system

Abstract

We provide the system. [Solution] A means of creating questions to present to the purchaser based on product-related information using a generating device, A means of displaying the aforementioned question to the purchaser using the device provided, A means for receiving and evaluating the purchaser's response using a verification device, A means of granting purchase rights to a purchaser whose answer is evaluated as correct using a device that grants purchase rights, A system that includes this.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] An object of the present invention is to solve the problem that it is difficult to prevent purchases for resale purposes in limited or popular products and provide an opportunity to purchase to consumers who actually need the product. In the conventional method, it is difficult to determine the true intention of the purchaser, and there is a problem of promoting incorrect market habits due to resale.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides a system that generates questions to be presented to a purchaser based on product-related information using a generating device, and displays the questions to the purchaser using a presenting device. Furthermore, it receives and evaluates the purchaser's answers using a verification device, and then grants the right to purchase to purchasers whose answers are evaluated as correct using a purchase right granting device. This eliminates purchasers with the intention of reselling and makes it possible to provide products to legitimate purchasers.

[0006] A "generating device" is a device that has the function of automatically creating questions to be presented to the purchaser based on information related to the product.

[0007] A "presentation device" is a device that provides generated questions to prospective buyers visually or audibly, enabling them to answer the questions.

[0008] A "verification device" is a device that receives responses from purchasers and evaluates their content and accuracy.

[0009] A "device that grants the right to purchase" is a device that has the function of granting the purchaser the right to purchase a product if the evaluated answer is determined to be correct.

[0010] A "machine learning model" is an artificial intelligence technology that learns from data and has the flexibility to generate a variety of questions related to a product.

[0011] "Natural language processing technology" is a technology that automatically interprets text input from customers, enabling computers to understand and process human language. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. <统一码转义字符,无法翻译,保留原文 <统一码转义字符,无法翻译,保留原文 [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. <统一码转义字符,无法翻译,保留原文 <统一码转义字符,无法翻译,保留原文 [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0013] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0014] First, the language used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] As a specific embodiment for carrying out the present invention, an example of a system combining a generating device, a presenting device, a verification device, and a purchase right granting device is shown. This system is used when selling popular products in stores.

[0034] The server acts as the initial generating device, retrieving detailed information about the target product from the database. This information includes release date, product characteristics, brand history, and the latest related news. Based on this information, the server uses machine learning models to generate questions to present to potential buyers. This increases the variety of questions and deters purchases made for resale purposes.

[0035] The generated questions are sent from the server to terminals installed in the store. The terminals, acting as display devices, present the received questions to potential customers. Users review the presented questions on the terminal and enter their answers based on their knowledge.

[0036] The entered response is sent to a server that functions as a verification device. The server uses natural language processing technology to analyze the received response and evaluate whether it is correct. If the evaluation determines that the response is correct, the server functions as a device that grants purchase rights and notifies the terminal that the user has the right to purchase the product.

[0037] As a concrete example, consider a scenario where a user tries to purchase a limited-edition pair of sneakers. Suppose the server generates and presents the question to the user's device: "In what year were these sneakers first released?" If the user answers with the correct year, the server evaluates the answer, and if correct, grants the user the right to purchase them. This allows the user to complete the sneaker purchase process.

[0038] As described above, by implementing the present invention, it is possible to exclude buyers who intend to resell the products and to provide fair purchasing opportunities to genuine buyers who sincerely seek the products.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The server retrieves detailed information about products scheduled for sale from the database. This includes the product's release date, characteristics, brand history, and latest news.

[0042] Step 2:

[0043] The server requests a machine learning model to use this acquired information to generate questions to present to the buyer. The generated questions will be designed to verify whether the buyer understands the product's characteristics.

[0044] Step 3:

[0045] The server sends the generated questions to terminals installed in the store. These questions are then ready to be presented to potential customers.

[0046] Step 4:

[0047] The terminal displays questions to the user in the store. The user enters their answers to the questions presented on the spot.

[0048] Step 5:

[0049] The terminal sends the user's response to the server, so that the user's input can be analyzed and evaluated.

[0050] Step 6:

[0051] The server uses natural language processing technology to analyze the received responses and evaluate their accuracy. It then determines whether the response is correct.

[0052] Step 7:

[0053] If the server determines that the answer is correct, it sends a notification to the device granting the user the right to purchase the item.

[0054] Step 8:

[0055] The user completes the purchase process, and the device sends that information to the server. The server records the purchase information in its database and updates the sales status.

[0056] This series of steps creates a system that eliminates buyers who intend to resell the products and ensures that only legitimate buyers receive them.

[0057] (Example 1)

[0058] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0059] In retail settings, there is a need to curb purchases made for resale purposes while providing fair purchasing opportunities to legitimate buyers. Existing systems have the challenge of not being able to accurately determine the buyer's intentions and appropriately grant purchasing rights.

[0060] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0061] In this invention, the server includes means for acquiring product information related to a prospective buyer and generating questions to present to the buyer based on that information; means for displaying the questions to the prospective buyer using a terminal device for presenting the questions generated using a generation AI model; and means for analyzing and evaluating the answers entered by the prospective buyer using natural language processing technology. This makes it possible to suppress purchases for resale purposes and to grant fair purchasing rights to sincere prospective buyers.

[0062] A "prospective buyer" refers to an individual or legal entity that intends to purchase a specific product.

[0063] "Product information" refers to important data regarding a purchase, including product characteristics, release date, brand history, and related news.

[0064] A "generative AI model" refers to a technology that uses machine learning to analyze data and generate questions or sentences tailored to specific purposes.

[0065] A "terminal device" refers to a device installed within a store that is equipped with a user interface and functions to display questions to users and receive answers.

[0066] "Natural language processing technology" refers to algorithms and methods that enable computers to understand, analyze, and determine the meaning of human language.

[0067] "Right to purchase" refers to the qualification or permission to purchase a specific product.

[0068] This invention is a system implemented through the collaboration of a server, a terminal, and a user. The server functions as the core of this system, processing and analyzing detailed product information using a generative AI model. Specifically, it automatically generates questions to be presented to potential buyers based on product information obtained from a database. Machine learning technology is used for this generation, and various data points such as product characteristics, release date, and brand history are utilized.

[0069] Questions provided by the server are sent to a terminal. The terminal, installed in the store and equipped with a user interface, allows prospective customers to read the received questions and enter answers based on their own knowledge. The terminal can use a touchscreen or keyboard as its user interface.

[0070] The user enters an answer to a question displayed on their device. The entered answer is sent from the device to the server. The server then analyzes the received answer using natural language processing technology to determine its accuracy. The analysis technology includes text classification and semantic analysis, which allows for efficient evaluation of the correctness of the answer.

[0071] For answers deemed correct, the server grants the buyer the right to purchase. This granting of the right is notified to the user via their device, and the purchase process proceeds. This format effectively suppresses purchases for resale purposes and provides fair purchasing opportunities to genuine buyers.

[0072] For example, if the question generated by the server is "In what year were these sneakers first released?", the user answers that year on their device. The server then evaluates the answer, and if it is correct, the user is granted the right to purchase them.

[0073] An example of a prompt message might be, "Please describe the events related to this product based on a timeline."

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The server retrieves product information from the database. Specifically, it extracts information such as product characteristics, release date, brand history, and the latest related news. Based on this information, it prepares data to be input into the generative AI model. The output at this stage is an organized set of information to be passed to the model.

[0077] Step 2:

[0078] The server uses a generative AI model to generate questions based on acquired product information. In this process, the model analyzes the given information and creates questions to present to potential buyers. For example, a question such as "In what year were these sneakers first released?" might be generated. The input in this case is the information data prepared in the previous step, and the output is the generated question.

[0079] Step 3:

[0080] The server sends the generated question to the terminal. The terminal is installed in the store and prepares to display the sent question on its screen. The input here is the question data from the server, and the output is the display data, which is the question converted into a format that can be displayed.

[0081] Step 4:

[0082] The user views the question displayed on the device and enters an answer based on their knowledge. Specifically, they directly input the answer to the question using the device's touch panel or keyboard. At this stage, the input is the question displayed on the device, and the output is the answer data entered by the user.

[0083] Step 5:

[0084] The terminal sends the user's response to the server. The server analyzes the received response data using natural language processing technology. Specifically, the processing involves text classification and semantic analysis to determine whether the response is correct. The input is the user's response data, and the output is the result of determining whether the response is correct or incorrect.

[0085] Step 6:

[0086] The server grants the user the right to purchase if the answer is evaluated as correct. The server sends this information to the terminal, which displays a notification to the user such as "Purchase rights have been granted." The input here is the evaluation result of the answer, and the output is the notification message to the user.

[0087] (Application Example 1)

[0088] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0089] When popular products are sold in stores, it is necessary to prevent purchases for resale purposes and to provide fair purchasing opportunities to genuine buyers. However, conventional methods have made it difficult to effectively identify genuine buyers and ensure fair purchasing opportunities. Against this backdrop, a system is needed that accurately grasps the intentions of buyers and provides fair purchasing procedures.

[0090] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0091] In this invention, the server includes means for creating tasks to be presented to prospective buyers based on information related to the articles using an information generation device, means for presenting the tasks to the prospective buyers using an information display device, and means for receiving and evaluating the prospective buyers' answers using an information verification device. This makes it possible to evaluate whether the prospective buyer has a sincere intention and not intends to resell the goods, and to provide a fair purchasing procedure.

[0092] An "information generation device" is a device that creates tasks to be presented to prospective buyers based on information related to goods.

[0093] An "information display device" is a device used to present problems generated by an information generation device to prospective buyers.

[0094] An "information verification device" is a device used to receive and evaluate responses from prospective buyers.

[0095] A "purchase right granting device" is a device that grants purchase rights to prospective buyers who have provided correct answers based on the evaluation of the information verification device.

[0096] A "communication device" is a device that transmits purchase information to a mobile information terminal and displays that information.

[0097] A "learning model" is a mathematical model used to generate problems related to objects using machine learning techniques.

[0098] "Natural language processing techniques" are technologies that use computers to analyze text and understand human language when evaluating responses from potential buyers.

[0099] A "potential buyer" is a person who wishes to purchase a specific product.

[0100] "Goods" refers to all products and merchandise sold in stores.

[0101] The system for implementing this invention targets the sale of popular products in stores. The server functions as an information generation device, retrieving information related to the items from a database. This information includes product name, release date, features, related news, etc. Based on the retrieved information, the server uses a learning model to generate tasks to present to potential buyers.

[0102] The generated task is displayed on a terminal via an information display device. This terminal may be a smartphone or a digital display installed in the store. The task is designed to verify that the prospective buyer is not intending to resell the item. The user enters their answer to the presented task based on their knowledge and experience.

[0103] The entered answer is sent to a server that functions as an information verification device. The server evaluates the answer using natural language processing techniques. If the evaluation determines that the answer is correct, the server functions as a purchase right granting device and grants the user who provided the correct answer a purchase right. The purchase right is embodied as a QR code (registered trademark) displayed on the terminal, and the actual purchase procedure is completed by presenting this to the store staff.

[0104] For example, if the server generates the question "Who is the designer of this product?", and the user answers with the correct designer name, the server will evaluate the answer as correct, and a QR code granting purchase rights will be immediately issued. Another example of a prompt message is, "Please generate a question about this product. Possible questions include the product's history, designer, and initial release year."

[0105] The system consists of a server-side implementation combining Python and Django, a user interface for the terminal using Flutter®, and natural language processing using Hugging Face's Transformers. This enables a smooth purchase process in stores and ensures fair purchasing opportunities.

[0106] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0107] Step 1:

[0108] The server retrieves data about an item from a database. This data includes product name, release date, features, and brand history. Based on this data, the server generates prompts and questions using a learning model. The input is information from the database, and the output is the generated question.

[0109] Step 2:

[0110] The server sends the generated question to the terminal. The terminal activates the interface and prepares a screen for user interaction to display this question to the user. The input in this step is the question from the server, and the output is the question displayed to the user.

[0111] Step 3:

[0112] The user enters their answer to a question presented on the terminal. The user interface accepts the answer via touch input, voice input, etc., formats the received data, and sends it to the server. The input here is the user's answer, and the output is the formatted answer data sent to the server.

[0113] Step 4:

[0114] The server analyzes the received answers using natural language processing techniques. It uses Hugging Face's Transformers to evaluate whether the answers are correct. The input is the answer data received from the user, and the output is the evaluation result.

[0115] Step 5:

[0116] If the server evaluates the answer as correct, it functions as a purchase right granting device and generates a QR code to grant the purchase right to the user's terminal. This QR code is presented to store staff at the time of actual purchase. The input for this step is the correctness of the evaluated answer, and the output is the generated QR code.

[0117] Step 6:

[0118] The user displays the generated QR code on their device and presents it to the store staff. This allows them to exercise their right to purchase the product and complete the actual purchase process. The input for this step is the QR code on the device, and the output is the completion of the purchase process.

[0119] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0120] As a specific embodiment for carrying out the present invention, an example of a system incorporating an emotion engine is shown, in addition to a generating device, a presenting device, a confirmation device, and a device for granting purchase rights. This system is used when selling popular products in stores, and aims not only to prevent resale but also to improve the customer experience.

[0121] First, the server functions as a generation device, retrieving data from a database regarding the characteristics and historical background of the products being sold. Based on this information, it uses a machine learning model to generate questions to suggest to buyers. The generated questions ask users about their understanding of the product.

[0122] The generated questions are sent from the server to a terminal installed in the store. This terminal presents the questions to users who wish to make a purchase. The terminal provides an interface where users can review the questions and enter their answers.

[0123] In this system, an emotion engine is built into the terminal and recognizes and analyzes the user's emotions in real time while they are entering their answers. The emotion engine can detect the user's emotional state using camera and voice analysis technology. The analyzed emotion data is taken into consideration when evaluating answers and granting purchase rights.

[0124] When a user enters an answer to a question into their device, that answer is sent from the device to the server. The server uses natural language processing technology to evaluate the answer and improves the accuracy of the evaluation by supplementing it with data from the sentiment engine.

[0125] After the evaluation is complete, the server decides whether to grant the right to purchase based on the evaluation results and notifies the terminal. If the user is deemed to have answered appropriately and their emotional state is deemed suitable, the right to purchase is granted, and the user gains the right to buy the product.

[0126] As a concrete example, if a user attempts to purchase a limited-edition piece of clothing, the server will generate the question, "Who is the designer of this clothing?" If the user answers immediately and the emotion engine confirms their sincere intention to purchase, the user will be granted the right to purchase. In this way, the present invention can be implemented to prevent resale while providing users with a good purchasing experience.

[0127] The following describes the processing flow.

[0128] Step 1:

[0129] The server retrieves detailed product information from the database. This includes product features, brand information, and related news.

[0130] Step 2:

[0131] The server automatically generates questions to present to the buyer based on information obtained using a machine learning model. The generated questions assess the buyer's understanding of the product.

[0132] Step 3:

[0133] The server sends the generated question to a terminal installed in the store. The terminal prepares to display the question.

[0134] Step 4:

[0135] The terminal displays questions to users who are interested in purchasing items at the store. The user reviews the questions and enters their answers.

[0136] Step 5:

[0137] The device uses the user's face and voice to activate an emotion engine, identifying and recording the user's emotional state in real time.

[0138] Step 6:

[0139] The terminal sends the user's entered responses and sentiment data to the server. The server receives this data.

[0140] Step 7:

[0141] The server uses natural language processing technology to evaluate the user's responses. Simultaneously, it references sentiment data provided by the sentiment engine and uses it to assist in the evaluation.

[0142] Step 8:

[0143] The server decides to grant the right to purchase based on the evaluation results. If the answer is correct or the emotional state is judged to be good, a notification of the granting of the right to purchase is sent to the terminal.

[0144] Step 9:

[0145] Users receive a notification from their device granting them the right to purchase the product, and can then proceed with the purchase process.

[0146] This entire process makes it possible to curb reselling while providing users with a more personalized purchasing experience.

[0147] (Example 2)

[0148] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0149] In recent years, the resale problem that arises when purchasing popular products has become a serious issue for both consumers and sellers. Furthermore, there is a need for new methods to verify whether consumers have honest and appropriate intentions when purchasing products, and to improve the customer experience. Traditional methods make it difficult to assess the psychological state of buyers in real time, and as a result, honest customers may be denied the right to purchase.

[0150] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0151] In this invention, the server includes means for creating questions to be presented to a purchaser based on product-related information using a generating device, means for displaying the questions to the purchaser using a presenting device, and means for analyzing the purchaser's emotional state using an emotion detection device. This makes it possible to improve the consumer purchasing experience while increasing the purchaser's understanding and sincerity, and deterring resale.

[0152] A "generating device" is a device that acquires information related to a product and uses a machine learning model to create questions to present to the buyer based on that information.

[0153] A "presenting device" is a device that provides a buyer with an interface to display generated questions and has the function of allowing the user to input answers to the questions.

[0154] An "emotion detection device" is a device designed to analyze the emotional state of a purchaser. It uses cameras and voice analysis technology to measure the user's facial expressions and tone of voice, and has the function of evaluating emotions in real time.

[0155] A "verification device" is a device that receives responses entered by purchasers and evaluates their accuracy using natural language processing technology.

[0156] A "device that grants the right to purchase" is a device that, if the buyer's answer is evaluated as correct, grants that buyer the right to purchase the product.

[0157] Embodiments of the present invention will now be described. This system aims to prevent resale and improve the customer experience in product sales, and is particularly effective when selling popular products in stores.

[0158] The server retrieves information about the product's characteristics and historical background from a database. Using this retrieved data, the server generates product-related questions to present to the buyer, based on a generative AI model. For example, for a user considering purchasing a limited-edition piece of clothing, it can generate a specific question such as, "Who is the designer of this clothing?"

[0159] The generated questions are sent to the device and displayed to the buyer. The device provides an interface for the user to answer the questions. The device has a built-in camera and microphone, which function as an emotion detection device. This device analyzes the user's facial expressions and tone of voice in real time to obtain data to evaluate whether the user is giving honest answers.

[0160] User responses are sent from the device to the server, which evaluates the responses using natural language processing technology. Furthermore, sentiment data is taken into consideration to improve the accuracy and sincerity of the responses.

[0161] Based on the evaluation results, the server decides whether to grant the right to purchase and notifies the user of the result via the terminal. If the user answers the questions accurately and their emotional state is deemed appropriate for the sales intent, the right to purchase is granted to that user.

[0162] This system provides a direct and interactive purchasing experience while ensuring fair trade for both consumers and sellers.

[0163] An example of a prompt message is: "Analyze the sentiment of users who have shown interest in the limited-edition product, confirm that you have accurate knowledge, and then explain how to offer them the right to purchase it."

[0164] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0165] Step 1:

[0166] The server retrieves data about product characteristics and historical background from a database. It accepts product IDs and category information as input. Based on the product information retrieved from the database, it extracts and outputs specific attributes and details used in the next step.

[0167] Step 2:

[0168] The server uses a generative AI model to create questions to present to the buyer based on the acquired product information. The input here is the product information acquired in step 1, and the AI ​​model generates appropriate questions through natural language processing. For example, it might output a specific question such as, "Who designed this product?"

[0169] Step 3:

[0170] The server sends the generated question to a terminal in the store. The input here is the question created in step 2. The terminal receives this question and displays it on its screen. The output is made visible to the user.

[0171] Step 4:

[0172] The terminal provides an interface for the user to read and answer questions. The user enters their answers into input fields provided on the screen. The input is text data entered by the user, which the terminal temporarily stores and prepares to send to the server in a later step.

[0173] Step 5:

[0174] An emotion detection device built into the device analyzes the user's facial expressions and voice in real time. Inputs here are video from the camera and audio data from the microphone. This data is analyzed, and the user's emotional state is output as numerical data.

[0175] Step 6:

[0176] The terminal sends the user's responses and emotional state data to the server. The inputs are the text responses from step 4 and the emotional state data obtained in step 5. The server receives these inputs and prepares to proceed.

[0177] Step 7:

[0178] The server uses natural language processing technology to evaluate the user's response. The input here is the text response received from step 6. The accuracy of the response is analyzed, and the evaluation result is quantified and output. Furthermore, emotional state data is taken into consideration to arrive at the final evaluation.

[0179] Step 8:

[0180] The server decides whether to grant the right to purchase based on the evaluation results. The input is the evaluation result obtained in step 7. If the evaluation meets the criteria, the server decides to grant the right to purchase to the user and sends the result as output to the terminal.

[0181] Step 9:

[0182] The terminal receives the result of the purchase right grant from the server and notifies the user. The input here is the purchase right grant decision output by the server. If the user has obtained the purchase right, the message "Congratulations, you have been granted the purchase right" is displayed and output on the screen. The user can then proceed with the purchase process.

[0183] (Application Example 2)

[0184] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0185] Traditional product sales methods face challenges such as fraudulent purchases by resellers and difficulty in providing buyers with a fair purchasing experience. In particular, when selling popular or limited-edition items, legitimate buyers are often at a disadvantage. Furthermore, the lack of mechanisms for buyers to demonstrate their understanding of and sincerity regarding a product makes it difficult to ensure that products reach the right buyers.

[0186] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0187] In this invention, the server includes means for creating questions to be presented to a purchaser based on product-related information using a generating device, means for displaying the questions to the purchaser using a presenting device, means for receiving and evaluating the purchaser's answers using a confirmation device, and means for analyzing the purchaser's emotional state using an emotion-recognizing device. This makes it possible to appropriately provide products to purchasers who understand and have sincerity towards the products.

[0188] A "generating device" is a device that has the function of creating questions to be presented to the purchaser based on information related to the product.

[0189] A "presentation device" is a device that displays generated questions to the purchaser and communicates with the user through an interface.

[0190] A "verification device" is a device that has the function of receiving responses from purchasers and evaluating them.

[0191] A "device for granting purchase rights" is a device that has the function of granting purchase rights to buyers based on an evaluation.

[0192] A "device that recognizes emotions" is a device that uses cameras and voice analysis to detect emotions in order to analyze the user's emotional state and has the function of processing that information.

[0193] A "machine learning model" is a mathematical model that learns from a set of data and can automatically make predictions and decisions regarding a specified task.

[0194] "Natural language processing technology" is a technology that enables computers to understand and process natural language, which is the language spoken by humans.

[0195] A "prompt statement" is a sentence that provides instructions or information to a generative AI model to perform a specific task.

[0196] The system for carrying out this invention comprises a server, a presentation device, an emotion recognition device, and a purchase right granting device. The server uses a generative AI model to generate questions to present to the purchaser based on product-related information. These generated questions are created based on prompt statements and assess the purchaser's understanding of the product, as will be shown in the specific examples described later.

[0197] The server generates a question and sends it to a terminal used within the store. This terminal provides users who wish to make a purchase with an interface to view the question and input their answer. The display device could be a smart glasses display or a display installed in the store.

[0198] When a user answers questions via a terminal, an emotion recognition device analyzes the user's emotional state. Emotion recognition is performed through a camera and microphone, detecting emotions from the user's facial expressions and tone of voice. Specifically, OpenCV is used for the camera, and a speech recognition library is used for speech analysis.

[0199] User responses and sentiment data are sent to a server for evaluation, which uses natural language processing techniques to perform an overall assessment. Sentiment data is used as supplementary information to determine the truthfulness and sincerity of the responses.

[0200] If the evaluation determines that the user has provided appropriate answers and emotional states, the right to purchase will be granted. This granting of the right to purchase will be notified to the user via their device.

[0201] For example, if a user wants to purchase a limited-edition new clothing item, the server generates the question, "Who is the designer of this clothing item?" and presents it to the user through smart glasses. If the user answers immediately and their facial expression is deemed sincere, they are granted the right to purchase the item.

[0202] An example of a prompt to input into the generation AI model would be: "Generate a question that asks the user for specific product knowledge. The product name should be 'New Clothing Item,' and the related information should include 'Designer's Name.'"

[0203] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0204] Step 1:

[0205] The server retrieves product-related data from the database. Product IDs and category information are provided as input, and the server processes this information to retrieve related product characteristics and historical background from the database. The retrieved product information is provided as output.

[0206] Step 2:

[0207] The server generates questions using a generation AI model. As input, a prompt sentence is constructed based on the product information obtained in step 1, and this prompt sentence is input into the generation AI model. Through data calculation, questions that ask about relevant product knowledge are generated, and specific question sentences are obtained as output.

[0208] Step 3:

[0209] The server sends the generated question to the terminal. The input is the question text generated in step 2, which is sent to the terminal in the store via the network. The output is the question to be displayed, which is provided to the terminal.

[0210] Step 4:

[0211] The terminal presents a question to the user and accepts their response. The input is the question text sent to the terminal in step 3. The terminal visualizes the question for the user via a display device. It accepts voice responses and text input from the user, and the user response data is obtained as output.

[0212] Step 5:

[0213] An emotion recognition device analyzes the user's emotions. The input consists of audio and video data acquired when the user responds. Based on this data, an emotion recognition algorithm analyzes the user's facial expressions and vocal characteristics to detect their emotional state. The output is the analyzed emotion data.

[0214] Step 6:

[0215] The server uses natural language processing technology to evaluate the user's responses. The input consists of user response data obtained in step 4 and sentiment data obtained in step 5. The natural language processing model analyzes this data to evaluate the accuracy and sincerity of the responses. The output includes an evaluation score and whether or not the purchase right is granted.

[0216] Step 7:

[0217] The server decides whether to grant the purchase right and notifies the terminal of the result. The input is the evaluation result obtained in step 6. The server makes a decision on whether to grant the purchase right and sends the result to the terminal. The output is a notification regarding the granting of the purchase right provided to the user.

[0218] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0219] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0220] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0221] [Second Embodiment]

[0222] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0223] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0224] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0225] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0226] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0227] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0228] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0229] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0230] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0231] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0232] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0233] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0234] As a specific embodiment for carrying out the present invention, an example of a system combining a generating device, a presenting device, a verification device, and a purchase right granting device is shown. This system is used when selling popular products in stores.

[0235] The server acts as the initial generating device, retrieving detailed information about the target product from the database. This information includes release date, product characteristics, brand history, and the latest related news. Based on this information, the server uses machine learning models to generate questions to present to potential buyers. This increases the variety of questions and deters purchases made for resale purposes.

[0236] The generated questions are sent from the server to terminals installed in the store. The terminals, acting as display devices, present the received questions to potential customers. Users review the presented questions on the terminal and enter their answers based on their knowledge.

[0237] The entered response is sent to a server that functions as a verification device. The server uses natural language processing technology to analyze the received response and evaluate whether it is correct. If the evaluation determines that the response is correct, the server functions as a device that grants purchase rights and notifies the terminal that the user has the right to purchase the product.

[0238] As a concrete example, consider a scenario where a user tries to purchase a limited-edition pair of sneakers. Suppose the server generates and presents the question to the user's device: "In what year were these sneakers first released?" If the user answers with the correct year, the server evaluates the answer, and if correct, grants the user the right to purchase them. This allows the user to complete the sneaker purchase process.

[0239] As described above, by implementing the present invention, it is possible to exclude buyers who intend to resell the products and to provide fair purchasing opportunities to genuine buyers who sincerely seek the products.

[0240] The following describes the processing flow.

[0241] Step 1:

[0242] The server retrieves detailed information about products scheduled for sale from the database. This includes the product's release date, characteristics, brand history, and latest news.

[0243] Step 2:

[0244] The server requests a machine learning model to use this acquired information to generate questions to present to the buyer. The generated questions will be designed to verify whether the buyer understands the product's characteristics.

[0245] Step 3:

[0246] The server sends the generated questions to terminals installed in the store. These questions are then ready to be presented to potential customers.

[0247] Step 4:

[0248] The terminal displays questions to the user in the store. The user enters their answers to the questions presented on the spot.

[0249] Step 5:

[0250] The terminal sends the user's response to the server, so that the user's input can be analyzed and evaluated.

[0251] Step 6:

[0252] The server uses natural language processing technology to analyze the received responses and evaluate their accuracy. It then determines whether the response is correct.

[0253] Step 7:

[0254] If the server determines that the answer is correct, it sends a notification to the device granting the user the right to purchase the item.

[0255] Step 8:

[0256] The user completes the purchase process, and the device sends that information to the server. The server records the purchase information in its database and updates the sales status.

[0257] This series of steps creates a system that eliminates buyers who intend to resell the products and ensures that only legitimate buyers receive them.

[0258] (Example 1)

[0259] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0260] In retail settings, there is a need to curb purchases made for resale purposes while providing fair purchasing opportunities to legitimate buyers. Existing systems have the challenge of not being able to accurately determine the buyer's intentions and appropriately grant purchasing rights.

[0261] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0262] In this invention, the server includes means for acquiring product information related to a prospective buyer and generating questions to present to the buyer based on that information; means for displaying the questions to the prospective buyer using a terminal device for presenting the questions generated using a generation AI model; and means for analyzing and evaluating the answers entered by the prospective buyer using natural language processing technology. This makes it possible to suppress purchases for resale purposes and to grant fair purchasing rights to sincere prospective buyers.

[0263] A "prospective buyer" refers to an individual or legal entity that intends to purchase a specific product.

[0264] "Product information" refers to important data regarding a purchase, including product characteristics, release date, brand history, and related news.

[0265] A "generative AI model" refers to a technology that uses machine learning to analyze data and generate questions or sentences tailored to specific purposes.

[0266] A "terminal device" refers to a device installed within a store that is equipped with a user interface and functions to display questions to users and receive answers.

[0267] "Natural language processing technology" refers to algorithms and methods that enable computers to understand, analyze, and determine the meaning of human language.

[0268] "Right to purchase" refers to the qualification or permission to purchase a specific product.

[0269] This invention is a system implemented through the collaboration of a server, a terminal, and a user. The server functions as the core of this system, processing and analyzing detailed product information using a generative AI model. Specifically, it automatically generates questions to be presented to potential buyers based on product information obtained from a database. Machine learning technology is used for this generation, and various data points such as product characteristics, release date, and brand history are utilized.

[0270] Questions provided by the server are sent to a terminal. The terminal, installed in the store and equipped with a user interface, allows prospective customers to read the received questions and enter answers based on their own knowledge. The terminal can use a touchscreen or keyboard as its user interface.

[0271] The user enters an answer to a question displayed on their device. The entered answer is sent from the device to the server. The server then analyzes the received answer using natural language processing technology to determine its accuracy. The analysis technology includes text classification and semantic analysis, which allows for efficient evaluation of the correctness of the answer.

[0272] For answers deemed correct, the server grants the buyer the right to purchase. This granting of the right is notified to the user via their device, and the purchase process proceeds. This format effectively suppresses purchases for resale purposes and provides fair purchasing opportunities to genuine buyers.

[0273] For example, if the question generated by the server is "In what year were these sneakers first released?", the user answers that year on their device. The server then evaluates the answer, and if it is correct, the user is granted the right to purchase them.

[0274] An example of a prompt message might be, "Please describe the events related to this product based on a timeline."

[0275] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0276] Step 1:

[0277] The server retrieves product information from the database. Specifically, it extracts information such as product characteristics, release date, brand history, and the latest related news. Based on this information, it prepares data to be input into the generative AI model. The output at this stage is an organized set of information to be passed to the model.

[0278] Step 2:

[0279] The server uses a generative AI model to generate questions based on acquired product information. In this process, the model analyzes the given information and creates questions to present to potential buyers. For example, a question such as "In what year were these sneakers first released?" might be generated. The input in this case is the information data prepared in the previous step, and the output is the generated question.

[0280] Step 3:

[0281] The server sends the generated question to the terminal. The terminal is installed in the store and prepares to display the sent question on its screen. The input here is the question data from the server, and the output is the display data, which is the question converted into a format that can be displayed.

[0282] Step 4:

[0283] The user checks the questions displayed on the terminal and enters an answer based on the knowledge they possess. Specifically, using the touch panel or keyboard of the terminal, they directly input the answer to the question. The input at this stage is the question on the terminal, and the output is the answer data input by the user.

[0284] Step 5:

[0285] The terminal sends the user's answer to the server. The server analyzes the received answer data using natural language processing technology. As specific processing, text classification and semantic analysis are performed to determine whether the answer is correct. The input is the user's answer data, and the output is the result of the correct / incorrect judgment of the answer.

[0286] Step 6:

[0287] If the server evaluates that the answer is correct, it grants the user the right to purchase. The server sends this information to the terminal, and the terminal displays a notification such as "The purchase right has been granted" to the user. The input here is the evaluation result of the answer, and the output is the notification message to the user.

[0288] (Application Example 1)

[0289] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0290] When popular products are sold in stores etc., it is required to prevent purchases for resale purposes and provide a fair purchasing opportunity to honest buyers. However, with conventional methods, it has been difficult to effectively identify buyers and ensure a proper purchasing opportunity. Against such a background, a mechanism is needed to accurately grasp the intentions of buyers and provide a fair purchasing procedure.

[0291] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0292] In this invention, the server includes means for creating tasks to be presented to prospective buyers based on information related to the articles using an information generation device, means for presenting the tasks to the prospective buyers using an information display device, and means for receiving and evaluating the prospective buyers' answers using an information verification device. This makes it possible to evaluate whether the prospective buyer has a sincere intention and not intends to resell the goods, and to provide a fair purchasing procedure.

[0293] An "information generation device" is a device that creates tasks to be presented to prospective buyers based on information related to goods.

[0294] An "information display device" is a device used to present problems generated by an information generation device to prospective buyers.

[0295] An "information verification device" is a device used to receive and evaluate responses from prospective buyers.

[0296] A "purchase right granting device" is a device that grants purchase rights to prospective buyers who have provided correct answers based on the evaluation of the information verification device.

[0297] A "communication device" is a device that transmits purchase information to a mobile information terminal and displays that information.

[0298] A "learning model" is a mathematical model used to generate problems related to objects using machine learning techniques.

[0299] "Natural language processing techniques" are technologies that use computers to analyze text and understand human language when evaluating responses from potential buyers.

[0300] A "potential buyer" is a person who wishes to purchase a specific product.

[0301] "Goods" refers to all products and merchandise sold in stores.

[0302] The system for implementing this invention targets the sale of popular products in stores. The server functions as an information generation device, retrieving information related to the items from a database. This information includes product name, release date, features, related news, etc. Based on the retrieved information, the server uses a learning model to generate tasks to present to potential buyers.

[0303] The generated task is displayed on a terminal via an information display device. This terminal may be a smartphone or a digital display installed in the store. The task is designed to verify that the prospective buyer is not intending to resell the item. The user enters their answer to the presented task based on their knowledge and experience.

[0304] The entered answer is sent to a server that functions as an information verification device. The server evaluates the answer using natural language processing techniques. If the evaluation determines that the answer is correct, the server functions as a purchase right granting device and grants the user who provided the correct answer a purchase right. The purchase right is embodied as a QR code displayed on the terminal, and the actual purchase procedure is completed by presenting this to the store staff.

[0305] For example, if the server generates the question "Who is the designer of this product?", and the user answers with the correct designer name, the server will evaluate the answer as correct, and a QR code granting purchase rights will be immediately issued. Another example of a prompt message is, "Please generate a question about this product. Possible questions include the product's history, designer, and initial release year."

[0306] The system consists of a server-side implementation combining Python and Django, a user interface for the device using Flutter, and natural language processing using Hugging Face's Transformers. This enables a smooth purchase process in stores and ensures fair purchasing opportunities.

[0307] The flow of the specific process in Application Example 1 will be described with reference to FIG. 12.

[0308] Step 1:

[0309] The server retrieves data related to the item from the database. The information retrieved includes the product name, release date, features, brand history, etc. Based on this data, the server generates a prompt sentence and uses a learning model to generate questions. The input is the information from the database, and the output is the generated questions.

[0310] Step 2:

[0311] The server sends the generated questions to the terminal. The terminal activates the interface and prepares a screen for user interaction to display these questions to the user. The input for this step is the question from the server, and the output is the question on the display presented to the user.

[0312] Step 3:

[0313] The user inputs an answer to the question presented on the terminal. The user interface accepts the answer corresponding to touch input, voice input, etc., formats the received data, and transfers it to the server. The input here is the user's answer, and the output is the formatted answer data sent to the server.

[0314] Step 4:

[0315] The server analyzes the received answer using natural language processing techniques. Using Transformers from Hugging Face, it evaluates whether the answer is correct. The input is the answer data received from the user, and the output is the evaluation result.

[0316] Step 5:

[0317] If the server evaluates the answer as correct, it functions as a purchase right granting device and generates a QR code to grant the purchase right to the user's terminal. This QR code is presented to store staff at the time of actual purchase. The input for this step is the correctness of the evaluated answer, and the output is the generated QR code.

[0318] Step 6:

[0319] The user displays the generated QR code on their device and presents it to the store staff. This allows them to exercise their right to purchase the product and complete the actual purchase process. The input for this step is the QR code on the device, and the output is the completion of the purchase process.

[0320] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0321] As a specific embodiment for carrying out the present invention, an example of a system incorporating an emotion engine is shown, in addition to a generating device, a presenting device, a confirmation device, and a device for granting purchase rights. This system is used when selling popular products in stores, and aims not only to prevent resale but also to improve the customer experience.

[0322] First, the server functions as a generation device, retrieving data from a database regarding the characteristics and historical background of the products being sold. Based on this information, it uses a machine learning model to generate questions to suggest to buyers. The generated questions ask users about their understanding of the product.

[0323] The generated questions are sent from the server to a terminal installed in the store. This terminal presents the questions to users who wish to make a purchase. The terminal provides an interface where users can review the questions and enter their answers.

[0324] In this system, an emotion engine is built into the terminal and recognizes and analyzes the user's emotions in real time while they are entering their answers. The emotion engine can detect the user's emotional state using camera and voice analysis technology. The analyzed emotion data is taken into consideration when evaluating answers and granting purchase rights.

[0325] When a user enters an answer to a question into their device, that answer is sent from the device to the server. The server uses natural language processing technology to evaluate the answer and improves the accuracy of the evaluation by supplementing it with data from the sentiment engine.

[0326] After the evaluation is complete, the server decides whether to grant the right to purchase based on the evaluation results and notifies the terminal. If the user is deemed to have answered appropriately and their emotional state is deemed suitable, the right to purchase is granted, and the user gains the right to buy the product.

[0327] As a concrete example, if a user attempts to purchase a limited-edition piece of clothing, the server will generate the question, "Who is the designer of this clothing?" If the user answers immediately and the emotion engine confirms their sincere intention to purchase, the user will be granted the right to purchase. In this way, the present invention can be implemented to prevent resale while providing users with a good purchasing experience.

[0328] The following describes the processing flow.

[0329] Step 1:

[0330] The server retrieves detailed product information from the database. This includes product features, brand information, and related news.

[0331] Step 2:

[0332] The server automatically generates questions to present to the buyer based on information obtained using a machine learning model. The generated questions assess the buyer's understanding of the product.

[0333] Step 3:

[0334] The server sends the generated question to a terminal installed in the store. The terminal prepares to display the question.

[0335] Step 4:

[0336] The terminal displays questions to users who are interested in purchasing items at the store. The user reviews the questions and enters their answers.

[0337] Step 5:

[0338] The device uses the user's face and voice to activate an emotion engine, identifying and recording the user's emotional state in real time.

[0339] Step 6:

[0340] The terminal sends the user's entered responses and sentiment data to the server. The server receives this data.

[0341] Step 7:

[0342] The server uses natural language processing technology to evaluate the user's responses. Simultaneously, it references sentiment data provided by the sentiment engine and uses it to assist in the evaluation.

[0343] Step 8:

[0344] The server decides to grant the right to purchase based on the evaluation results. If the answer is correct or the emotional state is judged to be good, a notification of the granting of the right to purchase is sent to the terminal.

[0345] Step 9:

[0346] Users receive a notification from their device granting them the right to purchase the product, and can then proceed with the purchase process.

[0347] This entire process makes it possible to curb reselling while providing users with a more personalized purchasing experience.

[0348] (Example 2)

[0349] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0350] In recent years, the resale problem that arises when purchasing popular products has become a serious issue for both consumers and sellers. Furthermore, there is a need for new methods to verify whether consumers have honest and appropriate intentions when purchasing products, and to improve the customer experience. Traditional methods make it difficult to assess the psychological state of buyers in real time, and as a result, honest customers may be denied the right to purchase.

[0351] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0352] In this invention, the server includes means for creating questions to be presented to a purchaser based on product-related information using a generating device, means for displaying the questions to the purchaser using a presenting device, and means for analyzing the purchaser's emotional state using an emotion detection device. This makes it possible to improve the consumer purchasing experience while increasing the purchaser's understanding and sincerity, and deterring resale.

[0353] A "generating device" is a device that acquires information related to a product and uses a machine learning model to create questions to present to the buyer based on that information.

[0354] A "presenting device" is a device that provides a buyer with an interface to display generated questions and has the function of allowing the user to input answers to the questions.

[0355] An "emotion detection device" is a device designed to analyze the emotional state of a purchaser. It uses cameras and voice analysis technology to measure the user's facial expressions and tone of voice, and has the function of evaluating emotions in real time.

[0356] A "verification device" is a device that receives responses entered by purchasers and evaluates their accuracy using natural language processing technology.

[0357] A "device that grants the right to purchase" is a device that, if the buyer's answer is evaluated as correct, grants that buyer the right to purchase the product.

[0358] Embodiments of the present invention will now be described. This system aims to prevent resale and improve the customer experience in product sales, and is particularly effective when selling popular products in stores.

[0359] The server retrieves information about the product's characteristics and historical background from a database. Using this retrieved data, the server generates product-related questions to present to the buyer, based on a generative AI model. For example, for a user considering purchasing a limited-edition piece of clothing, it can generate a specific question such as, "Who is the designer of this clothing?"

[0360] The generated questions are sent to the device and displayed to the buyer. The device provides an interface for the user to answer the questions. The device has a built-in camera and microphone, which function as an emotion detection device. This device analyzes the user's facial expressions and tone of voice in real time to obtain data to evaluate whether the user is giving honest answers.

[0361] User responses are sent from the device to the server, which evaluates the responses using natural language processing technology. Furthermore, sentiment data is taken into consideration to improve the accuracy and sincerity of the responses.

[0362] Based on the evaluation results, the server decides whether to grant the right to purchase and notifies the user of the result via the terminal. If the user answers the questions accurately and their emotional state is deemed appropriate for the sales intent, the right to purchase is granted to that user.

[0363] This system provides a direct and interactive purchasing experience while ensuring fair trade for both consumers and sellers.

[0364] An example of a prompt message is: "Analyze the sentiment of users who have shown interest in the limited-edition product, confirm that you have accurate knowledge, and then explain how to offer them the right to purchase it."

[0365] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0366] Step 1:

[0367] The server retrieves data about product characteristics and historical background from a database. It accepts product IDs and category information as input. Based on the product information retrieved from the database, it extracts and outputs specific attributes and details used in the next step.

[0368] Step 2:

[0369] The server uses a generative AI model to create questions to present to the buyer based on the acquired product information. The input here is the product information acquired in step 1, and the AI ​​model generates appropriate questions through natural language processing. For example, it might output a specific question such as, "Who designed this product?"

[0370] Step 3:

[0371] The server sends the generated question to a terminal in the store. The input here is the question created in step 2. The terminal receives this question and displays it on its screen. The output is made visible to the user.

[0372] Step 4:

[0373] The terminal provides an interface for the user to read and answer questions. The user enters their answers into input fields provided on the screen. The input is text data entered by the user, which the terminal temporarily stores and prepares to send to the server in a later step.

[0374] Step 5:

[0375] An emotion detection device built into the device analyzes the user's facial expressions and voice in real time. Inputs here are video from the camera and audio data from the microphone. This data is analyzed, and the user's emotional state is output as numerical data.

[0376] Step 6:

[0377] The terminal sends the user's responses and emotional state data to the server. The inputs are the text responses from step 4 and the emotional state data obtained in step 5. The server receives these inputs and prepares to proceed.

[0378] Step 7:

[0379] The server uses natural language processing technology to evaluate the user's response. The input here is the text response received from step 6. The accuracy of the response is analyzed, and the evaluation result is quantified and output. Furthermore, emotional state data is taken into consideration to arrive at the final evaluation.

[0380] Step 8:

[0381] The server decides whether to grant the right to purchase based on the evaluation results. The input is the evaluation result obtained in step 7. If the evaluation meets the criteria, the server decides to grant the right to purchase to the user and sends the result as output to the terminal.

[0382] Step 9:

[0383] The terminal receives the result of the purchase right grant from the server and notifies the user. The input here is the purchase right grant decision output by the server. If the user has obtained the purchase right, the message "Congratulations, you have been granted the purchase right" is displayed and output on the screen. The user can then proceed with the purchase process.

[0384] (Application Example 2)

[0385] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0386] Traditional product sales methods face challenges such as fraudulent purchases by resellers and difficulty in providing buyers with a fair purchasing experience. In particular, when selling popular or limited-edition items, legitimate buyers are often at a disadvantage. Furthermore, the lack of mechanisms for buyers to demonstrate their understanding of and sincerity regarding a product makes it difficult to ensure that products reach the right buyers.

[0387] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0388] In this invention, the server includes means for creating questions to be presented to a purchaser based on product-related information using a generating device, means for displaying the questions to the purchaser using a presenting device, means for receiving and evaluating the purchaser's answers using a confirmation device, and means for analyzing the purchaser's emotional state using an emotion-recognizing device. This makes it possible to appropriately provide products to purchasers who understand and have sincerity towards the products.

[0389] A "generating device" is a device that has the function of creating questions to be presented to the purchaser based on information related to the product.

[0390] A "presentation device" is a device that displays generated questions to the purchaser and communicates with the user through an interface.

[0391] A "verification device" is a device that has the function of receiving responses from purchasers and evaluating them.

[0392] A "device for granting purchase rights" is a device that has the function of granting purchase rights to buyers based on an evaluation.

[0393] A "device that recognizes emotions" is a device that uses cameras and voice analysis to detect emotions in order to analyze the user's emotional state and has the function of processing that information.

[0394] A "machine learning model" is a mathematical model that learns from a set of data and can automatically make predictions and decisions regarding a specified task.

[0395] "Natural language processing technology" is a technology that enables computers to understand and process natural language, which is the language spoken by humans.

[0396] A "prompt statement" is a sentence that provides instructions or information to a generative AI model to perform a specific task.

[0397] The system for carrying out this invention comprises a server, a presentation device, an emotion recognition device, and a purchase right granting device. The server uses a generative AI model to generate questions to present to the purchaser based on product-related information. These generated questions are created based on prompt statements and assess the purchaser's understanding of the product, as will be shown in the specific examples described later.

[0398] The server generates a question and sends it to a terminal used within the store. This terminal provides users who wish to make a purchase with an interface to view the question and input their answer. The display device could be a smart glasses display or a display installed in the store.

[0399] When a user answers questions via a terminal, an emotion recognition device analyzes the user's emotional state. Emotion recognition is performed through a camera and microphone, detecting emotions from the user's facial expressions and tone of voice. Specifically, OpenCV is used for the camera, and a speech recognition library is used for speech analysis.

[0400] User responses and sentiment data are sent to a server for evaluation, which uses natural language processing techniques to perform an overall assessment. Sentiment data is used as supplementary information to determine the truthfulness and sincerity of the responses.

[0401] If the evaluation determines that the user has provided appropriate answers and emotional states, the right to purchase will be granted. This granting of the right to purchase will be notified to the user via their device.

[0402] For example, if a user wants to purchase a limited-edition new clothing item, the server generates the question, "Who is the designer of this clothing item?" and presents it to the user through smart glasses. If the user answers immediately and their facial expression is deemed sincere, they are granted the right to purchase the item.

[0403] An example of a prompt to input into the generation AI model would be: "Generate a question that asks the user for specific product knowledge. The product name should be 'New Clothing Item,' and the related information should include 'Designer's Name.'"

[0404] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0405] Step 1:

[0406] The server retrieves product-related data from the database. Product IDs and category information are provided as input, and the server processes this information to retrieve related product characteristics and historical background from the database. The retrieved product information is provided as output.

[0407] Step 2:

[0408] The server generates questions using a generation AI model. As input, a prompt sentence is constructed based on the product information obtained in step 1, and this prompt sentence is input into the generation AI model. Through data calculation, questions that ask about relevant product knowledge are generated, and specific question sentences are obtained as output.

[0409] Step 3:

[0410] The server sends the generated question to the terminal. The input is the question text generated in step 2, which is sent to the terminal in the store via the network. The output is the question to be displayed, which is provided to the terminal.

[0411] Step 4:

[0412] The terminal presents a question to the user and accepts their response. The input is the question text sent to the terminal in step 3. The terminal visualizes the question for the user via a display device. It accepts voice responses and text input from the user, and the user response data is obtained as output.

[0413] Step 5:

[0414] An emotion recognition device analyzes the user's emotions. The input consists of audio and video data acquired when the user responds. Based on this data, an emotion recognition algorithm analyzes the user's facial expressions and vocal characteristics to detect their emotional state. The output is the analyzed emotion data.

[0415] Step 6:

[0416] The server uses natural language processing technology to evaluate the user's responses. The input consists of user response data obtained in step 4 and sentiment data obtained in step 5. The natural language processing model analyzes this data to evaluate the accuracy and sincerity of the responses. The output includes an evaluation score and whether or not the purchase right is granted.

[0417] Step 7:

[0418] The server decides whether to grant the purchase right and notifies the terminal of the result. The input is the evaluation result obtained in step 6. The server makes a decision on whether to grant the purchase right and sends the result to the terminal. The output is a notification regarding the granting of the purchase right provided to the user.

[0419] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0420] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0421] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0422] [Third Embodiment]

[0423] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0424] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0425] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0426] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0427] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0428] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0429] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0430] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0431] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0432] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0433] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0434] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0435] As a specific embodiment for carrying out the present invention, an example of a system combining a generating device, a presenting device, a verification device, and a purchase right granting device is shown. This system is used when selling popular products in stores.

[0436] The server acts as the initial generating device, retrieving detailed information about the target product from the database. This information includes release date, product characteristics, brand history, and the latest related news. Based on this information, the server uses machine learning models to generate questions to present to potential buyers. This increases the variety of questions and deters purchases made for resale purposes.

[0437] The generated questions are sent from the server to terminals installed in the store. The terminals, acting as display devices, present the received questions to potential customers. Users review the presented questions on the terminal and enter their answers based on their knowledge.

[0438] The entered response is sent to a server that functions as a verification device. The server uses natural language processing technology to analyze the received response and evaluate whether it is correct. If the evaluation determines that the response is correct, the server functions as a device that grants purchase rights and notifies the terminal that the user has the right to purchase the product.

[0439] As a concrete example, consider a scenario where a user tries to purchase a limited-edition pair of sneakers. Suppose the server generates and presents the question to the user's device: "In what year were these sneakers first released?" If the user answers with the correct year, the server evaluates the answer, and if correct, grants the user the right to purchase them. This allows the user to complete the sneaker purchase process.

[0440] As described above, by implementing the present invention, it is possible to exclude buyers who intend to resell the products and to provide fair purchasing opportunities to genuine buyers who sincerely seek the products.

[0441] The following describes the processing flow.

[0442] Step 1:

[0443] The server retrieves detailed information about products scheduled for sale from the database. This includes the product's release date, characteristics, brand history, and latest news.

[0444] Step 2:

[0445] The server requests a machine learning model to use this acquired information to generate questions to present to the buyer. The generated questions will be designed to verify whether the buyer understands the product's characteristics.

[0446] Step 3:

[0447] The server sends the generated questions to terminals installed in the store. These questions are then ready to be presented to potential customers.

[0448] Step 4:

[0449] The terminal displays questions to the user in the store. The user enters their answers to the questions presented on the spot.

[0450] Step 5:

[0451] The terminal sends the user's response to the server, so that the user's input can be analyzed and evaluated.

[0452] Step 6:

[0453] The server uses natural language processing technology to analyze the received responses and evaluate their accuracy. It then determines whether the response is correct.

[0454] Step 7:

[0455] If the server determines that the answer is correct, it sends a notification to the device granting the user the right to purchase the item.

[0456] Step 8:

[0457] The user completes the purchase process, and the device sends that information to the server. The server records the purchase information in its database and updates the sales status.

[0458] This series of steps creates a system that eliminates buyers who intend to resell the products and ensures that only legitimate buyers receive them.

[0459] (Example 1)

[0460] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0461] In retail settings, there is a need to curb purchases made for resale purposes while providing fair purchasing opportunities to legitimate buyers. Existing systems have the challenge of not being able to accurately determine the buyer's intentions and appropriately grant purchasing rights.

[0462] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0463] In this invention, the server includes means for acquiring product information related to a prospective buyer and generating questions to present to the buyer based on that information; means for displaying the questions to the prospective buyer using a terminal device for presenting the questions generated using a generation AI model; and means for analyzing and evaluating the answers entered by the prospective buyer using natural language processing technology. This makes it possible to suppress purchases for resale purposes and to grant fair purchasing rights to sincere prospective buyers.

[0464] A "prospective buyer" refers to an individual or legal entity that intends to purchase a specific product.

[0465] "Product information" refers to important data regarding a purchase, including product characteristics, release date, brand history, and related news.

[0466] A "generative AI model" refers to a technology that uses machine learning to analyze data and generate questions or sentences tailored to specific purposes.

[0467] A "terminal device" refers to a device installed within a store that is equipped with a user interface and functions to display questions to users and receive answers.

[0468] "Natural language processing technology" refers to algorithms and methods that enable computers to understand, analyze, and determine the meaning of human language.

[0469] "Right to purchase" refers to the qualification or permission to purchase a specific product.

[0470] This invention is a system implemented through the collaboration of a server, a terminal, and a user. The server functions as the core of this system, processing and analyzing detailed product information using a generative AI model. Specifically, it automatically generates questions to be presented to potential buyers based on product information obtained from a database. Machine learning technology is used for this generation, and various data points such as product characteristics, release date, and brand history are utilized.

[0471] Questions provided by the server are sent to a terminal. The terminal, installed in the store and equipped with a user interface, allows prospective customers to read the received questions and enter answers based on their own knowledge. The terminal can use a touchscreen or keyboard as its user interface.

[0472] The user enters an answer to a question displayed on their device. The entered answer is sent from the device to the server. The server then analyzes the received answer using natural language processing technology to determine its accuracy. The analysis technology includes text classification and semantic analysis, which allows for efficient evaluation of the correctness of the answer.

[0473] For answers deemed correct, the server grants the buyer the right to purchase. This granting of the right is notified to the user via their device, and the purchase process proceeds. This format effectively suppresses purchases for resale purposes and provides fair purchasing opportunities to genuine buyers.

[0474] For example, if the question generated by the server is "In what year were these sneakers first released?", the user answers that year on their device. The server then evaluates the answer, and if it is correct, the user is granted the right to purchase them.

[0475] An example of a prompt message might be, "Please describe the events related to this product based on a timeline."

[0476] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0477] Step 1:

[0478] The server retrieves product information from the database. Specifically, it extracts information such as product characteristics, release date, brand history, and the latest related news. Based on this information, it prepares data to be input into the generative AI model. The output at this stage is an organized set of information to be passed to the model.

[0479] Step 2:

[0480] The server uses a generative AI model to generate questions based on acquired product information. In this process, the model analyzes the given information and creates questions to present to potential buyers. For example, a question such as "In what year were these sneakers first released?" might be generated. The input in this case is the information data prepared in the previous step, and the output is the generated question.

[0481] Step 3:

[0482] The server sends the generated question to the terminal. The terminal is installed in the store and prepares to display the sent question on its screen. The input here is the question data from the server, and the output is the display data, which is the question converted into a format that can be displayed.

[0483] Step 4:

[0484] The user views the question displayed on the device and enters an answer based on their knowledge. Specifically, they directly input the answer to the question using the device's touch panel or keyboard. At this stage, the input is the question displayed on the device, and the output is the answer data entered by the user.

[0485] Step 5:

[0486] The terminal sends the user's response to the server. The server analyzes the received response data using natural language processing technology. Specifically, the processing involves text classification and semantic analysis to determine whether the response is correct. The input is the user's response data, and the output is the result of determining whether the response is correct or incorrect.

[0487] Step 6:

[0488] The server grants the user the right to purchase if the answer is evaluated as correct. The server sends this information to the terminal, which displays a notification to the user such as "Purchase rights have been granted." The input here is the evaluation result of the answer, and the output is the notification message to the user.

[0489] (Application Example 1)

[0490] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0491] When popular products are sold in stores, it is necessary to prevent purchases for resale purposes and to provide fair purchasing opportunities to genuine buyers. However, conventional methods have made it difficult to effectively identify genuine buyers and ensure fair purchasing opportunities. Against this backdrop, a system is needed that accurately grasps the intentions of buyers and provides fair purchasing procedures.

[0492] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0493] In this invention, the server includes means for creating tasks to be presented to prospective buyers based on information related to the articles using an information generation device, means for presenting the tasks to the prospective buyers using an information display device, and means for receiving and evaluating the prospective buyers' answers using an information verification device. This makes it possible to evaluate whether the prospective buyer has a sincere intention and not intends to resell the goods, and to provide a fair purchasing procedure.

[0494] An "information generation device" is a device that creates tasks to be presented to prospective buyers based on information related to goods.

[0495] An "information display device" is a device used to present problems generated by an information generation device to prospective buyers.

[0496] An "information verification device" is a device used to receive and evaluate responses from prospective buyers.

[0497] A "purchase right granting device" is a device that grants purchase rights to prospective buyers who have provided correct answers based on the evaluation of the information verification device.

[0498] A "communication device" is a device that transmits purchase information to a mobile information terminal and displays that information.

[0499] A "learning model" is a mathematical model used to generate problems related to objects using machine learning techniques.

[0500] "Natural language processing techniques" are technologies that use computers to analyze text and understand human language when evaluating responses from potential buyers.

[0501] A "potential buyer" is a person who wishes to purchase a specific product.

[0502] "Goods" refers to all products and merchandise sold in stores.

[0503] The system for implementing this invention targets the sale of popular products in stores. The server functions as an information generation device, retrieving information related to the items from a database. This information includes product name, release date, features, related news, etc. Based on the retrieved information, the server uses a learning model to generate tasks to present to potential buyers.

[0504] The generated task is displayed on a terminal via an information display device. This terminal may be a smartphone or a digital display installed in the store. The task is designed to verify that the prospective buyer is not intending to resell the item. The user enters their answer to the presented task based on their knowledge and experience.

[0505] The entered answer is sent to a server that functions as an information verification device. The server evaluates the answer using natural language processing techniques. If the evaluation determines that the answer is correct, the server functions as a purchase right granting device and grants the user who provided the correct answer a purchase right. The purchase right is embodied as a QR code displayed on the terminal, and the actual purchase procedure is completed by presenting this to the store staff.

[0506] For example, if the server generates the question "Who is the designer of this product?", and the user answers with the correct designer name, the server will evaluate the answer as correct, and a QR code granting purchase rights will be immediately issued. Another example of a prompt message is, "Please generate a question about this product. Possible questions include the product's history, designer, and initial release year."

[0507] The system consists of a server-side implementation combining Python and Django, a user interface for the device using Flutter, and natural language processing using Hugging Face's Transformers. This enables a smooth purchase process in stores and ensures fair purchasing opportunities.

[0508] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0509] Step 1:

[0510] The server retrieves data about an item from a database. This data includes product name, release date, features, and brand history. Based on this data, the server generates prompts and questions using a learning model. The input is information from the database, and the output is the generated question.

[0511] Step 2:

[0512] The server sends the generated question to the terminal. The terminal activates the interface and prepares a screen for user interaction to display this question to the user. The input in this step is the question from the server, and the output is the question displayed to the user.

[0513] Step 3:

[0514] The user enters their answer to a question presented on the terminal. The user interface accepts the answer via touch input, voice input, etc., formats the received data, and sends it to the server. The input here is the user's answer, and the output is the formatted answer data sent to the server.

[0515] Step 4:

[0516] The server analyzes the received answers using natural language processing techniques. It uses Hugging Face's Transformers to evaluate whether the answers are correct. The input is the answer data received from the user, and the output is the evaluation result.

[0517] Step 5:

[0518] If the server evaluates the answer as correct, it functions as a purchase right granting device and generates a QR code to grant the purchase right to the user's terminal. This QR code is presented to store staff at the time of actual purchase. The input for this step is the correctness of the evaluated answer, and the output is the generated QR code.

[0519] Step 6:

[0520] The user displays the generated QR code on their device and presents it to the store staff. This allows them to exercise their right to purchase the product and complete the actual purchase process. The input for this step is the QR code on the device, and the output is the completion of the purchase process.

[0521] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0522] As a specific embodiment for carrying out the present invention, an example of a system incorporating an emotion engine is shown, in addition to a generating device, a presenting device, a confirmation device, and a device for granting purchase rights. This system is used when selling popular products in stores, and aims not only to prevent resale but also to improve the customer experience.

[0523] First, the server functions as a generation device, retrieving data from a database regarding the characteristics and historical background of the products being sold. Based on this information, it uses a machine learning model to generate questions to suggest to buyers. The generated questions ask users about their understanding of the product.

[0524] The generated questions are sent from the server to a terminal installed in the store. This terminal presents the questions to users who wish to make a purchase. The terminal provides an interface where users can review the questions and enter their answers.

[0525] In this system, an emotion engine is built into the terminal and recognizes and analyzes the user's emotions in real time while they are entering their answers. The emotion engine can detect the user's emotional state using camera and voice analysis technology. The analyzed emotion data is taken into consideration when evaluating answers and granting purchase rights.

[0526] When a user enters an answer to a question into their device, that answer is sent from the device to the server. The server uses natural language processing technology to evaluate the answer and improves the accuracy of the evaluation by supplementing it with data from the sentiment engine.

[0527] After the evaluation is complete, the server decides whether to grant the right to purchase based on the evaluation results and notifies the terminal. If the user is deemed to have answered appropriately and their emotional state is deemed suitable, the right to purchase is granted, and the user gains the right to buy the product.

[0528] As a concrete example, if a user attempts to purchase a limited-edition piece of clothing, the server will generate the question, "Who is the designer of this clothing?" If the user answers immediately and the emotion engine confirms their sincere intention to purchase, the user will be granted the right to purchase. In this way, the present invention can be implemented to prevent resale while providing users with a good purchasing experience.

[0529] The following describes the processing flow.

[0530] Step 1:

[0531] The server retrieves detailed product information from the database. This includes product features, brand information, and related news.

[0532] Step 2:

[0533] The server automatically generates questions to present to the buyer based on information obtained using a machine learning model. The generated questions assess the buyer's understanding of the product.

[0534] Step 3:

[0535] The server sends the generated question to a terminal installed in the store. The terminal prepares to display the question.

[0536] Step 4:

[0537] The terminal displays questions to users who are interested in purchasing items at the store. The user reviews the questions and enters their answers.

[0538] Step 5:

[0539] The device uses the user's face and voice to activate an emotion engine, identifying and recording the user's emotional state in real time.

[0540] Step 6:

[0541] The terminal sends the user's entered responses and sentiment data to the server. The server receives this data.

[0542] Step 7:

[0543] The server uses natural language processing technology to evaluate the user's responses. Simultaneously, it references sentiment data provided by the sentiment engine and uses it to assist in the evaluation.

[0544] Step 8:

[0545] The server decides to grant the right to purchase based on the evaluation results. If the answer is correct or the emotional state is judged to be good, a notification of the granting of the right to purchase is sent to the terminal.

[0546] Step 9:

[0547] Users receive a notification from their device granting them the right to purchase the product, and can then proceed with the purchase process.

[0548] This entire process makes it possible to curb reselling while providing users with a more personalized purchasing experience.

[0549] (Example 2)

[0550] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0551] In recent years, the resale problem that arises when purchasing popular products has become a serious issue for both consumers and sellers. Furthermore, there is a need for new methods to verify whether consumers have honest and appropriate intentions when purchasing products, and to improve the customer experience. Traditional methods make it difficult to assess the psychological state of buyers in real time, and as a result, honest customers may be denied the right to purchase.

[0552] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0553] In this invention, the server includes means for creating questions to be presented to a purchaser based on product-related information using a generating device, means for displaying the questions to the purchaser using a presenting device, and means for analyzing the purchaser's emotional state using an emotion detection device. This makes it possible to improve the consumer purchasing experience while increasing the purchaser's understanding and sincerity, and deterring resale.

[0554] A "generating device" is a device that acquires information related to a product and uses a machine learning model to create questions to present to the buyer based on that information.

[0555] A "presenting device" is a device that provides a buyer with an interface to display generated questions and has the function of allowing the user to input answers to the questions.

[0556] An "emotion detection device" is a device designed to analyze the emotional state of a purchaser. It uses cameras and voice analysis technology to measure the user's facial expressions and tone of voice, and has the function of evaluating emotions in real time.

[0557] A "verification device" is a device that receives responses entered by purchasers and evaluates their accuracy using natural language processing technology.

[0558] A "device that grants the right to purchase" is a device that, if the buyer's answer is evaluated as correct, grants that buyer the right to purchase the product.

[0559] Embodiments of the present invention will now be described. This system aims to prevent resale and improve the customer experience in product sales, and is particularly effective when selling popular products in stores.

[0560] The server retrieves information about the product's characteristics and historical background from a database. Using this retrieved data, the server generates product-related questions to present to the buyer, based on a generative AI model. For example, for a user considering purchasing a limited-edition piece of clothing, it can generate a specific question such as, "Who is the designer of this clothing?"

[0561] The generated questions are sent to the device and displayed to the buyer. The device provides an interface for the user to answer the questions. The device has a built-in camera and microphone, which function as an emotion detection device. This device analyzes the user's facial expressions and tone of voice in real time to obtain data to evaluate whether the user is giving honest answers.

[0562] User responses are sent from the device to the server, which evaluates the responses using natural language processing technology. Furthermore, sentiment data is taken into consideration to improve the accuracy and sincerity of the responses.

[0563] Based on the evaluation results, the server decides whether to grant the right to purchase and notifies the user of the result via the terminal. If the user answers the questions accurately and their emotional state is deemed appropriate for the sales intent, the right to purchase is granted to that user.

[0564] This system provides a direct and interactive purchasing experience while ensuring fair trade for both consumers and sellers.

[0565] An example of a prompt message is: "Analyze the sentiment of users who have shown interest in the limited-edition product, confirm that you have accurate knowledge, and then explain how to offer them the right to purchase it."

[0566] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0567] Step 1:

[0568] The server retrieves data about product characteristics and historical background from a database. It accepts product IDs and category information as input. Based on the product information retrieved from the database, it extracts and outputs specific attributes and details used in the next step.

[0569] Step 2:

[0570] The server uses a generative AI model to create questions to present to the buyer based on the acquired product information. The input here is the product information acquired in step 1, and the AI ​​model generates appropriate questions through natural language processing. For example, it might output a specific question such as, "Who designed this product?"

[0571] Step 3:

[0572] The server sends the generated question to a terminal in the store. The input here is the question created in step 2. The terminal receives this question and displays it on its screen. The output is made visible to the user.

[0573] Step 4:

[0574] The terminal provides an interface for the user to read and answer questions. The user enters their answers into input fields provided on the screen. The input is text data entered by the user, which the terminal temporarily stores and prepares to send to the server in a later step.

[0575] Step 5:

[0576] An emotion detection device built into the device analyzes the user's facial expressions and voice in real time. Inputs here are video from the camera and audio data from the microphone. This data is analyzed, and the user's emotional state is output as numerical data.

[0577] Step 6:

[0578] The terminal sends the user's responses and emotional state data to the server. The inputs are the text responses from step 4 and the emotional state data obtained in step 5. The server receives these inputs and prepares to proceed.

[0579] Step 7:

[0580] The server uses natural language processing technology to evaluate the user's response. The input here is the text response received from step 6. The accuracy of the response is analyzed, and the evaluation result is quantified and output. Furthermore, emotional state data is taken into consideration to arrive at the final evaluation.

[0581] Step 8:

[0582] The server decides whether to grant the right to purchase based on the evaluation results. The input is the evaluation result obtained in step 7. If the evaluation meets the criteria, the server decides to grant the right to purchase to the user and sends the result as output to the terminal.

[0583] Step 9:

[0584] The terminal receives the result of the purchase right grant from the server and notifies the user. The input here is the purchase right grant decision output by the server. If the user has obtained the purchase right, the message "Congratulations, you have been granted the purchase right" is displayed and output on the screen. The user can then proceed with the purchase process.

[0585] (Application Example 2)

[0586] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0587] Traditional product sales methods face challenges such as fraudulent purchases by resellers and difficulty in providing buyers with a fair purchasing experience. In particular, when selling popular or limited-edition items, legitimate buyers are often at a disadvantage. Furthermore, the lack of mechanisms for buyers to demonstrate their understanding of and sincerity regarding a product makes it difficult to ensure that products reach the right buyers.

[0588] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0589] In this invention, the server includes means for creating questions to be presented to a purchaser based on product-related information using a generating device, means for displaying the questions to the purchaser using a presenting device, means for receiving and evaluating the purchaser's answers using a confirmation device, and means for analyzing the purchaser's emotional state using an emotion-recognizing device. This makes it possible to appropriately provide products to purchasers who understand and have sincerity towards the products.

[0590] A "generating device" is a device that has the function of creating questions to be presented to the purchaser based on information related to the product.

[0591] A "presentation device" is a device that displays generated questions to the purchaser and communicates with the user through an interface.

[0592] A "verification device" is a device that has the function of receiving responses from purchasers and evaluating them.

[0593] A "device for granting purchase rights" is a device that has the function of granting purchase rights to buyers based on an evaluation.

[0594] A "device that recognizes emotions" is a device that uses cameras and voice analysis to detect emotions in order to analyze the user's emotional state and has the function of processing that information.

[0595] A "machine learning model" is a mathematical model that learns from a set of data and can automatically make predictions and decisions regarding a specified task.

[0596] "Natural language processing technology" is a technology that enables computers to understand and process natural language, which is the language spoken by humans.

[0597] A "prompt statement" is a sentence that provides instructions or information to a generative AI model to perform a specific task.

[0598] The system for carrying out this invention comprises a server, a presentation device, an emotion recognition device, and a purchase right granting device. The server uses a generative AI model to generate questions to present to the purchaser based on product-related information. These generated questions are created based on prompt statements and assess the purchaser's understanding of the product, as will be shown in the specific examples described later.

[0599] The server generates a question and sends it to a terminal used within the store. This terminal provides users who wish to make a purchase with an interface to view the question and input their answer. The display device could be a smart glasses display or a display installed in the store.

[0600] When a user answers questions via a terminal, an emotion recognition device analyzes the user's emotional state. Emotion recognition is performed through a camera and microphone, detecting emotions from the user's facial expressions and tone of voice. Specifically, OpenCV is used for the camera, and a speech recognition library is used for speech analysis.

[0601] User responses and sentiment data are sent to a server for evaluation, which uses natural language processing techniques to perform an overall assessment. Sentiment data is used as supplementary information to determine the truthfulness and sincerity of the responses.

[0602] If the evaluation determines that the user has provided appropriate answers and emotional states, the right to purchase will be granted. This granting of the right to purchase will be notified to the user via their device.

[0603] For example, if a user wants to purchase a limited-edition new clothing item, the server generates the question, "Who is the designer of this clothing item?" and presents it to the user through smart glasses. If the user answers immediately and their facial expression is deemed sincere, they are granted the right to purchase the item.

[0604] An example of a prompt to input into the generation AI model would be: "Generate a question that asks the user for specific product knowledge. The product name should be 'New Clothing Item,' and the related information should include 'Designer's Name.'"

[0605] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0606] Step 1:

[0607] The server retrieves product-related data from the database. Product IDs and category information are provided as input, and the server processes this information to retrieve related product characteristics and historical background from the database. The retrieved product information is provided as output.

[0608] Step 2:

[0609] The server generates questions using a generation AI model. As input, a prompt sentence is constructed based on the product information obtained in step 1, and this prompt sentence is input into the generation AI model. Through data calculation, questions that ask about relevant product knowledge are generated, and specific question sentences are obtained as output.

[0610] Step 3:

[0611] The server sends the generated question to the terminal. The input is the question text generated in step 2, which is sent to the terminal in the store via the network. The output is the question to be displayed, which is provided to the terminal.

[0612] Step 4:

[0613] The terminal presents a question to the user and accepts their response. The input is the question text sent to the terminal in step 3. The terminal visualizes the question for the user via a display device. It accepts voice responses and text input from the user, and the user response data is obtained as output.

[0614] Step 5:

[0615] An emotion recognition device analyzes the user's emotions. The input consists of audio and video data acquired when the user responds. Based on this data, an emotion recognition algorithm analyzes the user's facial expressions and vocal characteristics to detect their emotional state. The output is the analyzed emotion data.

[0616] Step 6:

[0617] The server uses natural language processing technology to evaluate the user's responses. The input consists of user response data obtained in step 4 and sentiment data obtained in step 5. The natural language processing model analyzes this data to evaluate the accuracy and sincerity of the responses. The output includes an evaluation score and whether or not the purchase right is granted.

[0618] Step 7:

[0619] The server decides whether to grant the purchase right and notifies the terminal of the result. The input is the evaluation result obtained in step 6. The server makes a decision on whether to grant the purchase right and sends the result to the terminal. The output is a notification regarding the granting of the purchase right provided to the user.

[0620] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0621] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0622] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0623] [Fourth Embodiment]

[0624] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0625] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0626] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0627] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0628] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0629] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0630] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0631] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0632] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0633] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0634] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0635] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0636] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0637] As a specific embodiment for carrying out the present invention, an example of a system combining a generating device, a presenting device, a verification device, and a purchase right granting device is shown. This system is used when selling popular products in stores.

[0638] The server acts as the initial generating device, retrieving detailed information about the target product from the database. This information includes release date, product characteristics, brand history, and the latest related news. Based on this information, the server uses machine learning models to generate questions to present to potential buyers. This increases the variety of questions and deters purchases made for resale purposes.

[0639] The generated questions are sent from the server to terminals installed in the store. The terminals, acting as display devices, present the received questions to potential customers. Users review the presented questions on the terminal and enter their answers based on their knowledge.

[0640] The entered response is sent to a server that functions as a verification device. The server uses natural language processing technology to analyze the received response and evaluate whether it is correct. If the evaluation determines that the response is correct, the server functions as a device that grants purchase rights and notifies the terminal that the user has the right to purchase the product.

[0641] As a concrete example, consider a scenario where a user tries to purchase a limited-edition pair of sneakers. Suppose the server generates and presents the question to the user's device: "In what year were these sneakers first released?" If the user answers with the correct year, the server evaluates the answer, and if correct, grants the user the right to purchase them. This allows the user to complete the sneaker purchase process.

[0642] As described above, by implementing the present invention, it is possible to exclude buyers who intend to resell the products and to provide fair purchasing opportunities to genuine buyers who sincerely seek the products.

[0643] The following describes the processing flow.

[0644] Step 1:

[0645] The server retrieves detailed information about products scheduled for sale from the database. This includes the product's release date, characteristics, brand history, and latest news.

[0646] Step 2:

[0647] The server requests a machine learning model to use this acquired information to generate questions to present to the buyer. The generated questions will be designed to verify whether the buyer understands the product's characteristics.

[0648] Step 3:

[0649] The server sends the generated questions to terminals installed in the store. These questions are then ready to be presented to potential customers.

[0650] Step 4:

[0651] The terminal displays questions to the user in the store. The user enters their answers to the questions presented on the spot.

[0652] Step 5:

[0653] The terminal sends the user's response to the server, so that the user's input can be analyzed and evaluated.

[0654] Step 6:

[0655] The server uses natural language processing technology to analyze the received responses and evaluate their accuracy. It then determines whether the response is correct.

[0656] Step 7:

[0657] If the server determines that the answer is correct, it sends a notification to the device granting the user the right to purchase the item.

[0658] Step 8:

[0659] The user completes the purchase process, and the device sends that information to the server. The server records the purchase information in its database and updates the sales status.

[0660] This series of steps creates a system that eliminates buyers who intend to resell the products and ensures that only legitimate buyers receive them.

[0661] (Example 1)

[0662] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0663] In retail settings, there is a need to curb purchases made for resale purposes while providing fair purchasing opportunities to legitimate buyers. Existing systems have the challenge of not being able to accurately determine the buyer's intentions and appropriately grant purchasing rights.

[0664] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0665] In this invention, the server includes means for acquiring product information related to a prospective buyer and generating questions to present to the buyer based on that information; means for displaying the questions to the prospective buyer using a terminal device for presenting the questions generated using a generation AI model; and means for analyzing and evaluating the answers entered by the prospective buyer using natural language processing technology. This makes it possible to suppress purchases for resale purposes and to grant fair purchasing rights to sincere prospective buyers.

[0666] A "prospective buyer" refers to an individual or legal entity that intends to purchase a specific product.

[0667] "Product information" refers to important data regarding a purchase, including product characteristics, release date, brand history, and related news.

[0668] A "generative AI model" refers to a technology that uses machine learning to analyze data and generate questions or sentences tailored to specific purposes.

[0669] A "terminal device" refers to a device installed within a store that is equipped with a user interface and functions to display questions to users and receive answers.

[0670] "Natural language processing technology" refers to algorithms and methods that enable computers to understand, analyze, and determine the meaning of human language.

[0671] "Right to purchase" refers to the qualification or permission to purchase a specific product.

[0672] This invention is a system implemented through the collaboration of a server, a terminal, and a user. The server functions as the core of this system, processing and analyzing detailed product information using a generative AI model. Specifically, it automatically generates questions to be presented to potential buyers based on product information obtained from a database. Machine learning technology is used for this generation, and various data points such as product characteristics, release date, and brand history are utilized.

[0673] Questions provided by the server are sent to a terminal. The terminal, installed in the store and equipped with a user interface, allows prospective customers to read the received questions and enter answers based on their own knowledge. The terminal can use a touchscreen or keyboard as its user interface.

[0674] The user enters an answer to a question displayed on their device. The entered answer is sent from the device to the server. The server then analyzes the received answer using natural language processing technology to determine its accuracy. The analysis technology includes text classification and semantic analysis, which allows for efficient evaluation of the correctness of the answer.

[0675] For answers deemed correct, the server grants the buyer the right to purchase. This granting of the right is notified to the user via their device, and the purchase process proceeds. This format effectively suppresses purchases for resale purposes and provides fair purchasing opportunities to genuine buyers.

[0676] For example, if the question generated by the server is "In what year were these sneakers first released?", the user answers that year on their device. The server then evaluates the answer, and if it is correct, the user is granted the right to purchase them.

[0677] An example of a prompt message might be, "Please describe the events related to this product based on a timeline."

[0678] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0679] Step 1:

[0680] The server retrieves product information from the database. Specifically, it extracts information such as product characteristics, release date, brand history, and the latest related news. Based on this information, it prepares data to be input into the generative AI model. The output at this stage is an organized set of information to be passed to the model.

[0681] Step 2:

[0682] The server uses a generative AI model to generate questions based on acquired product information. In this process, the model analyzes the given information and creates questions to present to potential buyers. For example, a question such as "In what year were these sneakers first released?" might be generated. The input in this case is the information data prepared in the previous step, and the output is the generated question.

[0683] Step 3:

[0684] The server sends the generated question to the terminal. The terminal is installed in the store and prepares to display the sent question on its screen. The input here is the question data from the server, and the output is the display data, which is the question converted into a format that can be displayed.

[0685] Step 4:

[0686] The user views the question displayed on the device and enters an answer based on their knowledge. Specifically, they directly input the answer to the question using the device's touch panel or keyboard. At this stage, the input is the question displayed on the device, and the output is the answer data entered by the user.

[0687] Step 5:

[0688] The terminal sends the user's response to the server. The server analyzes the received response data using natural language processing technology. Specifically, the processing involves text classification and semantic analysis to determine whether the response is correct. The input is the user's response data, and the output is the result of determining whether the response is correct or incorrect.

[0689] Step 6:

[0690] The server grants the user the right to purchase if the answer is evaluated as correct. The server sends this information to the terminal, which displays a notification to the user such as "Purchase rights have been granted." The input here is the evaluation result of the answer, and the output is the notification message to the user.

[0691] (Application Example 1)

[0692] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0693] When popular products are sold in stores, it is necessary to prevent purchases for resale purposes and to provide fair purchasing opportunities to genuine buyers. However, conventional methods have made it difficult to effectively identify genuine buyers and ensure fair purchasing opportunities. Against this backdrop, a system is needed that accurately grasps the intentions of buyers and provides fair purchasing procedures.

[0694] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0695] In this invention, the server includes means for creating tasks to be presented to prospective buyers based on information related to the articles using an information generation device, means for presenting the tasks to the prospective buyers using an information display device, and means for receiving and evaluating the prospective buyers' answers using an information verification device. This makes it possible to evaluate whether the prospective buyer has a sincere intention and not intends to resell the goods, and to provide a fair purchasing procedure.

[0696] An "information generation device" is a device that creates tasks to be presented to prospective buyers based on information related to goods.

[0697] An "information display device" is a device used to present problems generated by an information generation device to prospective buyers.

[0698] An "information verification device" is a device used to receive and evaluate responses from prospective buyers.

[0699] A "purchase right granting device" is a device that grants purchase rights to prospective buyers who have provided correct answers based on the evaluation of the information verification device.

[0700] A "communication device" is a device that transmits purchase information to a mobile information terminal and displays that information.

[0701] A "learning model" is a mathematical model used to generate problems related to objects using machine learning techniques.

[0702] "Natural language processing techniques" are technologies that use computers to analyze text and understand human language when evaluating responses from potential buyers.

[0703] A "potential buyer" is a person who wishes to purchase a specific product.

[0704] "Goods" refers to all products and merchandise sold in stores.

[0705] The system for implementing this invention targets the sale of popular products in stores. The server functions as an information generation device, retrieving information related to the items from a database. This information includes product name, release date, features, related news, etc. Based on the retrieved information, the server uses a learning model to generate tasks to present to potential buyers.

[0706] The generated task is displayed on a terminal via an information display device. This terminal may be a smartphone or a digital display installed in the store. The task is designed to verify that the prospective buyer is not intending to resell the item. The user enters their answer to the presented task based on their knowledge and experience.

[0707] The entered answer is sent to a server that functions as an information verification device. The server evaluates the answer using natural language processing techniques. If the evaluation determines that the answer is correct, the server functions as a purchase right granting device and grants the user who provided the correct answer a purchase right. The purchase right is embodied as a QR code displayed on the terminal, and the actual purchase procedure is completed by presenting this to the store staff.

[0708] For example, if the server generates the question "Who is the designer of this product?", and the user answers with the correct designer name, the server will evaluate the answer as correct, and a QR code granting purchase rights will be immediately issued. Another example of a prompt message is, "Please generate a question about this product. Possible questions include the product's history, designer, and initial release year."

[0709] The system consists of a server-side implementation combining Python and Django, a user interface for the device using Flutter, and natural language processing using Hugging Face's Transformers. This enables a smooth purchase process in stores and ensures fair purchasing opportunities.

[0710] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0711] Step 1:

[0712] The server retrieves data about an item from a database. This data includes product name, release date, features, and brand history. Based on this data, the server generates prompts and questions using a learning model. The input is information from the database, and the output is the generated question.

[0713] Step 2:

[0714] The server sends the generated question to the terminal. The terminal activates the interface and prepares a screen for user interaction to display this question to the user. The input in this step is the question from the server, and the output is the question displayed to the user.

[0715] Step 3:

[0716] The user enters their answer to a question presented on the terminal. The user interface accepts the answer via touch input, voice input, etc., formats the received data, and sends it to the server. The input here is the user's answer, and the output is the formatted answer data sent to the server.

[0717] Step 4:

[0718] The server analyzes the received answers using natural language processing techniques. It uses Hugging Face's Transformers to evaluate whether the answers are correct. The input is the answer data received from the user, and the output is the evaluation result.

[0719] Step 5:

[0720] If the server evaluates the answer as correct, it functions as a purchase right granting device and generates a QR code to grant the purchase right to the user's terminal. This QR code is presented to store staff at the time of actual purchase. The input for this step is the correctness of the evaluated answer, and the output is the generated QR code.

[0721] Step 6:

[0722] The user displays the generated QR code on their device and presents it to the store staff. This allows them to exercise their right to purchase the product and complete the actual purchase process. The input for this step is the QR code on the device, and the output is the completion of the purchase process.

[0723] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0724] As a specific embodiment for carrying out the present invention, an example of a system incorporating an emotion engine is shown, in addition to a generating device, a presenting device, a confirmation device, and a device for granting purchase rights. This system is used when selling popular products in stores, and aims not only to prevent resale but also to improve the customer experience.

[0725] First, the server functions as a generation device, retrieving data from a database regarding the characteristics and historical background of the products being sold. Based on this information, it uses a machine learning model to generate questions to suggest to buyers. The generated questions ask users about their understanding of the product.

[0726] The generated questions are sent from the server to a terminal installed in the store. This terminal presents the questions to users who wish to make a purchase. The terminal provides an interface where users can review the questions and enter their answers.

[0727] In this system, an emotion engine is built into the terminal and recognizes and analyzes the user's emotions in real time while they are entering their answers. The emotion engine can detect the user's emotional state using camera and voice analysis technology. The analyzed emotion data is taken into consideration when evaluating answers and granting purchase rights.

[0728] When a user enters an answer to a question into their device, that answer is sent from the device to the server. The server uses natural language processing technology to evaluate the answer and improves the accuracy of the evaluation by supplementing it with data from the sentiment engine.

[0729] After the evaluation is complete, the server decides whether to grant the right to purchase based on the evaluation results and notifies the terminal. If the user is deemed to have answered appropriately and their emotional state is deemed suitable, the right to purchase is granted, and the user gains the right to buy the product.

[0730] As a concrete example, if a user attempts to purchase a limited-edition piece of clothing, the server will generate the question, "Who is the designer of this clothing?" If the user answers immediately and the emotion engine confirms their sincere intention to purchase, the user will be granted the right to purchase. In this way, the present invention can be implemented to prevent resale while providing users with a good purchasing experience.

[0731] The following describes the processing flow.

[0732] Step 1:

[0733] The server retrieves detailed product information from the database. This includes product features, brand information, and related news.

[0734] Step 2:

[0735] The server automatically generates questions to present to the buyer based on information obtained using a machine learning model. The generated questions assess the buyer's understanding of the product.

[0736] Step 3:

[0737] The server sends the generated question to a terminal installed in the store. The terminal prepares to display the question.

[0738] Step 4:

[0739] The terminal displays questions to users who are interested in purchasing items at the store. The user reviews the questions and enters their answers.

[0740] Step 5:

[0741] The device uses the user's face and voice to activate an emotion engine, identifying and recording the user's emotional state in real time.

[0742] Step 6:

[0743] The terminal sends the user's entered responses and sentiment data to the server. The server receives this data.

[0744] Step 7:

[0745] The server uses natural language processing technology to evaluate the user's responses. Simultaneously, it references sentiment data provided by the sentiment engine and uses it to assist in the evaluation.

[0746] Step 8:

[0747] The server decides to grant the right to purchase based on the evaluation results. If the answer is correct or the emotional state is judged to be good, a notification of the granting of the right to purchase is sent to the terminal.

[0748] Step 9:

[0749] Users receive a notification from their device granting them the right to purchase the product, and can then proceed with the purchase process.

[0750] This entire process makes it possible to curb reselling while providing users with a more personalized purchasing experience.

[0751] (Example 2)

[0752] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0753] In recent years, the resale problem that arises when purchasing popular products has become a serious issue for both consumers and sellers. Furthermore, there is a need for new methods to verify whether consumers have honest and appropriate intentions when purchasing products, and to improve the customer experience. Traditional methods make it difficult to assess the psychological state of buyers in real time, and as a result, honest customers may be denied the right to purchase.

[0754] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0755] In this invention, the server includes means for creating questions to be presented to a purchaser based on product-related information using a generating device, means for displaying the questions to the purchaser using a presenting device, and means for analyzing the purchaser's emotional state using an emotion detection device. This makes it possible to improve the consumer purchasing experience while increasing the purchaser's understanding and sincerity, and deterring resale.

[0756] A "generating device" is a device that acquires information related to a product and uses a machine learning model to create questions to present to the buyer based on that information.

[0757] A "presenting device" is a device that provides a buyer with an interface to display generated questions and has the function of allowing the user to input answers to the questions.

[0758] An "emotion detection device" is a device designed to analyze the emotional state of a purchaser. It uses cameras and voice analysis technology to measure the user's facial expressions and tone of voice, and has the function of evaluating emotions in real time.

[0759] A "verification device" is a device that receives responses entered by purchasers and evaluates their accuracy using natural language processing technology.

[0760] A "device that grants the right to purchase" is a device that, if the buyer's answer is evaluated as correct, grants that buyer the right to purchase the product.

[0761] Embodiments of the present invention will now be described. This system aims to prevent resale and improve the customer experience in product sales, and is particularly effective when selling popular products in stores.

[0762] The server retrieves information about the product's characteristics and historical background from a database. Using this retrieved data, the server generates product-related questions to present to the buyer, based on a generative AI model. For example, for a user considering purchasing a limited-edition piece of clothing, it can generate a specific question such as, "Who is the designer of this clothing?"

[0763] The generated questions are sent to the device and displayed to the buyer. The device provides an interface for the user to answer the questions. The device has a built-in camera and microphone, which function as an emotion detection device. This device analyzes the user's facial expressions and tone of voice in real time to obtain data to evaluate whether the user is giving honest answers.

[0764] User responses are sent from the device to the server, which evaluates the responses using natural language processing technology. Furthermore, sentiment data is taken into consideration to improve the accuracy and sincerity of the responses.

[0765] Based on the evaluation results, the server decides whether to grant the right to purchase and notifies the user of the result via the terminal. If the user answers the questions accurately and their emotional state is deemed appropriate for the sales intent, the right to purchase is granted to that user.

[0766] This system provides a direct and interactive purchasing experience while ensuring fair trade for both consumers and sellers.

[0767] An example of a prompt message is: "Analyze the sentiment of users who have shown interest in the limited-edition product, confirm that you have accurate knowledge, and then explain how to offer them the right to purchase it."

[0768] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0769] Step 1:

[0770] The server retrieves data about product characteristics and historical background from a database. It accepts product IDs and category information as input. Based on the product information retrieved from the database, it extracts and outputs specific attributes and details used in the next step.

[0771] Step 2:

[0772] The server uses a generative AI model to create questions to present to the buyer based on the acquired product information. The input here is the product information acquired in step 1, and the AI ​​model generates appropriate questions through natural language processing. For example, it might output a specific question such as, "Who designed this product?"

[0773] Step 3:

[0774] The server sends the generated question to a terminal in the store. The input here is the question created in step 2. The terminal receives this question and displays it on its screen. The output is made visible to the user.

[0775] Step 4:

[0776] The terminal provides an interface for the user to read and answer questions. The user enters their answers into input fields provided on the screen. The input is text data entered by the user, which the terminal temporarily stores and prepares to send to the server in a later step.

[0777] Step 5:

[0778] An emotion detection device built into the device analyzes the user's facial expressions and voice in real time. Inputs here are video from the camera and audio data from the microphone. This data is analyzed, and the user's emotional state is output as numerical data.

[0779] Step 6:

[0780] The terminal sends the user's responses and emotional state data to the server. The inputs are the text responses from step 4 and the emotional state data obtained in step 5. The server receives these inputs and prepares to proceed.

[0781] Step 7:

[0782] The server uses natural language processing technology to evaluate the user's response. The input here is the text response received from step 6. The accuracy of the response is analyzed, and the evaluation result is quantified and output. Furthermore, emotional state data is taken into consideration to arrive at the final evaluation.

[0783] Step 8:

[0784] The server decides whether to grant the right to purchase based on the evaluation results. The input is the evaluation result obtained in step 7. If the evaluation meets the criteria, the server decides to grant the right to purchase to the user and sends the result as output to the terminal.

[0785] Step 9:

[0786] The terminal receives the result of the purchase right grant from the server and notifies the user. The input here is the purchase right grant decision output by the server. If the user has obtained the purchase right, the message "Congratulations, you have been granted the purchase right" is displayed and output on the screen. The user can then proceed with the purchase process.

[0787] (Application Example 2)

[0788] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0789] Traditional product sales methods face challenges such as fraudulent purchases by resellers and difficulty in providing buyers with a fair purchasing experience. In particular, when selling popular or limited-edition items, legitimate buyers are often at a disadvantage. Furthermore, the lack of mechanisms for buyers to demonstrate their understanding of and sincerity regarding a product makes it difficult to ensure that products reach the right buyers.

[0790] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0791] In this invention, the server includes means for creating questions to be presented to a purchaser based on product-related information using a generating device, means for displaying the questions to the purchaser using a presenting device, means for receiving and evaluating the purchaser's answers using a confirmation device, and means for analyzing the purchaser's emotional state using an emotion-recognizing device. This makes it possible to appropriately provide products to purchasers who understand and have sincerity towards the products.

[0792] A "generating device" is a device that has the function of creating questions to be presented to the purchaser based on information related to the product.

[0793] A "presentation device" is a device that displays generated questions to the purchaser and communicates with the user through an interface.

[0794] A "verification device" is a device that has the function of receiving responses from purchasers and evaluating them.

[0795] A "device for granting purchase rights" is a device that has the function of granting purchase rights to buyers based on an evaluation.

[0796] A "device that recognizes emotions" is a device that uses cameras and voice analysis to detect emotions in order to analyze the user's emotional state and has the function of processing that information.

[0797] A "machine learning model" is a mathematical model that learns from a set of data and can automatically make predictions and decisions regarding a specified task.

[0798] "Natural language processing technology" is a technology that enables computers to understand and process natural language, which is the language spoken by humans.

[0799] A "prompt statement" is a sentence that provides instructions or information to a generative AI model to perform a specific task.

[0800] The system for carrying out this invention comprises a server, a presentation device, an emotion recognition device, and a purchase right granting device. The server uses a generative AI model to generate questions to present to the purchaser based on product-related information. These generated questions are created based on prompt statements and assess the purchaser's understanding of the product, as will be shown in the specific examples described later.

[0801] The server generates a question and sends it to a terminal used within the store. This terminal provides users who wish to make a purchase with an interface to view the question and input their answer. The display device could be a smart glasses display or a display installed in the store.

[0802] When a user answers questions via a terminal, an emotion recognition device analyzes the user's emotional state. Emotion recognition is performed through a camera and microphone, detecting emotions from the user's facial expressions and tone of voice. Specifically, OpenCV is used for the camera, and a speech recognition library is used for speech analysis.

[0803] User responses and sentiment data are sent to a server for evaluation, which uses natural language processing techniques to perform an overall assessment. Sentiment data is used as supplementary information to determine the truthfulness and sincerity of the responses.

[0804] If the evaluation determines that the user has provided appropriate answers and emotional states, the right to purchase will be granted. This granting of the right to purchase will be notified to the user via their device.

[0805] For example, if a user wants to purchase a limited-edition new clothing item, the server generates the question, "Who is the designer of this clothing item?" and presents it to the user through smart glasses. If the user answers immediately and their facial expression is deemed sincere, they are granted the right to purchase the item.

[0806] An example of a prompt to input into the generation AI model would be: "Generate a question that asks the user for specific product knowledge. The product name should be 'New Clothing Item,' and the related information should include 'Designer's Name.'"

[0807] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0808] Step 1:

[0809] The server retrieves product-related data from the database. Product IDs and category information are provided as input, and the server processes this information to retrieve related product characteristics and historical background from the database. The retrieved product information is provided as output.

[0810] Step 2:

[0811] The server generates questions using a generation AI model. As input, a prompt sentence is constructed based on the product information obtained in step 1, and this prompt sentence is input into the generation AI model. Through data calculation, questions that ask about relevant product knowledge are generated, and specific question sentences are obtained as output.

[0812] Step 3:

[0813] The server sends the generated question to the terminal. The input is the question text generated in step 2, which is sent to the terminal in the store via the network. The output is the question to be displayed, which is provided to the terminal.

[0814] Step 4:

[0815] The terminal presents a question to the user and accepts their response. The input is the question text sent to the terminal in step 3. The terminal visualizes the question for the user via a display device. It accepts voice responses and text input from the user, and the user response data is obtained as output.

[0816] Step 5:

[0817] An emotion recognition device analyzes the user's emotions. The input consists of audio and video data acquired when the user responds. Based on this data, an emotion recognition algorithm analyzes the user's facial expressions and vocal characteristics to detect their emotional state. The output is the analyzed emotion data.

[0818] Step 6:

[0819] The server uses natural language processing technology to evaluate the user's responses. The input consists of user response data obtained in step 4 and sentiment data obtained in step 5. The natural language processing model analyzes this data to evaluate the accuracy and sincerity of the responses. The output includes an evaluation score and whether or not the purchase right is granted.

[0820] Step 7:

[0821] The server decides whether to grant the purchase right and notifies the terminal of the result. The input is the evaluation result obtained in step 6. The server makes a decision on whether to grant the purchase right and sends the result to the terminal. The output is a notification regarding the granting of the purchase right provided to the user.

[0822] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0823] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0824] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0825] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0826] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0827] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0828] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0829] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0830] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0831] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0832] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0833] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0834] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0835] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0836] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0837] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0838] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0839] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0840] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0841] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0842] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0843] The following is further disclosed regarding the embodiments described above.

[0844] (Claim 1)

[0845] A means of creating questions to present to the purchaser based on product-related information using a generating device,

[0846] A means of displaying the aforementioned question to the purchaser using the device provided,

[0847] A means for receiving and evaluating the purchaser's response using a verification device,

[0848] A means of granting purchase rights to a purchaser whose answer is evaluated as correct using a device that grants purchase rights,

[0849] A system that includes this.

[0850] (Claim 2)

[0851] The system according to claim 1, wherein the generating device creates questions using a machine learning model.

[0852] (Claim 3)

[0853] The system according to claim 1, wherein the means for evaluation uses natural language processing technology to evaluate the buyer's response.

[0854] "Example 1"

[0855] (Claim 1)

[0856] A means for obtaining product information related to prospective buyers and generating questions to present to buyers based on that information,

[0857] A terminal device for presenting the questions generated using a generative AI model, and means for displaying the questions to the prospective buyer,

[0858] A means for analyzing and evaluating the responses entered by the prospective buyer using natural language processing technology,

[0859] A means of granting the right to purchase to a prospective buyer if the aforementioned evaluation is shown to be correct,

[0860] A system that includes this.

[0861] (Claim 2)

[0862] The system according to claim 1, wherein the generating means diversifies questions for the buyer through a generated AI model using product information obtained from a database.

[0863] (Claim 3)

[0864] The system according to claim 1, wherein the means for evaluation uses natural language processing techniques including text classification and semantic analysis to accurately analyze the responses of prospective buyers.

[0865] "Application Example 1"

[0866] (Claim 1)

[0867] A means for creating tasks to be presented to prospective buyers based on information related to goods using an information generation device,

[0868] A means for presenting the aforementioned problem to the prospective buyer using an information display device,

[0869] A means for receiving and evaluating the responses of the prospective buyer using an information verification device,

[0870] A means for granting purchase rights to prospective buyers whose answers are evaluated as correct using a purchase rights granting device,

[0871] A means of transmitting and displaying purchase information to a mobile information terminal using a communication device,

[0872] A system that includes this.

[0873] (Claim 2)

[0874] The system according to claim 1, wherein the information generation device creates tasks using a learning model.

[0875] (Claim 3)

[0876] The system according to claim 1, wherein the answer evaluation means evaluates the answers of prospective buyers using a natural language processing method.

[0877] "Example 2 of combining an emotion engine"

[0878] (Claim 1)

[0879] A means of creating questions to present to the purchaser based on product-related information using a generating device,

[0880] A means of displaying the aforementioned question to the purchaser using the device provided,

[0881] A means of analyzing the emotional state of a purchaser using an emotion detection device,

[0882] A means for receiving and evaluating the purchaser's response using a verification device,

[0883] A means of granting purchase rights to a purchaser whose answer is evaluated as correct using a device that grants purchase rights,

[0884] A system that includes this.

[0885] (Claim 2)

[0886] The system according to claim 1, wherein the generating device creates questions using a machine learning model.

[0887] (Claim 3)

[0888] The system according to claim 1, wherein the means for evaluation uses natural language processing technology to evaluate the purchaser's response and takes into account the analysis results of the emotion detection device.

[0889] "Application example 2 of combining emotional engines"

[0890] (Claim 1)

[0891] A means of creating questions to present to the purchaser based on product-related information using a generating device,

[0892] A means of displaying the aforementioned question to the purchaser using the device provided,

[0893] A means for receiving and evaluating the purchaser's response using a verification device,

[0894] A means of granting purchase rights to a purchaser whose answer is evaluated as correct using a device that grants purchase rights,

[0895] A means of analyzing the emotional state of a purchaser using an emotion recognition device,

[0896] A system that includes this.

[0897] (Claim 2)

[0898] The system according to claim 1, wherein the generating device creates a question using a machine learning model and generates a prompt sentence.

[0899] (Claim 3)

[0900] The system according to claim 1, wherein the means for evaluation uses natural language processing technology to evaluate the buyer's response and emotional state. [Explanation of Symbols]

[0901] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of creating questions to present to the purchaser based on product-related information using a generating device, A means of displaying the aforementioned question to the purchaser using the device provided, A means for receiving and evaluating the purchaser's response using a verification device, A means of granting purchase rights to a purchaser whose answer is evaluated as correct using a device that grants purchase rights, A system that includes this.

2. The system according to claim 1, wherein the generating device creates questions using a machine learning model.

3. The system according to claim 1, wherein the means for evaluation uses natural language processing technology to evaluate the purchaser's response.

Images