Information processing apparatus and information processing method

Abstract

The invention discloses an information processing apparatus and an information processing method, which can improve the convenience of promotion to customers by using generated AIs. The information processing apparatus includes an acquisition unit, a detection unit, a first generation unit, a second generation unit, and an output control unit. The acquisition unit acquires, from a camera provided in a facility, a camera image captured by the camera. And a detection unit that detects a feature of the customer reflected in the camera image. And a first generation unit that generates first text information indicating a feature of the customer on the basis of the detected feature. And a second generation unit that inputs the inquiry text to which the first text information has been added to a generation AI that generates a text relating to a product sold in the facility in accordance with the input of the inquiry text, and generates second text information relating to the promotion of the product on the basis of the text generated by the generation AI. And an output control unit that outputs the second text information.

Description

[0001] This application claims priority to a Japanese application with an application date of January 26, 2024 and an application number of JP2024-010479, and incorporates the content of the above application by reference in its entirety. Technical Field

[0002] Embodiments of the present invention relate to an information processing apparatus and an information processing method. Background Art

[0003] In recent years, generative AI (Artificial Intelligence) that generates text, images, etc. has attracted attention. The accuracy of generative AI is increasing day by day, and it is becoming increasingly popular to use generative AI that generates text to promote products that match the customer's inquiry in response to the customer's inquiry.

[0004] However, promotional services using the above generative AI are usually provided in the cloud. Therefore, in the case of information such as the customer's personal information that is not desired to be output to the cloud, it may not be possible to use the service. In addition, the generative AI used in the promotional service provided in the cloud is not optimized for the store, so it may lead to a situation where customers are recommended to purchase products that are not sold in the store. Summary of the Invention

[0005] In view of the above problems, the problem to be solved by the present invention is to provide an information processing apparatus and an information processing method that can improve the convenience of promoting (advertising) customers using generative AI.

[0006] To solve the above problems, the information processing apparatus according to the embodiment includes an acquisition unit, a detection unit, a first generation unit, a second generation unit, and an output control unit. The acquisition unit acquires a camera image captured by a camera provided in the facility. The detection unit detects the characteristics of a customer reflected in the camera image. The first generation unit generates first text information representing the characteristics of the customer based on the detected characteristics. The second generation unit inputs an inquiry text with the first text information added thereto to a generative AI that generates text related to products sold in the facility based on the input of the inquiry text, and generates second text information related to the promotion of the product based on the text generated by the generative AI. The output control unit outputs the second text information.

[0007] According to the above information processing apparatus, the convenience of promoting customers using generative AI can be improved.

[0008] In the above information processing apparatus, the detection unit detects features on the appearance of the customer, the first generation unit generates the first text information representing the detected features on the appearance of the customer, and the second generation unit inputs the inquiry text to the first large language model serving as the generation AI and obtains the text output by the first large language model as the second text information. Among them, the generation AI has a function of outputting text related to a product based on a condition corresponding to an input of text specifying a condition, and the inquiry text adds a description related to the feature on the appearance as the condition.

[0009] According to the above information processing apparatus, it is possible to generate recommended product text incorporating emotions inferred from the customer's clothing, customer's expression, etc.

[0010] In the above information processing apparatus, it further includes: a second acquisition unit that acquires the purchase history of the customer corresponding to the detected feature. Among them, the second generation unit inputs the inquiry text with a description related to the acquired purchase history added as the condition to the first large language model and obtains the text output by the first large language model as the second text information.

[0011] According to the above information processing apparatus, it is possible to prevent the situation of recommending purchased products to customers.

[0012] In the above information processing apparatus, the second acquisition unit acquires the purchase history from a database that associates the features of each customer with the purchase history of that customer and stores them, or from a portable terminal carried by the customer.

[0013] According to the above information processing apparatus, it is possible to acquire the purchase history from a database or a portable terminal.

[0014] In the above information processing apparatus, it further includes: a second specifying unit that specifies nearby products near the customer based on the position information indicating the position of the customer in the facility. Among them, the second generation unit inputs the inquiry text with a description related to the specified nearby products added as the condition to the first large language model and obtains the text output by the first large language model as the second text information.

[0015] According to the above information processing apparatus, it is possible to recommend to the customer to purchase products near the customer's current position.

[0016] In the above information processing apparatus, it further includes: a third generation unit that generates promotional information that converts the content represented by the second text information into data including at least one of image data and voice data. Among them, the output control unit outputs the generated promotional information to an output device.

[0017] According to the above information processing device, it is possible to recommend to customers to purchase products near the customer's current location.

[0018] In the above information processing device, the third generation unit inputs the second text information into a second large language model serving as a generation AI, and generates the promotion information by converting the text output by the second large language model into voice data, wherein the generation AI has a function of inputting text related to a product and outputting text for promoting the product.

[0019] According to the above information processing device, even in a scenario where the image of the product cannot be confirmed, it is possible to understand the product recommended for purchase.

[0020] In the above information processing device, the third generation unit reads the image data corresponding to the name of the product included in the second text information from a product image database associating the name of each product with the image data of the product, and generates the promotion information based on the read image data and the second text information.

[0021] According to the above information processing device, customers can easily understand what product they are recommended to purchase.

[0022] In the above information processing device, the output control unit outputs the promotion information to the output device when the change in the position information of the customer within a specified time is within a specified range.

[0023] According to the above information processing device, it is possible to prevent the situation of recommending to customers to purchase products that the customers are not interested in.

[0024] In the above information processing device, the output control unit outputs the promotion information to the output device closest to the latest position information of the customer.

[0025] According to the above information processing device, it is possible to prevent the situation of outputting the promotion information in a form that cannot be conveyed to the customers.

[0026] On the other hand, an information processing method of the present invention is an information processing method based on an information processing apparatus, which includes the following steps: obtaining a camera image captured by a camera provided in a facility; detecting features of a customer reflected in the camera image; generating first text information representing the features of the customer based on the detected features; inputting an inquiry text appended with the first text information to a generation AI, and generating second text information related to the promotion of a product based on the text generated by the generation AI, where the generation AI generates the text related to the products sold in the facility according to the input of the inquiry text; and outputting the second text information.

[0027] According to the above information processing method, the convenience of promoting customers using the generation AI can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 FIG. is a system diagram showing an example of the connection relationship of each device of the information processing system according to the embodiment.

[0029] Figure 2 FIG. is a block diagram showing an example of the hardware structure of the SC according to the embodiment.

[0030] Figure 3 FIG. is a block diagram showing an example of the functional structure of the SC according to the embodiment.

[0031] Figure 4 FIG. is a flowchart showing an example of the processing executed by the SC according to the embodiment.

[0032] DESCRIPTION OF REFERENCE NUMERALS

[0033] 1 SC 2 Image display device 3 Voice output device

[0034] 4 Camera 5 Access point 6 Portable terminal 7 Communication line

[0035] 11 CPU 12 ROM 13 RAM 14 Memory unit

[0036] 100 Control unit 101 LLM preprocessing unit 102 LLM processing unit

[0037] 103 LLM postprocessing unit 111 Acquisition unit 112 First specific unit

[0038] 113 Detection unit 114 Second designation unit 115 First generation unit

[0039] 116 Second generation unit 117 Judgment unit 118 Conversion unit 119 Third generation unit

[0040] 120 Fourth generation unit 121 Fifth generation unit 122 Output control unit

[0041] 142 LLM for Promotion, 143 LLM for Speech Conversion, 144 Personal Information DB

[0042] 145 Nearby Commodity DB, 146 Commodity Image DB Detailed Implementation Manner

[0043] Next, reference will be made to Figures 1 to 4 to describe in detail the information processing apparatus and information processing method of the embodiment. In addition, in the embodiment described below, a store computer (SC) provided in a store (an example of a facility) such as a department store or a supermarket will be described as an example of the information processing apparatus, but the embodiment does not limit the present invention.

[0044] Figure 1 FIG. is a system diagram showing an example of the connection relationship of each device of the information processing system S according to the embodiment. In Figure 1 the system includes an SC (Store Computer) 1, a plurality of image display devices 2, a plurality of voice output devices 3, a plurality of cameras 4, and a plurality of portable terminals 6.

[0045] The SC 1, the plurality of image display devices 2, the plurality of voice output devices 3, and the plurality of cameras 4 are connected to each other via a communication line 7 such as a LAN (Local Area Network). In addition, the plurality of portable terminals 6 are connected to the SC 1 via an access point 5 as a wireless communication repeater and the communication line 7.

[0046] In addition,[[]] Figure 1 the number of each device shown in Figure 1 is an example, and the number of each device included in the information processing system S is not limited to

[0047] the number shown in

[0048] For example, the information processing system S may have a plurality of access points 5.

[0049] The image display device 2 displays a promotion image for promoting a commodity to be recommended for purchase to a customer. For example, the image display device 2 is an information processing device having a display device such as a liquid crystal display or an organic EL (Electro Luminescence) display. In addition, the image display device 2 may be the display device itself.

[0050] For example, the voice output device 3 receives the promotional voice generated by the SC1 via the communication line 7 and controls the output of the voice output device.

[0051] The SC1 generates information for promoting to customers (promotional images, promotional voices). For example, the SC1 is a server device. In addition, the SC1 can perform processes such as collecting and managing the product sales registration information received from a POS terminal (not shown). The SC1 can be composed of one server device or multiple server devices.

[0052] For example, the SC1 receives the camera images obtained by the camera 4 photographing the store interior via the communication line 7. In addition, for example, the SC1 can receive the reception results of the radio waves continuously transmitted from multiple transmitters (for example, transmitters of radio waves such as Bluetooth (registered trademark), Wi-Fi, etc.) (not shown) provided in the store from the portable terminal 6.

[0053] In addition, for example, the SC1 sends the generated promotional images to the image display device 2. In addition, for example, the SC1 sends the generated promotional voices to the voice output device 3.

[0054] The camera 4 photographs images including people in the store. For example, multiple cameras 4 are arranged at regular intervals along the ceiling near the aisle, etc., so as to be able to photograph people walking in the store.

[0055] As an example, the multiple cameras 4 arranged photograph the walking routes of people from entering the store to leaving the store. In Figure 1 In the example, n cameras 4 are arranged along the aisle in the store, and these cameras 4 photograph the person PA and the person PB. The images photographed by the camera 4 contain information indicating the shooting time and the shooting position (for example, the installation position of the camera 4 that photographed the image, etc.).

[0056] The portable terminal 6 is a device held by a customer and exchanges various information with the SC1. The portable terminal 6 is, for example, a smart phone, a tablet terminal, etc. For example, the portable terminal 6 receives radio waves from multiple transmitters provided in the store. The portable terminal 6 sends the reception results of the radio waves to the SC1 via the access point 5 and the communication line 7.

[0057] Next, the hardware structure of the SC1 will be described. Figure 2 It is a block diagram showing an example of the hardware structure of the SC1.

[0058] As Figure 2As shown in the figure, SC1 includes a CPU (Central Processing Unit) 11 as a control main body, a ROM (Read Only Memory) 12 that stores various programs, a RAM (Random Access Memory) 13 that loads various data, a memory unit 14 that stores various programs, and the like.

[0059] The CPU 11, ROM 12, RAM 13, and memory unit 14 are interconnected via a data bus 15. The CPU 11, ROM 12, and RAM 13 constitute a control unit 100. That is, the control unit 100 operates according to a control program 141 stored in the ROM 12 or memory unit 14 and loaded in the RAM 13 through the CPU 11 to perform various processes. Various processes will be described later.

[0060] In addition to loading various programs including the control program 141, the RAM 13 temporarily stores images captured by the camera 4 before storing the images captured by the camera 4 in the memory unit 14.

[0061] The memory unit 14 is a non-volatile memory such as an HDD (Hard Disc Drive) or a flash memory that retains stored information even when the power is turned off, and stores programs including the control program 141. In addition, the memory unit 14 further includes a promotion LLM 142, a voice conversion LLM 143, a personal information DB 144, a nearby product DB 145, and a product image DB 146.

[0062] The promotion LLM 142 is a generative AI that generates text and is a large language model (LLM: Large language Models). The promotion LLM 142 generates a recommendation product text that prompts products recommended for customers to purchase. In addition, although an LLM is used as the generative AI in this embodiment, the generative AI is not limited to an LLM as long as it can generate text.

[0063] For example, the recommendation product text is text data that records the names of products sold in the store and the content of promoting the products. In addition, the recommendation product text can be text data in a list form that includes the names of multiple products and the content of promoting each of the multiple products.

[0064] For example, the promotion LLM 142 is an LLM constructed using known deep learning techniques and that responds to the input of text specifying conditions and outputs text related to products based on the conditions. Here, for example, the conditions are reference conditions for searching for reference conditions used as references for deriving output results or limiting conditions for output results.

[0065] The promotion LLM 142 of this embodiment generates a recommended product text for a customer in response to the input of an inquiry text with conditions attached, such as content related to the customer's location information, customer's characteristic information, and customer's personal information. The customer location information, customer characteristic information, and customer personal information will be described later.

[0066] The speech conversion LLM 143 is a generative AI that generates text and is an LLM. The speech conversion LLM 143 generates text for promotional speech, which is text data that serves as the basis for promotional speech. For example, the text for promotional speech is text that recommends purchasing products to customers in an expression that also sounds natural when spoken orally.

[0067] For example, the speech conversion LLM 143 is an LLM constructed by known deep learning techniques that outputs text for promoting a product in response to the input of text related to the product.

[0068] The speech conversion LLM 143 of this embodiment generates text for promotional speech for a customer in response to the input of text data with content related to the customer's location information, customer's characteristic information, and customer's personal information attached.

[0069] The personal information DB (Data Base) 144 manages the personal information of customers. For example, personal information includes information of customers such as the customer's address, name, age, gender, customer ID, telephone number, email address, face image, information of the logged-in portable terminal, purchase history of products in the store, and output history of recommended product text.

[0070] As an example, the personal information DB 144 is a database that stores the customer's address, name, age, gender, customer ID, telephone number, email address, face image, identification information (terminal ID) of the logged-in portable terminal, purchase history of products in the store, and history of recommended product text associated with each customer.

[0071] The nearby products DB 145 is a database that defines products located near each position in the store. As an example, the nearby products DB 145 is a database that associates product information with each position information in the store and stores it. Additionally, multiple product information can be associated with one position information. Furthermore, the same product information can be associated with different position information.

[0072] The product image DB 146 is a database that manages images of products. As an example, the product image DB 146 is a database that stores, in association with each product, the product ID, the product name, and the product image. Additionally, the product image may include information obtained by converting product-related information such as text introducing the product into an image. Furthermore, the product image may be multiple images taken of the product from various angles.

[0073] Furthermore, the operation unit 17 and the display unit 18 are connected to the data bus 15 via the controller 16.

[0074] The operation unit 17 accepts various inputs from an operator such as a store clerk. For example, the operation unit 17 includes numeric keys for inputting numbers, various function keys, and the like.

[0075] The display unit 18 displays various information. For example, the display unit 18 can display an image of the interior of the store input from the camera 4. Additionally, the display unit 18 can display an image taken by a specified camera 4. Furthermore, the display unit 18 can divide the screen and display images taken by multiple cameras 4 on the same screen at once.

[0076] Additionally, the data bus 15 is connected to a communication I / F 19 such as a LAN I / F (Interface). The communication I / F 19 is connected to the communication line 7.

[0077] The communication I / F 19 transmits and receives various information. For example, the communication I / F 19 receives in real time the images taken by the camera 4.

[0078] Next, the functional structure of the SC1 will be described. Figure 3 is a functional block diagram showing an example of the functional structure of the SC1. The control unit 100 functions as the LLM preprocessing unit 101, the LLM processing unit 102, and the LLM postprocessing unit 103 by operating in accordance with various programs including the control program 141 stored in the ROM 12 and the memory unit 14.

[0079] First, the LLM preprocessing unit 101 will be described. The LLM preprocessing unit 101 performs LLM preprocessing. For example, the LLM preprocessing is a series of processes before the process of inputting an inquiry text to the promotion LLM 142 becomes executable in the process of generating promotion information using the promotion LLM 142.

[0080] As Figure 3 shown, the LLM preprocessing unit 101 includes an acquisition unit 111, a first specifying unit 112, a detection unit 113, a second specifying unit 114, and a first generation unit 115.

[0081] The acquisition unit 111 acquires the camera image captured by the camera 4. For example, the acquisition unit 111 acquires the camera image by receiving in real time the camera images from a plurality of cameras 4 via the communication line 7. The acquisition unit 111 sends the acquired camera image to the first specifying unit 112, the detection unit 113, and the second specifying unit 114.

[0082] The first specifying unit 112 specifies the personal information of the customer. For example, a known image recognition technique is used to extract the face image of the customer from the camera image sent by the acquisition unit 111. The first specifying unit 112 refers to the personal information DB144 stored in the memory unit 14, and designates the address, name, age, gender, customer ID, telephone number, e-mail address, purchase history of products in the store, and output history of recommended product texts corresponding to the extracted face image as the personal information of the customer corresponding to the face image.

[0083] In addition, the first specifying unit 112 associates the specified customer ID with the extracted face image and sends it to the detection unit 113. In addition, the first specifying unit 112 associates the specified customer ID with the information of the registered portable terminal and sends it to the second specifying unit 114.

[0084] In addition, the first specifying unit 112 associates the specified customer ID with the specified personal information and sends it to the first generation unit 115 and the determination unit 117. The personal information sent to the first generation unit 115 and the determination unit 117 may be a part of the specified personal information. In addition, the types of personal information sent to the first generation unit 115 and the types of personal information sent to the determination unit 117 may be different.

[0085] Here, it can be said that the first specifying unit 112 specifies the purchase history of products of the customer in the store, so it can be said that the first specifying unit 112 is an example of the second acquisition unit.

[0086] The detection unit 113 detects the characteristic information of the customer reflected in the camera image. For example, the characteristic information is information indicating the appearance characteristics of the customer. Specifically, it is information indicating the customer's clothing (for example, wearing a white sweater of ○○ brand and black trousers of XX brand, etc.). In addition, the characteristic information may include information about the customer's mood inferred from the customer's expression, etc., such as happy, angry, sad, happy, etc.

[0087] For example, the detection unit 113 designates a customer corresponding to the face image transmitted by the first designation unit 112 from the camera image transmitted by the acquisition unit 111. The detection unit 113 extracts the appearance features of the designated customer through known image recognition techniques. The detection unit 113 transmits the extracted features as the customer's feature information to the first generation unit 115 and the determination unit 117 in association with the customer ID associated with the face image transmitted from the first designation unit 112.

[0088] The second designation unit 114 designates the position information of the customer. For example, the position information is information indicating the position of the customer in the store. For example, the second designation unit 114 receives the reception result of the radio wave from the portable terminal 6 existing in the store via the communication line 7. Here, it is assumed that the terminal ID is associated with the reception result of this radio wave.

[0089] For example, the second designation unit 114 confirms the terminal ID associated with the reception result of the received radio wave and designates the reception result of the radio wave associated with the terminal ID that matches the terminal ID transmitted from the first designation unit 112. In addition, the second designation unit 114 designates the position of the portable terminal 6 identified by the terminal ID based on the information included in the reception result of the radio wave, which indicates the degree of intensity at which the radio wave from which transmitter in the store is received.

[0090] The second designation unit 114 transmits the information indicating the position of the designated portable terminal 6 as the customer's position information to the first generation unit 115 and the determination unit 117 corresponding to the customer ID associated with the terminal ID transmitted from the first designation unit 112.

[0091] Here, it is assumed that the customer position information transmitted to the first generation unit 115 and the determination unit 117 includes information indicating the reception time of the radio wave included in the reception result of the radio wave of the portable terminal 6 corresponding to this position information (hereinafter also referred to as the time of the position information). Accordingly, the customer's position information transmitted to the first generation unit 115 and the determination unit 117 can specify the position information of the customer at which time.

[0092] Incidentally, there are not only cases where customers may not necessarily enter the store with the portable terminal 6, but also cases where the portable terminal 6 may not be able to receive radio waves from the transmitters installed in the store for some reason. Therefore, in the case where the reception result of the radio wave of the portable terminal 6 corresponding to the terminal ID transmitted from the first designation unit 112 cannot be obtained or the position of the portable terminal 6 cannot be accurately designated, the second designation unit 114 designates the customer's position information based on the camera image.

[0093] For example, when the reception result of the radio wave of the portable terminal 6 corresponding to the terminal ID transmitted from the first specifying unit 112 cannot be obtained, the second specifying unit 114 requests the first specifying unit 112 to transmit the customer ID associated with the terminal ID, and transmits the face image corresponding to the customer ID. The first specifying unit 112 that has received the request associates the customer ID with the face image corresponding to the customer ID and transmits the same to the second specifying unit 114.

[0094] The second specifying unit 114 retrieves a plurality of camera images transmitted from the acquisition unit 111, and specifies the camera image in which the customer corresponding to the face image transmitted from the first specifying unit 112 is captured. The second specifying unit 114 specifies the position of the customer corresponding to the face image transmitted from the first specifying unit 112 based on the information indicating the imaging position included in the specified camera image.

[0095] In addition, when the customer corresponding to the face image transmitted from the first specifying unit 112 is reflected in a plurality of camera images, the second specifying unit 114 refers to the information indicating the imaging time included in the camera image, and specifies the position of the customer corresponding to the face image transmitted from the first specifying unit 112 from the information indicating the imaging position included in the latest camera image. In addition, in this case, it is assumed that the time of the position information is the imaging time of the latest camera image.

[0096] The first generation unit 115 generates an inquiry text based on the characteristic information of the customer. The inquiry text is instruction information (prompt) indicating the content of the text generated by the generation AI. Hereinafter, the content indicated by the instruction information is also referred to as the instruction content.

[0097] For example, the first generation unit 115 generates an inquiry text that describes instructing the promotion LLM 142 to generate a text including a product name and the content of promoting the product, and at the same time indicates that the recommended product is a product sold in the store and the recommended product is a product derived from the conditions based on the processing results of the first specifying unit 112, the detection unit 113, and the second specifying unit 114.

[0098] Here, templates for generating instruction information are stored in advance in the memory unit 14 or the like. In addition, a plurality of templates can be stored in the memory unit 14 or the like. In this case, the first generation unit 115 can selectively use a plurality of templates according to the situation. For example, the first generation unit 115 switches the template according to the keyword included in the inquiry text (for example, a word that can distinguish the category of the product (food, clothing, etc.)).

[0099] In addition, the first generation unit 115 attaches text data to the inquiry text based on the conditions specified by the instruction content and based on the processing of the first specifying unit 112, the detection unit 113, and the second specifying unit 114.

[0100] For example, the first generation unit 115 attaches text data including information associated with the customer ID sent from the first specifying unit 112, the detection unit 113, and the second specifying unit 114 as a condition to the inquiry text. Here, since each piece of information is associated with the customer ID, it is possible to prevent the information of other customers from being mixed into the inquiry text.

[0101] Specifically, the first generation unit 115 attaches the text data as a condition to the inquiry text, where the text data includes a description related to the customer's location information, product information of products existing near the customer, a description related to the customer's characteristic information, a description related to the purchase history of the customer's products, and a description related to the output history of the recommended product text.

[0102] As an example, based on the personal information of the customer sent from the first specifying unit 112 and the location information of the customer sent from the second specifying unit 114, the first generation unit 115, as a description related to the customer's location information, attaches text data such as "A (customer's name) in front of the shelf in the lingerie section" as a condition to the inquiry text.

[0103] In addition, the first generation unit 115 refers to the nearby product DB 145 and specifies product information corresponding to the location information of the customer sent from the second specifying unit 114. In this case, it can be said that the first generation unit 115 cooperates with the second specifying unit 114 to specify nearby products, so the second specifying unit 114 and the first generation unit 115 can be said to be an example of the second specifying unit.

[0104] The first generation unit 115 attaches text data stating the product name included in the specified product information as a condition to the inquiry text as the product information of the products existing near the customer.

[0105] In addition, based on the personal information of the customer sent from the first specifying unit 112 and the characteristic information of the customer sent from the detection unit 113, the first generation unit 115, as a description related to the customer characteristic information, attaches text data such as "A is wearing a white sweater of XX brand and black trousers of XX brand" as a condition to the inquiry text.

[0106] In addition, based on the personal information of the customer sent from the first specifying unit 112, the first generation unit 115, as a description related to the purchase history of the customer's products, attaches text data such as "A purchased a shirt with product code XX on △ month □ day" as a condition to the inquiry text.

[0107] In the inquiry text, it is a condition to include a record related to the customer's purchase history of goods, and an instruction meaning not to output the purchased goods is added to the instruction content, so as to prevent the situation of recommending to the customer to purchase the goods that the customer has already purchased.

[0108] In addition, based on the personal information of the customer sent from the first specifying unit 112, the first generation unit 115 adds text data such as "has recommended to A to purchase a shirt with product code YY ○ times" as a condition to the inquiry text as a record related to the output history of the recommended product text.

[0109] In the inquiry text, it is a condition to include a record related to the output history of the recommended product text, and by adding an instruction meaning not to output the goods that have not been purchased even after being recommended to purchase a specified number of times to the instruction content, it is possible to prevent the situation of recommending to the customer the goods that have not been purchased even after being recommended to purchase multiple times (goods considered to be of no interest to the customer).

[0110] The first generation unit 115 associates the generated inquiry text with the customer ID corresponding to the inquiry text and sends it to the second generation unit 116. Here, it is assumed that the inquiry text sent to the second generation unit 116 includes the time of the customer location information on which the generated inquiry text is based (hereinafter also referred to as the inquiry time).

[0111] Next, the LLM processing unit 102 will be described. The LLM processing unit 102 performs LLM processing. LLM processing is a process of inputting text to the LLM and obtaining the text output from the LLM. As Figure 3 shown, the LLM processing unit 102 includes a second generation unit 116 and a fourth generation unit 120. The fourth generation unit 120 will be described later.

[0112] The second generation unit 116 generates a recommended product text based on the inquiry text. The recommended product text is an example of the second text information. For example, the second generation unit 116 inputs the inquiry text sent from the first generation unit 115 into the promotion LLM 142 stored in the memory unit 14. The second generation unit 116 obtains the text data output from the promotion LLM 142 as the recommended product text.

[0113] In addition, the second generation unit 116 sends the obtained recommended product text to the judgment unit 117. Here, it is assumed that the recommended product text sent to the judgment unit 117 includes the inquiry time of the inquiry text sent from the first generation unit 115.

[0114] In addition, the second generation unit 116 refers to the personal information DB 144 to specify the output history of the recommended product text corresponding to the customer ID sent in association with the inquiry text from the first generation unit 115. The second generation unit 116 performs a process of adding the obtained recommended product text to the specified output history of the recommended product text.

[0115] In addition, the second generation unit 116 may execute part or all of the processing of the first generation unit 115 described above. Moreover, the first generation unit 115 may execute part or all of the processing of the second generation unit 116.

[0116] Next, the LLM post-processing unit 103 will be described. The LLM post-processing unit 103 performs LLM post-processing. For example, the LLM post-processing is a process performed on the recommended product text generated by the second generation unit 116 (promotion LLM 142) in order to generate promotion information during the process of generating promotion information using the promotion LLM 142.

[0117] As Figure 3 shown, the LLM post-processing unit 103 includes a determination unit 117, a conversion unit 118, a third generation unit 119, a fifth generation unit 121, and an output control unit 122.

[0118] The determination unit 117 makes determinations related to the output of promotion information. For example, the determination unit 117 determines whether to output promotion information based on the location information of the customer sent from the second specifying unit 114. As an example, when the location information of the customer has not changed after a specified time, the determination unit 117 determines to output promotion information.

[0119] In addition, the determination unit 117 may regard a movement within a specified range (for example, the customer's movement within a radius of ○ meters of the location information) as no movement and determine the change in the customer's location information.

[0120] Moreover, when the determination unit 117 determines that promotion information is to be output, it determines whether a re-inquiry is required. For example, the determination unit 117 compares the latest customer location information sent from the second specifying unit 114 with the customer location information at the time of inquiry. If the two match, it determines that a re-inquiry is not required, and if they do not match, it determines that a re-inquiry is required.

[0121] In addition, the determination unit 117 may regard a change in location information within a specified range (for example, a change within a radius of ○ meters of the customer's location information) as a match between the two location information and determine whether a re-inquiry is required.

[0122] When the determination unit 117 determines that a re-inquiry is required, it sends a re-inquiry request to the first generation unit 115. In addition, when the determination unit 117 determines not to output promotional information, it also sends a re-inquiry request in the same manner as described above. The first generation unit 115 that receives the re-inquiry request generates an inquiry text based on the latest location information, feature information, and personal information, and sends it to the second generation unit 116.

[0123] In addition, when the determination unit 117 determines that promotional information is to be output and determines that a re-inquiry is not required, it determines the output destination of the promotional information. For example, for each of the image display device 2 and the voice output device 3, the determination unit 117 designates the device (image display device 2 or voice output device 3) closest to the latest customer location information sent from the second designation unit 114.

[0124] In addition, the determination unit 117 determines the device among the designated image display device 2 and voice output device 3 that is closer to the customer's location information as the output destination of the promotional information. In addition, the determination unit 117 determines whether another device exists within the specified range of the latest customer location information. If it exists within the specified range, the determination unit 117 determines that the other device is also the output destination of the promotional information.

[0125] In addition, when the image display device 2 is included in the devices determined to be the output destination, the determination unit 117 sends the recommended product text sent from the second generation unit 116 to the conversion unit 118. Here, it is assumed that the recommended product text sent to the conversion unit 118 is associated with the information of the image display device 2 designated as the output destination (hereinafter also referred to as image display device information).

[0126] In addition, when the voice output device 3 is included in the devices determined to be the output destination, the determination unit 117 sends the recommended product text sent from the second generation unit 116 to the third generation unit 119. Here, it is assumed that the recommended product text sent to the third generation unit 119 is associated with the information of the voice output device 3 designated as the output destination (hereinafter also referred to as voice output device information).

[0127] In addition, it is assumed that the recommended product text sent to the third generation unit 119 is associated with the personal information, feature information, and location information of the customer corresponding to the recommended product text.

[0128] In addition, the determination unit 117 may determine both the image display device 2 closest to the latest customer location information sent from the second designation unit 114 and the voice output device 3 closest to the latest customer location information as the output destination, regardless of the distance from the latest customer location information.

[0129] The conversion unit 118 converts the recommended product text into a promotional image including the product image of the recommended product. The converter 118 is an example of the third generation unit.

[0130] For example, the conversion unit 118 refers to the product image DB 146 to specify a product image corresponding to the name of the product included in the recommended product text sent from the determination unit 117. The conversion unit 118 converts the recommended product text into the specified product image. Then, the conversion unit 118 arranges the converted product image according to a predetermined template and generates a promotional image.

[0131] In addition, the conversion unit 118 associates the generated promotional image with the image display device information and sends it to the output control unit 122.

[0132] The third generation unit 119 generates text for voice conversion based on the recommended product text. Here, the text for voice conversion is instruction information for instructing the voice conversion LLM 143 to generate text.

[0133] For example, the third generation unit 119 generates text for voice conversion that records content instructing the voice conversion LLM 143 to convert the expression of the recommended product text sent from the determination unit 117 into an expression that does not cause disharmony when generated as voice.

[0134] Here, the template for generating the instruction information is stored in advance in the memory unit 14 or the like. In addition, multiple templates can be stored in the memory unit 14 or the like. In this case, the third generation unit 119 can selectively use multiple templates according to the situation. For example, the third generation unit 119 switches templates according to keywords (such as words for male, female, etc.) included in the text for voice conversion.

[0135] In this embodiment, the instruction content of the text for voice conversion includes an instruction to convert the expression of the text that attaches information about the customer (such as the customer's current location, appearance characteristics, previously purchased products, etc.) based on the record related to the customer's location information, the record related to the customer's characteristic information, and the record related to the customer's personal information in the recommended product text into an expression that does not cause disharmony when generated as voice.

[0136] Specifically, the third generation unit 119 attaches text data including the record related to the customer's location information, the record related to the customer's characteristic information, and the record related to the customer's personal information to the text for voice conversion.

[0137] As an example, based on the customer's personal information and the customer's location information sent from the determination unit 117, the third generation unit 119 attaches text data recorded as "Customer A is shopping in the lingerie section" or the like as the record related to the customer's location information to the text for voice conversion.

[0138] In addition, based on the customer's personal information and characteristic information sent from the determination unit 117, the third generation unit 119 attaches text data such as "Customer A wearing a white sweater of brand ○○" to the text for speech conversion as an entry related to the customer's characteristic information.

[0139] In addition, based on the customer personal information sent from the determination unit 117, the third generation unit 119 attaches text data such as "Customer A purchased a shirt with product code XX on △ month □ day" to the text for speech conversion as an entry related to the customer's personal information.

[0140] In addition, the instruction content of the text for speech conversion may include instructing the output order of each element included in the text of the designated recommended product (for example, the introduction order when there are multiple recommended products, etc.), and summarizing the content of the text of the recommended product output.

[0141] In addition, the third generation unit 119 associates the generated text for speech conversion with the voice output device information and sends it to the fourth generation unit 120.

[0142] Next, the fourth generation unit 120 of the LLM processing unit 102 will be described. The fourth generation unit 120 generates text for promotional voice. The fourth generation unit 120 is an example of the third generation unit. The text for promotional voice is text related to the recommended product that can be generated into voice without a sense of disharmony.

[0143] For example, the fourth generation unit 120 inputs the text for speech conversion sent from the third generation unit 119 into the speech conversion LLM 143 stored in the memory unit 14. The fourth generation unit 120 obtains the text data output from the speech conversion LLM 143 as the text for promotional voice.

[0144] In addition, the fourth generation unit 120 associates the generated text for promotional voice with the voice output device information and sends it to the fifth generation unit 121.

[0145] Next, the fifth generation unit 121 of the LLM post-processing unit 103 will be described. The fifth generation unit 121 generates promotional voice. The fifth generation unit 121 is an example of the third generation unit. For example, the fifth generation unit 121 converts the text for promotional voice sent from the fourth generation unit 120 into voice data by a known technique of converting text into voice, and generates promotional voice.

[0146] In addition, the fifth generation unit 121 associates the generated promotional voice with the voice output device information and sends it to the output control unit 122.

[0147] In addition, the fifth generation unit 121 may execute part or all of the processing of the above-mentioned fourth generation unit 120. Furthermore, the fourth generation unit 120 may execute part or all of the processing of the fifth generation unit 121.

[0148] The output control unit 122 outputs promotional information.

[0149] For example, the output control unit 122 sends the promotional image sent from the conversion unit 118 to the image display device 2 specified by the image display device information associated with the promotional image via the communication line 7. The image display device 2 displays the received promotional image on the display device.

[0150] In addition, the output control unit 122 sends the promotional voice sent from the fifth generation unit 121 to the voice output device 3 specified by the voice output device information associated with the promotional voice via the communication line 7. The voice output device 3 causes the voice output device to output the received promotional sound.

[0151] Next, Figure 4 is used to illustrate the processing executed by SC1. Figure 4 is a flowchart showing an example of the processing executed by SC1.

[0152] First, the acquisition unit 111 acquires a camera image (step S1). For example, the acquisition unit 111 acquires a camera image by receiving in real time the camera images from each of the multiple cameras 4 via the communication line 7.

[0153] In addition, although Figure 4 records the process of acquiring the camera image as step S1, it is assumed that the process of acquiring the camera image is continuously executed.

[0154] Next, the first specifying unit 112 specifies the personal information of the customer (step S2). For example, the first specifying unit 112 uses known image recognition technology to extract the face image of the customer from the camera image acquired in step S1. The first specifying unit 112 refers to the personal information DB144 stored in the memory unit 14 to specify the information corresponding to the extracted face image as the personal information.

[0155] In addition, although Figure 4 records the process of specifying the personal information of the customer as step S2, it is assumed that the process of specifying the personal information of the customer continues.

[0156] Next, the detection unit 113 detects the characteristic information of the customer (step S3). For example, the detection unit 113 specifies the customer corresponding to the face image extracted in step S2 from the customers shown in the camera image acquired in step S1, and uses known image recognition technology to detect the characteristics of the appearance of the customer.

[0157] In addition, although in Figure 4 the process of detecting the characteristic information of the customer is described as step S3, it is assumed that the process of detecting the characteristic information of the customer is continuously performed.

[0158] Next, the second specifying unit 114 specifies the position information of the customer (step S4). For example, the second specifying unit 114 receives, via the communication line 7 from the portable terminal 6, the reception result of the radio wave including the terminal ID (including the terminal ID of the portable terminal 6).

[0159] The second specifying unit 114 specifies the position of the portable terminal 6 in the store based on the reception result, which includes the terminal ID of the portable terminal 6 of the customer included in the personal information of the customer specified in step S2. The second specifying unit 114 designates the specified position of the portable terminal 6 as the position information of the customer.

[0160] In addition, although in Figure 4 the process of specifying the position information of the customer is described as step S4, it is assumed that the process of specifying the position information of the customer is continuously performed.

[0161] Next, the first generation unit 115 generates an inquiry text (step S5). For example, the first generation unit 115 generates an inquiry text that instructs to generate a text related to a certain product processed in the store with conditions attached, including the description related to the customer personal information specified in step S2, the description related to the characteristic information of the customer detected in step S3, and the description related to the position information of the customer specified in step S4.

[0162] Next, the second generation unit 116 generates a recommended product text (step S6). For example, the second generation unit 116 inputs the inquiry text generated in step S5 to the promotion LLM 142 stored in the memory unit 14. The second generation unit 116 obtains the text data output from the promotion LLM 142 as the recommended product text.

[0163] Next, the determination unit 117 determines whether to output promotion information (step S7).

[0164] For example, when the position information of the customer continuously specified in step S4 does not change within a predetermined time, the determination unit 117 determines to output promotion information. On the other hand, when the position information of the customer changes, the determination unit 117 determines not to output promotion information. In the case where it is determined not to output promotion information (step S7: No), the process proceeds to step S9, which will be described later.

[0165] On the other hand, when it is determined that promotional information is to be output (step S7: Yes), the determination unit 117 determines whether a re-inquiry is required (step S8).

[0166] For example, the determination unit 117 compares the position information of the customer corresponding to the inquiry text generated in step S5 with the latest position information, and determines that a re-inquiry is required when the two do not match. On the other hand, when the two match, the determination unit 117 determines that a re-inquiry is not required.

[0167] When it is determined that a re-inquiry is required (step S8: Yes), the determination unit 117 sends a re-inquiry request to the first generation unit 115 (step S9), and transitions to the process of step S5. The first generation unit 115 that receives the re-inquiry request performs the process of step S5 based on the latest customer personal information, characteristic information, and position information obtained in the continuously executed processes of steps S1 to S4.

[0168] On the other hand, when it is determined that a re-inquiry is not required (step S8: No), the determination unit 117 determines whether the image display device 2 is included in the output destination (step S10).

[0169] For example, when the image display device 2 closest to the latest customer position information specified in step S4 is closer to the latest customer position information than the voice output device 3 closest to the latest customer position information, the determination unit 117 determines that the image display device 2 is included in the output destination.

[0170] In addition, even when the voice output device 3 is closer to the latest customer position information, if the image display device 2 closest to the latest customer position information is within a predetermined range of the latest customer's position information, the determination unit 117 determines that the image display device 2 is included in the output destination. When the image display device 2 is not included in the output destination (step S10: No), the process transitions to step S13, which will be described later.

[0171] On the other hand, when the output destination includes the image display device 2 (step S10: Yes), the conversion unit 118 converts the recommended product text into a promotional image (step S11).

[0172] For example, the conversion unit 118 refers to the product image DB146 stored in the memory unit 14 to specify the product image corresponding to the product name included in the recommended product text. The conversion unit 118 generates a promotional image by converting the recommended product text into the specified product image and configuring the converted image according to the template.

[0173] Next, the output control unit 122 sends the promotion image to the image display device 2 (step S12). For example, the output control unit 122 sends the promotion image converted in step S11 to the image display device 2 closest to the latest customer location information specified in step S4 via the communication line 7.

[0174] Next, the determination unit 117 determines whether the voice output device 3 is included in the output destination (step S13).

[0175] For example, when the voice output device 3 closest to the latest customer location information specified in step S4 is closer to the latest customer location information than the image display device 2 closest to the latest customer location information, the determination unit 117 determines that the voice output device 3 is included in the output destination.

[0176] In addition, even when the image display device 2 is near the latest customer location information, if the voice output device 3 closest to the latest customer location information is within the specified range of the latest customer location information, the determination unit 117 determines that the voice output device 3 is included in the output destination. When the voice output device 3 is not included in the output destination (step S13: No), this process ends.

[0177] On the other hand, when the voice output device 3 is included in the output destination (step S13: Yes), the third generation unit 119 generates text for voice conversion (step S14).

[0178] For example, the third generation unit 119 generates text for voice conversion that instructs to generate text related to the promotion of the product, which is added to the recommended product text generated in step S6 and includes descriptions based on the customer's personal information, customer characteristic information, and customer location information corresponding to the product text.

[0179] Next, the fourth generation unit 120 generates text for promotion voice (step S15).

[0180] For example, the fourth generation unit 120 inputs the text for voice conversion generated in step S15 to the voice conversion LLM 143 stored in the memory unit 14. The third generation unit 119 obtains the text data output from the voice conversion LLM 143 as the text for promotion voice.

[0181] Next, the fifth generation unit 121 generates a promotion voice (step S16). For example, the fifth generation unit 121 converts the text for promotion voice generated (obtained) in step S15 into voice data by a known technique of converting text data into voice data, and generates a promotion voice.

[0182] Next, the output control unit 122 sends the promotional voice to the voice output device 3 (step S17). For example, the output control unit 122 sends the promotional voice generated in step S16 to the voice output device 3 closest to the latest customer position information specified in step S4 via the communication line 7.

[0183] In addition, although the process of step S13 is described as the process after step S12 in Figure 4 , the process of step S13 can be executed in parallel with step S10. In addition, the process of step S13 can also be performed after the process of step S8 and before step S10.

[0184] As described above, the SC1 according to the present embodiment acquires a camera image from a camera provided in a facility, detects customer features reflected in the camera image, generates a recommended product text by inputting an inquiry text representing the detected customer features to the promotional LLM 142, and outputs information based on the recommended product text. The promotional LLM 142 outputs a text related to products sold in the store according to the input of an inquiry text including human features.

[0185] Accordingly, the SC1 according to the present embodiment can generate an inquiry text incorporating the detected customer features. By inputting the inquiry text incorporating customer features to the promotional LM 142 and generating a recommended product text, it is possible to generate a recommended product text more suitable for the customer. That is, according to the SC1 according to the present embodiment, the convenience of promoting customers using generative AI can be improved.

[0186] In addition, the SC1 according to the present embodiment generates an inquiry text with a condition of adding a description of the customer's appearance features. Accordingly, the SC1 according to the present embodiment can generate a recommended product text incorporating the customer's current clothing, the mood inferred from the customer's expression, etc.

[0187] In addition, the SC1 according to the present embodiment designates a customer from the camera image, designates the customer's product purchase history from the personal information DB 144 including the product purchase history, and generates an inquiry text with a condition of adding a description related to the designated product purchase history. Accordingly, the SC1 according to the present embodiment can prevent the situation of recommending products that the customer has already purchased.

[0188] In addition, the SC1 according to the present embodiment designates the customer's position information in the store, designates the product information of products located near the designated position information from the designated position information, and generates an inquiry text with a condition of adding a description related to the designated product information. Accordingly, the SC1 according to the present embodiment can recommend purchasing products near the customer's current position.

[0189] In addition, the SC1 according to this embodiment converts the recommended product text into a product image based on the recommended product text including the name of the product and the product image DB146 that associates the product name with the product image, and generates a promotional image for output to the image display device 2 including the product image. Accordingly, it becomes easier for customers to understand what product is recommended for purchase. That is, the SC1 according to this embodiment can conduct promotions in a form that is visually easy for customers to understand.

[0190] In addition, the SC1 according to this embodiment converts the promotional product text into a promotional voice file by using the recommended product text including the name of the product and the speech conversion LLM143 that converts the recommended product text into a promotional speech text without a sense of disharmony, and converts the promotional speech text into voice data, thereby generating a promotional voice for output to the voice output device 3. Accordingly, customers can understand the product recommended for purchase even when they cannot confirm the product image. That is, the SC1 according to this embodiment can conduct promotions in a form that is aurally easy for customers to understand.

[0191] In addition, when the change in the customer location information within a specified time is within a specified range, the SC1 according to this embodiment outputs the promotional information to the output device. Here, the case where the location information does not change (is less) means that the customer is staying at the location indicated by the location information. In addition, the case of staying mostly indicates an interest in the place. That is, the SC1 according to this embodiment can prevent the situation of recommending products that are not interesting to customers by outputting promotional information related to the location information only when the location information does not change (is less).

[0192] In addition, the SC1 according to this embodiment outputs the promotional information to the output device close to the current location information of the customer. Accordingly, the SC1 according to this embodiment can prevent the situation of outputting promotional information in a form that cannot be conveyed to the customer.

[0193] Furthermore, the above-described embodiment can be appropriately modified by changing a part of the structure or function of the SC1. Therefore, several modification examples related to the above-described embodiment will be described as other embodiments below. In addition, the points different from the above-described embodiment will be mainly described below, and the detailed description of the common points that have already been described will be omitted. Moreover, the modification examples described below can be implemented alone or in appropriate combination.

[0194] (Modification Example 1)

[0195] In the above-described embodiment, the form in which SC1 includes the promotion LLM 142 and the speech conversion LLM 143 has been described. In the present embodiment, a form in which server devices other than SC1 include the promotion LLM 142 and the speech conversion LLM 143 will be described.

[0196] In this modification, the server device (hereinafter also simply referred to as the server device) including the promotion LLM 142 and the speech conversion LLM 143 is installed in the store in the same manner as SC1. Additionally, the server device can be installed outside the store, but since information including customer personal information is input to the promotion LLM 142 and the speech conversion LLM 143, it is preferably installed in a place where people unrelated to the store are not easily accessible when the server device is installed outside the store.

[0197] The second generation unit 116 of this modification sends the inquiry text sent from the first generation unit 115 to the server device via the communication line 7. The server device inputs the received inquiry text into the promotion LLM 142. The server device sends the recommended product text output from the promotion LLM 142 to SC1. The second generation unit 116 sends the recommended product text sent from the server device to the determination unit 117.

[0198] Furthermore, the fourth generation unit 120 sends the speech conversion text generated by the third generation unit 119 to the server device via the communication line 7. The server device inputs the received speech conversion text into the speech conversion LLM 143. The server device sends the promotional speech text output from the speech conversion LLM 143 to SC1. The fifth generation unit 121 converts the promotional speech text sent from the server device into a promotional speech.

[0199] In addition, in the above, the same server device includes the promotion LLM 142 and the speech conversion LLM 143, but the server device including the promotion LLM 142 and the server device including the speech conversion LLM 143 can be separately provided server devices.

[0200] According to this modification, the processing load on SC1 can be reduced.

[0201] (Modification 2)

[0202] In the above-described embodiment, the form in which the information processing system S includes both the image display device 2 and the voice output device 3 has been described. However, the information processing system S can include only one of the image display device 2 and the voice output device 3.

[0203] According to this modification, for example, it is possible to promote sales to customers using only the output device according to the situation of the store.

[0204] (Third Modified Example)

[0205] In the above-described embodiment, the form in which the merchandise purchase history of the customer is stored in the personal information DB144 in the memory unit 14 of the SC1 has been described. In this modified example, the form in which the merchandise purchase history of the customer is stored in the customer's portable terminal 6 will be described.

[0206] In this modified example, the first specifying unit 112 specifies the terminal ID of the customer's portable terminal 6 from the personal information DB144. The first specifying unit 112 acquires the purchase history of the customer's merchandise from the portable terminal 6 identified by the specified terminal ID via the access point 5 and the communication line 7.

[0207] According to this modified example, the amount of information stored in the personal information DB144 in the memory unit 14 of the SC1 can be reduced.

[0208] (Fourth Modified Example)

[0209] In the above-described embodiment, the form in which the SC1 converts the recommended merchandise text into image data or voice data and outputs it has been described. However, the SC1 may also directly output the recommended merchandise text to the display device in the form of text data.

[0210] According to this modified example, since the recommended merchandise text can be displayed even on a simple display device that can only display characters, merchandise promotion can be carried out at low cost.

[0211] In addition, the program executed by the SC1 of the above-described embodiment is stored in a computer-readable storage medium such as a CD-ROM, a floppy disk (FD), a CD-R, a DVD (Digital Versatile Disk), etc. in an installable form or an executable form and provided.

[0212] Furthermore, the program executed by the SC1 of the above-described embodiment can be configured to be stored in a computer connected to a network such as the Internet, and can be provided by downloading via the network. In addition, the program executed by the SC1 of the embodiment can be configured to be provided or distributed via a network such as the Internet.

[0213] In addition, the program executed by the SC1 of the embodiment can be configured to be pre-installed in the ROM 12 or the like and provided.

[0214] Thus far, although several embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other ways, and various omissions, substitutions, changes, and combinations can be made without departing from the gist of the invention. These embodiments and their modifications are included within the scope and gist of the invention and are included within the invention described in the claims and its equivalents.

Claims

1. An information processing apparatus, characterized in that, Comprising: An acquisition unit that acquires a camera image captured by a camera provided in a facility from the camera; A detection unit that detects characteristics of a customer reflected in the camera image; A first generation unit that generates first text information representing the characteristics of the customer based on the detected characteristics; A second generation unit that inputs an inquiry text appended with the first text information to a generation AI, and generates second text information related to the promotion of a product based on the text generated by the generation AI, wherein the generation AI generates the text related to the products sold in the facility according to the input of the inquiry text; And An output control unit that outputs the second text information.

2. The information processing apparatus according to claim 1, wherein The detection unit detects characteristics on the appearance of the customer, The first generation unit generates the first text information representing the detected characteristics on the appearance of the customer, The second generation unit inputs the inquiry text to a first large language model as the generation AI, and obtains the text output by the first large language model as the second text information, wherein the generation AI has a function of corresponding to the input of the text specifying conditions, and outputting text related to products based on the conditions, and the inquiry text appends a description related to the characteristics on the appearance as the condition.

3. The information processing apparatus according to claim 2, wherein Further comprising: A second acquisition unit that acquires the purchase history of the customer corresponding to the detected characteristics, wherein the second generation unit inputs the inquiry text appended with a description related to the acquired purchase history as the condition to the first large language model, and obtains the text output by the first large language model as the second text information.

4. The information processing apparatus according to claim 3, wherein The second acquisition unit acquires the purchase history from a database that associates the characteristics of each customer with the purchase history of the customer or from a portable terminal carried by the customer.

5. The information processing apparatus according to claim 2, wherein, Further comprising: A second specifying unit that specifies nearby products in the vicinity of the customer based on position information indicating the position of the customer in the facility, wherein The second generation unit inputs the inquiry text appended with a description related to the specified nearby products as the condition to the first large language model, and obtains the text output by the first large language model as the second text information.

6. The information processing apparatus according to claim 5, wherein, Further comprising: A third generation unit that generates a promotion information that converts the content represented by the second text information into data including at least one of image data and voice data, wherein The output control unit outputs the generated promotion information to an output device.

7. The information processing apparatus according to claim 6, wherein The third generation unit inputs the second text information to a second large language model as the generation AI, and generates the promotion information by converting the text output by the second large language model into voice data, wherein the generation AI has a function of corresponding to the input of text related to products and outputting text for promoting the products.

8. The information processing apparatus according to claim 6, wherein the third generation unit reads the image data corresponding to the name of the product included in the second text information from a product image database that associates the name of each product with the image data of the product, and generates the promotion information based on the read image data and the second text information.

9. The information processing apparatus according to claim 6, wherein the output control unit outputs the promotion information to the output device when the change in the location information of the customer within a specified time is within a specified range.

10. The information processing apparatus according to claim 6, wherein the output control unit outputs the promotion information to the output device closest to the latest location information of the customer.

11. An information processing method, which is an information processing method based on an information processing apparatus, and includes the following steps: acquiring a camera image captured by a camera provided in a facility; detecting features of a customer reflected in the camera image; generating first text information representing the features of the customer based on the detected features; Input the inquiry text appended with the first text information into the generative AI, and generate second text information related to the promotion of the product based on the text generated by the generative AI, where the generation AI generates the text related to the products sold in the facility according to the input of the inquiry text; and outputting the second text information.

Images