Information processing apparatus, control method, program, and information processing system

Abstract

To provide an information processor, a control method, a program, and an information processing system capable of generating an effective advertisement for promoting purchase.SOLUTION: An information processor includes a state acquiring unit that acquires a state of an information processor that changes according to a predetermined event occurring in the information processor operated by a customer, a determining unit that determines an advertisement creation plan using advertisement creation information corresponding to the acquired state and for creating an advertisement for the customer, and a generating unit that generates a prompt for instructing a generative AI model to generate the advertisement on the basis of the advertisement creation plan.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, a control method, a program, and an information processing system. [Background technology]

[0002] One type of consumer purchasing behavior is unplanned purchasing. Unplanned purchasing is when the product to be purchased is not decided in advance, and the decision is changed due to factors such as price and advertising. In Japan, unplanned purchases are said to account for approximately 70% of purchasing behavior, and it is said that this influence led to the development of tastings and point-of-purchase (POP) displays in Japan. With this background, there is technology that advertises to customers on smart carts, where customers register products as they shop.

[0003] For example, Patent Document 1 discloses an intelligent cart that determines recommended products based on the store situation (stock, sales), past purchase history, and products in the cart. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2020-102043 Summary of the Invention [Problem to be solved by the invention]

[0005] However, simply recommending products based on past purchase history or products in a cart makes it difficult to generate effective advertisements to encourage purchases, including the unplanned purchases mentioned above.

[0006] One aspect of the present disclosure provides an information processing device, a control method, a program, and an information processing system that are capable of generating effective advertisements to encourage purchases. [Means for solving the problem]

[0007] An information processing device according to one embodiment of the present disclosure includes a state acquisition unit that acquires the state of the information processing device, which changes in response to a predetermined event that occurs on the information processing device operated by a customer; a decision unit that corresponds to the acquired state and determines an advertisement creation policy using advertisement creation information for creating an advertisement for the customer; and a generation unit that generates a prompt that instructs a generative AI model to generate the advertisement based on the advertisement creation policy. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 illustrates an example of an advertisement generation system. [Figure 2A] FIG. 10 is a diagram illustrating an example of the configuration of member attribute information. [Figure 2B] FIG. 10 is a diagram illustrating an example of the configuration of basket information. [Figure 2C] FIG. 10 is a diagram illustrating an example of the configuration of store product information. [Figure 2D] FIG. 2 is a diagram illustrating an example of the configuration of store information. [Figure 3A] FIG. 10 is a diagram illustrating an example of the configuration of advertising condition information. [Figure 3B] FIG. 10 is a diagram showing an example of the configuration of advertisement reference information. [Figure 3C] FIG. 10 is a diagram illustrating an example of the configuration of real-time POS information. [Figure 4] FIG. 2 is a sequence diagram showing a processing flow of the advertisement generation system. [Figure 5A] FIG. 10 is a diagram illustrating an example of the configuration of recommendation information. [Figure 5B] FIG. 10 is a diagram showing correspondence between terminal states and advertisement creation policies. [Figure 6] FIG. 10 illustrates an example of a prompt generated based on an advertisement creation policy. [Figure 7] FIG. 10 illustrates an example advertisement generated by a generative AI model given a prompt. [Figure 8] FIG. 10 is a diagram illustrating an example of a configuration in which each functional unit of a smart cart terminal is distributed to a cloud server. [Figure 9]FIG. 2 is a diagram illustrating an example of the hardware configuration of a smart cart terminal, a knowledge server, and a generation device. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an embodiment according to one aspect of the present disclosure will be described with reference to the drawings. Note that the embodiment described below is an example, and the embodiment to which the present disclosure is applied is not limited to the following embodiment.

[0010] 1 is a diagram illustrating an example of an advertisement generation system 10 according to an embodiment of the present disclosure. The advertisement generation system 10 includes a smart cart terminal 100, a knowledge server 200, and a generation device 300. The smart cart terminal 100 and the knowledge server 200 are capable of communicating with each other. The smart cart terminal 100 and the generation device 300 are capable of communicating with each other.

[0011] The smart cart terminal 100 is an example of an information processing device operated by a customer, such as a smartphone or tablet. The smart cart terminal 100 is a terminal that allows a customer to register products and make payments by themselves. The smart cart terminal 100 may be pre-installed in the smart cart, or may be a customer's smartphone with an application installed. The smart cart terminal 100 according to this embodiment changes its state (hereinafter referred to as "terminal state") in response to a predetermined event that occurs in the smart cart terminal 100.

[0012] In this embodiment, the predetermined events include a customer starting shopping, a customer logging in, a customer adding a product to purchase, a customer moving around the store, or a customer paying for a product.

[0013] The terminal states correspond to the above-mentioned predetermined events and include a pre-login state in which the customer has not performed a login operation after the shopping start operation, a login state in which the customer has performed a login operation, a product addition state in which the customer has performed an operation to add a product to purchase, a location change state in which the customer has moved within the store, or a payment completion state in which the customer has performed a product payment operation. The above-mentioned predetermined events and terminal states will be explained below using the configuration of the smart cart terminal 100.

[0014] The smart cart terminal 100 includes an authentication unit 101, a product registration unit 102, a location acquisition unit 103, a payment unit 104, a status acquisition unit 105, a determination unit 106, a generation unit 107, a prompt transmission unit 108, an advertisement reception unit 109, and an advertisement display unit 110.

[0015] The authentication unit 101 authenticates the customer when the customer performs an operation to start shopping. The terminal state before successful authentication is the pre-login state. When authentication is successful, the terminal state changes from the pre-login state to the login state. Furthermore, the smart cart terminal 100 acquires a customer identification number, which will be described later, through authentication.

[0016] The product registration unit 102 registers products purchased by a customer through a purchase product addition operation. For example, when a customer performs an operation of scanning a barcode attached to a product using a reading device (not shown) (an example of a purchase product addition operation), the product registration unit 102 acquires the obtained product identification information such as a JAN code, and registers the product identification information as the product to be purchased. Once the product is registered, the terminal state changes to a product addition state.

[0017] The location acquisition unit 103 acquires the location using a GPS (Global Positioning System) or Wi-Fi (not shown), and detects the current sales floor based on the acquired location and sales floor information indicating the sales floor where the product is located (for example, the store floor or the sales floor for each product (fresh fish section, meat section, etc.)). When the customer moves around the store and the acquired sales floor changes, the terminal status changes to indicate the new sales floor.

[0018] The settlement unit 104 settles the registered product in response to a product payment operation. When the payment is completed, the terminal status becomes a payment completed status. These terminal statuses are stored in a storage device (not shown) in the smart cart terminal 100 and are updated as needed.

[0019] The status acquisition unit 105 acquires the terminal status from the storage device. The determination unit 106 searches the knowledge server 200 for necessary information based on the terminal status, and generates advertisement creation information (hereinafter referred to as "recommendation information"). The determination unit 106 determines an advertisement creation policy using the generated recommendation information. The recommendation information and advertisement creation policy will be described in detail later.

[0020] Based on the advertisement creation policy, the generation unit 107 uses Retrieval-Augmented Generation (RAG), a type of prompt augmentation technology, to generate a prompt that instructs a Generative AI (Generative AI) model included in the generation device 300 to generate an advertisement. Here, a prompt refers to an instruction or question input by a user in a dialogue with a Generative AI model such as a Large Language Model (LLM). A common application example of RAG is when a user makes a request to an LLM, searches for similar documents in a search system in advance, and then requests those documents together with the request to the LLM. This allows the LLM to generate an answer based on a specific document, such as company information.

[0021] The prompt sending unit 108 sends the prompt generated by the generation unit 107 to the generation device 300. The advertisement receiving unit 109 receives the advertisement generated by the generative AI model based on the sent prompt from the generation device 300. The advertisement display unit 110 displays the received advertisement on a display unit (not shown).

[0022] Next, a description will be given of the generating device 300. The generating device 300 includes a prompt receiving unit 301, a generating AI model 302, and an advertisement sending unit 303.

[0023] The prompt receiving unit 301 receives a prompt sent by the smart cart terminal 100 and inputs it to the AI ​​model 302. The AI ​​model 302 functions as a generating AI as described above and outputs an advertisement corresponding to the prompt. The advertisement sending unit 303 outputs the advertisement output by the AI ​​model 302 to the smart cart terminal 100.

[0024] Next, a description will be given of the knowledge server 200. The knowledge server 200 includes a storage unit 202. The storage unit 202 stores member attribute information 211, basket information 212, store product information 213, store information 214, advertising condition information 215, advertising reference information 216, and real-time POS information 217.

[0025] Each of these pieces of information will be explained below. In the following explanation, duplicate explanations of data included in each piece of information that have already been mentioned will be omitted.

[0026] FIG. 2A is a diagram showing an example of the configuration of member attribute information 211. Member attribute information 211 includes a customer identification number, family structure, age, and hobbies and preferences. Of these, the customer identification number indicates a number that uniquely identifies a customer. Family structure indicates, for example, single or family. Age indicates the age of the customer, and hobbies and preferences indicate the hobbies and preferences of the customer. In this embodiment, the family structure, age, and hobbies and preferences are collectively referred to as attributes.

[0027] 2B is a diagram showing an example of the configuration of basket information 212. Basket information 212 includes a purchase history and current contents. The purchase history indicates a history of products that a customer has purchased in the past. The current contents is information that is set when a customer is shopping (in a logged-in state) and indicates products that are currently registered in the smart cart terminal 100.

[0028] FIG. 2C is a diagram showing an example of the configuration of store product information 213. Store product information 213 includes product identification number, product name, price, stock, and sales area. Product identification number indicates a number that uniquely identifies a product. Product name indicates the name of the product. Price indicates the price of the product. Manufacturer indicates the manufacturer of the product. Seller indicates the seller of the product. Product description indicates a description of the product (such as the product's features). Place of production indicates the place of production of the product. Stock indicates the number of products in stock at the store.

[0029] FIG. 2D is a diagram showing an example of the configuration of store information 214. Store information 214 includes a store identification number, an area identification number, area characteristics, weather, and date and time. The store identification number indicates a number that uniquely identifies a store. The area identification number indicates a number that identifies the area in which the store is located. The area characteristics indicate the characteristics of the area in which the store is located (such as the main purchasing demographic and best-selling products at a certain date, time, or weather). The weather indicates the current weather. The date and time indicates the current date and time.

[0030] FIG. 3A is a diagram showing an example of the configuration of advertising condition information 215. Advertising condition information 215 indicates an advertised product identification number, display conditions, purchase benefit information, product information, importance, and appeal effect. The advertised product identification number indicates the product identification information of the product being advertised. The display conditions indicate the conditions for displaying the advertisement. Specifically, the display conditions are conditions that specify the terminal status, attributes, and related purchase information. When the display conditions are met, an advertisement for the product indicated by the product identification number can be displayed. Note that the related purchase information specifies that an advertisement for product A should be displayed when product B is added. In this case, the advertised product identification number in the advertising condition information indicates the product identification number of product A, and the display conditions indicate the product identification number of product B as the related purchase information.

[0031] Purchase benefit information indicates the discount rate, point award information, novelty items received at the time of purchase, and the period during which the benefit can be obtained at the time of purchase. Product information indicates the product identification number, product name, price, manufacturer, distributor, product description, production location, inventory, and sales area. Importance indicates information indicating the importance of promoting purchases, such as whether there is a quota or the degree to which a store, manufacturer, etc. wants to sell the product (high / low or score). Appeal effect is information indicating how much the probability of a product being purchased increases by displaying an advertisement, but it may also be information indicating the expected value of a purchase, or may include various information necessary for generating an advertisement, such as layout.

[0032] 3B is a diagram showing an example of the configuration of advertisement reference information 216. The advertisement reference information 216 includes an advertisement product identification number, example sentences, and example images. The example sentences indicate sentences that the generative AI model uses as reference when generating an advertisement. The example images indicate images that the generative AI model 302 uses as reference when generating an advertisement.

[0033] 3C is a diagram showing an example of the configuration of the real-time POS information 217. The real-time POS information 217 includes sales trends and distribution status. The sales trends indicate the sales trends of products in the store. The distribution status indicates the status of the product distribution rate in the store.

[0034] Fig. 4 is a sequence diagram showing the processing flow of the advertisement generation system 10. In Fig. 4, when a predetermined event occurs (step S101), the smart cart terminal 100 acquires the terminal status (step S102). The smart cart terminal 100 searches and acquires necessary information from the knowledge server 200 based on the terminal status and advertisement condition information (step S103), and generates the above-mentioned recommendation information (step S104).

[0035] The smart cart terminal 100 determines an advertisement creation policy using the recommendation information (step S105), and generates a prompt that instructs the generation AI model 302 to generate an advertisement in accordance with the advertisement creation policy (step S106). The smart cart terminal 100 transmits the generated prompt to the generation device 300 (step S107). The generation device 300 provides the received prompt to the generation AI model 302, and the generation AI model 302 generates an advertisement (step S108). The generation device 300 transmits the generated advertisement to the smart cart terminal 100 (step S109). The smart cart terminal 100 displays the received advertisement (step S110).

[0036] In the above-described process, an advertisement creation policy is determined in accordance with the terminal status. This determination method will be explained. FIG. 5A is a diagram showing an example of the configuration of recommendation information. This recommendation information corresponds to the terminal status and is information for creating advertisements for customers. The recommendation information includes the above-described product identification information, product information, purchase benefit information, importance, appeal effect, example sentences, and example images. Using this recommendation information, the determination unit 106 determines an advertisement creation policy.

[0037] Next, the correspondence between the terminal state and the advertisement creation policy will be described. FIG. 5B is a diagram showing the correspondence between the terminal state and the advertisement creation policy. As shown in FIG. 5B, the determination unit 106 determines, as the advertisement creation policy corresponding to the pre-login state, a policy of creating advertisements corresponding to products common to all customers. The determination unit 106 determines, as the advertisement creation policy corresponding to the login state, a policy of creating advertisements corresponding to products according to the attributes of the logged-in customer. The determination unit 106 determines, as the advertisement creation policy corresponding to the product addition state, a policy of creating advertisements corresponding to products to be purchased in association with the added products. The determination unit 106 determines, as the advertisement creation policy corresponding to the location change state, a policy of creating advertisements corresponding to products arranged in a changed location (sales floor). The determination unit 106 determines, as the advertisement creation policy corresponding to the payment completion state, a policy of creating advertisements to encourage repeat visits, product advertisements, etc.

[0038] A specific example of creating an advertisement creation policy will be described. The determination unit 106 generates recommendation information according to the terminal state. For example, when the terminal state is in a logged-in state, the display conditions of the advertisement condition information 215 are referenced to search for products that match the customer attributes. When the terminal state is in a product addition state, the display conditions of the advertisement condition information 215 are referenced to search for products that match related purchases. In either case, multiple products may be the target of advertisement. When multiple products are the target of advertisement, for example, the inventory quantity and delivery status of the products may be taken into consideration (for example, the greater the inventory quantity, the higher the importance of promoting purchases). Furthermore, the importance of promoting purchases may be changed according to the current weather, time, and regional characteristics.

[0039] In addition, when a certain product is added in related purchases, a learning model can be used to learn the relationship with the products to be purchased as a set, and when the terminal state is in a product addition state, the added product can be used as input to output the product to be advertised using the above learning model.

[0040] In response to the products searched for in this manner, the determination unit 106 searches for necessary information from the knowledge server 200 and generates recommendation information including product identification information, product information, purchase benefit information, importance, appeal effect, sales area, example sentences, and example images as shown in Fig. 5A. Note that when generating recommendation information, if there are many products to be advertised, the products may be narrowed down to those with high importance (for example, those with importance higher than a predetermined threshold).

[0041] Using the recommendation information generated in this way, the determination unit 106 determines an advertisement creation policy. A specific example of an advertisement creation policy (when there are two advertised products in related purchases) is as follows. Advertised product 1: "Extra-high-grade, medium-spicy curry" Purchase bonus information: 10% off coupon Purchase promotion importance (score) “86 points” Example sentences and retroactive effects (scores): "We are currently offering a special 10% off coupon.", "97 points" "Delicious curry tonight." "67 points" Advertised product 2: "Next Generation Stew 6G" …

[0042] The advertised product may include not only the product name but also information such as the manufacturer, distributor, product description, place of production, and sales area.

[0043] Based on such advertisement creation guidelines, the generation unit 107 generates a prompt that instructs the generation AI model 302 to generate an advertisement. Fig. 6 is a diagram showing an example of a prompt generated based on the above-described advertisement creation guidelines.

[0044] 6, prompt 400 shows purchase benefit information 401, information 402 indicating the importance of purchase promotion, example sentences that the generation AI model 302 uses as reference when generating advertisements and information 403 indicating the appealing effect of the example sentences, images 404 that the generation AI model 302 uses as reference when generating advertisements, and target information 405. Target information 405 indicates the attributes of the target audience, and may include hobbies and preferences in addition to age and family structure.

[0045] As shown in FIG. 6, the generated prompt may be information describing a role, a task, or a condition. The role may be information specifying the person who will create the advertisement (e.g., advertisement creator, copywriter, designer, advertising agency representative, etc.). The task may be information instructing the generation of advertisement content (e.g., text file, image file, etc.). The condition may be advertisement creation policy information written directly or information based on this.

[0046] FIG. 7 is a diagram showing an example advertisement generated by the generative AI model 302 given a prompt corresponding to advertised product 1 in the prompt shown in FIG. 6. This advertisement example corresponds to a product addition state in which, for example, carrots and potatoes are in a basket and an onion is added to the basket by an add-to-purchase operation. As shown in FIG. 7, the advertisement generated by the generative AI model 302 includes an image as well as the advertised product name, benefits, etc. This advertisement is displayed by the advertisement display unit 110 of the smart cart terminal 100, as described above.

[0047] As described above, according to this embodiment, it is possible to generate an effective advertisement for encouraging purchases. Specifically, in conventional technology, it was necessary for a person to create the advertisement copy and the images to be displayed with the advertisement copy in advance. In this case, in order to set up a more effective advertisement, it was necessary to create the advertisement by combining customer attributes, combination patterns of related purchases, and discount information, etc. However, the number of cases was so large that it was very difficult to create the advertisement by a person in terms of time and ability.

[0048] In contrast, in this embodiment, the generation AI model 302 generates appropriate advertising copy etc. in accordance with various conditions (related purchases, attributes, discounts, etc.), and the generated advertisements are based on the state of the smart cart terminal 100, making it possible to generate highly effective advertisements that are more appealing and have a direct impact on customer purchasing behavior.

[0049] <Modification> In the above-described embodiment, the smart cart terminal 100 searches for various information from the knowledge server 200 to generate recommendation information, but the smart cart terminal 100 may store various information stored in the knowledge server 200 in a storage device of the smart cart terminal 100. This configuration can be realized by setting the search destination of the smart cart terminal 100 in the above-described embodiment to its own storage device instead of the knowledge server 200.

[0050] Furthermore, in the system configuration of the advertisement generation system 10 described above, the generative AI model 302 is implemented in a device connected to the smart cart terminal 100 via a different network, but may be implemented in the smart cart terminal 100. Furthermore, the generation unit 107 that generates a prompt using RAG is implemented in the smart cart terminal 100, but may be implemented in a device in which the generative AI model is implemented, or may be implemented in a device other than the device in which the generative AI model is implemented. Furthermore, the various information stored in the memory unit of the knowledge server 200 may be stored in the smart cart terminal 100 or the generation device 300.

[0051] Furthermore, each functional unit included in each of the smart cart terminal 100 and the generation device 300 may be distributed and implemented on the cloud. Also, each functional unit may be implemented in multiple information processing devices. Furthermore, the same functional unit may be realized by multiple information processing devices. Various information stored in the storage unit 202 of the knowledge server 200 may be distributed and implemented on the cloud.

[0052] An example of a configuration distributed on the cloud will be described. Fig. 8 is a diagram showing an example of a configuration in which the functional units of the smart cart terminal 100 shown in Fig. 1 are distributed to a cloud server 500. The configuration shown in Fig. 8 is a configuration in which the configuration of the smart cart terminal 100 shown in Fig. 1 is assigned to the cloud server 500 and a new smart cart terminal 600. A system including the cloud server 500 and smart cart terminal 600 shown in this configuration is an example of an information processing system.

[0053] Specifically, the cloud server 500 implements each part of the smart cart terminal 100 described in Figure 1 (authentication unit 101, product registration unit 102, location acquisition unit 103, payment unit 104, status acquisition unit 105, determination unit 106, generation unit 107, prompt transmission unit 108, advertisement reception unit 109), and is provided with a new configuration, an advertisement transmission unit 501, which transmits advertisements to the smart cart terminal 600.

[0054] On the other hand, the smart cart terminal 600 includes a cloud transmission / reception unit 601 and an advertisement display unit 110. The cloud transmission / reception unit 801 transmits and receives various information to and from the cloud server 500. Here, the various information includes information relating to actions in the smart cart terminal 600 (operations such as authentication operations, product registration operations, and payment operations, and information indicating the location of the smart cart terminal 600 which changes as the consumer moves), advertisements displayed on the smart cart terminal 600, and the like. The advertisement display unit 110 displays advertisements received from the cloud server 500 on the display unit.

[0055] The configuration shown in Figure 8 is intended to use the smart cart terminal 600 solely for the purpose of "supplementing consumer behavior" and "displaying advertisements," and is intended to assume that the cloud server 500 will determine what kind of advertisements can be applied based on consumer behavior and generate prompts.

[0056] With this configuration, various data and functional units are centrally managed on the server side by the cloud server 500, facilitating management of updates, security measures, etc. Furthermore, since the hardware requirements of the smart cart terminal 600 can be reduced, the initial investment for the smart cart terminal 600 can be reduced, and since the amount of processing executed can be significantly reduced compared to the configuration of the smart cart terminal 100 shown in Fig. 1, power consumption can be reduced, and as a result, running costs can also be reduced.

[0057] <Hardware configuration example> The smart cart terminals 100, 600, knowledge server 200, and generation device 300 according to an embodiment of the present disclosure may function as computers that perform processing of the wireless communication method of the present disclosure. Fig. 9 is a diagram illustrating an example of the hardware configuration of the smart cart terminal 100, knowledge server 200, and generation device 300 according to an embodiment of the present disclosure. The smart cart terminal 100, knowledge server 200, and generation device 300 described above may be physically configured as computer devices including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.

[0058] In the following description, the term "apparatus" can be read as a circuit, a device, a unit, etc. The hardware configurations of the smart cart terminal 100, the knowledge server 200, and the generation apparatus 300 may be configured to include one or more of the apparatuses shown in the drawings, or may be configured to exclude some of the apparatuses.

[0059] Each function of the smart cart terminals 100, 600, knowledge server 200, and generation device 300 is realized by loading specified software (programs) onto hardware such as a processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0060] The processor 1001 controls the entire computer by running, for example, an operating system, and may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc.

[0061] The processor 1001 also reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes in accordance with these. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. For example, each unit of the smart cart terminal 100 may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and similar implementations may be made for other functional blocks. While the above-described various processes have been described as being executed by one processor 1001, they may also be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may also be transmitted from a network via a telecommunications line.

[0062] The memory 1002 is a computer-readable recording medium and may be configured, for example, by at least one of a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a random access memory (RAM), etc. The memory 1002 may also be called a register, a cache, a main memory (primary storage device), etc. The memory 1002 can store executable programs (program codes), software modules, etc. for implementing a wireless communication method according to an embodiment of the present disclosure.

[0063] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blue-ray® disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy disk, a magnetic strip, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate medium including at least one of memory 1002 and storage 1003.

[0064] The communication device 1004 is hardware (transmission / reception device) for communicating between computers via at least one of a wired network and a wireless network, and is also called, for example, a network device, a network controller, a network card, or a communication module.

[0065] The input device 1005 is an input device (for example, a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (for example, a display, a speaker, an LED lamp, etc.) that outputs to the outside. The input device 1005 and the output device 1006 may be integrated into one device (for example, a touch panel).

[0066] Furthermore, each device, such as the processor 1001 and the memory 1002, is connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses between each device.

[0067] Furthermore, the smart cart terminal 100, the knowledge server 200, and the generating device 300 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware. [Industrial Applicability]

[0068] One aspect of the present disclosure is useful for marketing. [Explanation of symbols]

[0069] 10. Ad Generation System 100 Smart Cart Terminals 105 Status acquisition unit 106 Decision Section 107 Generation part 200 Knowledge Server 300 generator 1001 processor 1002 memory 1003 Storage 1004 Communication equipment 1005 Input Device 1006 Output Device 1007 Bus

Claims

1. a status acquisition unit that acquires a status of the information processing device that changes in response to a predetermined event that occurs in the information processing device operated by a customer; a decision unit that determines an advertisement creation policy according to the acquired state and using advertisement creation information for creating an advertisement for the customer; A generation unit that generates a prompt that instructs a generation AI model to generate the advertisement based on the advertisement creation policy; An information processing device comprising:

2. The information processing device according to claim 1 , wherein the predetermined event is a shopping start operation by the customer, a login operation by the customer, an operation by the customer to add a product to purchase, the customer moving around inside the store, or an operation by the customer to pay for a product.

3. 2. The information processing device according to claim 1, wherein the state is a pre-login state in which the customer has not performed a login operation after the shopping start operation, a login state in which the customer has performed a login operation, a product addition state in which the customer has performed an operation to add a product to purchase, a location change state in which the customer has moved within the store, or a payment completion state in which the customer has performed a payment operation for the product price.

4. The determination unit determining a policy for creating the advertisement corresponding to a product common to all of the customers as the advertisement creation policy corresponding to the pre-login state; determining a policy for creating the advertisement corresponding to a product according to an attribute of the logged-in customer as the advertisement creation policy corresponding to the logged-in state; determining a policy for creating the advertisement corresponding to the added product and a product to be purchased in association with the added product as the advertisement creation policy corresponding to the product addition state; determining a policy for creating the advertisement corresponding to the product arranged in the changed position as the advertisement creation policy corresponding to the position change state; The information processing device according to claim 3 , wherein a policy for creating the advertisement to encourage revisiting the store is determined as the advertisement creation policy corresponding to the payment completion state.

5. The information processing device according to claim 1, wherein the generation unit generates the prompt indicating purchase bonus information, information indicating the importance of purchase promotion, example sentences for the generation AI model to refer to when generating the advertisement, information indicating the appeal effect of the example sentences on the advertisement, or an image for the generation AI model to refer to when generating the advertisement.

6. The information processing device according to claim 1 , wherein the advertisement generated by the generating AI model is displayed in response to the prompt.

7. The information processing device operated by the customer is acquiring a state of the information processing device that changes in response to a predetermined event that occurs in the information processing device; determining an advertisement creation policy in response to the acquired status and using advertisement creation information for creating an advertisement for the customer; generating a prompt that instructs a generative AI model to generate the advertisement based on the advertisement creation policy; Control method.

8. On the computer, acquiring a state of the information processing device that changes in response to a predetermined event that occurs in the information processing device operated by the customer; determining an advertisement creation policy in response to the acquired status and using advertisement creation information for creating an advertisement for the customer; generating a prompt that instructs a generative AI model to generate the advertisement based on the advertisement creation policy; A program for executing a process.

9. a status acquisition unit that acquires a status of the information processing device that changes in response to a predetermined event that occurs in the information processing device operated by a customer; a decision unit that determines an advertisement creation policy according to the acquired state and using advertisement creation information for creating an advertisement for the customer; A generation unit that generates a prompt that instructs a generation AI model to generate the advertisement based on the advertisement creation policy; An information processing system comprising:

Images