Information processing apparatus and program

Abstract

To provide an information processing apparatus and a program that generate, for a customer visiting a store, sales promotion information for improving the power to appeal a commodity sold in the store to the customer.SOLUTION: An information processing apparatus of an embodiment comprises: first acquisition means that acquires the attribute of customers who visit a store; first generation means that generates inquiry information on the basis of condition information including at least the attribute of the customers and instruction sentences instructing derivation of commodities suitable for elements included in the condition information; second acquisition means that inputs the inquiry information to generative AI functioned to generate a text related to a commodity according to the details of an instruction in the inquiry information and acquires a generated text generated by the generative AI; extraction means that extracts a commodity related to the commodity described in the generated text from commodities sold in the store; and second generation means that generates sales promotion information of the commodity extracted by the extraction means on the basis of commodity information of the commodity extracted by the extraction means and the details of description of the generated text related to the commodity.SELECTED DRAWING: Figure 10

Description

[Technical Field]

[0001] An embodiment of the present invention relates to an information processing device and a program. [Background technology]

[0002] Conventionally, department stores, supermarkets, and other stores advertise products sold in the stores through promotions using paper media, etc. Furthermore, a technology has been proposed that automatically generates advertisements based on the field to which the advertisement target belongs (for example, Patent Document 1).

[0003] However, the above-mentioned method promotes the same product to all customers, so there is room for further improvement in the appeal of the product through promotion. Summary of the Invention [Problem to be solved by the invention]

[0004] The problem to be solved by the present invention is to provide an information processing device and a program for generating sales promotion information that increases the appeal of products sold in a store to customers who visit the store. [Means for solving the problem]

[0005] The information processing device of the embodiment comprises a first acquisition means for acquiring attributes of customers who visit a store, a first generation means for generating inquiry information based on condition information including at least the customer attributes and an instruction statement instructing the derivation of products suitable for elements included in the condition information, a second acquisition means for inputting the inquiry information to a generation AI that is functionalized to generate text related to products according to the instruction content of the inquiry information and acquiring the generated text generated by the generation AI, an extraction means for extracting products related to the products described in the generated text from among the products sold at the store, and a second generation means for generating promotional information for the products extracted by the extraction means based on product information of the products extracted by the extraction means and the description content of the generated text related to the products. [Brief explanation of the drawings]

[0006] [Figure 1] FIG. 1 is a schematic diagram showing a schematic configuration of an information processing system according to an embodiment. [Figure 2] FIG. 2 is a block diagram illustrating an example of a hardware configuration of an edge device according to the embodiment. [Figure 3] FIG. 3 is a block diagram illustrating an example of a hardware configuration of an edge server according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of a data configuration of the product master according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of a data configuration of the prompt DB according to the embodiment. [Figure 6] FIG. 6 is a block diagram illustrating an example of a functional configuration of an edge device according to the embodiment. [Figure 7] FIG. 7 is a block diagram illustrating an example of a functional configuration of the edge server according to the embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of visualized sales promotion information generated by the edge server according to the embodiment. [Figure 9] FIG. 9 is a diagram illustrating an example of visualized sales promotion information generated by the edge server according to the embodiment. [Figure 10] FIG. 10 is a sequence diagram illustrating an example of a control process of the information processing system according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0007] Hereinafter, an information processing device and a program according to an embodiment will be described in detail with reference to the drawings. In the embodiment described below, an edge server installed in a store (an example of a facility) such as a department store or supermarket will be described as an example of an information processing device, but the present invention is not limited to the embodiment.

[0008] 1 is a schematic diagram showing a schematic configuration of an information processing system S according to an embodiment. As shown in FIG. 1, the information processing system S includes an edge device 1 and an edge server 2.

[0009] The edge device 1 and the edge server 2 are communicatively connected via a network Na such as a LAN (Local Area Network), and the edge server 2 is communicatively connected to a network Nb such as the Internet.

[0010] The number of edge devices 1 connected to the edge server 2 is not limited to the illustrated example.

[0011] The edge device 1 is a device installed in a store. The edge device 1 also refers to various devices that serve as a point of contact between a customer who visits the store and the information processing system S, or a system including such devices. For example, the edge device 1 may be an information processing device such as a self-service POS (Point of Sale) terminal, a smartphone, a tablet terminal, or the like.

[0012] The edge device 1 exchanges various types of information with the edge server 2. Specifically, the edge device 1 uses an imaging unit 108 (see FIG. 2 ), which will be described later, to capture an image of a customer who visits the store (hereinafter also referred to as a customer image). The edge device 1 then transmits the captured customer image to the edge server 2. Furthermore, upon receiving sales promotion information from the edge server 2, the edge device 1 uses a printing unit 109 of the edge device 1 to output the sales promotion information. Details of the sales promotion information will be described later.

[0013] The customer image is, for example, an image showing the face of the customer. Alternatively, the customer image may be an image showing the whole body of the customer so that the customer's clothing can be seen. Note that the customer image is preferably an image showing only one customer who is the subject of the image capture.

[0014] The edge server 2 is a server device installed in a store or an external data center, etc. The edge server 2 generates sales promotion information for products to be proposed to customers from among the products sold in the store.

[0015] Specifically, when the edge server 2 receives the customer image from the edge device 1, it extracts feature quantities (hereinafter also referred to as feature quantities) representing the customer's external characteristics from the customer image by using a known image recognition technology, etc. Then, the edge server 2 estimates the customer attributes, such as the customer's age and gender, from the extracted feature quantities, thereby acquiring the customer attributes of the customer depicted in the customer image.

[0016] The edge server 2 also acquires environmental information around the store via the network Nb. The edge server 2 acquires external data such as the weather and temperature around the store from an external server such as a server that provides weather data. The edge server 2 may also acquire external data from a sensor device such as a temperature sensor installed outside the store.

[0017] The edge server 2 then inputs the prompt generated based on the estimated customer attributes and the acquired external data to the product proposal LLM 2043, which will be described later, to acquire the product text generated by the product proposal LLM 2043. The prompt and the product text will be described in detail later.

[0018] The edge server 2 also extracts a product from the products registered in the product master 2042 (described later) based on the product information described in the product text. The edge server 2 then generates sales promotion information for the extracted product based on the product information, etc. The edge server 2 then transmits the sales promotion information to the edge device 1.

[0019] The edge server 2 may also perform processing such as collecting information related to product sales and product registration from a POS terminal (not shown). For example, the edge server 2 may acquire information such as the number of purchases and sales of products as external data from a POS terminal (not shown). Furthermore, the edge server 2 may determine the listing order of products when extracting products from the product master 2042 or generating sales promotion information based on the external data acquired from the POS terminal.

[0020] Next, a description will be given of the hardware configuration of the edge device 1. Fig. 2 is a block diagram showing an example of the hardware configuration of the edge device 1 according to the embodiment.

[0021] As shown in FIG. 2, the edge device 1 includes a CPU (Central Processing Unit) 101, which is an example of a processor, a ROM (Read Only Memory) 102, a RAM (Random Access Memory) 103, and a memory unit 104.

[0022] The CPU 101 comprehensively controls each part of the edge device 1. The ROM 102 stores various programs. The RAM 103 is a workspace where programs and various data are expanded.

[0023] The memory unit 104 is a non-volatile memory such as a hard disk drive (HDD) or flash memory that retains stored information even when the power is turned off. The memory unit 104 includes a control program unit 1041.

[0024] The control program unit 1041 stores a control program for controlling the edge device 1. The CPU 101, ROM 102, RAM 103, and memory unit 104 are connected to one another via a bus 110. The CPU 101, ROM 102, and RAM 103 constitute a control unit 100 having a computer configuration. That is, the control unit 100 executes a control process for the edge device 1, which will be described later, by the CPU 101 operating in accordance with the control program unit 1041 stored in the ROM 102 or memory unit 104 and expanded in the RAM 103.

[0025] The control unit 100 is connected to a communication unit 105 , a display unit 106 , an operation unit 107 , an imaging unit 108 , and a printing unit 109 via a bus 110 .

[0026] The communication unit 105 is a communication interface such as a LAN I / F (Interface), and is connected to the network Na. The communication unit 105 transmits and receives various information to and from the edge server 2, for example, via the network Na.

[0027] The display unit 106 is a display device such as an LCD (Liquid Crystal Display). The display unit 106 displays various information related to sales promotion information under the control of the CPU 101. The display unit 106 may also be a display device such as a signage.

[0028] The operation unit 107 is realized by, for example, a touch panel. The operation unit 107 accepts various inputs from the customer. Note that the operation unit 107 may also be an input device such as a keyboard or a pointing device.

[0029] The imaging unit 108 is an imaging device. The imaging unit 108 includes a solid-state imaging element such as a CCD (Charge Coupled Device) or a CMOS (Complementary MOS). In this embodiment, the imaging unit 108 is provided on the surface of the edge device 1 on which the display unit 106 is provided. The imaging unit 108 captures an image of a customer operating the edge device 1.

[0030] The printing unit 109 is a printing device. The printing unit 109 includes a print head, a paper transport mechanism, etc., and performs printing (image formation) on a printing medium such as paper based on instructions from the control unit 100. For example, under the control of the control unit 100, the printing unit 109 prints sales promotion information received from the edge server 2 on the printing medium. Note that the printing method of the printing unit 109 is not particularly limited.

[0031] Next, a description will be given of the hardware configuration of the edge server 2. Fig. 3 is a block diagram showing an example of the hardware configuration of the edge server 2 according to the embodiment.

[0032] As shown in FIG. 3, the edge server 2 includes a CPU 201, which is an example of a processor, a ROM 202, a RAM 203, and a memory unit 204.

[0033] The CPU 201 comprehensively controls each unit of the edge server 2. The ROM 202 stores various programs. The RAM 203 is a workspace where programs and various data are expanded.

[0034] The memory unit 204 is a non-volatile memory such as a HDD or flash memory that retains stored information even when the power is turned off. The memory unit 204 includes a control program unit 2041, a product master 2042, a product proposal LLM 2043, and a prompt DB 2044.

[0035] The memory unit 204 also stores a prompt template DB (not shown). The prompt template DB is a data table or database that stores prompt templates corresponding to prompt types stored in a prompt DB 2044 (described later). The memory unit 204 also stores a sales promotion information template DB (not shown). The sales promotion information template DB will be described in detail later.

[0036] The control program unit 2041 stores a control program for controlling the edge server 2. The CPU 201, ROM 202, RAM 203, and memory unit 204 are connected to one another via a bus 206. The CPU 201, ROM 202, and RAM 203 constitute a control unit 200 having a computer configuration. That is, the control unit 200 executes a control process for the edge server 2, which will be described later, by the CPU 201 operating in accordance with the control program unit 2041 stored in the ROM 202 or memory unit 204 and loaded into the RAM 203.

[0037] The product master 2042 is a data table or database for managing product information for products sold in a store. Fig. 4 is a diagram showing an example of the data configuration of the product master 2042. As shown in Fig. 4, the product master 2042 associates the type of product sold in a store with an identifiable product code, and stores product information such as the product name, product price, product image, and product description of the product corresponding to the product code.

[0038] The product description includes information such as the product location in the store, product category, keywords, etc. The product category indicates the category of the product corresponding to the product code. Furthermore, multiple product categories may be stored for each product. For example, the product categories for the product name "orange juice" may include "fruit," "orange," "groceries," and "drinks."

[0039] Keywords include text that describes product characteristics, such as product type, production, country of origin, and manufacturer. Multiple keywords may be stored for each product. For example, keywords for the product name "orange juice" may include "100% juice" and "Made in America."

[0040] Here, the product categories and keywords are not limited to being stored in a format written in natural language, but may be stored in a format written in semantic vectors calculated by known natural language processing techniques, etc. Furthermore, the product categories and keywords may be stored in either a format written in natural language or a format written in semantic vectors.

[0041] The product suggestion LLM2043 is a generation AI that generates text, such as a large language model (LLM). The product suggestion LLM2043 generates product text related to products recommended for purchase to customers. Note that, although an LLM is used as the generation AI in this embodiment, the generation AI is not limited to an LLM as long as it can generate text.

[0042] The product suggestion LLM2043 is an LLM built using well-known deep learning technology that accepts text input specifying conditions and outputs text related to products based on those conditions. Here, the conditions can be, for example, reference conditions that serve as references for deriving the output results or constraint conditions for narrowing down the output results.

[0043] Furthermore, for example, the product text is text data that describes the name of the product, the product category of the product, and the content of promoting the product (hereinafter, promotional text). Note that the product text may be text data in a list format that includes the names of multiple products, the product categories corresponding to each of the multiple products, and promotional text corresponding to each of the multiple products.

[0044] The product proposal LLM2043 of this embodiment generates product text corresponding to the customer in response to input of a query text (hereinafter also referred to as a prompt) that includes an instruction statement instructing the generation of product text and conditions related to customer information such as external data such as weather and temperature, and attribute information indicating customer attributes.

[0045] The prompt DB 2044 is a data table or database that stores customer attributes and external data in association with prompts. Fig. 5 is a diagram showing an example of the data configuration of the prompt DB 2044. As shown in Fig. 5, the prompt DB 2044 stores prompt type, date and time, weather, age, gender, etc.

[0046] The prompt type is identification information for identifying a prompt corresponding to the contents of a data entry, such as date and time, weather, age, and gender, stored in the prompt DB 2044. Furthermore, a prompt template associated with the identification information identified by the prompt type is stored in a prompt template DB (not shown) in the memory unit 204. Here, the date and time and weather are examples of external data, and the age and gender are examples of attribute information indicating customer attributes.

[0047] Returning to FIG. 3, the control unit 200 is connected to the communication unit 205 via a bus 206 .

[0048] The communication unit 205 is a communication interface such as a LAN I / F, and is connected to the networks Na and Nb. The communication unit 205 transmits and receives various information to and from, for example, the edge device 1 and an external server (not shown) via the networks Na and Nb.

[0049] Next, a functional configuration of the edge device 1 will be described. Fig. 6 is a block diagram showing an example of the functional configuration of the edge device 1. As shown in Fig. 6, the control unit 100 includes, as functional components, an image acquisition unit 1001, a transmission / reception unit 1002, and an output control unit 1003. Note that the functional configuration of the edge device 1 is not limited to this.

[0050] Specifically, the control unit 100 (CPU 101) of the edge device 1 realizes the above-mentioned functional configuration by executing the control program unit 1041 stored in the memory unit 104. Note that in this embodiment, the above-mentioned functional configuration is a software configuration realized by cooperation between the processor and program of the edge device 1, but is not limited to this, and a hardware configuration in which part or all of the functional configuration is realized by a dedicated circuit or the like may also be used.

[0051] The image acquisition unit 1001 acquires a customer image of a customer who visits a store. Specifically, when the image acquisition unit 1001 receives an operation from the operation unit 107 of the edge device 1, it captures the customer image using the imaging unit 108. Then, the image acquisition unit 1001 acquires the customer image.

[0052] The image acquisition unit 1001 may acquire customer images captured by a network camera (not shown) installed in the store instead of the imaging unit 108 of the edge device 1. The image acquisition unit 1001 may capture customer images not only in response to an operation received from the operation unit 107, but also, for example, when a customer is detected by a sensor (not shown) installed in the store. The image acquisition unit 1001 may capture customer images in response, for example, when a microphone (not shown) installed in the store detects the voice of the customer.

[0053] The transmitting / receiving unit 1002 transmits and receives various information to and from the edge server 2. Specifically, when the image acquiring unit 1001 acquires a customer image, the transmitting / receiving unit 1002 transmits the customer image to the edge server 2. The transmitting / receiving unit 1002 also receives sales promotion information from the edge server 2.

[0054] The output control unit 1003 outputs the sales promotion information. Specifically, the output control unit 1003 controls the printing unit 109 to print (output) the sales promotion information received by the transmitting / receiving unit 1002.

[0055] The output control unit 1003 may control the display unit 106 to display (output) the promotional information received by the transmission / reception unit 1002 on the display unit 106.

[0056] Next, the functional configuration of the edge server 2 will be described. Fig. 7 is a block diagram showing an example of the functional configuration of the edge server 2. As shown in Fig. 7, the control unit 200 includes, as its functional components, a customer attribute acquisition unit 2001, an external data acquisition unit 2002, a prompt generation unit 2003, a text acquisition processing unit 2004, a product information extraction unit 2005, and a sales promotion information generation processing unit 2006. Note that the functional configuration of the edge server 2 is not limited to this.

[0057] Specifically, the control unit 200 (CPU 201) of the edge server 2 realizes the above-mentioned functional configuration by executing the control program unit 2041 stored in the memory unit 204. In this embodiment, the above-mentioned functional configuration is a software configuration realized by cooperation between the processor and program of the edge server 2, but is not limited to this, and a hardware configuration in which part or all of the functional configuration is realized by a dedicated circuit or the like may also be used.

[0058] The customer attribute acquisition unit 2001 is an example of a first acquisition means. The customer attribute acquisition unit 2001 acquires customer attributes of customers who visit a store. Specifically, when the customer attribute acquisition unit 2001 receives a customer image transmitted by the transmission / reception unit 1002 of the edge device 1, it extracts feature amounts from the customer image. Then, the customer attribute acquisition unit 2001 estimates customer attributes from the extracted feature amounts and acquires the estimated customer attributes. Here, when extracting feature amounts from a customer image, it is preferable to extract feature amounts based on parts that are likely to reveal characteristics such as the customer's age and gender, such as the customer's face, in order to improve the accuracy of estimating the customer attributes.

[0059] The external data acquisition unit 2002 acquires various information from an external server (not shown). Specifically, the external data acquisition unit 2002 acquires external data such as weather and temperature from the external server (not shown) via the network Nb.

[0060] The external data acquisition unit 2002 may acquire external data from a sensor device such as a temperature sensor installed outside the store. The external data acquisition unit 2002 may also acquire information such as the number of purchases and sales of products as external data from a POS terminal (not shown).

[0061] The prompt generation unit 2003 is an example of a first generation means. The prompt generation unit 2003 generates a query text based on information including customer attributes and external data and an instruction statement that instructs the generation of product text. Specifically, the prompt generation unit 2003 references the prompt DB 2044 and acquires a prompt type that matches the customer attributes and external data.

[0062] When acquiring a prompt type, the prompt generation unit 2003 preferably acquires a prompt type in which the customer attributes and external data completely match the contents of each data entry in the prompt DB 2044, but it may also acquire a prompt type in which the customer attributes and external data have a high degree of match with the contents of each data entry in the prompt DB 2044.

[0063] The prompt generation unit 2003 then references a prompt template DB (not shown) in the memory unit 204 and acquires a prompt template corresponding to the prompt type from the prompt templates stored in the prompt template DB. The prompt generation unit 2003 then generates a prompt by incorporating customer attributes and external data into the acquired prompt template. Here, the prompt template includes an instruction statement that instructs the generation of product text.

[0064] The text acquisition processing unit 2004 is an example of a second acquisition unit. The text acquisition processing unit 2004 inputs the query text to the product proposal LLM 2043, which is functionally configured to generate text related to a product according to the instructions in the query text, thereby acquiring the product text generated by the product proposal LLM 2043. Specifically, the text acquisition processing unit 2004 inputs the prompt generated by the prompt generation unit 2003 to the product proposal LLM 2043. Next, the text acquisition processing unit 2004 acquires the product text generated by the product proposal LLM 2043.

[0065] The product information extraction unit 2005 is an example of an extraction means. The product information extraction unit 2005 extracts products based on information about the products described in the product text. Specifically, the product information extraction unit 2005 extracts product information about products that include, as product information, a product category similar to the product category included in the product text acquired by the text acquisition processing unit 2004 from the product master 2042.

[0066] Here, as a method for extracting product categories included in the product text and products included in similar product categories from the product master 2042, the product information extraction unit 2005 vectorizes the product categories included in the product text using a known natural language processing technique. Next, the product information extraction unit 2005 calculates vector similarity between the vectorized product categories and pre-vectorized product categories stored in the product master 2042. Then, for products whose product information includes a product category whose vector similarity is equal to or greater than a predetermined threshold, the product information extraction unit 2005 extracts product information of the products from the product master 2042. Here, the product information extraction unit 2005 may extract multiple pieces of product information from the product master 2042.

[0067] When prioritizing and extracting product information from the product information extracted from the product master 2042, the product information extraction unit 2005 may, for example, determine the priority based on the product price, product description, etc. included in the product information. For example, product information on low-priced products or products that are the subject of a campaign being held in a store may be preferentially extracted.

[0068] The promotional information generation processor 2006 is an example of a second generation means. The promotional information generation processor 2006 generates promotional information for the product extracted by the product information extraction unit 2005. Specifically, the promotional information generation processor 2006 generates the promotional information based on the product text from the product information extracted by the product information extraction unit 2005 from the product master 2042 and the promotional text included in the product text.

[0069] Here, the sales promotion information generation processing unit 2006 generates sales promotion information by associating the product information of each product (information) extracted by the product information extraction unit 2005 with the promotional text included in the product text, and then formatting the information.

[0070] As a method of generating promotional information, for example, the promotional information generation processing unit 2006 references a promotional information template DB (not shown) in the memory unit 204, and generates promotional information by incorporating product information and promotional text contained in the product text into a promotional information template stored in the promotional information template DB.

[0071] Here, the promotional information template may include information about the store, such as the store name, store location, and store map, as well as product information about products the store is running a campaign for and discount information (coupons, etc.). There may be multiple types of promotional information templates, and the promotional information templates may be configured to be switched depending on customer attributes, external data, etc.

[0072] Furthermore, the sales promotion information generation processor 2006 may determine the order in which products are to be included in the sales promotion information when generating the sales promotion information based on external data acquired from a POS terminal. For example, the sales promotion information generation processor 2006 may generate sales promotion information by arranging and formatting information consisting of product information and promotional text in order of the number of purchases or the best-selling products.

[0073] The sales promotion information generation processing unit 2006 also transmits the generated sales promotion information to the edge device 1.

[0074] Next, we will explain the promotional information printed by the printing unit 109 of the edge device 1. The output control unit 1003 of the edge device 1 controls the printing unit 109 to output promotional information such as that shown in Fig. 8. Fig. 8 is a diagram showing an example of a visualized state of promotional information generated by the edge server 2. As shown in Fig. 8, the promotional information has areas Gaa, Gab, etc. within the promotional information area Ga.

[0075] Area Gaa displays store-related information such as the store name and text promoting products to customers visiting the store. Area Gab is provided for each product (product information) extracted by the product information extraction unit 2005 of the edge server 2, and product information is displayed within the area. For example, area Gab has display areas such as area Gac, area Gad, area Gae, area Gaf, and area Gag related to the display of product information.

[0076] Area Gac displays the product name and product price included in the product information extracted by the product information extraction unit 2005. Area Gad displays the product image included in the product information extracted by the product information extraction unit 2005.

[0077] Area Gae displays the placement location included in the product information extracted by the product information extraction unit 2005. Area Gaf displays the product information extracted by the product information extraction unit 2005 and the corresponding product text promotion sentences. Area Gag displays various product information for products that the store is running a campaign for.

[0078] The promotional information is generated from promotional text included in product text generated based on customer attributes and external data, and product information extracted from the product master 2042. In other words, the promotional information is product information personalized for each customer. Therefore, by viewing the promotional information, the appeal of the products sold in the store can be improved.

[0079] Next, we will explain the promotional information printed by the printing unit 109 of the edge device 1 when a promotional information template different from that shown in Figure 8 is used. Note that explanations of items common to Figure 8 will be omitted. The output control unit 1003 of the edge device 1 causes the printing unit 109 to print, for example, promotional information such as that shown in Figure 9. Figure 9 is a diagram showing an example of a visualized state of promotional information generated by the edge server 2. As shown in Figure 9, the promotional information has an area Gba in addition to the above-mentioned area Gaa within the promotional information area Gb.

[0080] A map of the store's interior is displayed in area Gba. The locations of the sales areas for the products corresponding to the products in area Gaa are also displayed superimposed on the map of the store's interior.

[0081] The promotional information described above visualizes the location of the product, and by a customer viewing the promotional information, it is possible to assist the customer in purchasing the product.

[0082] Next, the control processing of the information processing system S will be described. Fig. 10 is a sequence diagram showing an example of the control processing of the information processing system S according to the embodiment. The sequence diagram shown in Fig. 10 shows an example of a process in which a customer image acquired by the edge device 1 is sent to the edge server 2, and then promotional information is generated based on product text generated by the product proposal LLM 2043 of the edge server 2. Next, the promotional information is sent to the edge device 1, and the promotional information is printed (output) by the edge device 1.

[0083] First, when the image acquisition unit 1001 of the edge device 1 receives an instruction from the operator of the edge device 1 via the operation unit 107 to create sales promotion information, the image acquisition unit 1001 captures an image of a customer using the imaging unit 108. Then, the image acquisition unit 1001 acquires the customer image (step S101). Next, the transmitting / receiving unit 1002 of the edge device 1 transmits the customer image acquired by the image acquisition unit 1001 to the edge server 2 (step S102).

[0084] When the customer image is received from the edge device 1, the customer attribute acquisition unit 2001 of the edge server 2 extracts feature quantities from the customer image. Then, the customer attribute acquisition unit 2001 estimates customer attributes from the extracted feature quantities and acquires the estimated customer attributes (step S103). Next, the external data acquisition unit 2002 of the edge server 2 acquires external data such as weather and temperature from an external server (not shown) via the network Nb (step S104).

[0085] Next, the prompt generation unit 2003 of the edge server 2 references the prompt DB 2044 and acquires a prompt type that matches the customer attributes and external data.The prompt generation unit 2003 then acquires a prompt template that corresponds to the prompt type from the prompt templates stored in the prompt template DB.The prompt generation unit 2003 then generates a prompt by incorporating the customer attributes and external data into the acquired prompt template (step S105).

[0086] Next, the text acquisition processing unit 2004 of the edge server 2 inputs the prompt generated by the prompt generation unit 2003 to the product proposal LLM 2043 (step S106). Next, the text acquisition processing unit 2004 acquires the product text generated by the product proposal LLM 2043 (step S107).

[0087] Next, the product information extraction unit 2005 of the edge server 2 extracts product information for products whose product information includes a product category similar to the product category included in the product text acquired by the text acquisition processing unit 2004 from the product master 2042 (step S108). Next, the sales promotion information generation processing unit 2006 of the edge server 2 generates sales promotion information from the product information extracted from the product master 2042 in step S108 and the promotional text included in the product text, based on the product text (step S109). Then, the sales promotion information generation processing unit 2006 of the edge server 2 transmits the sales promotion information to the edge device 1 (step S110).

[0088] When the transmitting / receiving unit 1002 of the edge device 1 receives the promotional information transmitted from the edge server 2, the output control unit 1003 controls the printing unit 109 to output the promotional information received by the transmitting / receiving unit 1002 (step S111).

[0089] As described above, the information processing system S of this embodiment generates product text based on the customer attributes of customers who visit a store and external data acquired from an external server (not shown). Then, product information of products similar to the generated product text is extracted from the product master 2042, and sales promotion information is generated from the extracted product information and promotional text included in the product text.

[0090] As a result, the information processing system S of this embodiment can perform processing that reflects the customer attributes by generating product text based on the customer attributes of customers who visit the store and external data. Furthermore, the information processing system S of this embodiment can generate personalized sales promotion information by extracting products sold in the store based on the product text. Therefore, the information processing system S of this embodiment can generate sales promotion information that increases the appeal of the products sold in the store to customers who visit the store.

[0091] The above-described embodiment can be modified as needed by partially changing the configuration or functions of each of the above-described devices. Therefore, several modifications of the above-described embodiment will be described below as other embodiments. The following mainly focuses on differences from the above-described embodiment, and detailed descriptions of commonalities with the content already described will be omitted. The modifications described below may be implemented individually or in appropriate combination.

[0092] (Variation 1) In the above-described embodiment, the edge server 2 is configured to extract features of a customer image based on the customer image captured by the imaging unit 108 of the edge device 1, and acquire customer attributes from the extracted features. However, this is not limited to this. The edge server 2 may also be configured to read an ID card held by a customer using a card reader (not shown) of the edge device 1, and acquire customer attributes corresponding to the customer information on the read ID card from a customer master (not shown) stored in the memory unit 204 of the edge server 2.

[0093] (Variation 2) In the above-described embodiment, the prompt generation unit 2003 of the edge server 2 is configured to refer to the prompt DB 2044 and obtain a prompt template corresponding to a prompt type similar to the customer attributes and external data from a prompt template DB (not shown) of the edge server 2. However, this is not limited to this, and the prompt generation unit 2003 may be configured to vectorize the customer attributes and external data using known natural language processing technology, and then calculate the vector similarity between the vectorized customer attributes and external data and each pre-vectorized prompt template stored in a prompt template DB (not shown), thereby obtaining a prompt template with a high vector similarity.

[0094] (Variation 3) In the above-described embodiment, the promotional information generation processing unit 2006 of the edge server 2 is configured to generate promotional information based on product information extracted from the product master 2042 and a promotional information template, and to send the generated promotional information to the edge device 1. However, this is not limited to this, and the extracted product information and promotional information template may be sent to an MFP (Multifunction Peripheral / Printer / Product) not shown, and the MFP not shown may generate the promotional information based on the product information and the promotional information template, and then print (output) the promotional information.

[0095] (Variation 4) In the above embodiment, the promotional information generation processing unit 2006 of the edge server 2 sends the promotional information to the edge device 1, but this is not limiting. The promotional information may be sent to a printing device such as an MFP or a display device such as digital signage, so that the promotional information is output via these devices. In other words, the promotional information generation processing unit 2006 of the edge server 2 may function as an example of an output unit that outputs the promotional information to either or both of the printing device and the display device.

[0096] (Variation 5) In the above embodiment, the edge server 2 generates a prompt based on customer attributes and external data, but this is not limited to this. The edge server 2 may also generate a prompt from customer attributes only, without using external data.

[0097] The programs executed by the information processing system S of the embodiment and the modified example may be stored on a computer connected to a network such as the Internet and provided by being downloaded via the network. Also, the programs executed by the information processing system S of the embodiment and the modified example may be provided or distributed via a network such as the Internet.

[0098] The programs executed by each device in the above-described embodiments are provided in a state where they are pre-installed in a ROM, a storage unit, etc. The programs executed by each device in the above-described embodiments may be provided by being recorded in an installable or executable file format on a computer-readable recording medium such as a CD-ROM, a flexible disk (FD), a CD-R, or a digital versatile disk (DVD).

[0099] Furthermore, the programs executed by each device in the above-described embodiments may be stored on a computer connected to a network such as the Internet and provided by being downloaded via the network. Also, the programs executed by each device in the above-described embodiments may be provided or distributed via a network such as the Internet.

[0100] These novel embodiments and their modifications may be embodied in various other forms, and various omissions, substitutions, changes, and combinations may be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the inventions, and are also included in the inventions described in the claims and their equivalents. [Explanation of symbols]

[0101] S Information Processing System 1. Edge Devices 2 Edge Server 1001 Image acquisition unit 1002 Transmitter / Receiver 1003 Output control section 2001 Customer Attribute Acquisition Department 2002 External Data Acquisition Department 2003 Prompt Generation Unit 2004 Text acquisition processing section 2005 Product information extraction department 2006 Sales promotion information generation processing unit [Prior art documents] [Patent documents]

[0102] [Patent Document 1] Japanese Patent Publication No. 2022-028881

Claims

1. a first acquisition means for acquiring attributes of customers who visit the store; a first generating means for generating inquiry information based on condition information including at least attributes of the customer and an instruction statement for instructing deriving a product suitable for the elements included in the condition information; a second acquisition means for inputting the inquiry information into a generation AI that is configured to generate text related to a product in accordance with instructions in the inquiry information, and acquiring the generated text generated by the generation AI; extraction means for extracting products related to the products described in the generated text from the products sold in the store; a second generating means for generating sales promotion information for the product extracted by the extracting means based on the product information of the product extracted by the extracting means and the description content of the generated text related to the product; An information processing device comprising:

2. the first generation means generates the inquiry information based on the condition information including environmental information around the store. The information processing device according to claim 1 .

3. the extraction means extracts products whose inter-category similarity is equal to or greater than a threshold based on the product categories described in the generated text and the product categories sold in the store; The information processing device according to claim 1 .

4. the second generating means generates sales promotion information for each product extracted by the extracting means, in which the product information of the product is associated with the description content and the sales promotion information is formatted. The information processing device according to claim 1 .

5. further comprising an output unit that outputs the sales promotion information generated by the second generation unit to either a printing device or a display device, or both.

5. The information processing device according to claim 1.

6. The computer of the information processing device, a first acquisition means for acquiring attributes of customers who visit the store; a first generating means for generating inquiry information based on condition information including at least attributes of the customer and an instruction statement for instructing deriving a product suitable for the elements included in the condition information; a second acquisition means for inputting the inquiry information into a generation AI that is configured to generate text related to a product in accordance with instructions in the inquiry information, and acquiring the generated text generated by the generation AI; extraction means for extracting products related to the products described in the generated text from the products sold in the store; a second generating means for generating sales promotion information for the product extracted by the extracting means based on the product information of the product extracted by the extracting means and the description content of the generated text related to the product; A program to function as a

Images