured with multiple servers or personal computers. Furthermore, the terminal (storage means) for storing management figures and purchase history information may be an internal storage means (for example, the storage device 26 shown in Figure 2) connected to the system terminal 12 via a local network (for example, LAN or P2P), or it may be the storage means of an external terminal 16, or it may be any other storage means.

[0048] External terminals 16 are terminals used by users of the information processing system 10 (for example, sellers who sell goods (including buyers of goods)), and consist of personal computers, tablets, smartphones, etc. The type of external terminal 16 is not particularly limited, but examples include smartphones, personal computers, tablets, etc. used by individuals.

[0049] The network NW is a line that allows the system terminal 12, the information storage terminal 12d, and the external terminal 16 to communicate with each other, and is typically composed of a WAN (Wide Area Network), also known as the Internet. The network NW may be wired or wireless, a LAN (Local Area Network), a dedicated line such as a VPN (Virtual Private Network), or a combination of these lines.

[0050] <System Terminal / Hardware Configuration Example> Next, we will describe an example of the hardware configuration of system terminal 12.

[0051] As shown in Figure 2, the system terminal 12 is configured to include, for example, a CPU 21 and a ROM 22, RAM 23, external storage drive 25, storage device 26, input device 27, display device 28, communication unit 29, etc., all connected to the CPU 21 via a bus.

[0052] The CPU 21 is a control means that controls the entire system terminal 12, and performs processes such as executing application programs and operating systems (OS) stored in ROM 22 and storage devices 26, and storing data and files necessary for program execution in RAM 23 and storage devices 26.

[0053] ROM22 is a storage means for storing basic I / O programs and various data, and is composed of, for example, PROM, flash memory, etc. RAM23 is a storage means for temporarily storing data, and is composed of, for example, SDRAM, DRAM, etc. External storage drive25 is a control means that can read and write data to recording media 24 such as magnetic tape, DVD, etc., and is composed of, for example, magnetic tape storage, DVD drive, etc.

[0054] The storage device 26 is a storage means for storing application programs, the OS, control programs, related programs, various information, etc., and is composed of, for example, a hard disk drive (HDD), a solid-state drive (SDD), etc. The input device 27 is for inputting commands (instructions), etc., to the system terminal 12, and is composed of, for example, a keyboard, a pointing device (mouse, etc.), a touch panel, etc.

[0055] The display device 28 displays commands input by the input device 27, the response output of the system terminal 12 to those commands, and various other displays, and is composed of, for example, a liquid crystal display, a plasma display, or an organic EL display. The communication unit 29 is a control means that controls communication with the information storage terminal 12d and external terminals 16, etc. via the network NW, and is composed of, for example, a communication card.

[0056] <System Terminal / Function> Next, we will explain the functions of the system terminal 12.

[0057] The storage device 26 of the system terminal 12 stores a program (information processing program) that causes the system terminal 12 to function as a learning means 12a, an analysis means 12b, a generation means 12c, and a verification means 12e.

[0058] <System terminal / Functions / Learning methods> Next, we will explain the learning method 12a.

[0059] The learning means 12a is a means for learning the purchasing activities of multiple buyers of a certain product, and in this example, it consists of a program stored in the storage device 26 of the system terminal 12, and the storage device 26, etc.

[0060] As mentioned above, "buyer purchasing activities" refer to the various activities (actions) that a buyer of goods performs in the process of purchasing or selling goods to a retail company or other business. Examples of "buyer purchasing activities" include procurement (the process of ordering goods), sales promotion activities (activities of advertising and promoting goods), product search (activities of finding goods), product selection (activities of choosing goods), price negotiation, and price determination.

[0061] The learning means 12a learns the purchasing activities of multiple buyers of a particular product by referring to purchase history information stored in the information storage terminal 12d and the external terminal 16, as well as operation logs and product transaction history on the external terminal 16.

[0062] For example, if the information storage terminal 12d stores information about the purchase history, including campaign information (status of campaigns and events), and it is recorded that Buyer X was in charge of a campaign or event for a certain product, the learning means 12a will acquire information such as Buyer X's name, the content, date, and store of the campaign or event for a certain product, and the name of the product for which the campaign or event was conducted. This information will then be associated with Buyer X's ID and stored in the storage device 26 as Buyer X's purchasing activity.

[0063] Furthermore, for example, if the product information (product name, purchase price, purchasing manager) of the product transaction history stored in the external terminal 16 contains information indicating that buyer Y was in charge of purchasing, the learning means 12a acquires information such as buyer Y's name, the name of a certain product purchased, and the purchase price, and stores this information in the storage device 26 as buyer Y's purchasing activity, associating it with buyer Y's ID.

[0064] Furthermore, for example, if the operation log of the external terminal 16 contains information that buyer Z has placed an order for a certain product using the external terminal 16, the learning means 12a acquires information such as buyer Z's name, the name of the purchased product, and the purchase price, and stores this information in the storage device 26 as buyer Z's purchasing activity, associated with buyer Z's ID.

[0065] The learning means 12a learns the purchasing activities of multiple buyers of a particular product by periodically repeating these processes for multiple buyers.

[0066] <System terminal / Function / Analysis method> Next, the analytical means 12b will be described.

[0067] The analysis means 12b is a means capable of analyzing the relationship between product sales information relating to the sale of a certain product and the purchasing activities of a specific buyer among multiple buyers. In this example, it consists of a program stored in the storage device 26 of the system terminal 12, and the storage device 26, etc.

[0068] As mentioned above, "product sales information" refers to information related to the sale of a product (marketing information). Examples of "product sales information" include purchase history information, which is information about the history of a particular product purchased by a customer (past performance data), and demand forecast information, which is information about the forecast of future demand for a product (future forecast data).

[0069] Examples of "purchase history information" include: (1) customer information (customer ID, gender, age, membership rank, personal information, etc.), (2) product information (product ID, product name, category, brand, unit price, etc.), (3) purchase information (purchase date, purchase time, purchase quantity, total amount, payment method, surveys, staff interaction records, etc.), (4) store information (store ID, store name, sales channel (store / EC), etc.), (5) campaign information (status of campaigns and events, coupon usage, point usage, discount rate, etc.), and (6) purchase frequency (number of purchases, average purchase interval, most recent purchase date, etc.).

[0070] Examples of "demand forecasting information" include information that forecasts product demand by category, information that forecasts product demand by store, information that forecasts product demand on a monthly basis, information that forecasts product demand in the short, medium, and long term, information that forecasts product demand based on predictions of customer purchasing intent, and information that forecasts product demand from product trends.

[0071] First, the analysis means 12b refers to the purchase history information stored in the information storage terminal 12d and the external terminal 16, as well as the demand forecast information stored in the external terminal 16, to obtain product sales information related to the sale of a certain product.

[0072] For example, if the purchase history information stored in the information storage terminal 12d contains purchase information for product A (product ID, purchase date, purchase time, purchase quantity, etc.), the analysis means 12b acquires the product ID, purchase date, purchase time, purchase quantity, etc. for product A, and stores this information in the storage device 26 as product sales information for product A, associating it with the ID of product A.

[0073] Furthermore, for example, if the demand forecast information stored in the external terminal 16 contains information predicting the demand for product B (product ID, demand forecast period, predicted sales quantity, etc.), the analysis means 12b acquires the product ID, demand forecast period, predicted sales quantity, etc. for product B, and stores this information in the storage device 26 as product sales information for product B, associating it with the ID of product B.

[0074] Next, the analysis means 12b refers to the purchasing activity of a buyer of a certain product stored in the memory device 26 by the learning means 12a and analyzes its relationship with the product sales information stored in the memory device 26.

[0075] For example, consider a case where the memory device 26 stores information such as Buyer X's name, the details, date, and store of any campaigns or events for product A, and the name of product A that was the subject of the campaign or event, as part of Buyer X's purchasing activities, and also stores information such as product ID, purchase date, purchase time, and purchase quantity for product A as part of product sales information.

[0076] In this case, the analysis means 12b analyzes the relationship between the sales information of product A and the purchasing activity of buyer X, based on the fact that there is a relationship (commonality) between the sales information of product A and the purchasing activity of buyer X.

[0077] If the analysis reveals, for example, that the dates of campaigns or events for product A handled by buyer X are close to the purchase date of product A, and that the quantity of product A purchased is greater than in the period before and after the purchase date, then it is determined that there is a causal relationship between the implementation of campaigns or events for product A handled by buyer X and the increase in sales of product A. This analysis result is then stored in the storage device 26 as information relating product sales information for product A and buyer X's purchasing activities, associated with the IDs of product A and buyer X.

[0078] On the other hand, if the purchase quantity of product A does not change compared to the period before and after the purchase date of product A, it is determined that there is no causal relationship between the implementation of campaigns or events for product A handled by buyer X and the increase in sales of product A. In this case, the analysis result is stored in the storage device 26 as information relating product sales information for product A and buyer X's purchasing activities, associated with the IDs of product A and buyer X.

[0079] Furthermore, consider a case where, for example, the memory device 26 stores information such as buyer Y's name, the name and purchase price of product A purchased by buyer Y, as part of buyer Y's purchasing activities, and information such as product ID, purchase date, purchase time, and purchase quantity of product A as part of product sales information for product A.

[0080] In this case, the analysis means 12b analyzes the relationship between the sales information of product A and the purchasing activity of buyer Y, based on the fact that there is a relationship (commonality) between the sales information of product A and the purchasing activity of buyer Y.

[0081] If the analysis reveals, for example, that the product ID of product A purchased by buyer Y is the same as the product ID of product A stored in the purchase history information, and that the quantity of product A purchased is greater than the period before and after the purchase date of product A, then it is determined that there is a causal relationship between the purchase price of product A handled by buyer Y and the increase in sales of product A. This analysis result is then stored in the storage device 26 as information relating product sales information of product A and buyer Y's purchasing activities, associated with the IDs of product A and buyer Y.

[0082] On the other hand, if the purchase quantity of product A does not change compared to the period before and after the purchase date of product A, it is determined that there is no causal relationship between the purchase price of product A, which was procured by buyer Y, and the increase in sales of product A. This analysis result is then stored in the storage device 26 as information relating product sales information of product A and buyer Y's purchasing activities, associated with the IDs of product A and buyer Y.

[0083] Furthermore, consider a case where, for example, the memory device 26 stores information such as buyer Z's name, the name and purchase price of product B purchased by buyer Z as part of buyer Z's purchasing activities, and information such as product ID, demand forecast period, and forecast sales quantity of product B as part of product B sales information.

[0084] In this case, the analysis means 12b analyzes the relationship between the sales information of product B and the purchasing activity of buyer Z, since there is a relationship (commonality) between the sales information of product B and the purchasing activity of buyer Z.

[0085] If the analysis reveals, for example, that the product name of product B purchased by buyer Z is the same as the product name of product B stored in the demand forecast information, and that the predicted sales quantity of product B is greater than the number of product B purchased, then it is determined that there is a correlation between the number of product B purchased by buyer Z and the predicted sales quantity of product B. This analysis result is then stored in the storage device 26 as information relating the sales information of product B to buyer Z's purchasing activities, and is associated with the IDs of product B and buyer Z.

[0086] On the other hand, if the predicted sales quantity of product B is less than the number of product B purchased, it is determined that there is no correlation between the number of product B purchased by buyer Z and the predicted sales quantity of product B. This analysis result is then stored in the storage device 26 as information relating product sales information for product B and buyer Z's purchasing activities, and is associated with the IDs of product B and buyer Z.

[0087] <System terminal / Function / Generation method> Next, the generation means 12c will be described.

[0088] The generation means 12c is a means capable of generating criteria for a buyer's purchasing activity regarding a certain product, based on the relationship between sales information of a certain product and the purchasing activity of a specific buyer. In this example, it is composed of a program stored in the storage device 26 of the system terminal 12, and the storage device 26, etc.

[0089] As mentioned above, "buyer's purchasing criteria" refers to information that serves as a basis (indicator) for buyers when making purchasing decisions. Examples of "buyer's purchasing criteria" include the timing of purchasing goods, the number of goods purchased and sold, the timing of sales promotion activities, the methods of sales promotion activities, the purchase price and selling price of goods, newly launched products, and products that will be discontinued.

[0090] The generation means 12c generates criteria for determining a buyer's purchasing activity for a certain product, based on the relationship between sales information of a certain product stored in the storage device 26 by the analysis means 12b and the purchasing activity of a specific buyer.

[0091] For example, as shown in Figure 3(a), consider a case where, as information relating to the sales information of product A and the purchasing activities of buyer X, the memory device 26 stores an analysis result indicating a causal relationship between the sales information of product A (information showing an increase in sales of product A) and the purchasing activities of buyer X (information showing that buyer X implemented a campaign or event for product A).

[0092] In this case, the generation means 12c determines that the campaigns and events for product A handled by buyer X are effective in increasing sales of product A, generates a decision criterion of "execute campaigns and events for product A" as a criterion for the buyer's purchasing activity for product A, and stores the generated decision criterion in the storage device 26 in association with product A.

[0093] In this example, since the criteria for buyers' purchasing activities can be shared among multiple buyers, other buyers besides buyer X can also refer to the purchasing activity criteria associated with product A, and understand that it is recommended to run campaigns or events when purchasing product A, thereby optimizing buyers' purchasing activities for product A.

[0094] Furthermore, consider the case where, as shown in Figure 3(b), the memory device 26 stores an analysis result indicating a causal relationship between the sales information of product A (information showing an increase in sales of product A) and the purchasing activity of buyer Y (information that buyer Y purchased product A at a certain purchase price).

[0095] In this case, the generation means 12c determines that the purchase price handled by buyer Y is effective in increasing sales of product A, and generates a decision criterion, "use the purchase price set by buyer Y as the basis," as the basis for the buyer's purchasing activity for product A, and stores the generated decision criterion in the storage device 26 in association with product A.

[0096] In this example, since the criteria for buyers' purchasing activities can be shared among multiple buyers, other buyers besides buyer Y can also refer to the purchasing criteria of buyers associated with product A and understand that the purchase price set by buyer Y is recommended for product A, thereby optimizing the buyers' purchasing activities for product A.

[0097] Furthermore, consider a case where, as shown in Figure 3(c), the memory device 26 stores an analysis result indicating a correlation between the predicted sales quantity of product B and buyer Z's purchasing activity (information that buyer Z purchased a certain quantity of product B).

[0098] In this case, the generation means 12c determines that the number of items purchased by buyer Z is effective in increasing sales of product B, and generates a decision criterion, "based on the number of items purchased by buyer Z," as the basis for the buyer's purchasing activity for product B, and stores the generated decision criterion in the storage device 26 in association with product B.

[0099] In this example, since the criteria for buyers' purchasing activities can be shared among multiple buyers, by referring to the purchasing activity criteria of buyers associated with product B, it is possible to understand that the quantity of product B to be purchased as set by buyer Z is recommended, thereby optimizing the buyers' purchasing activities for product B.

[0100] <System terminal / function / verification method> Next, the verification means 12e will be described.

[0101] The verification means 12e is a means that can analyze management numerical information after a buyer has carried out a purchasing activity based on the criteria for the purchasing activity, and verify whether the management numerical information has improved. In this example, it consists of a program stored in the storage device 26 of the system terminal 12, and the storage device 26, etc.

[0102] The verification means 12e acquires management numerical information from the information storage terminal 12d, etc., after the buyer has carried out the purchasing activity based on the purchasing activity judgment criteria, analyzes the acquired management numerical information, and verifies whether the management numerical information has improved. Whether the buyer carried out the purchasing activity based on the purchasing activity judgment criteria can be determined by referring to the purchasing history information stored in the information storage terminal 12d or the external terminal 16, as well as the operation log and product transaction history on the external terminal 16.

[0103] For example, consider the case shown in Figure 3(a), where the criterion for a buyer's purchasing activity for product A is stored in the memory device 26: "Execute a campaign or event."

[0104] In this case, the verification means 12e obtains management numerical information (e.g., sales data) from the information storage terminal 12d, etc., after a buyer has carried out a campaign or event (purchase activity) for product A based on the purchasing activity criterion of "executing a campaign or event," analyzes the obtained management numerical information, and verifies whether the management numerical information has improved.

[0105] Furthermore, consider, for example, the case shown in Figure 3(b), where the decision criterion for a buyer's purchasing activity for product A is stored in the memory device 26, which is "based on the purchase price set by buyer Y."

[0106] In this case, the verification means 12e obtains management numerical information (e.g., profit data) from the information storage terminal 12d, etc., after a buyer has performed the purchase operation (purchase activity) of product A at the purchase price set by buyer Y, based on the purchasing activity criterion of "using the purchase price set by buyer Y as a basis," and analyzes the obtained management numerical information to verify whether or not the management numerical information has improved.

[0107] Furthermore, consider, for example, the case shown in Figure 3(c), where the decision criterion for a buyer's purchasing activity for product B is stored in the memory device 26, which states, "Based on the quantity to be purchased set by buyer Z."

[0108] In this case, the verification means 12e retrieves management numerical information (e.g., financial indicators) from the information storage terminal 12d, etc., after a buyer has performed the purchase operation (purchase activity) of product B based on the purchase quantity set by buyer Z, based on the purchasing activity judgment criterion of "using the purchase quantity set by buyer Z as a basis," and analyzes the retrieved management numerical information to verify whether or not the management numerical information has improved.

[0109] In this example, by verifying whether the purchasing criteria generated based on management data are appropriate, it is possible to understand the effectiveness of purchasing activities and improve the accuracy of the purchasing criteria generated.

[0110] Furthermore, the verification means 12e may be configured to analyze purchase history information (e.g., results of marketing measures) after a buyer has carried out a purchase activity based on the criteria for making a purchase, and to verify whether or not the purchase history information has improved.

[0111] With this configuration, by verifying whether the criteria for generating purchasing activities are appropriate based on purchase history information (past performance data), it is possible to grasp the effectiveness of purchasing activities and improve the accuracy of the criteria for generating purchasing activities.

[0112] <Information Processing Systems / Summary> As described above, the information processing system according to this embodiment (for example, the information processing system 10 shown in Figures 1 and 2) is an information processing system configured to have a computer AI agent (for example, the AI ​​agent 12 shown in Figure 1, the system terminal 12 shown in Figure 2), wherein the AI ​​agent comprises: a learning means (for example, the learning means 12a shown in Figures 1 and 2) for learning the purchasing activities of multiple buyers of a certain product; an analysis means (for example, the analysis means 12b shown in Figures 1 and 2) capable of analyzing the relationship between product sales information relating to the sale of a certain product and the purchasing activities of a specific buyer among the multiple buyers; and a generation means (for example, the generation means 12c shown in Figures 1 and 2) capable of generating criteria for the purchasing activities of a buyer for a certain product based on the relationship between the product sales information of a certain product and the purchasing activities of the specific buyer.

[0113] Furthermore, the information processing method according to this embodiment (for example, the method executed by the information processing system 10 shown in Figures 1 and 2) is an information processing method executed using an AI agent which is a computer (for example, the AI ​​agent 12 shown in Figure 1, the system terminal 12 shown in Figure 2), wherein the AI ​​agent performs at least the following steps: a learning step (for example, the process executed by the learning means 12a shown in Figures 1 and 2) for learning the purchasing activities of multiple buyers of a certain product; an analysis step (for example, the process executed by the analysis means 12b shown in Figures 1 and 2) for analyzing the relationship between product sales information relating to the sale of a certain product and the purchasing activities of a specific buyer among the multiple buyers; and a generation step (for example, the process executed by the generation means 12c shown in Figures 1 and 2) for generating criteria for judging the purchasing activities of a certain buyer for that product based on the relationship between the product sales information of a certain product and the purchasing activities of the specific buyer.

[0114] Furthermore, the information processing program according to this embodiment (for example, the program executed by the information processing system 10 shown in Figures 1 and 2) is an information processing program characterized in that it causes the AI ​​agent, which is a computer (for example, the AI ​​agent 12 shown in Figure 1, the system terminal 12 shown in Figure 2), to function as a learning means (for example, the learning means 12a shown in Figures 1 and 2) for learning the purchasing activities of multiple buyers of a certain product, an analysis means (for example, the analysis means 12b shown in Figures 1 and 2) capable of analyzing the relationship between product sales information relating to the sale of a certain product and the purchasing activities of a specific buyer among the multiple buyers, and a generation means (for example, the generation means 12c shown in Figures 1 and 2) capable of generating criteria for the purchasing activities of a buyer for a certain product based on the relationship between the product sales information of a certain product and the purchasing activities of the specific buyer.

[0115] Furthermore, the AI ​​agent according to this embodiment (for example, the AI ​​agent 12 shown in Figure 1, the system terminal 12 shown in Figure 2) is an AI agent that operates as a substitute for a human and has the ability to learn and make decisions on its own. The AI ​​agent, which is a computer, is configured to function as a learning means (for example, the learning means 12a shown in Figures 1 and 2) for learning the purchasing activities of multiple buyers of a certain product, an analysis means (for example, the analysis means 12b shown in Figures 1 and 2) capable of analyzing the relationship between product sales information relating to the sale of a certain product and the purchasing activities of a specific buyer among the multiple buyers, and a generation means (for example, the generation means 12c shown in Figures 1 and 2) capable of generating judgment criteria for the purchasing activities of a certain product based on the relationship between the product sales information of a certain product and the purchasing activities of the specific buyer. The AI ​​agent is configured to repeatedly provide the judgment criteria for purchasing activities as learning data and to acquire the judgment criteria for purchasing activities through machine learning.

[0116] According to the information processing system, information processing method, information processing program, and AI agent of this embodiment, it is possible to generate criteria for purchasing activities of buyers in the retail industry, and to optimize the purchasing activities of buyers.

[0117] Furthermore, the system may include storage means (for example, storage means 12d shown in Figure 1, information storage terminal 12d shown in Figure 2) capable of storing management numerical information, which is numerical information that visualizes the company's management status through management indicators and financial indicators, and verification means (for example, verification means 12e shown in Figures 1 and 2) capable of analyzing the management numerical information after the buyer has carried out the purchasing activity based on the judgment criteria for the purchasing activity and verifying whether the management numerical information has improved.

[0118] With this configuration, it becomes possible to understand the effectiveness of purchasing activities and improve the accuracy of the purchasing activity criteria generated by verifying whether the criteria for purchasing activities generated based on management numerical information are appropriate.

[0119] Furthermore, the management numerical information may include purchase history information, which is information about the history of a certain product purchased by a customer, and the verification means (or verification step) may be configured to analyze the purchase history information after the buyer has performed the purchase activity based on the criteria for the purchase activity, and to verify whether the purchase history information has improved.

[0120] With this configuration, by verifying whether the criteria for generating purchasing activities are appropriate based on purchase history information (past performance data), it is possible to grasp the effectiveness of purchasing activities and improve the accuracy of the criteria for generating purchasing activities.

[0121] Furthermore, the buyer's purchasing activities may include the procurement of a certain product and sales promotion activities for that product.

[0122] With this configuration, purchasing decision criteria can be generated based on the buyer's product procurement and sales promotion activities, and these purchasing decision criteria can be optimized.

[0123] Furthermore, the sales information for a certain product may include purchase history information, which is information about the history of a customer's purchase of the product, and demand forecast information, which is information about the forecast of demand for the product.

[0124] With this configuration, purchasing decision-making criteria can be generated based on both past performance data (purchase history information) and future forecast data (demand forecast information), thereby optimizing the purchasing decision-making criteria.

[0125] Furthermore, the aforementioned specific buyer may be one of the aforementioned multiple buyers.

[0126] With this configuration, for example, purchasing criteria can be generated based on the purchasing activities of a high-performing buyer (the subjective opinion of a single buyer), and these purchasing criteria can be optimized.

[0127] Furthermore, the aforementioned specific buyer may be two or more buyers from among the aforementioned group of buyers whose purchasing activities are the same or similar.

[0128] With this configuration, purchasing decision criteria can be generated based on the purchasing activities of buyers whose purchasing activities are the same or similar (public opinion from multiple buyers with similar purchasing activities), and these purchasing decision criteria can be optimized.

[0129] Furthermore, the criteria for making purchasing decisions may be repeatedly provided as training data, and the system may be configured to acquire these purchasing criteria through machine learning.

[0130] With this configuration, purchasing decision-making criteria can be accumulated as training data, thereby improving the accuracy of those criteria.

[0131] It should be noted that the information processing system, information processing method, information processing program, and AI agent according to the present invention are not limited to the embodiments described above, and various modifications can be made without departing from the spirit of the present invention.

[0132] Therefore, for example, the verification means 12e shown in Figure 1 is not an essential component of the information processing system according to the present invention, and the information processing system according to the present invention may not be equipped with any verification means.

[0133] Furthermore, the verification means may be configured to analyze the management figures after the buyer has carried out the purchasing activity based on the purchasing activity judgment criteria, and to verify whether the management figures have improved. If it is determined that the management figures have improved, the system may acquire the purchasing activity judgment criteria that were able to improve the management figures as learning data. On the other hand, if it is determined that the management figures have not improved, the system may not acquire the purchasing activity judgment criteria that were unable to improve the management figures as learning data.

[0134] Furthermore, a buyer's purchasing activities are not limited to the procurement of a particular product and sales promotion activities for that product, but may include other purchasing activities. Also, product sales information for a particular product is not limited to purchase history information and demand forecast information, but may include other information. [Industrial applicability]

[0135] The information processing system, information processing method, information processing program, and AI agent according to the present invention can be widely applied to fields such as manufacturing, service industries, and retail industries. [Explanation of symbols]

[0136] 10. Information Processing Systems 12 System Terminals 12a Learning methods 12b Analysis tools 12c Generating means 12d Information Storage Terminal 12e Verification method 16 External terminals 21 CPU 22 ROM 23 RAM 24 Recording media 25 External storage drives 26 Storage device 27 Input devices 28 Display device 29 Communications Department

Claims

1. An information processing system configured to include an AI agent, which is a computer, The aforementioned AI agent, A learning method for learning the purchasing activities of multiple buyers of a certain product, An analytical means capable of analyzing the relationship between product sales information relating to the sale of a certain product and the purchasing activities of a specific buyer among the multiple buyers, The system comprises a generation means capable of generating criteria for a buyer's purchasing activity regarding a certain product, based on the relationship between the sales information of the said product and the purchasing activity of a specific buyer. An information processing system characterized by the following:

2. In the information processing system described in claim 1, It is equipped with a storage means capable of storing management numerical information, which is numerical information that visualizes the management status of a company through management indicators and financial indicators. The system includes verification means capable of analyzing the management figures after the buyer has carried out the purchasing activity based on the purchasing activity criteria, and verifying whether the management figures have improved. An information processing system characterized by the following:

3. In the information processing system described in claim 2, The aforementioned management figures include purchase history information, which is information about the history of a certain product purchased by a customer. The verification means is configured to analyze the purchase history information after the buyer has performed the purchase activity based on the purchase activity judgment criteria, and to verify whether the purchase history information has improved. An information processing system characterized by the following:

4. In the information processing system according to any one of claims 1 to 3, The aforementioned buyer's purchasing activities include the procurement of a certain product and sales promotion activities for that product. An information processing system characterized by the following:

5. In the information processing system according to claim 1 or 2, The sales information for the aforementioned product includes purchase history information, which is information about the history of the product purchased by the customer, and demand forecast information, which is information about the demand forecast for the product. An information processing system characterized by the following:

6. In the information processing system according to claim 1 or 2, The aforementioned specific buyer is one of the aforementioned multiple buyers. An information processing system characterized by the following:

7. In the information processing system according to claim 1 or 2, The aforementioned specific buyer is two or more buyers among the aforementioned group of buyers whose purchasing activities are the same or similar. An information processing system characterized by the following:

8. In the information processing system according to claim 1 or 2, The criteria for the purchasing activity are repeatedly provided as training data, and the system is configured to acquire these purchasing activity criteria through machine learning. An information processing system characterized by the following:

9. An information processing method that is performed using an AI agent, which is a computer, The aforementioned AI agent, A learning step to learn the purchasing activities of multiple buyers for a certain product, An analysis step that enables the analysis of the relationship between product sales information relating to the sale of a certain product and the purchasing activities of a specific buyer among the multiple buyers, A generation step is performed that enables the generation of criteria for a buyer's purchasing activity for a certain product, based on the relationship between the sales information of a certain product and the purchasing activity of a specific buyer. An information processing method characterized by the following:

10. In the information processing method described in claim 9, Using a storage device capable of storing management figures, which are numerical information that visualizes the management status of a company through management indicators and financial indicators, Further, a verification step is performed that allows for the analysis of the management figures after the buyer has carried out the purchasing activity based on the purchasing activity criteria, and to verify whether the management figures have improved. An information processing method characterized by the following:

11. In the information processing method described in claim 10, The aforementioned management figures include purchase history information, which is information about the history of a certain product purchased by a customer. The verification step is configured to analyze the purchase history information after the buyer has performed the purchase activity based on the purchase activity judgment criteria, and to verify whether the purchase history information has improved. An information processing method characterized by the following:

12. A program for an information processing system configured to include an AI agent, The aforementioned AI agent, which is a computer, A learning method for learning the purchasing activities of multiple buyers of a certain product, An analytical means capable of analyzing the relationship between product sales information relating to the sale of a certain product and the purchasing activities of a specific buyer among the multiple buyers, A generating means capable of generating criteria for a buyer's purchasing activity regarding a certain product, based on the relationship between the sales information of a certain product and the purchasing activity of a specific buyer, An information processing program characterized by the following features.

13. In the information processing program described in claim 12, It is equipped with a storage means capable of storing management numerical information, which is numerical information that visualizes the management status of a company through management indicators and financial indicators. The system includes verification means capable of analyzing the management figures after the buyer has carried out the purchasing activity based on the purchasing activity criteria, and verifying whether the management figures have improved. An information processing program characterized by the following features.

14. In the information processing program described in claim 13, The aforementioned management figures include purchase history information, which is information about the history of a certain product purchased by a customer. The verification means is configured to analyze the purchase history information after the buyer has performed the purchase activity based on the purchase activity judgment criteria, and to verify whether the purchase history information has improved. An information processing program characterized by the following features.

15. An AI agent that acts as a substitute for a human, and has the ability to learn and make decisions on its own, The aforementioned AI agent, which is a computer, A learning method for learning the purchasing activities of multiple buyers of a certain product, An analytical means capable of analyzing the relationship between product sales information relating to the sale of a certain product and the purchasing activities of a specific buyer among the multiple buyers, A generating means capable of generating criteria for a buyer's purchasing activity regarding a certain product, based on the relationship between the sales information of a certain product and the purchasing activity of a specific buyer, The criteria for the purchasing activity are repeatedly provided as training data, and the system is configured to acquire these purchasing activity criteria through machine learning. An AI agent characterized by the following.

Images