system

Abstract

We provide the system. [Solution] A means for receiving basic information from the user, A means for generating a list of questions based on the aforementioned basic information, A means for presenting the generated list of questions to the user, A means for receiving the user's response, analyzing that response, and selecting the most suitable product, A means for presenting the selected product to the user, A system that includes this.

Description

[Technical Field]

[0001] The technology disclosed herein relates to a system. [Background technology]

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, comprising the steps of: receiving a user utterance; adding the user utterance to a prompt that includes instructions relating to a description of the chatbot's character; encoding the prompt; and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance. [Prior art documents] [Patent Documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 [Overview of the project] [Problems that the invention aims to solve]

[0004] In recent years, consumers face the problem of difficulty in selecting appropriate products when purchasing expensive electronic products and home appliances due to the existence of diverse selection criteria. This problem is particularly pronounced with high-priced items such as refrigerators, personal computers, and air conditioners. In such cases, consumers are unsure of what criteria to use for selection and are at risk of purchasing unsuitable products. The present invention aims to solve this problem and provide a system that allows consumers to easily select the optimal product. [Means for solving the problem]

[0005] This invention provides a system that receives basic information from the user (e.g., budget, room size, purpose of use, etc.) and generates a list of questions based on this information. The generated list of questions is presented to the user, who answers them. Next, the system analyzes the user's answers and selects the most suitable product. Furthermore, it presents the selected product to the user and includes means for the user to input additional requests. Based on the additional requests, the system re-evaluates the products and presents updated candidate products. In addition, after presenting the optimal product, it includes means for the user to input an instruction to "see second candidates," and based on this instruction, the ranking of candidate products is re-evaluated and second candidate products are presented, enabling the consumer to choose a more appropriate product.

[0006] A "user" is an individual or legal entity that uses the system to select products.

[0007] "Basic information" refers to information entered by the user, including important elements related to the product they wish to purchase (such as budget, room size, and intended use).

[0008] A "question list" is a collection of questions generated based on basic information provided by the user. These questions are presented to the user, and their answers are used in product selection.

[0009] "Answers" are the information that users provide in response to a list of questions, and this data is used by the system to analyze and select the most suitable product.

[0010] "Product specifications" refer to information that indicates the technical specifications and performance of a particular product.

[0011] "Analysis" refers to the calculation and decision-making process that a system performs to select the most suitable product based on basic information and responses received from the user.

[0012] The "optimal product" refers to the product that best matches the user's needs, selected based on the user's basic information and answers to a list of questions.

[0013] "Candidate products" refer to multiple products selected as purchase targets and presented to the user as a result of analysis.

[0014] "Re-evaluation" is a process in which the system re-selects products based on additional requests from the user or an instruction to "view second candidates".

[0015] "Second candidates" refer to the next suitable products presented when the user is not satisfied with the first optimal product candidates.

Brief Description of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main 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. [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. <00XXXX094>It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12]This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0017] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0018] First, let's explain the terminology used in the following explanation.

[0019] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0020] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0021] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] 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."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] This invention relates to a system for assisting users in the process of selecting expensive electronic products and home appliances. This system receives basic information from the user, and based on the user's answers to a generated list of questions, selects and suggests the most suitable products. The program processing of this system is described below in natural language.

[0038] Program Processing Description

[0039] Initial setup

[0040] The server stores selection criteria and question lists for each product category in its database. Product categories include, for example, refrigerators, personal computers, and air conditioners.

[0041] Entering user information

[0042] The user uses their device to first select the product category they wish to purchase. Next, the user enters basic information such as their budget, room size, and intended use.

[0043] Generating a list of questions

[0044] Based on the basic information received, the server generates a list of questions tailored to the relevant product category. For example, in the case of an air conditioner, the server lists questions such as room size, monthly electricity costs, initial purchase cost, and whether the customer wants to control it via smartphone.

[0045] Displaying questions and collecting answers

[0046] A list of questions is displayed to the user sequentially on their device. The user answers these questions, and the answers are sent to the server in real time.

[0047] AI-powered analysis of responses

[0048] The server analyzes the responses received from the user and extracts product specifications. Based on these product specifications, it narrows down the database to the most suitable product.

[0049] Suggesting the optimal product

[0050] Based on the analysis results, the server lists the most suitable products and sends the top-ranked candidate product to the user's terminal. The optimal product is then displayed to the user on the terminal.

[0051] Additional questions and reassessment

[0052] If the user enters additional requests, such as whether the product is operable on a smartphone, the server will incorporate this information into its analysis and perform a re-evaluation. The updated list of candidate products will then be displayed on the user's device.

[0053] Specific example

[0054] Specific example 1: Air conditioner selection

[0055] The user selects an air conditioner category and enters basic information such as budget and room size. The server generates a list of questions about air conditioners based on this information and sends it to the user's device. The user answers whether they prioritize electricity costs or initial costs, etc. The server analyzes the answers, selects air conditioners with high energy efficiency, and presents them to the user. The user then enters a request for a "model that can be operated with a smartphone," and the server re-evaluates and presents updated air conditioner models.

[0056] Example 2: Choosing a PC

[0057] The user selects a PC category and enters their primary use (e.g., video editing, gaming) and budget. The server generates a list of questions based on this information and sends them to the terminal. The user answers questions about "CPU performance" and "storage capacity." The server analyzes the answers, selects a high-performance PC that meets the user's needs, and presents it to the user. Furthermore, if the user wants to see a second option, the server relaxes the settings, re-evaluates, and presents the second PC as well.

[0058] As described above, the present invention allows consumers to easily choose the optimal product that suits their needs.

[0059] The following describes the processing flow.

[0060] Program execution flow

[0061] Initial setup

[0062] Step 1:

[0063] The server stores selection criteria and question lists for each product category in its database. For example, different criteria are set for each category, such as refrigerators, personal computers, and air conditioners.

[0064] Entering user information

[0065] Step 2:

[0066] The user uses their device to select the product category they wish to purchase. Users can choose from options such as refrigerators, computers, and air conditioners.

[0067] Step 3:

[0068] The user fills in the required information in a form, including basic details such as budget, room size, and purpose of use. Once completed, they press the submit button.

[0069] Generating a list of questions

[0070] Step 4:

[0071] The server analyzes the received basic information and generates a list of questions tailored to the relevant product category. For example, for an air conditioner, it would prepare questions such as room size, monthly electricity costs, initial purchase cost, and whether the customer wants to control it with their smartphone.

[0072] Displaying questions and collecting answers

[0073] Step 5:

[0074] The server sends the generated list of questions to the user's terminal. On the user's terminal, the list of questions is displayed sequentially in an easy-to-understand format.

[0075] Step 6:

[0076] The user sequentially enters answers to the displayed questions. For example, they might enter information such as the room size being "20 square meters" and whether they prioritize electricity costs.

[0077] Step 7:

[0078] User responses are sent to the server in real time and stored in the database.

[0079] AI-powered analysis of responses

[0080] Step 8:

[0081] The server analyzes the user's responses and extracts the corresponding product specifications. The analysis uses an algorithm based on the user's response data.

[0082] Step 9:

[0083] The server narrows down the database to the most suitable products based on the extracted product specifications. It then lists the most appropriate products as a result of this filtering.

[0084] Suggesting the optimal product

[0085] Step 10:

[0086] The server prepares detailed information on the listed optimal products and sends it to the user's terminal.

[0087] Step 11:

[0088] The user terminal presents the optimal product to the user in a visually easy-to-understand format. For example, it might display something like "Air conditioner A with high energy efficiency."

[0089] Additional questions and reassessment

[0090] Step 12:

[0091] If a user has additional requests (e.g., a model that can be operated via smartphone), they will enter the information using an additional question form on their device. Once they have finished entering the information, they will press the submit button again.

[0092] Step 13:

[0093] The server analyzes the additional request information and incorporates it into the initial analysis results to re-evaluate the product. A new algorithm that takes the added requests into account is used for the re-evaluation.

[0094] Step 14:

[0095] The updated list of candidate products resulting from the re-evaluation is sent to the user's terminal, which then presents them to the user.

[0096] Confirmation of the second candidate

[0097] Step 15:

[0098] If the user is not satisfied with the first recommended product, they can press the "View Second Choice" button.

[0099] Step 16:

[0100] The server uses the initial responses as a basis, but slightly relaxes the criteria and selects products again. Different algorithms can be used for this process.

[0101] Step 17:

[0102] The server re-analyzes the data and selects a second-choice product. This information is then sent to the user's terminal, which then presents the second-choice product to the user.

[0103] Through these steps, users can effectively select the product that best suits their needs. This system significantly simplifies the product selection process.

[0104] (Example 1)

[0105] 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."

[0106] Traditional product selection systems suggest the most suitable products based on the user's basic information, but they have the problem of not being able to flexibly respond to additional requests or changes. Furthermore, the generated list of questions is limited and sometimes does not adequately reflect the user's needs. As a result, it was difficult for users to select a product that perfectly matched their requirements.

[0107] 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.

[0108] In this invention, the server includes means for receiving basic information from a user, means for generating a list of questions based on the basic information, means for presenting the generated list of questions to the user, means for receiving the user's answers, analyzing those answers, and selecting the most suitable product, means for presenting the selected product to the user, and means for re-evaluating the product based on the user's additional requests and presenting updated candidate products. This enables product selection that more accurately reflects the user's needs and can quickly respond to additional requests and changes.

[0109] A "user" is an individual or organization that uses the system to input basic information and additional requests in order to select products.

[0110] "Basic information" refers to initial information such as the user's desired product category, budget, space size, and intended use, and is used by the system to generate appropriate question lists and product suggestions.

[0111] A "question list" is a series of questions generated based on a user's basic information, designed to gain a more detailed understanding of their needs and requests.

[0112] "Answers" refer to the selections and text information that users enter based on a list of questions, providing data for the system to analyze and select products.

[0113] "Product specifications" refer to the specific specifications and characteristics required for a product, extracted based on user responses.

[0114] A "selected product" is a product that the server has determined to be optimal after analyzing the user's basic information and responses.

[0115] "Additional requests" are new conditions or preferences that users would like to consider, separate from the initial information and responses.

[0116] "Re-evaluation" is the process by which the server incorporates additional requests into its analysis, re-evaluates existing data and conditions, and updates the list of potential products.

[0117] This invention relates to a system for assisting users in the process of selecting expensive electronic products and home appliances. This system receives basic information from the user and, based on the user's answers to a generated list of questions, selects and suggests the most suitable products. Specific embodiments of this system are described below.

[0118] Initial setup

[0119] server

[0120] The server stores selection criteria and question lists for each product category in a database. Product categories include refrigerators, personal computers, air conditioners, etc. For example, the server uses a MySQL database and stores the selection criteria and corresponding question lists for each product category in database tables. These question lists and selection criteria include specific items such as "energy efficiency" and "cooling capacity."

[0121] Entering user information

[0122] User

[0123] The user selects the product category they wish to purchase using their device. For example, using a smartphone app, they might select "air conditioner" on the category selection screen. Next, the user enters information such as "budget of 50,000 yen" and "room size of 15 tatami mats."

[0124] Generating a list of questions

[0125] server

[0126] The server generates a list of questions corresponding to the relevant product category based on the user's basic information received. The server uses Python to dynamically generate a list of questions for air conditioners from the given basic information. For example, it might prepare questions such as, "Your room is 15 tatami mats in size, what are your expectations for your monthly electricity bill?"

[0127] Displaying questions and collecting answers

[0128] terminal

[0129] A list of questions is displayed sequentially to the user on their device. The user answers these questions, and the answers are sent to the server in real time. For example, a smartphone app displays a list of questions retrieved from the server based on the information entered by the user, and each time the user taps an option, the answer data is sent to the server.

[0130] AI-powered analysis of responses

[0131] server

[0132] The server analyzes the user's responses using an AI model. The server uses TensorFlow to build a generative AI model and analyze the user's responses. For example, if the server receives a response indicating that "electricity costs are a priority," the model will narrow down the candidates to air conditioners with particularly excellent energy-saving performance.

[0133] Suggesting the optimal product

[0134] server

[0135] Based on the analysis results, the system lists the most suitable products and sends the top-ranked candidate product to the user's device. The server generates a list of recommended products and sends the most suitable product from that list to the user's smartphone app in JSON format.

[0136] terminal

[0137] The most suitable products are displayed to the user. The smartphone app displays product details to the user based on the data received.

[0138] Additional questions and reassessment

[0139] User

[0140] The user enters any additional requests. For example, if the user wants a model that can be operated with a smartphone, they enter that request from their device.

[0141] server

[0142] The server incorporates the additional requests into its analysis and performs a re-evaluation. Once the analysis is complete, it resends the updated list of candidate products to the user's device. The smartphone app immediately reflects the changes to the user.

[0143] Specific example

[0144] Specific example 1: Air conditioner selection

[0145] The user selects an air conditioner category and enters basic information such as budget and room size. The server generates a list of questions about air conditioners based on this information and sends it to the user's device. The user answers whether they prioritize electricity costs or initial costs, etc. The server analyzes the answers, selects air conditioners with high energy efficiency, and presents them to the user. If the user adds a request for a "model that can be operated with a smartphone," the server re-evaluates and presents updated air conditioner models.

[0146] Example of a prompt

[0147] Please simulate the process a user goes through when selecting an air conditioner. The budget is 50,000 yen, the room size is 15 tatami mats, the purpose is heating and cooling, and the additional request is for a model that can be controlled via smartphone.

[0148] Example 2: Choosing a PC

[0149] The user selects a PC category and enters their primary use (e.g., video editing, gaming) and budget. The server generates a list of questions based on this information and sends them to the terminal. The user answers questions about "CPU performance" and "storage capacity." The server analyzes the answers, selects a high-performance PC that meets the user's needs, and presents it to the user. Furthermore, if the user wants to see a second option, the server relaxes the settings, re-evaluates, and presents the second PC as well.

[0150] Example of a prompt

[0151] Please simulate the process a user goes through when selecting a PC. The purpose is video editing, the budget is 150,000 yen, and additional requirements include a high-performance CPU and storage capacity of 1TB or more. Please provide an example of this scenario.

[0152] As described above, the present invention allows consumers to easily choose the optimal product that suits their needs.

[0153] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0154] Step 1: Database Setup

[0155] The server stores selection criteria and question lists for each product category in a database. The server uses a MySQL database and stores the selection criteria and corresponding question lists in database tables for each product category (refrigerators, personal computers, air conditioners, etc.). For example, the refrigerator category includes criteria such as "overall capacity" and "energy efficiency." Input is the data for the selection criteria and question lists, and output is the selection criteria and question lists stored in the database.

[0156] Step 2: Enter user information

[0157] The user selects the product category they wish to purchase using their device. Next, the user enters basic information such as budget, space size, and intended use. This information is entered using the smartphone app interface, and the entered information is sent from the device to the server. The input is the user's basic information, and the output is the basic information sent to the server.

[0158] Step 3: Generate the question list

[0159] The server generates a list of questions corresponding to the product category based on the user's basic information received. The server executes a Python script to dynamically generate the necessary questions from the basic information. For example, in the case of the air conditioner category, questions such as "room size," "budget," and "desire for smartphone control" are created. The input is the user's basic information, and the output is the generated list of questions.

[0160] Step 4: Display the questions and collect the answers.

[0161] A list of questions generated for the user is displayed sequentially on the terminal. The user answers the questions as they appear, and the answers are sent to the server in real time. For example, if the terminal interface displays the question "Are you thinking about your monthly electricity bill?", and the user enters an answer, that answer is sent to the server. The input is the list of questions and the user's answers, and the output is the user's answers sent to the server.

[0162] Step 5: AI-driven analysis of the response

[0163] The server analyzes the user's responses using an AI model. The server uses TensorFlow to build a generative AI model and extracts product specifications from the user's responses. For example, if it receives a response indicating a focus on electricity costs, it will narrow down the candidates to products with high energy efficiency. The input is the user's response data, and the output is the analyzed product specifications.

[0164] Step 6: Proposing the optimal product

[0165] The server lists the most suitable products based on the analysis results and sends the top-ranked candidate product to the user's terminal. The server generates a list of recommended products and sends it to the user's smartphone app in JSON format. The smartphone app displays product details to the user based on the received data. The input is the analyzed product specifications, and the output is the list of optimal products sent to the user's terminal.

[0166] Step 7: Additional questions and reassessment

[0167] The user enters additional requests. For example, if they want a "model that can be operated with a smartphone," they enter that request from their device. The server incorporates the additional requests into its analysis and performs a re-evaluation. After the re-evaluation, the updated list of candidate products is resent to the user's device. The smartphone app immediately reflects the changes to the user. The input consists of the additional requests and existing data, and the output is the re-evaluated, updated product list.

[0168] (Application Example 1)

[0169] 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."

[0170] Modern consumers face the challenge of quickly selecting the optimal product to suit their specific needs in a physical store with numerous options. In particular, they require selection support that addresses not only basic information such as budget and intended use, but also specific factors like electricity costs and ease of use. Furthermore, a lack of adequate means to provide product and location information within physical stores can cause consumers to become lost. It is necessary to address these challenges and provide consumers with an efficient and intuitive product selection support system.

[0171] 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.

[0172] In this invention, the server includes means for receiving basic information from a user, means for generating a list of questions based on the basic information, means for presenting the generated list of questions to the user, means for receiving the user's answers and analyzing those answers to select the optimal product, means for presenting the selected product to the user, means for providing product information and location information available in the store to the user in the physical store, and means for providing product selection support using a smartphone-based user interface. This makes it possible for consumers to efficiently select the optimal product even in a physical store.

[0173] "Basic information" refers to initial settings such as budget, room size, and intended use that users enter when selecting a product.

[0174] A "question list" is a collection of specific questions necessary for product selection, generated based on the user's basic information.

[0175] "User response" refers to the specific content of the user's response to the list of questions.

[0176] The "optimal product" is the product that best suits the user's needs, selected based on the user's basic information and responses.

[0177] "Selected products" refer to specific products that are recommended to the user based on the analysis results.

[0178] A "physical store" is a physical sales location where consumers can go in person and purchase products.

[0179] "Product information" refers to detailed data about a product, such as its characteristics, specifications, and price.

[0180] "Location information" refers to information used to identify the location of a product within a physical store.

[0181] A "user interface" refers to the operating screen and display functions used for exchanging information between the user and the system.

[0182] A "smartphone" is a portable mobile terminal device that provides a variety of operating applications in addition to the functions of a mobile phone.

[0183] This invention is a system that helps consumers efficiently select the most suitable products in a physical store. This system is realized using a server, terminals such as smartphones, a database, and an AI model.

[0184] First, the server stores selection criteria and question lists for each product category in a database. Product categories include refrigerators, personal computers, air conditioners, etc. Next, the user launches the application using their smartphone in a physical store and selects the product category they wish to purchase. The user enters basic information such as budget, room size, and intended use. The server then generates a question list corresponding to the product category based on the received basic information and sends it to the terminal. For example, for an air conditioner, the list would include questions such as room size, monthly electricity costs, initial purchase cost, and whether the user wants to control it with a smartphone.

[0185] The terminal displays a list of questions to the user sequentially, and the user answers them. The answers are sent to the server in real time. The server analyzes the answers and uses an AI model to extract product specifications. Generative AI models such as TensorFlow are used for this analysis process. Based on the extracted product specifications, the server narrows down the best products from the database and lists candidate products. This list of candidate products is sent to the terminal and presented to the user.

[0186] Furthermore, product information and location data are provided to make it easier for users to check potential products within physical stores. Users can check the specific location and detailed information of products through their smartphone interface.

[0187] As a concrete example, consider a case where a user purchases a refrigerator at a physical electronics store. In this example, the user selects a category, then enters their budget, room size, and intended use. The server generates a list of questions for the refrigerator and sends it to the user's terminal. The user answers the questions, and the server analyzes them using a generated AI model. Based on the analysis results, the server selects the most suitable refrigerator and provides the user with its product information and location.

[0188] Example of a prompt message: "My budget is 200,000 yen. I'm looking for a refrigerator. The room size is 3m x 3m. I prioritize low monthly electricity costs, a standard size is fine, and I don't have a preference for the door opening direction. Please recommend a refrigerator."

[0189] This system configuration allows users to efficiently and intuitively select the most suitable products even within a physical store.

[0190] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0191] Step 1:

[0192] The server stores selection criteria and question lists for each product category in a database. This process adds information such as product characteristics, usage scenarios, and price ranges to the database. The input is detailed information for each product category, and the output is the selection criteria and question lists stored in the database. Specifically, it creates appropriate question lists for each category, such as refrigerators, personal computers, and air conditioners.

[0193] Step 2:

[0194] The user launches the application using their smartphone while in a physical store. Next, they select the product category they wish to purchase and enter basic information such as their budget, room size, and intended use. This basic information is sent to the server. The input is the basic information such as budget and intended use entered by the user, and the output is the basic information sent to the server. Specifically, the user selects the refrigerator category and enters information such as "budget is 200,000 yen" and "intended use is for home use."

[0195] Step 3:

[0196] The server generates a list of questions corresponding to the relevant product category based on the basic information received and sends it to the terminal. The input is the basic information received from the user, and the output is the generated list of questions. Specifically, for the refrigerator category, questions such as "Are you concerned about monthly electricity costs?" and "What size refrigerator do you need?" are generated.

[0197] Step 4:

[0198] The terminal displays a generated list of questions to the user sequentially. The user answers these questions, and the answers are sent to the server in real time. The input is the list of questions sent from the server and the user's answers, and the output is the answer data for analysis sent to the server. Specifically, the user answers questions such as "I prioritize electricity costs" and "I want a standard-sized refrigerator."

[0199] Step 5:

[0200] The server uses a generative AI model to analyze user responses and extract product specifications. The input is user response data, and the output is the extracted product specifications. Specifically, a generative AI model using TensorFlow extracts the specifications "prioritizing low electricity consumption" and "standard size."

[0201] Step 6:

[0202] The server narrows down the database to the most suitable products based on the extracted product specifications, lists the candidate products, and sends them to the terminal. The input is the extracted product specifications, and the output is the list of candidate products presented to the user. Specifically, refrigerators that meet the conditions of "budget under 200,000 yen," "prioritizing low electricity consumption," and "standard size" are listed.

[0203] Step 7:

[0204] Within the physical store, users are provided with information on selected products and their locations. Input consists of a list of candidate products sent from the server and the product locations within the store; output consists of detailed product information and location information displayed on the terminal. Specifically, the detailed specifications of the listed refrigerators and their location within the store are presented.

[0205] Step 8:

[0206] Users check the specific location and details of products through their smartphone's user interface. Input is the product location and details displayed on the device, while output is the user's action based on their purchasing decision. Specifically, users check the location of listed refrigerators within a physical store, check the products on the spot, and decide to purchase them.

[0207] 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.

[0208] This invention combines an emotion engine with a system designed to assist users in the process of selecting electronic products and home appliances. This system receives basic information from the user, analyzes the user's emotions based on their answers to a generated list of questions using the emotion engine, and then selects and suggests the most suitable products based on that analysis. The following describes the program's processing in natural language.

[0209] Program Processing Description

[0210] Initial setup

[0211] The server stores selection criteria and question lists for each product category in a database. Product categories include, for example, refrigerators, personal computers, and air conditioners. The emotion engine includes algorithms that analyze user emotions from text and voice data.

[0212] Entering user information

[0213] The user uses their device to first select the product category they wish to purchase. Next, they enter basic information such as their budget, room size, and intended use.

[0214] Generating a list of questions

[0215] The server analyzes the received basic information and generates a list of questions tailored to the relevant product category. For example, for an air conditioner, it would prepare questions such as room size, monthly electricity costs, initial purchase cost, and whether the customer wants to control it with their smartphone.

[0216] Displaying questions and collecting answers

[0217] A list of questions is displayed to the user sequentially on their device. The user answers these questions, and the answers are sent to the server in real time.

[0218] Emotional analysis using an emotion engine

[0219] The emotion engine analyzes the user's response text and voice data to identify the user's emotions (e.g., satisfaction, dissatisfaction, excitement, indecision, etc.).

[0220] AI-powered analysis of responses

[0221] The server integrates responses received from the user with sentiment data from the sentiment engine and extracts product specifications. Based on these product specifications, it narrows down the database to the most suitable product.

[0222] Suggesting the optimal product

[0223] Based on the analysis results, the server lists the most suitable products and sends the top-ranked candidate product to the user's terminal. The optimal product is then displayed to the user on the terminal.

[0224] Additional questions and reassessment

[0225] If a user has additional requests (e.g., a model that can be operated via smartphone), they will enter the information using an additional question form on their device. Once they have finished entering the information, they will press the submit button again.

[0226] The server analyzes the additional request information and incorporates it into the initial analysis results to re-evaluate the products. A new algorithm based on the added requests is used for the re-evaluation. The updated candidate products are then displayed on the user's device.

[0227] Specific example

[0228] Specific example 1: Air conditioner selection

[0229] The user selects an air conditioner category and enters basic information such as budget and room size. The server generates a list of questions about air conditioners based on this information and sends it to the user's device. The user answers whether they prioritize electricity costs or initial costs, etc. As soon as the answers are sent to the server, an emotion engine analyzes the user's responses to identify their emotions, satisfaction level, and level of excitement. The server comprehensively analyzes this data to select and present air conditioners with high energy efficiency. If the user requests an additional model that can be operated via smartphone, the server re-evaluates and presents updated air conditioner models.

[0230] Example 2: Choosing a PC

[0231] The user selects a PC category and enters their primary use (e.g., video editing, gaming) and budget. The server generates a list of questions based on this information and sends them to the terminal. The user answers questions about "CPU performance" and "storage capacity." The emotion engine analyzes the user's responses to identify their stress level and level of interest. Based on the responses and emotion data, the server analyzes and selects a high-performance PC that meets the user's needs and presents it to the user. If the user wants to see a second option, the server relaxes the settings, re-evaluates, and presents the second PC.

[0232] As described above, the system of the present invention, by combining an emotion engine that analyzes the user's emotions, more accurately reflects the user's true needs and enables optimal product recommendations. As a result, users can find products that are more satisfying to them during the selection process.

[0233] The following describes the processing flow.

[0234] Program execution flow

[0235] Initial setup

[0236] Step 1:

[0237] The server stores selection criteria, question lists, and sentiment analysis algorithms for each product category in its database. For example, different criteria and sentiment analysis settings are prepared for each category, such as refrigerators, personal computers, and air conditioners.

[0238] Entering user information

[0239] Step 2:

[0240] The user uses their device to select the product category they wish to purchase. Categories include refrigerators, computers, air conditioners, and so on.

[0241] Step 3:

[0242] The user enters basic information such as budget, room size, and purpose of use into a form and presses the submit button.

[0243] Generating a list of questions

[0244] Step 4:

[0245] The server analyzes the basic information it receives and generates a list of questions based on that information, corresponding to the relevant product category. For example, in the case of an air conditioner, the server lists questions such as room size, monthly electricity costs, initial purchase cost, and whether the customer wants to control it with their smartphone.

[0246] Displaying questions and collecting answers

[0247] Step 5:

[0248] The server sends the generated list of questions to the user's terminal. On the user's terminal, the list of questions is displayed sequentially in an easy-to-understand format.

[0249] Step 6:

[0250] The user sequentially enters answers to the displayed questions. For example, they might enter information such as the room size being "20 square meters" and whether they prioritize electricity costs.

[0251] Step 7:

[0252] User responses are sent to the server in real time and stored in a database. Simultaneously, an emotion engine analyzes the response text and audio data.

[0253] Emotional analysis using an emotion engine

[0254] Step 8:

[0255] The emotion engine built into the server analyzes emotions based on the user's response text and voice data. For example, it uses natural language processing technology to identify emotions such as how satisfied, excited, or anxious the user is.

[0256] AI-powered analysis of responses

[0257] Step 9:

[0258] The server integrates the responses received from the user with sentiment data from the sentiment engine and extracts product specifications. The extracted product specifications are then compared with candidate products in the database.

[0259] Step 10:

[0260] The server narrows down the database to the most suitable products based on the extracted product specifications and sentiment data. It then lists the most appropriate products as a result of this filtering.

[0261] Suggesting the optimal product

[0262] Step 11:

[0263] The server prepares detailed information on the listed optimal products and sends it to the user's terminal.

[0264] Step 12:

[0265] The user terminal presents the optimal product to the user in a visually easy-to-understand format. For example, it might display something like "Air conditioner A with high energy efficiency."

[0266] Additional questions and reassessment

[0267] Step 13:

[0268] If a user has additional requests (e.g., a model that can be operated via smartphone), they will enter the information using an additional question form on their device. Once they have finished entering the information, they will press the submit button again.

[0269] Step 14:

[0270] The server analyzes the additional requirement information, reflects it in the initial analysis result, and re-evaluates the products. A new algorithm based on the added requirements is used for the re-evaluation.

[0271] Step 15:

[0272] The updated candidate products are displayed on the user's terminal. The user terminal presents the new optimal products that reflect the additional requirements to the user.

[0273] Confirmation of the second candidate

[0274] Step 16:

[0275] If the user is not satisfied with the first recommended product, the user presses the "View second candidate" button.

[0276] Step 17:

[0277] While basing on the first response content and sentiment data, the server relaxes the criteria slightly and selects products again. Different algorithms can be used in this process. [[ID=3,7]]

[0278] Step 18:

[0279] The server analyzes again and selects the second candidate products. Then, this information is sent to the user terminal, and the terminal presents the second candidate products to the user.

[0280] Through the above steps, the user can effectively select the products that best meet their needs. With this system, by considering the user's sentiment, a more satisfactory product selection is realized.

[0281] (Example 2)

[0282] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart device 14 is referred to as a "terminal".

[0283] In the selection process of conventional electronic products and home appliances, products are only selected based on the basic information and answers of users. The selection does not consider the feelings of users, and it is difficult to meet the true needs of users. In addition, in the selection based only on answers, there is a possibility of overlooking important factors that the user is not aware of. As a result, there is a problem that users are likely to make selections with low satisfaction, and the risk of regret after purchase increases.

[0284] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0285] In this invention, the server includes means for receiving basic information from a user, means for generating a question list based on the basic information, means for presenting the generated question list to the user, means for receiving the user's answer and analyzing the answer to identify the user's feelings, means for selecting an optimal product based on the analyzed feeling information and answer information, and means for presenting the selected product to the user. Thereby, it is possible to comprehensively analyze the user's answers and emotion data, and propose an optimal product that reflects the true needs of the user.

[0286] "Basic information" refers to information necessary for product selection, such as the budget input by the user, the size of the environment, and the purpose of use.

[0287] "Question list" refers to a series of questions generated based on the user's basic information and presented to the user.

[0288] "Emotion analysis" refers to a process of analyzing the user's answer text and voice data to identify emotions such as satisfaction, dissatisfaction, excitement, and confusion.

[0289] "Product specifications" refer to detailed information about the product's performance and functions, extracted based on the user's responses and sentiment analysis results.

[0290] The "optimal product" is the product that best meets the user's needs, selected based on the user's basic information, responses, and sentiment analysis results.

[0291] A "terminal" is a device used by a user to input information, answer questions, and be presented with the most suitable products, and includes smartphones, PCs, and other similar devices.

[0292] A "server" is a computer device that receives basic information, generates a list of questions, analyzes responses and emotions, and selects the most suitable product.

[0293] This invention combines an emotion engine with a system designed to assist users in the process of selecting electronic products and home appliances. The system receives basic information from the user, analyzes the user's emotions based on their responses to a generated list of questions using the emotion engine, and then selects and suggests the most suitable products based on that analysis.

[0294] The server stores selection criteria for each product category (e.g., refrigerators, personal computers, air conditioners) and corresponding question lists in a database. The sentiment engine is configured to analyze user response text and audio data using Google Cloud Natural Language API and IBM Watson's sentiment analysis capabilities. This configuration includes setting up API keys and importing model training data.

[0295] The user uses a device (such as a smartphone or PC) to select the product category they wish to purchase and enters basic information such as their budget, room size, and intended use. This prepares the system to generate a list of questions tailored to the user.

[0296] The server analyzes the received basic information and generates a list of questions corresponding to the relevant product category. For example, in the air conditioner category, it dynamically creates relevant questions based on clues such as room size and desired functions (energy-saving mode, remote control operation, etc.).

[0297] The terminal displays a list of questions sent from the server to the user, one by one. The user answers each question, and the answers are sent to the server in real time. For example, if the user is asked "What is the size of the room?" in the air conditioner question list, and answers "20m²", the user will answer "20m²". 2 When you answer "Yes," the response is immediately sent to the server.

[0298] The emotion engine on the server analyzes the user's response text and audio data. Based on the analysis, it identifies the user's emotions (e.g., satisfaction, dissatisfaction, excitement, indecision, etc.). For example, if a user answers, "I'm concerned about the electricity bill, but does it have energy-saving features?", the emotion engine will analyze the word "concerned" to identify the emotion of "worry."

[0299] The server integrates responses and sentiment data received from users and extracts product specifications using high-performance AI. This involves using machine learning models (e.g., scikit-learn or TensorFlow) to gain a deep understanding of user needs. For example, if a user prioritizes "energy efficiency," the server will narrow down the search to products with high energy efficiency.

[0300] The server lists the most suitable products based on the analysis results and sends the top candidate product to the user's terminal. The product is then displayed to the user on the terminal. For example, it might display "highly energy-efficient air conditioners" and provide detailed information and a purchase link for that product.

[0301] When the user inputs an additional requirement such as "a model that can be operated with a smartphone", new information is sent from the terminal to the server. The server re-evaluates the product list based on this information and sends the result back to the terminal. For example, when the user adds the condition of "operable with a smartphone", the air conditioner models that meet this condition are displayed again.

[0302] Specific example

[0303] Specific example 1: Selection of air conditioner

[0304] The user selects the air conditioner category and enters basic information such as budget and room size. Based on this, the server generates a list of questions about the air conditioner and sends it to the terminal. The user answers "whether to prioritize electricity cost or initial cost" and sends the answer to the server. At the same time, the emotion engine analyzes emotions such as "satisfied" and "worried". The server integrates these data, selects an air conditioner with high energy-saving performance, and presents it to the user. When the user enters "a model that can be operated with a smartphone" as an additional requirement, the server re-evaluates and presents a new air conditioner model.

[0305] Examples of prompt sentences

[0306] 1. "I am considering buying an air conditioner.The size of the room is 20m 2 and I want to reduce my monthly electricity bill. I prioritize running costs over initial costs."

[0307] 2. "I want an air conditioner that can be operated with a smartphone."

[0308] Specific example 2: Selection of personal computer

[0309] The user selects a PC category and enters their primary use (e.g., video editing, gaming) and budget. The server generates a list of questions based on this information and sends it to the terminal. The user answers questions about "CPU performance" and "storage capacity," and an emotion engine analyzes their "interests" and "stress levels." Based on the answers and emotion data, the server performs an analysis to select and present a high-performance PC that meets the user's needs. If the user wants to see a second option, the server relaxes the settings, re-evaluates, and presents another PC.

[0310] Example of a prompt

[0311] 1. "I'm considering buying a computer. My budget is 150,000 yen, and my main purpose is video editing. A large storage capacity would be ideal."

[0312] 2. "I want a model with a high CPU performance for video editing."

[0313] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0314] Step 1:

[0315] The server stores selection criteria and question lists for each product category in a database. Specifically, for each category such as refrigerators, personal computers, and air conditioners, it sets criteria related to budget and intended use, as well as question lists based on those criteria. A database system such as Google Cloud Firestore or MySQL is used for this setup. The input data consists of product categories, their selection criteria, and question lists, and the output is storage in the database.

[0316] Step 2:

[0317] The user uses a terminal to select the product category they wish to purchase. Specifically, they select one from a list of product categories displayed on the terminal screen, such as air conditioners, refrigerators, or personal computers. The user's input data is the selected product category, and the output is the transmission of the selection information to the server.

[0318] Step 3:

[0319] The user uses a terminal to input basic information such as budget, room size, and purpose of use. Specifically, they enter the necessary information in fields such as budget (amount), room size (square meters), and purpose of use (cooling, heating, other). This information is sent to the server. The input data is basic information, and the output is the transmission of this data to the server.

[0320] Step 4:

[0321] The server analyzes the received basic information and generates a list of questions tailored to the relevant product category. For example, in the case of an air conditioner, it generates questions about electricity costs, energy efficiency, and whether it can be controlled via smartphone, based on room size and budget. The analysis is performed using Python scripts or Node.js, and the algorithm is executed. The input data is basic information, and the output is the generated list of questions.

[0322] Step 5:

[0323] The terminal displays a list of questions sent from the server to the user in sequence. Specifically, each question is displayed on the terminal screen, prompting the user to input. The input data is the list of questions, and the output is the presentation of these questions to the user.

[0324] Step 6:

[0325] The user answers each question and sends the answers to the server in real time via their device. For example, to the question "What is the size of the room?", the answer might be "20m 2The system provides responses such as "[...]". The input data is the user's response, and the output is the transmission of that response data to the server.

[0326] Step 7:

[0327] The emotion engine on the server analyzes the text and audio data submitted by the user. Specifically, it uses the Google Cloud Natural Language API for text analysis and IBM Watson's emotion analysis function for audio data analysis. The emotion engine identifies emotions such as satisfaction, dissatisfaction, excitement, and indecision from the user's statements. The input data is the user's response, and the output is the analyzed emotion information.

[0328] Step 8:

[0329] The server integrates responses and sentiment data received from users and extracts product specifications using high-performance AI. For example, it creates an analysis model using Python libraries such as scikit-learn and TensorFlow to extract product specifications based on user requests. The input data consists of responses and sentiment data, and the output is the extracted product specifications.

[0330] Step 9:

[0331] The server lists the most suitable products based on the analysis results and sends the top candidate products to the user's terminal. Specifically, it searches the database for products that meet the criteria based on the extracted product specifications and lists the best ones. The input data is product specifications, and the output is a list of optimal products.

[0332] Step 10:

[0333] The terminal displays a list of optimal products to the user. The user can select from the presented products, and detailed product information and purchase links are also displayed. The input data is the list of optimal products, and the output is the display of the products.

[0334] Step 11:

[0335] If a user enters an additional request (for example, "a model that can be operated with a smartphone"), that request is sent to the server via the device. The input data is the additional request, and the output is the transmission of that data to the server.

[0336] Step 12:

[0337] The server analyzes the additional request information and incorporates it into the initial analysis results to re-evaluate the products. Specifically, it re-evaluates the product list based on the new conditions derived from the additional requests. The aforementioned AI model is used again for the analysis. The input data is the additional requests, and the output is the updated product list.

[0338] Step 13:

[0339] The terminal displays updated suggested products to the user again. The user can then review the new best product. The input data is the updated product list, and the output is a redisplay of the products.

[0340] (Application Example 2)

[0341] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0342] In traditional e-commerce sites, product suggestions were based solely on basic information and answers to questions, making it difficult to adequately reflect users' emotions and true desires. This resulted in users spending considerable time and effort finding the most suitable product from a wide range of options.

[0343] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving basic information from a user, means for generating a list of questions based on the basic information, means for presenting the generated list of questions to the user, means for receiving the user's answers and analyzing those answers to select the optimal product, means including an emotion engine for analyzing emotion data from the user's answers, means for optimizing the product selection process using the emotion data, and means for presenting the selected product to the user. This makes it possible to propose the optimal product that reflects the user's emotions and true feelings.

[0344] "User information" refers to basic information that users provide when selecting electronic products or home appliances, such as their budget, room size, and intended use.

[0345] A "question list" is a list of questions generated based on the user's basic information and presented to the user.

[0346] "Answer" refers to the response entered by the user based on the list of questions.

[0347] The "emotion engine" is a part of the system that includes an algorithm for analyzing emotions from user response data.

[0348] "Emotional data" is data that represents the user's emotional state (e.g., satisfaction, dissatisfaction, excitement, indecision, etc.) generated by the emotion engine through analysis of the user's responses.

[0349] The "product selection process" is a series of procedures that analyze data from the user's basic information and responses to determine the most suitable product.

[0350] "Product specifications" refer to a list of specific features and performance characteristics of a product, extracted based on user needs.

[0351] The "optimal product" is the product that best matches the user's needs and emotions, selected based on the user's basic information, responses, and sentiment data.

[0352] A "server" is a core computer system that receives basic user information, generates a list of questions, collects and analyzes responses, and selects and suggests the most suitable products.

[0353] System Overview

[0354] This invention relates to a system that uses an emotion engine to analyze user emotional data during the process of selecting electronic products and home appliances, and then proposes the most suitable product based on that analysis. The system performs user information input, generates a list of questions, collects responses, performs emotion analysis, selects products, and proposes the most suitable product.

[0355] Hardware and software configuration

[0356] server:

[0357] Hardware: High-performance computer (such as AWS EC2)

[0358] software:

[0359] Operating System: Linux

[0360] Application server: Node.js

[0361] Database: MySQL

[0362] Sentiment analysis engine: Natural language processing API (Google Cloud Natural Language API)

[0363] AI Analysis Module: Python-based machine learning models

[0364] User terminal:

[0365] Hardware: Smartphone, tablet, or PC

[0366] software:

[0367] Operating system (e.g., iOS, Android, Windows)

[0368] Browser or dedicated application

[0369] Processing flow

[0370] 1. Enter user information

[0371] The user uses a terminal to select the product category they wish to purchase. Next, they enter basic information such as their budget, room size, and intended use. This information is sent to the server and stored in the database.

[0372] 2. Generating a list of questions

[0373] The server analyzes the received basic information and generates a custom list of questions based on the relevant product category. For example, in the case of an air conditioner, it generates questions such as room size, monthly electricity cost, initial purchase cost, and whether it can be operated with a smart device.

[0374] 3. Displaying questions and collecting answers

[0375] A list of questions is displayed sequentially on the user's terminal, and the user answers them. The answers are sent to the server in real time.

[0376] 4. Emotional analysis using an emotion engine

[0377] The server analyzes each response using an emotion engine (Google Cloud Natural Language API) to identify the user's emotions (satisfied, dissatisfied, excited, confused, etc.). This emotion data is also stored in a database.

[0378] 5. AI-driven analysis of responses and selection of optimal products

[0379] The server integrates and analyzes user responses and sentiment data to extract product specifications. A Python-based machine learning model is used to narrow down the database to the most suitable products.

[0380] 6. Proposal of the optimal product

[0381] An optimal product list is generated and sent to the user's terminal. The user reviews it and enters additional information if they have any further requests.

[0382] 7. Processing of additional requests

[0383] When a user enters additional requests (e.g., a model that can be operated via smartphone), the server re-evaluates and presents the updated product list to the user.

[0384] Specific example

[0385] Example 1: The user selects a refrigerator category and enters a specific budget. The server generates questions about the refrigerator (e.g., energy efficiency, quietness, design), and the user answers them sequentially. The emotion engine analyzes these answers to gather emotional data and suggests the most suitable product.

[0386] Example 2: The user selects a PC category and enters their primary use (e.g., gaming, video editing, etc.) and budget. The server generates questions tailored to the user's purpose, and the user answers them. Using the sentiment data analyzed by the emotion engine and the user's response data, the server selects the most suitable PC and presents it to the user.

[0387] Example of a prompt

[0388] "What is your budget?"

[0389] "Is energy efficiency important for a refrigerator? (Please rate on a scale of 1-5)"

[0390] "Do you care about the design of your refrigerator? (Yes / No)"

[0391] The above describes a specific embodiment of the present invention system. By using this system, users can receive optimal product suggestions that reflect their own emotions, thereby improving the efficiency of the selection process and increasing satisfaction.

[0392] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0393] Step 1: Enter user information

[0394] Subject: User

[0395] Specific operation: The user accesses the system via a smartphone application or browser and selects the product category they wish to purchase. Next, they enter basic information such as budget, room size, and intended use. This information is sent from the device to the server.

[0396] Input: Desired product category, budget, room size, purpose of use

[0397] Output: Basic information is sent to the server.

[0398] Step 2: Generate the question list

[0399] Subject: Server

[0400] Specific operation: The server analyzes the received user's basic information and generates a list of questions corresponding to the relevant product category. The generated question list is stored in the database and sent to the user's terminal.

[0401] Input: User's basic information

[0402] Data processing / calculation: Analyze basic information and generate a list of questions.

[0403] Output: A provisional list of questions is displayed on the user's terminal.

[0404] Step 3: Display the questions and collect the answers.

[0405] Subject: User

[0406] Specific operation: A list of questions is displayed on the user's terminal, and the user answers them sequentially. The user's response data is sent to the server in real time.

[0407] Input: List of questions sent from the server

[0408] Output: Response data is sent to the server.

[0409] Step 4: Emotional analysis using the emotion engine

[0410] Subject: Server

[0411] Specific operation: The server uses an emotion engine to analyze user response data in real time and generate emotion data. Emotion data is data that indicates the user's emotional state, such as satisfaction, dissatisfaction, excitement, and indecision. Emotion data is also stored in a database.

[0412] Input: User response data

[0413] Data processing / calculation: Emotion analysis is performed using an emotion engine to generate emotion data.

[0414] Output: Emotional data is generated and stored in the database.

[0415] Step 5: AI-driven analysis of responses and selection of optimal products

[0416] Subject: Server

[0417] Specific operation: The server integrates user response data and sentiment data and performs analysis using an AI model (a Python-based machine learning model). This analysis extracts product specifications, and the server selects the product best suited to the user's needs from the database.

[0418] Input: Response data, sentiment data

[0419] Data processing / calculation: Analyze data using an AI model and extract product specifications.

[0420] Output: The optimal product is generated.

[0421] Step 6: Proposing the optimal product

[0422] Subject: Server

[0423] Specific operation: The server selects the most suitable product list, which is then sent to the user's terminal and displayed to the user. The user then reviews the displayed product list.

[0424] Input: List of products selected by the server

[0425] Output: A list of products best suited to the user's terminal is displayed.

[0426] Step 7: Processing additional requests

[0427] Subject: User

[0428] Specific operation: When a user enters an additional request (for example, a model that can be operated with a smartphone) from the displayed product list, the additional information is sent from the device to the server. The server re-analyzes the newly added request and proposes an updated product list.

[0429] Input: Additional request information

[0430] Output: The updated product list is redisplayed on the user's terminal.

[0431] 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.

[0432] 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 those described above. 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 shown 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.

[0433] 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.

[0434] [Second Embodiment]

[0435] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0436] 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.

[0437] 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).

[0438] 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.

[0439] 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.

[0440] 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).

[0441] 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.

[0442] 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.

[0443] 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.

[0444] 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.

[0445] 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.

[0446] 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".

[0447] This invention relates to a system for assisting users in the process of selecting expensive electronic products and home appliances. This system receives basic information from the user, and based on the user's answers to a generated list of questions, selects and suggests the most suitable products. The program processing of this system is described below in natural language.

[0448] Program Processing Description

[0449] Initial setup

[0450] The server stores selection criteria and question lists for each product category in its database. Product categories include, for example, refrigerators, personal computers, and air conditioners.

[0451] Entering user information

[0452] The user uses their device to first select the product category they wish to purchase. Next, the user enters basic information such as their budget, room size, and intended use.

[0453] Generating a list of questions

[0454] Based on the basic information received, the server generates a list of questions tailored to the relevant product category. For example, in the case of an air conditioner, the server lists questions such as room size, monthly electricity costs, initial purchase cost, and whether the customer wants to control it via smartphone.

[0455] Displaying questions and collecting answers

[0456] A list of questions is displayed to the user sequentially on their device. The user answers these questions, and the answers are sent to the server in real time.

[0457] AI-powered analysis of responses

[0458] The server analyzes the responses received from the user and extracts product specifications. Based on these product specifications, it narrows down the database to the most suitable product.

[0459] Suggesting the optimal product

[0460] Based on the analysis results, the server lists the most suitable products and sends the top-ranked candidate product to the user's terminal. The optimal product is then displayed to the user on the terminal.

[0461] Additional questions and reassessment

[0462] If the user enters additional requests, such as whether the product is operable on a smartphone, the server will incorporate this information into its analysis and perform a re-evaluation. The updated list of candidate products will then be displayed on the user's device.

[0463] Specific example

[0464] Specific example 1: Air conditioner selection

[0465] The user selects an air conditioner category and enters basic information such as budget and room size. The server generates a list of questions about air conditioners based on this information and sends it to the user's device. The user answers whether they prioritize electricity costs or initial costs, etc. The server analyzes the answers, selects air conditioners with high energy efficiency, and presents them to the user. The user then enters a request for a "model that can be operated with a smartphone," and the server re-evaluates and presents updated air conditioner models.

[0466] Example 2: Choosing a PC

[0467] The user selects a PC category and enters their primary use (e.g., video editing, gaming) and budget. The server generates a list of questions based on this information and sends them to the terminal. The user answers questions about "CPU performance" and "storage capacity." The server analyzes the answers, selects a high-performance PC that meets the user's needs, and presents it to the user. Furthermore, if the user wants to see a second option, the server relaxes the settings, re-evaluates, and presents the second PC as well.

[0468] As described above, the present invention allows consumers to easily choose the optimal product that suits their needs.

[0469] The following describes the processing flow.

[0470] Program execution flow

[0471] Initial setup

[0472] Step 1:

[0473] The server stores selection criteria and question lists for each product category in its database. For example, different criteria are set for each category, such as refrigerators, personal computers, and air conditioners.

[0474] Entering user information

[0475] Step 2:

[0476] The user uses their device to select the product category they wish to purchase. Users can choose from options such as refrigerators, computers, and air conditioners.

[0477] Step 3:

[0478] The user fills in the required information in a form, including basic details such as budget, room size, and purpose of use. Once completed, they press the submit button.

[0479] Generating a list of questions

[0480] Step 4:

[0481] The server analyzes the received basic information and generates a list of questions tailored to the relevant product category. For example, for an air conditioner, it would prepare questions such as room size, monthly electricity costs, initial purchase cost, and whether the customer wants to control it with their smartphone.

[0482] Displaying questions and collecting answers

[0483] Step 5:

[0484] The server sends the generated list of questions to the user's terminal. On the user's terminal, the list of questions is displayed sequentially in an easy-to-understand format.

[0485] Step 6:

[0486] The user sequentially enters answers to the displayed questions. For example, they might enter information such as the room size being "20 square meters" and whether they prioritize electricity costs.

[0487] Step 7:

[0488] User responses are sent to the server in real time and stored in the database.

[0489] AI-powered analysis of responses

[0490] Step 8:

[0491] The server analyzes the user's responses and extracts the corresponding product specifications. The analysis uses an algorithm based on the user's response data.

[0492] Step 9:

[0493] The server narrows down the database to the most suitable products based on the extracted product specifications. It then lists the most appropriate products as a result of this filtering.

[0494] Suggesting the optimal product

[0495] Step 10:

[0496] The server prepares detailed information on the listed optimal products and sends it to the user's terminal.

[0497] Step 11:

[0498] The user terminal presents the optimal product to the user in a visually easy-to-understand format. For example, it might display something like "Air conditioner A with high energy efficiency."

[0499] Additional questions and reassessment

[0500] Step 12:

[0501] If a user has additional requests (e.g., a model that can be operated via smartphone), they will enter the information using an additional question form on their device. Once they have finished entering the information, they will press the submit button again.

[0502] Step 13:

[0503] The server analyzes the additional request information and incorporates it into the initial analysis results to re-evaluate the product. A new algorithm that takes the added requests into account is used for the re-evaluation.

[0504] Step 14:

[0505] The updated list of candidate products resulting from the re-evaluation is sent to the user's terminal, which then presents them to the user.

[0506] Confirmation of the second candidate

[0507] Step 15:

[0508] If the user is not satisfied with the first recommended product, they can press the "View Second Choice" button.

[0509] Step 16:

[0510] The server uses the initial responses as a basis, but slightly relaxes the criteria and selects products again. Different algorithms can be used for this process.

[0511] Step 17:

[0512] The server re-analyzes the data and selects a second-choice product. This information is then sent to the user's terminal, which then presents the second-choice product to the user.

[0513] Through these steps, users can effectively select the product that best suits their needs. This system significantly simplifies the product selection process.

[0514] (Example 1)

[0515] 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."

[0516] Traditional product selection systems suggest the most suitable products based on the user's basic information, but they have the problem of not being able to flexibly respond to additional requests or changes. Furthermore, the generated list of questions is limited and sometimes does not adequately reflect the user's needs. As a result, it was difficult for users to select a product that perfectly matched their requirements.

[0517] 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.

[0518] In this invention, the server includes means for receiving basic information from a user, means for generating a list of questions based on the basic information, means for presenting the generated list of questions to the user, means for receiving the user's answers, analyzing those answers, and selecting the most suitable product, means for presenting the selected product to the user, and means for re-evaluating the product based on the user's additional requests and presenting updated candidate products. This enables product selection that more accurately reflects the user's needs and can quickly respond to additional requests and changes.

[0519] A "user" is an individual or organization that uses the system to input basic information and additional requests in order to select products.

[0520] "Basic information" refers to initial information such as the user's desired product category, budget, space size, and intended use, and is used by the system to generate appropriate question lists and product suggestions.

[0521] A "question list" is a series of questions generated based on a user's basic information, designed to gain a more detailed understanding of their needs and requests.

[0522] "Answers" refer to the selections and text information that users enter based on a list of questions, providing data for the system to analyze and select products.

[0523] "Product specifications" refer to the specific specifications and characteristics required for a product, extracted based on user responses.

[0524] A "selected product" is a product that the server has determined to be optimal after analyzing the user's basic information and responses.

[0525] "Additional requests" are new conditions or preferences that users would like to consider, separate from the initial information and responses.

[0526] "Re-evaluation" is the process by which the server incorporates additional requests into its analysis, re-evaluates existing data and conditions, and updates the list of potential products.

[0527] This invention relates to a system for assisting users in the process of selecting expensive electronic products and home appliances. This system receives basic information from the user and, based on the user's answers to a generated list of questions, selects and suggests the most suitable products. Specific embodiments of this system are described below.

[0528] Initial setup

[0529] server

[0530] The server stores selection criteria and question lists for each product category in a database. Product categories include refrigerators, personal computers, air conditioners, etc. For example, the server uses a MySQL database and stores the selection criteria and corresponding question lists for each product category in database tables. These question lists and selection criteria include specific items such as "energy efficiency" and "cooling capacity."

[0531] Entering user information

[0532] User

[0533] The user selects the product category they wish to purchase using their device. For example, using a smartphone app, they might select "air conditioner" on the category selection screen. Next, the user enters information such as "budget of 50,000 yen" and "room size of 15 tatami mats."

[0534] Generating a list of questions

[0535] server

[0536] The server generates a list of questions corresponding to the relevant product category based on the user's basic information received. The server uses Python to dynamically generate a list of questions for air conditioners from the given basic information. For example, it might prepare questions such as, "Your room is 15 tatami mats in size, what are your expectations for your monthly electricity bill?"

[0537] Displaying questions and collecting answers

[0538] terminal

[0539] A list of questions is displayed sequentially to the user on their device. The user answers these questions, and the answers are sent to the server in real time. For example, a smartphone app displays a list of questions retrieved from the server based on the information entered by the user, and each time the user taps an option, the answer data is sent to the server.

[0540] AI-powered analysis of responses

[0541] server

[0542] The server analyzes the user's responses using an AI model. The server uses TensorFlow to build a generative AI model and analyze the user's responses. For example, if the server receives a response indicating that "electricity costs are a priority," the model will narrow down the candidates to air conditioners with particularly excellent energy-saving performance.

[0543] Suggesting the optimal product

[0544] server

[0545] Based on the analysis results, the system lists the most suitable products and sends the top-ranked candidate product to the user's device. The server generates a list of recommended products and sends the most suitable product from that list to the user's smartphone app in JSON format.

[0546] terminal

[0547] The most suitable products are displayed to the user. The smartphone app displays product details to the user based on the data received.

[0548] Additional questions and reassessment

[0549] User

[0550] The user enters any additional requests. For example, if the user wants a model that can be operated with a smartphone, they enter that request from their device.

[0551] server

[0552] The server incorporates the additional requests into its analysis and performs a re-evaluation. Once the analysis is complete, it resends the updated list of candidate products to the user's device. The smartphone app immediately reflects the changes to the user.

[0553] Specific example

[0554] Specific example 1: Air conditioner selection

[0555] The user selects an air conditioner category and enters basic information such as budget and room size. The server generates a list of questions about air conditioners based on this information and sends it to the user's device. The user answers whether they prioritize electricity costs or initial costs, etc. The server analyzes the answers, selects air conditioners with high energy efficiency, and presents them to the user. If the user adds a request for a "model that can be operated with a smartphone," the server re-evaluates and presents updated air conditioner models.

[0556] Example of a prompt

[0557] Please simulate the process a user goes through when selecting an air conditioner. The budget is 50,000 yen, the room size is 15 tatami mats, the purpose is heating and cooling, and the additional request is for a model that can be controlled via smartphone.

[0558] Example 2: Choosing a PC

[0559] The user selects a PC category and enters their primary use (e.g., video editing, gaming) and budget. The server generates a list of questions based on this information and sends them to the terminal. The user answers questions about "CPU performance" and "storage capacity." The server analyzes the answers, selects a high-performance PC that meets the user's needs, and presents it to the user. Furthermore, if the user wants to see a second option, the server relaxes the settings, re-evaluates, and presents the second PC as well.

[0560] Example of a prompt

[0561] Please simulate the process a user goes through when selecting a PC. The purpose is video editing, the budget is 150,000 yen, and additional requirements include a high-performance CPU and storage capacity of 1TB or more. Please provide an example of this scenario.

[0562] As described above, the present invention allows consumers to easily choose the optimal product that suits their needs.

[0563] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0564] Step 1: Database Setup

[0565] The server stores selection criteria and question lists for each product category in a database. The server uses a MySQL database and stores the selection criteria and corresponding question lists in database tables for each product category (refrigerators, personal computers, air conditioners, etc.). For example, the refrigerator category includes criteria such as "overall capacity" and "energy efficiency." Input is the data for the selection criteria and question lists, and output is the selection criteria and question lists stored in the database.

[0566] Step 2: Enter user information

[0567] The user selects the product category they wish to purchase using their device. Next, the user enters basic information such as budget, space size, and intended use. This information is entered using the smartphone app interface, and the entered information is sent from the device to the server. The input is the user's basic information, and the output is the basic information sent to the server.

[0568] Step 3: Generate the question list

[0569] The server generates a list of questions corresponding to the product category based on the user's basic information received. The server executes a Python script to dynamically generate the necessary questions from the basic information. For example, in the case of the air conditioner category, questions such as "room size," "budget," and "desire for smartphone control" are created. The input is the user's basic information, and the output is the generated list of questions.

[0570] Step 4: Display the questions and collect the answers.

[0571] A list of questions generated for the user is displayed sequentially on the terminal. The user answers the questions as they appear, and the answers are sent to the server in real time. For example, if the terminal interface displays the question "Are you thinking about your monthly electricity bill?", and the user enters an answer, that answer is sent to the server. The input is the list of questions and the user's answers, and the output is the user's answers sent to the server.

[0572] Step 5: AI-driven analysis of the response

[0573] The server analyzes the user's responses using an AI model. The server uses TensorFlow to build a generative AI model and extracts product specifications from the user's responses. For example, if it receives a response indicating a focus on electricity costs, it will narrow down the candidates to products with high energy efficiency. The input is the user's response data, and the output is the analyzed product specifications.

[0574] Step 6: Proposing the optimal product

[0575] The server lists the most suitable products based on the analysis results and sends the top-ranked candidate product to the user's terminal. The server generates a list of recommended products and sends it to the user's smartphone app in JSON format. The smartphone app displays product details to the user based on the received data. The input is the analyzed product specifications, and the output is the list of optimal products sent to the user's terminal.

[0576] Step 7: Additional questions and reassessment

[0577] The user enters additional requests. For example, if they want a "model that can be operated with a smartphone," they enter that request from their device. The server incorporates the additional requests into its analysis and performs a re-evaluation. After the re-evaluation, the updated list of candidate products is resent to the user's device. The smartphone app immediately reflects the changes to the user. The input consists of the additional requests and existing data, and the output is the re-evaluated, updated product list.

[0578] (Application Example 1)

[0579] 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 glasses 214 will be referred to as the "terminal."

[0580] Modern consumers face the challenge of quickly selecting the optimal product to suit their specific needs in a physical store with numerous options. In particular, they require selection support that addresses not only basic information such as budget and intended use, but also specific factors like electricity costs and ease of use. Furthermore, a lack of adequate means to provide product and location information within physical stores can cause consumers to become lost. It is necessary to address these challenges and provide consumers with an efficient and intuitive product selection support system.

[0581] 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.

[0582] In this invention, the server includes means for receiving basic information from a user, means for generating a list of questions based on the basic information, means for presenting the generated list of questions to the user, means for receiving the user's answers and analyzing those answers to select the optimal product, means for presenting the selected product to the user, means for providing product information and location information available in the store to the user in the physical store, and means for providing product selection support using a smartphone-based user interface. This makes it possible for consumers to efficiently select the optimal product even in a physical store.

[0583] "Basic information" refers to initial settings such as budget, room size, and intended use that users enter when selecting a product.

[0584] A "question list" is a collection of specific questions necessary for product selection, generated based on the user's basic information.

[0585] "User response" refers to the specific content of the user's response to the list of questions.

[0586] The "optimal product" is the product that best suits the user's needs, selected based on the user's basic information and responses.

[0587] "Selected products" refer to specific products that are recommended to the user based on the analysis results.

[0588] A "physical store" is a physical sales location where consumers can go in person and purchase products.

[0589] "Product information" refers to detailed data about a product, such as its characteristics, specifications, and price.

[0590] "Location information" refers to information used to identify the location of a product within a physical store.

[0591] A "user interface" refers to the operating screen and display functions used for exchanging information between the user and the system.

[0592] A "smartphone" is a portable mobile terminal device that provides a variety of operating applications in addition to the functions of a mobile phone.

[0593] This invention is a system that helps consumers efficiently select the most suitable products in a physical store. This system is realized using a server, terminals such as smartphones, a database, and an AI model.

[0594] First, the server stores selection criteria and question lists for each product category in a database. Product categories include refrigerators, personal computers, air conditioners, etc. Next, the user launches the application using their smartphone in a physical store and selects the product category they wish to purchase. The user enters basic information such as budget, room size, and intended use. The server then generates a question list corresponding to the product category based on the received basic information and sends it to the terminal. For example, for an air conditioner, the list would include questions such as room size, monthly electricity costs, initial purchase cost, and whether the user wants to control it with a smartphone.

[0595] The terminal displays a list of questions to the user sequentially, and the user answers them. The answers are sent to the server in real time. The server analyzes the answers and uses an AI model to extract product specifications. Generative AI models such as TensorFlow are used for this analysis process. Based on the extracted product specifications, the server narrows down the best products from the database and lists candidate products. This list of candidate products is sent to the terminal and presented to the user.

[0596] Furthermore, product information and location data are provided to make it easier for users to check potential products within physical stores. Users can check the specific location and detailed information of products through their smartphone interface.

[0597] As a concrete example, consider a case where a user purchases a refrigerator at a physical electronics store. In this example, the user selects a category, then enters their budget, room size, and intended use. The server generates a list of questions for the refrigerator and sends it to the user's terminal. The user answers the questions, and the server analyzes them using a generated AI model. Based on the analysis results, the server selects the most suitable refrigerator and provides the user with its product information and location.

[0598] Example of a prompt message: "My budget is 200,000 yen. I'm looking for a refrigerator. The room size is 3m x 3m. I prioritize low monthly electricity costs, a standard size is fine, and I don't have a preference for the door opening direction. Please recommend a refrigerator."

[0599] This system configuration allows users to efficiently and intuitively select the most suitable products even within a physical store.

[0600] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0601] Step 1:

[0602] The server stores selection criteria and question lists for each product category in a database. This process adds information such as product characteristics, usage scenarios, and price ranges to the database. The input is detailed information for each product category, and the output is the selection criteria and question lists stored in the database. Specifically, it creates appropriate question lists for each category, such as refrigerators, personal computers, and air conditioners.

[0603] Step 2:

[0604] The user launches the application using their smartphone while in a physical store. Next, they select the product category they wish to purchase and enter basic information such as their budget, room size, and intended use. This basic information is sent to the server. The input is the basic information such as budget and intended use entered by the user, and the output is the basic information sent to the server. Specifically, the user selects the refrigerator category and enters information such as "budget is 200,000 yen" and "intended use is for home use."

[0605] Step 3:

[0606] The server generates a list of questions corresponding to the relevant product category based on the basic information received and sends it to the terminal. The input is the basic information received from the user, and the output is the generated list of questions. Specifically, for the refrigerator category, questions such as "Are you concerned about monthly electricity costs?" and "What size refrigerator do you need?" are generated.

[0607] Step 4:

[0608] The terminal displays a generated list of questions to the user sequentially. The user answers these questions, and the answers are sent to the server in real time. The input is the list of questions sent from the server and the user's answers, and the output is the answer data for analysis sent to the server. Specifically, the user answers questions such as "I prioritize electricity costs" and "I want a standard-sized refrigerator."

[0609] Step 5:

[0610] The server uses a generative AI model to analyze user responses and extract product specifications. The input is user response data, and the output is the extracted product specifications. Specifically, a generative AI model using TensorFlow extracts the specifications "prioritizing low electricity consumption" and "standard size."

[0611] Step 6:

[0612] The server narrows down the database to the most suitable products based on the extracted product specifications, lists the candidate products, and sends them to the terminal. The input is the extracted product specifications, and the output is the list of candidate products presented to the user. Specifically, refrigerators that meet the conditions of "budget under 200,000 yen," "prioritizing low electricity consumption," and "standard size" are listed.

[0613] Step 7:

[0614] Within the physical store, users are provided with information on selected products and their locations. Input consists of a list of candidate products sent from the server and the product locations within the store; output consists of detailed product information and location information displayed on the terminal. Specifically, the detailed specifications of the listed refrigerators and their location within the store are presented.

[0615] Step 8:

[0616] Users check the specific location and details of products through their smartphone's user interface. Input is the product location and details displayed on the device, while output is the user's action based on their purchasing decision. Specifically, users check the location of listed refrigerators within a physical store, check the products on the spot, and decide to purchase them.

[0617] 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.

[0618] This invention combines an emotion engine with a system designed to assist users in the process of selecting electronic products and home appliances. This system receives basic information from the user, analyzes the user's emotions based on their answers to a generated list of questions using the emotion engine, and then selects and suggests the most suitable products based on that analysis. The following describes the program's processing in natural language.

[0619] Program Processing Description

[0620] Initial setup

[0621] The server stores selection criteria and question lists for each product category in a database. Product categories include, for example, refrigerators, personal computers, and air conditioners. The emotion engine includes algorithms that analyze user emotions from text and voice data.

[0622] Entering user information

[0623] The user uses their device to first select the product category they wish to purchase. Next, they enter basic information such as their budget, room size, and intended use.

[0624] Generating a list of questions

[0625] The server analyzes the received basic information and generates a list of questions tailored to the relevant product category. For example, for an air conditioner, it would prepare questions such as room size, monthly electricity costs, initial purchase cost, and whether the customer wants to control it with their smartphone.

[0626] Displaying questions and collecting answers

[0627] A list of questions is displayed to the user sequentially on their device. The user answers these questions, and the answers are sent to the server in real time.

[0628] Emotional analysis using an emotion engine

[0629] The emotion engine analyzes the user's response text and voice data to identify the user's emotions (e.g., satisfaction, dissatisfaction, excitement, indecision, etc.).

[0630] AI-powered analysis of responses

[0631] The server integrates responses received from the user with sentiment data from the sentiment engine and extracts product specifications. Based on these product specifications, it narrows down the database to the most suitable product.

[0632] Suggesting the optimal product

[0633] Based on the analysis results, the server lists the most suitable products and sends the top-ranked candidate product to the user's terminal. The optimal product is then displayed to the user on the terminal.

[0634] Additional questions and reassessment

[0635] If a user has additional requests (e.g., a model that can be operated via smartphone), they will enter the information using an additional question form on their device. Once they have finished entering the information, they will press the submit button again.

[0636] The server analyzes the additional request information and incorporates it into the initial analysis results to re-evaluate the products. A new algorithm based on the added requests is used for the re-evaluation. The updated candidate products are then displayed on the user's device.

[0637] Specific example

[0638] Specific example 1: Air conditioner selection

[0639] The user selects an air conditioner category and enters basic information such as budget and room size. The server generates a list of questions about air conditioners based on this information and sends it to the user's device. The user answers whether they prioritize electricity costs or initial costs, etc. As soon as the answers are sent to the server, an emotion engine analyzes the user's responses to identify their emotions, satisfaction level, and level of excitement. The server comprehensively analyzes this data to select and present air conditioners with high energy efficiency. If the user requests an additional model that can be operated via smartphone, the server re-evaluates and presents updated air conditioner models.

[0640] Example 2: Choosing a PC

[0641] The user selects a PC category and enters their primary use (e.g., video editing, gaming) and budget. The server generates a list of questions based on this information and sends them to the terminal. The user answers questions about "CPU performance" and "storage capacity." The emotion engine analyzes the user's responses to identify their stress level and level of interest. Based on the responses and emotion data, the server analyzes and selects a high-performance PC that meets the user's needs and presents it to the user. If the user wants to see a second option, the server relaxes the settings, re-evaluates, and presents the second PC.

[0642] As described above, the system of the present invention, by combining an emotion engine that analyzes the user's emotions, more accurately reflects the user's true needs and enables optimal product recommendations. As a result, users can find products that are more satisfying to them during the selection process.

[0643] The following describes the processing flow.

[0644] Program execution flow

[0645] Initial setup

[0646] Step 1:

[0647] The server stores selection criteria, question lists, and sentiment analysis algorithms for each product category in its database. For example, different criteria and sentiment analysis settings are prepared for each category, such as refrigerators, personal computers, and air conditioners.

[0648] Entering user information

[0649] Step 2:

[0650] The user uses their device to select the product category they wish to purchase. Categories include refrigerators, computers, air conditioners, and so on.

[0651] Step 3:

[0652] The user enters basic information such as budget, room size, and purpose of use into a form and presses the submit button.

[0653] Generating a list of questions

[0654] Step 4:

[0655] The server analyzes the basic information it receives and generates a list of questions based on that information, corresponding to the relevant product category. For example, in the case of an air conditioner, the server lists questions such as room size, monthly electricity costs, initial purchase cost, and whether the customer wants to control it with their smartphone.

[0656] Displaying questions and collecting answers

[0657] Step 5:

[0658] The server sends the generated list of questions to the user's terminal. On the user's terminal, the list of questions is displayed sequentially in an easy-to-understand format.

[0659] Step 6:

[0660] The user sequentially enters answers to the displayed questions. For example, they might enter information such as the room size being "20 square meters" and whether they prioritize electricity costs.

[0661] Step 7:

[0662] User responses are sent to the server in real time and stored in a database. Simultaneously, an emotion engine analyzes the response text and audio data.

[0663] Emotional analysis using an emotion engine

[0664] Step 8:

[0665] The emotion engine built into the server analyzes emotions based on the user's response text and voice data. For example, it uses natural language processing technology to identify emotions such as how satisfied, excited, or anxious the user is.

[0666] AI-powered analysis of responses

[0667] Step 9:

[0668] The server integrates the responses received from the user with sentiment data from the sentiment engine and extracts product specifications. The extracted product specifications are then compared with candidate products in the database.

[0669] Step 10:

[0670] The server narrows down the database to the most suitable products based on the extracted product specifications and sentiment data. It then lists the most appropriate products as a result of this filtering.

[0671] Suggesting the optimal product

[0672] Step 11:

[0673] The server prepares detailed information on the listed optimal products and sends it to the user's terminal.

[0674] Step 12:

[0675] The user terminal presents the optimal product to the user in a visually easy-to-understand format. For example, it might display something like "Air conditioner A with high energy efficiency."

[0676] Additional questions and reassessment

[0677] Step 13:

[0678] If a user has additional requests (e.g., a model that can be operated via smartphone), they will enter the information using an additional question form on their device. Once they have finished entering the information, they will press the submit button again.

[0679] Step 14:

[0680] The server analyzes the additional request information and incorporates it into the initial analysis results to re-evaluate the product. The re-evaluation utilizes a new algorithm based on the added requests.

[0681] Step 15:

[0682] The updated list of candidate products is displayed on the user's device. The user's device then presents the user with new, optimal products that reflect the additional requests.

[0683] Confirmation of the second candidate

[0684] Step 16:

[0685] If the user is not satisfied with the first recommended product, they can press the "View Second Choice" button.

[0686] Step 17:

[0687] The server selects products again, based on the initial responses and sentiment data, but with slightly relaxed criteria. Different algorithms can be used for this process.

[0688] Step 18:

[0689] The server re-analyzes the data and selects a second-choice product. This information is then sent to the user's terminal, which then presents the second-choice product to the user.

[0690] By following these steps, users can effectively select the product that best suits their needs. This system also takes user emotions into consideration, resulting in a more satisfying product selection process.

[0691] (Example 2)

[0692] 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".

[0693] Traditional selection processes for electronic products and home appliances often relied solely on user information and responses, failing to consider user emotions and thus making it difficult to meet true user needs. Furthermore, selection based solely on responses can overlook important factors that users may not be aware of. As a result, users are more likely to make unsatisfactory choices, increasing the risk of post-purchase regret.

[0694] 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.

[0695] In this invention, the server includes means for receiving basic information from the user, means for generating a list of questions based on the basic information, means for presenting the generated list of questions to the user, means for receiving the user's answers and analyzing those answers to identify the user's emotions, means for selecting the optimal product based on the analyzed emotion information and answer information, and means for presenting the selected product to the user. This enables comprehensive analysis of the user's answers and emotion data, making it possible to propose the optimal product that reflects the user's true needs.

[0696] "Basic information" refers to information necessary for product selection, such as the user's budget, the size of the environment, and the purpose of use.

[0697] A "question list" is a series of questions generated based on the user's basic information and presented to the user.

[0698] "Sentiment analysis" is the process of analyzing user response text and voice data to identify emotions such as satisfaction, dissatisfaction, excitement, and indecision.

[0699] "Product specifications" refer to detailed information about the product's performance and functions, extracted based on the user's responses and sentiment analysis results.

[0700] The "optimal product" is the product that best meets the user's needs, selected based on the user's basic information, responses, and sentiment analysis results.

[0701] A "terminal" is a device used by a user to input information, answer questions, and be presented with the most suitable products, and includes smartphones, PCs, and other similar devices.

[0702] A "server" is a computer device that receives basic information, generates a list of questions, analyzes responses and emotions, and selects the most suitable product.

[0703] This invention combines an emotion engine with a system designed to assist users in the process of selecting electronic products and home appliances. The system receives basic information from the user, analyzes the user's emotions based on their responses to a generated list of questions using the emotion engine, and then selects and suggests the most suitable products based on that analysis.

[0704] The server stores selection criteria for each product category (e.g., refrigerators, personal computers, air conditioners) and corresponding question lists in a database. The sentiment engine is configured to analyze user response text and audio data using Google Cloud Natural Language API and IBM Watson's sentiment analysis capabilities. This configuration includes setting up API keys and importing model training data.

[0705] The user uses a device (such as a smartphone or PC) to select the product category they wish to purchase and enters basic information such as their budget, room size, and intended use. This prepares the system to generate a list of questions tailored to the user.

[0706] The server analyzes the received basic information and generates a list of questions corresponding to the relevant product category. For example, in the air conditioner category, it dynamically creates relevant questions based on clues such as room size and desired functions (energy-saving mode, remote control operation, etc.).

[0707] The terminal displays a list of questions sent from the server to the user, one by one. The user answers each question, and the answers are sent to the server in real time. For example, if the user is asked "What is the size of the room?" in the air conditioner question list, and answers "20m²", the user will answer "20m²". 2 When you answer "Yes," the response is immediately sent to the server.

[0708] The emotion engine on the server analyzes the user's response text and audio data. Based on the analysis, it identifies the user's emotions (e.g., satisfaction, dissatisfaction, excitement, indecision, etc.). For example, if a user answers, "I'm concerned about the electricity bill, but does it have energy-saving features?", the emotion engine will analyze the word "concerned" to identify the emotion of "worry."

[0709] The server integrates responses and sentiment data received from users and extracts product specifications using high-performance AI. This involves using machine learning models (e.g., scikit-learn or TensorFlow) to gain a deep understanding of user needs. For example, if a user prioritizes "energy efficiency," the server will narrow down the search to products with high energy efficiency.

[0710] The server lists the most suitable products based on the analysis results and sends the top candidate product to the user's terminal. The product is then displayed to the user on the terminal. For example, it might display "highly energy-efficient air conditioners" and provide detailed information and a purchase link for that product.

[0711] When a user enters additional requests, such as "models that can be operated with a smartphone," the device sends the new information to the server. The server then re-evaluates the product list based on this information and sends the results back to the device. For example, if the user adds "smartphone controllable" as a condition, the server will display air conditioner models that meet that condition again.

[0712] Specific example

[0713] Specific example 1: Air conditioner selection

[0714] The user selects an air conditioner category and enters basic information such as budget and room size. The server generates a list of questions about air conditioners based on this information and sends it to the user's device. The user answers whether they prioritize electricity costs or initial costs and sends their answer to the server. Simultaneously, an emotion engine analyzes emotions such as "satisfied" or "concerned." The server integrates this data to select and present air conditioners with high energy efficiency. If the user requests an additional model that can be operated via smartphone, the server re-evaluates and presents a new air conditioner model.

[0715] Example of a prompt

[0716] 1. "I'm thinking of buying an air conditioner. The room is 20m²." 2 So, I want to keep my monthly electricity bill down. I prioritize running costs over initial costs."

[0717] 2. "I want an air conditioner that I can control with my smartphone."

[0718] Example 2: Choosing a PC

[0719] The user selects a PC category and enters their primary use (e.g., video editing, gaming) and budget. The server generates a list of questions based on this information and sends it to the terminal. The user answers questions about "CPU performance" and "storage capacity," and an emotion engine analyzes their "interests" and "stress levels." Based on the answers and emotion data, the server performs an analysis to select and present a high-performance PC that meets the user's needs. If the user wants to see a second option, the server relaxes the settings, re-evaluates, and presents another PC.

[0720] Example of a prompt

[0721] 1. "I'm considering buying a computer. My budget is 150,000 yen, and my main purpose is video editing. A large storage capacity would be ideal."

[0722] 2. "I want a model with a high CPU performance for video editing."

[0723] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0724] Step 1:

[0725] The server stores selection criteria and question lists for each product category in a database. Specifically, for each category such as refrigerators, personal computers, and air conditioners, it sets criteria related to budget and intended use, as well as question lists based on those criteria. A database system such as Google Cloud Firestore or MySQL is used for this setup. The input data consists of product categories, their selection criteria, and question lists, and the output is storage in the database.

[0726] Step 2:

[0727] The user uses a terminal to select the product category they wish to purchase. Specifically, they select one from a list of product categories displayed on the terminal screen, such as air conditioners, refrigerators, or personal computers. The user's input data is the selected product category, and the output is the transmission of the selection information to the server.

[0728] Step 3:

[0729] The user uses a terminal to input basic information such as budget, room size, and purpose of use. Specifically, they enter the necessary information in fields such as budget (amount), room size (square meters), and purpose of use (cooling, heating, other). This information is sent to the server. The input data is basic information, and the output is the transmission of this data to the server.

[0730] Step 4:

[0731] The server analyzes the received basic information and generates a list of questions tailored to the relevant product category. For example, in the case of an air conditioner, it generates questions about electricity costs, energy efficiency, and whether it can be controlled via smartphone, based on room size and budget. The analysis is performed using Python scripts or Node.js, and the algorithm is executed. The input data is basic information, and the output is the generated list of questions.

[0732] Step 5:

[0733] The terminal displays a list of questions sent from the server to the user in sequence. Specifically, each question is displayed on the terminal screen, prompting the user to input. The input data is the list of questions, and the output is the presentation of these questions to the user.

[0734] Step 6:

[0735] The user answers each question and sends the answers to the server in real time via their device. For example, to the question "What is the size of the room?", the answer might be "20m 2 The system provides responses such as "[...]". The input data is the user's response, and the output is the transmission of that response data to the server.

[0736] Step 7:

[0737] The emotion engine on the server analyzes the text and audio data submitted by the user. Specifically, it uses the Google Cloud Natural Language API for text analysis and IBM Watson's emotion analysis function for audio data analysis. The emotion engine identifies emotions such as satisfaction, dissatisfaction, excitement, and indecision from the user's statements. The input data is the user's response, and the output is the analyzed emotion information.

[0738] Step 8:

[0739] The server integrates responses and sentiment data received from users and extracts product specifications using high-performance AI. For example, it creates an analysis model using Python libraries such as scikit-learn and TensorFlow to extract product specifications based on user requests. The input data consists of responses and sentiment data, and the output is the extracted product specifications.

[0740] Step 9:

[0741] The server lists the most suitable products based on the analysis results and sends the top candidate products to the user's terminal. Specifically, it searches the database for products that meet the criteria based on the extracted product specifications and lists the best ones. The input data is product specifications, and the output is a list of optimal products.

[0742] Step 10:

[0743] The terminal displays a list of optimal products to the user. The user can select from the presented products, and detailed product information and purchase links are also displayed. The input data is the list of optimal products, and the output is the display of the products.

[0744] Step 11:

[0745] If a user enters an additional request (for example, "a model that can be operated with a smartphone"), that request is sent to the server via the device. The input data is the additional request, and the output is the transmission of that data to the server.

[0746] Step 12:

[0747] The server analyzes the additional request information and incorporates it into the initial analysis results to re-evaluate the products. Specifically, it re-evaluates the product list based on the new conditions derived from the additional requests. The aforementioned AI model is used again for the analysis. The input data is the additional requests, and the output is the updated product list.

[0748] Step 13:

[0749] The terminal displays updated suggested products to the user again. The user can then review the new best product. The input data is the updated product list, and the output is a redisplay of the products.

[0750] (Application Example 2)

[0751] 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 will be referred to as the "terminal."

[0752] In traditional e-commerce sites, product suggestions were based solely on basic information and answers to questions, making it difficult to adequately reflect users' emotions and true desires. This resulted in users spending considerable time and effort finding the most suitable product from a wide range of options.

[0753] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving basic information from a user, means for generating a list of questions based on the basic information, means for presenting the generated list of questions to the user, means for receiving the user's answers and analyzing those answers to select the optimal product, means including an emotion engine for analyzing emotion data from the user's answers, means for optimizing the product selection process using the emotion data, and means for presenting the selected product to the user. This makes it possible to propose the optimal product that reflects the user's emotions and true feelings.

[0754] "User information" refers to basic information that users provide when selecting electronic products or home appliances, such as their budget, room size, and intended use.

[0755] A "question list" is a list of questions generated based on the user's basic information and presented to the user.

[0756] "Answer" refers to the response entered by the user based on the list of questions.

[0757] The "emotion engine" is a part of the system that includes an algorithm for analyzing emotions from user response data.

[0758] "Emotional data" is data that represents the user's emotional state (e.g., satisfaction, dissatisfaction, excitement, indecision, etc.) generated by the emotion engine through analysis of the user's responses.

[0759] The "product selection process" is a series of procedures that analyze data from the user's basic information and responses to determine the most suitable product.

[0760] "Product specifications" refer to a list of specific features and performance characteristics of a product, extracted based on user needs.

[0761] The "optimal product" is the product that best matches the user's needs and emotions, selected based on the user's basic information, responses, and sentiment data.

[0762] A "server" is a core computer system that receives basic user information, generates a list of questions, collects and analyzes responses, and selects and suggests the most suitable products.

[0763] System Overview

[0764] This invention relates to a system that uses an emotion engine to analyze user emotional data during the process of selecting electronic products and home appliances, and then proposes the most suitable product based on that analysis. The system performs user information input, generates a list of questions, collects responses, performs emotion analysis, selects products, and proposes the most suitable product.

[0765] Hardware and software configuration

[0766] server:

[0767] Hardware: High-performance computer (such as AWS EC2)

[0768] software:

[0769] Operating System: Linux

[0770] Application server: Node.js

[0771] Database: MySQL

[0772] Sentiment analysis engine: Natural language processing API (Google Cloud Natural Language API)

[0773] AI Analysis Module: Python-based machine learning models

[0774] User terminal:

[0775] Hardware: Smartphone, tablet, or PC

[0776] software:

[0777] Operating system (e.g., iOS, Android, Windows)

[0778] Browser or dedicated application

[0779] Processing flow

[0780] 1. Enter user information

[0781] The user uses a terminal to select the product category they wish to purchase. Next, they enter basic information such as their budget, room size, and intended use. This information is sent to the server and stored in the database.

[0782] 2. Generating a list of questions

[0783] The server analyzes the received basic information and generates a custom list of questions based on the relevant product category. For example, in the case of an air conditioner, it generates questions such as room size, monthly electricity cost, initial purchase cost, and whether it can be operated with a smart device.

[0784] 3. Displaying questions and collecting answers

[0785] A list of questions is displayed sequentially on the user's terminal, and the user answers them. The answers are sent to the server in real time.

[0786] 4. Emotional analysis using an emotion engine

[0787] The server analyzes each response using an emotion engine (Google Cloud Natural Language API) to identify the user's emotions (satisfied, dissatisfied, excited, confused, etc.). This emotion data is also stored in a database.

[0788] 5. AI-driven analysis of responses and selection of optimal products

[0789] The server integrates and analyzes user responses and sentiment data to extract product specifications. A Python-based machine learning model is used to narrow down the database to the most suitable products.

[0790] 6. Proposal of the optimal product

[0791] An optimal product list is generated and sent to the user's terminal. The user reviews it and enters additional information if they have any further requests.

[0792] 7. Processing of additional requests

[0793] When a user enters additional requests (e.g., a model that can be operated via smartphone), the server re-evaluates and presents the updated product list to the user.

[0794] Specific example

[0795] Example 1: The user selects a refrigerator category and enters a specific budget. The server generates questions about the refrigerator (e.g., energy efficiency, quietness, design), and the user answers them sequentially. The emotion engine analyzes these answers to gather emotional data and suggests the most suitable product.

[0796] Example 2: The user selects a PC category and enters their primary use (e.g., gaming, video editing, etc.) and budget. The server generates questions tailored to the user's purpose, and the user answers them. Using the sentiment data analyzed by the emotion engine and the user's response data, the server selects the most suitable PC and presents it to the user.

[0797] Example of a prompt

[0798] "What is your budget?"

[0799] "Is energy efficiency important for a refrigerator? (Please rate on a scale of 1-5)"

[0800] "Do you care about the design of your refrigerator? (Yes / No)"

[0801] The above describes a specific embodiment of the present invention system. By using this system, users can receive optimal product suggestions that reflect their own emotions, thereby improving the efficiency of the selection process and increasing satisfaction.

[0802] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0803] Step 1: Enter user information

[0804] Subject: User

[0805] Specific operation: The user accesses the system via a smartphone application or browser and selects the product category they wish to purchase. Next, they enter basic information such as budget, room size, and intended use. This information is sent from the device to the server.

[0806] Input: Desired product category, budget, room size, purpose of use

[0807] Output: Basic information is sent to the server.

[0808] Step 2: Generate the question list

[0809] Subject: Server

[0810] Specific operation: The server analyzes the received user's basic information and generates a list of questions corresponding to the relevant product category. The generated question list is stored in the database and sent to the user's terminal.

[0811] Input: User's basic information

[0812] Data processing / calculation: Analyze basic information and generate a list of questions.

[0813] Output: A provisional list of questions is displayed on the user's terminal.

[0814] Step 3: Display the questions and collect the answers.

[0815] Subject: User

[0816] Specific operation: A list of questions is displayed on the user's terminal, and the user answers them sequentially. The user's response data is sent to the server in real time.

[0817] Input: List of questions sent from the server

[0818] Output: Response data is sent to the server.

[0819] Step 4: Emotional analysis using the emotion engine

[0820] Subject: Server

[0821] Specific operation: The server uses an emotion engine to analyze user response data in real time and generate emotion data. Emotion data is data that indicates the user's emotional state, such as satisfaction, dissatisfaction, excitement, and indecision. Emotion data is also stored in a database.

[0822] Input: User response data

[0823] Data processing / calculation: Emotion analysis is performed using an emotion engine to generate emotion data.

[0824] Output: Emotional data is generated and stored in the database.

[0825] Step 5: AI-driven analysis of responses and selection of optimal products

[0826] Subject: Server

[0827] Specific operation: The server integrates user response data and sentiment data and performs analysis using an AI model (a Python-based machine learning model). This analysis extracts product specifications, and the server selects the product best suited to the user's needs from the database.

[0828] Input: Response data, sentiment data

[0829] Data processing / calculation: Analyze data using an AI model and extract product specifications.

[0830] Output: The optimal product is generated.

[0831] Step 6: Proposing the optimal product

[0832] Subject: Server

[0833] Specific operation: The server selects the most suitable product list, which is then sent to the user's terminal and displayed to the user. The user then reviews the displayed product list.

[0834] Input: List of products selected by the server

[0835] Output: A list of products best suited to the user's terminal is displayed.

[0836] Step 7: Processing additional requests

[0837] Subject: User

[0838] Specific operation: When a user enters an additional request (for example, a model that can be operated with a smartphone) from the displayed product list, the additional information is sent from the device to the server. The server re-analyzes the newly added request and proposes an updated product list.

[0839] Input: Additional request information

[0840] Output: The updated product list is redisplayed on the user's terminal.

[0841] 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.

[0842] 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 those described above. 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 shown 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.

[0843] 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.

[0844] [Third Embodiment]

[0845] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0846] 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.

[0847] 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).

[0848] 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.

[0849] 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.

[0850] 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).

[0851] 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.

[0852] 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.

[0853] 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.

[0854] 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.

[0855] 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.

[0856] 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".

[0857] This invention relates to a system for assisting users in the process of selecting expensive electronic products and home appliances. This system receives basic information from the user, and based on the user's answers to a generated list of questions, selects and suggests the most suitable products. The program processing of this system is described below in natural language.

[0858] Program Processing Description

[0859] Initial setup

[0860] The server stores selection criteria and question lists for each product category in its database. Product categories include, for example, refrigerators, personal computers, and air conditioners.

[0861] Entering user information

[0862] The user uses their device to first select the product category they wish to purchase. Next, the user enters basic information such as their budget, room size, and intended use.

[0863] Generating a list of questions

[0864] Based on the basic information received, the server generates a list of questions tailored to the relevant product category. For example, in the case of an air conditioner, the server lists questions such as room size, monthly electricity costs, initial purchase cost, and whether the customer wants to control it via smartphone.

[0865] Displaying questions and collecting answers

[0866] A list of questions is displayed to the user sequentially on their device. The user answers these questions, and the answers are sent to the server in real time.

[0867] AI-powered analysis of responses

[0868] The server analyzes the responses received from the user and extracts product specifications. Based on these product specifications, it narrows down the database to the most suitable product.

[0869] Suggesting the optimal product

[0870] Based on the analysis results, the server lists the most suitable products and sends the top-ranked candidate product to the user's terminal. The optimal product is then displayed to the user on the terminal.

[0871] Additional questions and reassessment

[0872] If the user enters additional requests, such as whether the product is operable on a smartphone, the server will incorporate this information into its analysis and perform a re-evaluation. The updated list of candidate products will then be displayed on the user's device.

[0873] Specific example

[0874] Specific example 1: Air conditioner selection

[0875] The user selects an air conditioner category and enters basic information such as budget and room size. The server generates a list of questions about air conditioners based on this information and sends it to the user's device. The user answers whether they prioritize electricity costs or initial costs, etc. The server analyzes the answers, selects air conditioners with high energy efficiency, and presents them to the user. The user then enters a request for a "model that can be operated with a smartphone," and the server re-evaluates and presents updated air conditioner models.

[0876] Example 2: Choosing a PC

[0877] The user selects a PC category and enters their primary use (e.g., video editing, gaming) and budget. The server generates a list of questions based on this information and sends them to the terminal. The user answers questions about "CPU performance" and "storage capacity." The server analyzes the answers, selects a high-performance PC that meets the user's needs, and presents it to the user. Furthermore, if the user wants to see a second option, the server relaxes the settings, re-evaluates, and presents the second PC as well.

[0878] As described above, the present invention allows consumers to easily choose the optimal product that suits their needs.

[0879] The following describes the processing flow.

[0880] Program execution flow

[0881] Initial setup

[0882] Step 1:

[0883] The server stores selection criteria and question lists for each product category in its database. For example, different criteria are set for each category, such as refrigerators, personal computers, and air conditioners.

[0884] Entering user information

[0885] Step 2:

[0886] The user uses their device to select the product category they wish to purchase. Users can choose from options such as refrigerators, computers, and air conditioners.

[0887] Step 3:

[0888] The user fills in the required information in a form, including basic details such as budget, room size, and purpose of use. Once completed, they press the submit button.

[0889] Generating a list of questions

[0890] Step 4:

[0891] The server analyzes the received basic information and generates a list of questions tailored to the relevant product category. For example, for an air conditioner, it would prepare questions such as room size, monthly electricity costs, initial purchase cost, and whether the customer wants to control it with their smartphone.

[0892] Displaying questions and collecting answers

[0893] Step 5:

[0894] The server sends the generated list of questions to the user's terminal. On the user's terminal, the list of questions is displayed sequentially in an easy-to-understand format.

[0895] Step 6:

[0896] The user sequentially enters answers to the displayed questions. For example, they might enter information such as the room size being "20 square meters" and whether they prioritize electricity costs.

[0897] Step 7:

[0898] User responses are sent to the server in real time and stored in the database.

[0899] AI-powered analysis of responses

[0900] Step 8:

[0901] The server analyzes the user's responses and extracts the corresponding product specifications. The analysis uses an algorithm based on the user's response data.

[0902] Step 9:

[0903] The server narrows down the database to the most suitable products based on the extracted product specifications. It then lists the most appropriate products as a result of this filtering.

[0904] Suggesting the optimal product

[0905] Step 10:

[0906] The server prepares detailed information on the listed optimal products and sends it to the user's terminal.

[0907] Step 11:

[0908] The user terminal presents the optimal product to the user in a visually easy-to-understand format. For example, it might display something like "Air conditioner A with high energy efficiency."

[0909] Additional questions and reassessment

[0910] Step 12:

[0911] If a user has additional requests (e.g., a model that can be operated via smartphone), they will enter the information using an additional question form on their device. Once they have finished entering the information, they will press the submit button again.

[0912] Step 13:

[0913] The server analyzes the additional request information and incorporates it into the initial analysis results to re-evaluate the product. A new algorithm that takes the added requests into account is used for the re-evaluation.

[0914] Step 14:

[0915] The updated list of candidate products resulting from the re-evaluation is sent to the user's terminal, which then presents them to the user.

[0916] Confirmation of the second candidate

[0917] Step 15:

[0918] If the user is not satisfied with the first recommended product, they can press the "View Second Choice" button.

[0919] Step 16:

[0920] The server uses the initial responses as a basis, but slightly relaxes the criteria and selects products again. Different algorithms can be used for this process.

[0921] Step 17:

[0922] The server re-analyzes the data and selects a second-choice product. This information is then sent to the user's terminal, which then presents the second-choice product to the user.

[0923] Through these steps, users can effectively select the product that best suits their needs. This system significantly simplifies the product selection process.

[0924] (Example 1)

[0925] 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."

[0926] Traditional product selection systems suggest the most suitable products based on the user's basic information, but they have the problem of not being able to flexibly respond to additional requests or changes. Furthermore, the generated list of questions is limited and sometimes does not adequately reflect the user's needs. As a result, it was difficult for users to select a product that perfectly matched their requirements.

[0927] 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.

[0928] In this invention, the server includes means for receiving basic information from a user, means for generating a list of questions based on the basic information, means for presenting the generated list of questions to the user, means for receiving the user's answers, analyzing those answers, and selecting the most suitable product, means for presenting the selected product to the user, and means for re-evaluating the product based on the user's additional requests and presenting updated candidate products. This enables product selection that more accurately reflects the user's needs and can quickly respond to additional requests and changes.

[0929] A "user" is an individual or organization that uses the system to input basic information and additional requests in order to select products.

[0930] "Basic information" refers to initial information such as the user's desired product category, budget, space size, and intended use, and is used by the system to generate appropriate question lists and product suggestions.

[0931] A "question list" is a series of questions generated based on a user's basic information, designed to gain a more detailed understanding of their needs and requests.

[0932] "Answers" refer to the selections and text information that users enter based on a list of questions, providing data for the system to analyze and select products.

[0933] "Product specifications" refer to the specific specifications and characteristics required for a product, extracted based on user responses.

[0934] A "selected product" is a product that the server has determined to be optimal after analyzing the user's basic information and responses.

[0935] "Additional requests" are new conditions or preferences that users would like to consider, separate from the initial information and responses.

[0936] "Re-evaluation" is the process by which the server incorporates additional requests into its analysis, re-evaluates existing data and conditions, and updates the list of potential products.

[0937] This invention relates to a system for assisting users in the process of selecting expensive electronic products and home appliances. This system receives basic information from the user and, based on the user's answers to a generated list of questions, selects and suggests the most suitable products. Specific embodiments of this system are described below.

[0938] Initial setup

[0939] server

[0940] The server stores selection criteria and question lists for each product category in a database. Product categories include refrigerators, personal computers, air conditioners, etc. For example, the server uses a MySQL database and stores the selection criteria and corresponding question lists for each product category in database tables. These question lists and selection criteria include specific items such as "energy efficiency" and "cooling capacity."

[0941] Entering user information

[0942] User

[0943] The user selects the product category they wish to purchase using their device. For example, using a smartphone app, they might select "air conditioner" on the category selection screen. Next, the user enters information such as "budget of 50,000 yen" and "room size of 15 tatami mats."

[0944] Generating a list of questions

[0945] server

[0946] The server generates a list of questions corresponding to the relevant product category based on the user's basic information received. The server uses Python to dynamically generate a list of questions for air conditioners from the given basic information. For example, it might prepare questions such as, "Your room is 15 tatami mats in size, what are your expectations for your monthly electricity bill?"

[0947] Displaying questions and collecting answers

[0948] terminal

[0949] A list of questions is displayed sequentially to the user on their device. The user answers these questions, and the answers are sent to the server in real time. For example, a smartphone app displays a list of questions retrieved from the server based on the information entered by the user, and each time the user taps an option, the answer data is sent to the server.

[0950] AI-powered analysis of responses

[0951] server

[0952] The server analyzes the user's responses using an AI model. The server uses TensorFlow to build a generative AI model and analyze the user's responses. For example, if the server receives a response indicating that "electricity costs are a priority," the model will narrow down the candidates to air conditioners with particularly excellent energy-saving performance.

[0953] Suggesting the optimal product

[0954] server

[0955] Based on the analysis results, the system lists the most suitable products and sends the top-ranked candidate product to the user's device. The server generates a list of recommended products and sends the most suitable product from that list to the user's smartphone app in JSON format.

[0956] terminal

[0957] The most suitable products are displayed to the user. The smartphone app displays product details to the user based on the data received.

[0958] Additional questions and reassessment

[0959] User

[0960] The user enters any additional requests. For example, if the user wants a model that can be operated with a smartphone, they enter that request from their device.

[0961] server

[0962] The server incorporates the additional requests into its analysis and performs a re-evaluation. Once the analysis is complete, it resends the updated list of candidate products to the user's device. The smartphone app immediately reflects the changes to the user.

[0963] Specific example

[0964] Specific example 1: Air conditioner selection

[0965] The user selects an air conditioner category and enters basic information such as budget and room size. The server generates a list of questions about air conditioners based on this information and sends it to the user's device. The user answers whether they prioritize electricity costs or initial costs, etc. The server analyzes the answers, selects air conditioners with high energy efficiency, and presents them to the user. If the user adds a request for a "model that can be operated with a smartphone," the server re-evaluates and presents updated air conditioner models.

[0966] Example of a prompt

[0967] Please simulate the process a user goes through when selecting an air conditioner. The budget is 50,000 yen, the room size is 15 tatami mats, the purpose is heating and cooling, and the additional request is for a model that can be controlled via smartphone.

[0968] Example 2: Choosing a PC

[0969] The user selects a PC category and enters their primary use (e.g., video editing, gaming) and budget. The server generates a list of questions based on this information and sends them to the terminal. The user answers questions about "CPU performance" and "storage capacity." The server analyzes the answers, selects a high-performance PC that meets the user's needs, and presents it to the user. Furthermore, if the user wants to see a second option, the server relaxes the settings, re-evaluates, and presents the second PC as well.

[0970] Example of a prompt

[0971] Please simulate the process a user goes through when selecting a PC. The purpose is video editing, the budget is 150,000 yen, and additional requirements include a high-performance CPU and storage capacity of 1TB or more. Please provide an example of this scenario.

[0972] As described above, the present invention allows consumers to easily choose the optimal product that suits their needs.

[0973] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0974] Step 1: Database Setup

[0975] The server stores selection criteria and question lists for each product category in a database. The server uses a MySQL database and stores the selection criteria and corresponding question lists in database tables for each product category (refrigerators, personal computers, air conditioners, etc.). For example, the refrigerator category includes criteria such as "overall capacity" and "energy efficiency." Input is the data for the selection criteria and question lists, and output is the selection criteria and question lists stored in the database.

[0976] Step 2: Enter user information

[0977] The user selects the product category they wish to purchase using their device. Next, the user enters basic information such as budget, space size, and intended use. This information is entered using the smartphone app interface, and the entered information is sent from the device to the server. The input is the user's basic information, and the output is the basic information sent to the server.

[0978] Step 3: Generate the question list

[0979] The server generates a list of questions corresponding to the product category based on the user's basic information received. The server executes a Python script to dynamically generate the necessary questions from the basic information. For example, in the case of the air conditioner category, questions such as "room size," "budget," and "desire for smartphone control" are created. The input is the user's basic information, and the output is the generated list of questions.

[0980] Step 4: Display the questions and collect the answers.

[0981] A list of questions generated for the user is displayed sequentially on the terminal. The user answers the questions as they appear, and the answers are sent to the server in real time. For example, if the terminal interface displays the question "Are you thinking about your monthly electricity bill?", and the user enters an answer, that answer is sent to the server. The input is the list of questions and the user's answers, and the output is the user's answers sent to the server.

[0982] Step 5: AI-driven analysis of the response

[0983] The server analyzes the user's responses using an AI model. The server uses TensorFlow to build a generative AI model and extracts product specifications from the user's responses. For example, if it receives a response indicating a focus on electricity costs, it will narrow down the candidates to products with high energy efficiency. The input is the user's response data, and the output is the analyzed product specifications.

[0984] Step 6: Proposing the optimal product

[0985] The server lists the most suitable products based on the analysis results and sends the top-ranked candidate product to the user's terminal. The server generates a list of recommended products and sends it to the user's smartphone app in JSON format. The smartphone app displays product details to the user based on the received data. The input is the analyzed product specifications, and the output is the list of optimal products sent to the user's terminal.

[0986] Step 7: Additional questions and reassessment

[0987] The user enters additional requests. For example, if they want a "model that can be operated with a smartphone," they enter that request from their device. The server incorporates the additional requests into its analysis and performs a re-evaluation. After the re-evaluation, the updated list of candidate products is resent to the user's device. The smartphone app immediately reflects the changes to the user. The input consists of the additional requests and existing data, and the output is the re-evaluated, updated product list.

[0988] (Application Example 1)

[0989] 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."

[0990] Modern consumers face the challenge of quickly selecting the optimal product to suit their specific needs in a physical store with numerous options. In particular, they require selection support that addresses not only basic information such as budget and intended use, but also specific factors like electricity costs and ease of use. Furthermore, a lack of adequate means to provide product and location information within physical stores can cause consumers to become lost. It is necessary to address these challenges and provide consumers with an efficient and intuitive product selection support system.

[0991] 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.

[0992] In this invention, the server includes means for receiving basic information from a user, means for generating a list of questions based on the basic information, means for presenting the generated list of questions to the user, means for receiving the user's answers and analyzing those answers to select the optimal product, means for presenting the selected product to the user, means for providing product information and location information available in the store to the user in the physical store, and means for providing product selection support using a smartphone-based user interface. This makes it possible for consumers to efficiently select the optimal product even in a physical store.

[0993] "Basic information" refers to initial settings such as budget, room size, and intended use that users enter when selecting a product.

[0994] A "question list" is a collection of specific questions necessary for product selection, generated based on the user's basic information.

[0995] "User response" refers to the specific content of the user's response to the list of questions.

[0996] The "optimal product" is the product that best suits the user's needs, selected based on the user's basic information and responses.

[0997] "Selected products" refer to specific products that are recommended to the user based on the analysis results.

[0998] A "physical store" is a physical sales location where consumers can go in person and purchase products.

[0999] "Product information" refers to detailed data about a product, such as its characteristics, specifications, and price.

[1000] "Location information" refers to information used to identify the location of a product within a physical store.

[1001] A "user interface" refers to the operating screen and display functions used for exchanging information between the user and the system.

[1002] A "smartphone" is a portable mobile terminal device that provides a variety of operating applications in addition to the functions of a mobile phone.

[1003] This invention is a system that helps consumers efficiently select the most suitable products in a physical store. This system is realized using a server, terminals such as smartphones, a database, and an AI model.

[1004] First, the server stores selection criteria and question lists for each product category in a database. Product categories include refrigerators, personal computers, air conditioners, etc. Next, the user launches the application using their smartphone in a physical store and selects the product category they wish to purchase. The user enters basic information such as budget, room size, and intended use. The server then generates a question list corresponding to the product category based on the received basic information and sends it to the terminal. For example, for an air conditioner, the list would include questions such as room size, monthly electricity costs, initial purchase cost, and whether the user wants to control it with a smartphone.

[1005] The terminal displays a list of questions to the user sequentially, and the user answers them. The answers are sent to the server in real time. The server analyzes the answers and uses an AI model to extract product specifications. Generative AI models such as TensorFlow are used for this analysis process. Based on the extracted product specifications, the server narrows down the best products from the database and lists candidate products. This list of candidate products is sent to the terminal and presented to the user.

[1006] Furthermore, product information and location data are provided to make it easier for users to check potential products within physical stores. Users can check the specific location and detailed information of products through their smartphone interface.

[1007] As a concrete example, consider a case where a user purchases a refrigerator at a physical electronics store. In this example, the user selects a category, then enters their budget, room size, and intended use. The server generates a list of questions for the refrigerator and sends it to the user's terminal. The user answers the questions, and the server analyzes them using a generated AI model. Based on the analysis results, the server selects the most suitable refrigerator and provides the user with its product information and location.

[1008] Example of a prompt message: "My budget is 200,000 yen. I'm looking for a refrigerator. The room size is 3m x 3m. I prioritize low monthly electricity costs, a standard size is fine, and I don't have a preference for the door opening direction. Please recommend a refrigerator."

[1009] This system configuration allows users to efficiently and intuitively select the most suitable products even within a physical store.

[1010] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1011] Step 1:

[1012] The server stores selection criteria and question lists for each product category in a database. This process adds information such as product characteristics, usage scenarios, and price ranges to the database. The input is detailed information for each product category, and the output is the selection criteria and question lists stored in the database. Specifically, it creates appropriate question lists for each category, such as refrigerators, personal computers, and air conditioners.

[1013] Step 2:

[1014] The user launches the application using their smartphone while in a physical store. Next, they select the product category they wish to purchase and enter basic information such as their budget, room size, and intended use. This basic information is sent to the server. The input is the basic information such as budget and intended use entered by the user, and the output is the basic information sent to the server. Specifically, the user selects the refrigerator category and enters information such as "budget is 200,000 yen" and "intended use is for home use."

[1015] Step 3:

[1016] The server generates a list of questions corresponding to the relevant product category based on the basic information received and sends it to the terminal. The input is the basic information received from the user, and the output is the generated list of questions. Specifically, for the refrigerator category, questions such as "Are you concerned about monthly electricity costs?" and "What size refrigerator do you need?" are generated.

[1017] Step 4:

[1018] The terminal displays a generated list of questions to the user sequentially. The user answers these questions, and the answers are sent to the server in real time. The input is the list of questions sent from the server and the user's answers, and the output is the answer data for analysis sent to the server. Specifically, the user answers questions such as "I prioritize electricity costs" and "I want a standard-sized refrigerator."

[1019] Step 5:

[1020] The server uses a generative AI model to analyze user responses and extract product specifications. The input is user response data, and the output is the extracted product specifications. Specifically, a generative AI model using TensorFlow extracts the specifications "prioritizing low electricity consumption" and "standard size."

[1021] Step 6:

[1022] The server narrows down the database to the most suitable products based on the extracted product specifications, lists the candidate products, and sends them to the terminal. The input is the extracted product specifications, and the output is the list of candidate products presented to the user. Specifically, refrigerators that meet the conditions of "budget under 200,000 yen," "prioritizing low electricity consumption," and "standard size" are listed.

[1023] Step 7:

[1024] Within the physical store, users are provided with information on selected products and their locations. Input consists of a list of candidate products sent from the server and the product locations within the store; output consists of detailed product information and location information displayed on the terminal. Specifically, the detailed specifications of the listed refrigerators and their location within the store are presented.

[1025] Step 8:

[1026] Users check the specific location and details of products through their smartphone's user interface. Input is the product location and details displayed on the device, while output is the user's action based on their purchasing decision. Specifically, users check the location of listed refrigerators within a physical store, check the products on the spot, and decide to purchase them.

[1027] 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.

[1028] This invention combines an emotion engine with a system designed to assist users in the process of selecting electronic products and home appliances. This system receives basic information from the user, analyzes the user's emotions based on their answers to a generated list of questions using the emotion engine, and then selects and suggests the most suitable products based on that analysis. The following describes the program's processing in natural language.

[1029] Program Processing Description

[1030] Initial setup

[1031] The server stores selection criteria and question lists for each product category in a database. Product categories include, for example, refrigerators, personal computers, and air conditioners. The emotion engine includes algorithms that analyze user emotions from text and voice data.

[1032] Entering user information

[1033] The user uses their device to first select the product category they wish to purchase. Next, they enter basic information such as their budget, room size, and intended use.

[1034] Generating a list of questions

[1035] The server analyzes the received basic information and generates a list of questions tailored to the relevant product category. For example, for an air conditioner, it would prepare questions such as room size, monthly electricity costs, initial purchase cost, and whether the customer wants to control it with their smartphone.

[1036] Displaying questions and collecting answers

[1037] A list of questions is displayed to the user sequentially on their device. The user answers these questions, and the answers are sent to the server in real time.

[1038] Emotional analysis using an emotion engine

[1039] The emotion engine analyzes the user's response text and voice data to identify the user's emotions (e.g., satisfaction, dissatisfaction, excitement, indecision, etc.).

[1040] AI-powered analysis of responses

[1041] The server integrates responses received from the user with sentiment data from the sentiment engine and extracts product specifications. Based on these product specifications, it narrows down the database to the most suitable product.

[1042] Suggesting the optimal product

[1043] Based on the analysis results, the server lists the most suitable products and sends the top-ranked candidate product to the user's terminal. The optimal product is then displayed to the user on the terminal.

[1044] Additional questions and reassessment

[1045] If a user has additional requests (e.g., a model that can be operated via smartphone), they will enter the information using an additional question form on their device. Once they have finished entering the information, they will press the submit button again.

[1046] The server analyzes the additional request information and incorporates it into the initial analysis results to re-evaluate the products. A new algorithm based on the added requests is used for the re-evaluation. The updated candidate products are then displayed on the user's device.

[1047] Specific example

[1048] Specific example 1: Air conditioner selection

[1049] The user selects an air conditioner category and enters basic information such as budget and room size. The server generates a list of questions about air conditioners based on this information and sends it to the user's device. The user answers whether they prioritize electricity costs or initial costs, etc. As soon as the answers are sent to the server, an emotion engine analyzes the user's responses to identify their emotions, satisfaction level, and level of excitement. The server comprehensively analyzes this data to select and present air conditioners with high energy efficiency. If the user requests an additional model that can be operated via smartphone, the server re-evaluates and presents updated air conditioner models.

[1050] Example 2: Choosing a PC

[1051] The user selects a PC category and enters their primary use (e.g., video editing, gaming) and budget. The server generates a list of questions based on this information and sends them to the terminal. The user answers questions about "CPU performance" and "storage capacity." The emotion engine analyzes the user's responses to identify their stress level and level of interest. Based on the responses and emotion data, the server analyzes and selects a high-performance PC that meets the user's needs and presents it to the user. If the user wants to see a second option, the server relaxes the settings, re-evaluates, and presents the second PC.

[1052] As described above, the system of the present invention, by combining an emotion engine that analyzes the user's emotions, more accurately reflects the user's true needs and enables optimal product recommendations. As a result, users can find products that are more satisfying to them during the selection process.

[1053] The following describes the processing flow.

[1054] Program execution flow

[1055] Initial setup

[1056] Step 1:

[1057] The server stores selection criteria, question lists, and sentiment analysis algorithms for each product category in its database. For example, different criteria and sentiment analysis settings are prepared for each category, such as refrigerators, personal computers, and air conditioners.

[1058] Entering user information

[1059] Step 2:

[1060] The user uses their device to select the product category they wish to purchase. Categories include refrigerators, computers, air conditioners, and so on.

[1061] Step 3:

[1062] The user enters basic information such as budget, room size, and purpose of use into a form and presses the submit button.

[1063] Generating a list of questions

[1064] Step 4:

[1065] The server analyzes the basic information it receives and generates a list of questions based on that information, corresponding to the relevant product category. For example, in the case of an air conditioner, the server lists questions such as room size, monthly electricity costs, initial purchase cost, and whether the customer wants to control it with their smartphone.

[1066] Displaying questions and collecting answers

[1067] Step 5:

[1068] The server sends the generated list of questions to the user's terminal. On the user's terminal, the list of questions is displayed sequentially in an easy-to-understand format.

[1069] Step 6:

[1070] The user sequentially enters answers to the displayed questions. For example, they might enter information such as the room size being "20 square meters" and whether they prioritize electricity costs.

[1071] Step 7:

[1072] User responses are sent to the server in real time and stored in a database. Simultaneously, an emotion engine analyzes the response text and audio data.

[1073] Emotional analysis using an emotion engine

[1074] Step 8:

[1075] The emotion engine built into the server analyzes emotions based on the user's response text and voice data. For example, it uses natural language processing technology to identify emotions such as how satisfied, excited, or anxious the user is.

[1076] AI-powered analysis of responses

[1077] Step 9:

[1078] The server integrates the responses received from the user with sentiment data from the sentiment engine and extracts product specifications. The extracted product specifications are then compared with candidate products in the database.

[1079] Step 10:

[1080] The server narrows down the database to the most suitable products based on the extracted product specifications and sentiment data. It then lists the most appropriate products as a result of this filtering.

[1081] Suggesting the optimal product

[1082] Step 11:

[1083] The server prepares detailed information on the listed optimal products and sends it to the user's terminal.

[1084] Step 12:

[1085] The user terminal presents the optimal product to the user in a visually easy-to-understand format. For example, it might display something like "Air conditioner A with high energy efficiency."

[1086] Additional questions and reassessment

[1087] Step 13:

[1088] If a user has additional requests (e.g., a model that can be operated via smartphone), they will enter the information using an additional question form on their device. Once they have finished entering the information, they will press the submit button again.

[1089] Step 14:

[1090] The server analyzes the additional request information and incorporates it into the initial analysis results to re-evaluate the product. The re-evaluation utilizes a new algorithm based on the added requests.

[1091] Step 15:

[1092] The updated list of candidate products is displayed on the user's device. The user's device then presents the user with new, optimal products that reflect the additional requests.

[1093] Confirmation of the second candidate

[1094] Step 16:

[1095] If the user is not satisfied with the first recommended product, they can press the "View Second Choice" button.

[1096] Step 17:

[1097] The server selects products again, based on the initial responses and sentiment data, but with slightly relaxed criteria. Different algorithms can be used for this process.

[1098] Step 18:

[1099] The server re-analyzes the data and selects a second-choice product. This information is then sent to the user's terminal, which then presents the second-choice product to the user.

[1100] By following these steps, users can effectively select the product that best suits their needs. This system also takes user emotions into consideration, resulting in a more satisfying product selection process.

[1101] (Example 2)

[1102] 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."

[1103] Traditional selection processes for electronic products and home appliances often relied solely on user information and responses, failing to consider user emotions and thus making it difficult to meet true user needs. Furthermore, selection based solely on responses can overlook important factors that users may not be aware of. As a result, users are more likely to make unsatisfactory choices, increasing the risk of post-purchase regret.

[1104] 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.

[1105] In this invention, the server includes means for receiving basic information from the user, means for generating a list of questions based on the basic information, means for presenting the generated list of questions to the user, means for receiving the user's answers and analyzing those answers to identify the user's emotions, means for selecting the optimal product based on the analyzed emotion information and answer information, and means for presenting the selected product to the user. This enables comprehensive analysis of the user's answers and emotion data, making it possible to propose the optimal product that reflects the user's true needs.

[1106] "Basic information" refers to information necessary for product selection, such as the user's budget, the size of the environment, and the purpose of use.

[1107] A "question list" is a series of questions generated based on the user's basic information and presented to the user.

[1108] "Sentiment analysis" is the process of analyzing user response text and voice data to identify emotions such as satisfaction, dissatisfaction, excitement, and indecision.

[1109] "Product specifications" refer to detailed information about the product's performance and functions, extracted based on the user's responses and sentiment analysis results.

[1110] The "optimal product" is the product that best meets the user's needs, selected based on the user's basic information, responses, and sentiment analysis results.

[1111] A "terminal" is a device used by a user to input information, answer questions, and be presented with the most suitable products, and includes smartphones, PCs, and other similar devices.

[1112] A "server" is a computer device that receives basic information, generates a list of questions, analyzes responses and emotions, and selects the most suitable product.

[1113] This invention combines an emotion engine with a system designed to assist users in the process of selecting electronic products and home appliances. The system receives basic information from the user, analyzes the user's emotions based on their responses to a generated list of questions using the emotion engine, and then selects and suggests the most suitable products based on that analysis.

[1114] The server stores selection criteria for each product category (e.g., refrigerators, personal computers, air conditioners) and corresponding question lists in a database. The sentiment engine is configured to analyze user response text and audio data using Google Cloud Natural Language API and IBM Watson's sentiment analysis capabilities. This configuration includes setting up API keys and importing model training data.

[1115] The user uses a device (such as a smartphone or PC) to select the product category they wish to purchase and enters basic information such as their budget, room size, and intended use. This prepares the system to generate a list of questions tailored to the user.

[1116] The server analyzes the received basic information and generates a list of questions corresponding to the relevant product category. For example, in the air conditioner category, it dynamically creates relevant questions based on clues such as room size and desired functions (energy-saving mode, remote control operation, etc.).

[1117] The terminal displays a list of questions sent from the server to the user, one by one. The user answers each question, and the answers are sent to the server in real time. For example, if the user is asked "What is the size of the room?" in the air conditioner question list, and answers "20m²", the user will answer "20m²". 2 When you answer "Yes," the response is immediately sent to the server.

[1118] The emotion engine on the server analyzes the user's response text and audio data. Based on the analysis, it identifies the user's emotions (e.g., satisfaction, dissatisfaction, excitement, indecision, etc.). For example, if a user answers, "I'm concerned about the electricity bill, but does it have energy-saving features?", the emotion engine will analyze the word "concerned" to identify the emotion of "worry."

[1119] The server integrates responses and sentiment data received from users and extracts product specifications using high-performance AI. This involves using machine learning models (e.g., scikit-learn or TensorFlow) to gain a deep understanding of user needs. For example, if a user prioritizes "energy efficiency," the server will narrow down the search to products with high energy efficiency.

[1120] The server lists the most suitable products based on the analysis results and sends the top candidate product to the user's terminal. The product is then displayed to the user on the terminal. For example, it might display "highly energy-efficient air conditioners" and provide detailed information and a purchase link for that product.

[1121] When a user enters additional requests, such as "models that can be operated with a smartphone," the device sends the new information to the server. The server then re-evaluates the product list based on this information and sends the results back to the device. For example, if the user adds "smartphone controllable" as a condition, the server will display air conditioner models that meet that condition again.

[1122] Specific example

[1123] Specific example 1: Air conditioner selection

[1124] The user selects an air conditioner category and enters basic information such as budget and room size. The server generates a list of questions about air conditioners based on this information and sends it to the user's device. The user answers whether they prioritize electricity costs or initial costs and sends their answer to the server. Simultaneously, an emotion engine analyzes emotions such as "satisfied" or "concerned." The server integrates this data to select and present air conditioners with high energy efficiency. If the user requests an additional model that can be operated via smartphone, the server re-evaluates and presents a new air conditioner model.

[1125] Example of a prompt

[1126] 1. "I'm thinking of buying an air conditioner. The room is 20m²." 2 So, I want to keep my monthly electricity bill down. I prioritize running costs over initial costs."

[1127] 2. "I want an air conditioner that I can control with my smartphone."

[1128] Example 2: Choosing a PC

[1129] The user selects a PC category and enters their primary use (e.g., video editing, gaming) and budget. The server generates a list of questions based on this information and sends it to the terminal. The user answers questions about "CPU performance" and "storage capacity," and an emotion engine analyzes their "interests" and "stress levels." Based on the answers and emotion data, the server performs an analysis to select and present a high-performance PC that meets the user's needs. If the user wants to see a second option, the server relaxes the settings, re-evaluates, and presents another PC.

[1130] Example of a prompt

[1131] 1. "I'm considering buying a computer. My budget is 150,000 yen, and my main purpose is video editing. A large storage capacity would be ideal."

[1132] 2. "I want a model with a high CPU performance for video editing."

[1133] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1134] Step 1:

[1135] The server stores selection criteria and question lists for each product category in a database. Specifically, for each category such as refrigerators, personal computers, and air conditioners, it sets criteria related to budget and intended use, as well as question lists based on those criteria. A database system such as Google Cloud Firestore or MySQL is used for this setup. The input data consists of product categories, their selection criteria, and question lists, and the output is storage in the database.

[1136] Step 2:

[1137] The user uses a terminal to select the product category they wish to purchase. Specifically, they select one from a list of product categories displayed on the terminal screen, such as air conditioners, refrigerators, or personal computers. The user's input data is the selected product category, and the output is the transmission of the selection information to the server.

[1138] Step 3:

[1139] The user uses a terminal to input basic information such as budget, room size, and purpose of use. Specifically, they enter the necessary information in fields such as budget (amount), room size (square meters), and purpose of use (cooling, heating, other). This information is sent to the server. The input data is basic information, and the output is the transmission of this data to the server.

[1140] Step 4:

[1141] The server analyzes the received basic information and generates a list of questions according to the corresponding product category. For example, in the case of an air conditioner, based on the room size and budget, questions regarding electricity cost, energy-saving performance, and whether it can be operated by a smartphone are generated. Python scripts or Node.js are used for the analysis to execute the algorithm. The input data is the basic information, and the output is the generated list of questions.

[1142] Step 5:

[1143] The terminal sequentially displays the list of questions sent from the server to the user. Specifically, each question is displayed one by one on the terminal screen to prompt the user for input. The input data is the list of questions, and the output is the presentation of these questions to the user.

[1144] Step 6:

[1145] The user answers each question and sends the answer content to the server in real time through the terminal. For example, for the question "What is the room size?", an answer like "20m 2 " is given. The input data is the user's answer, and the output is the transmission of that answer data to the server.

[1146] Step 7:

[1147] The emotion engine in the server analyzes the answer text and voice data sent from the user. Specifically, the Google Cloud Natural Language API is used for text analysis, and the emotion analysis function of IBM Watson is used for voice data analysis. The emotion engine identifies emotions such as satisfaction, dissatisfaction, excitement, and confusion from the user's speech. The input data is the user's answer, and the output is the analyzed emotion information.

[1148] Step 8:

[1149] The server integrates responses and sentiment data received from users and extracts product specifications using high-performance AI. For example, it creates an analysis model using Python libraries such as scikit-learn and TensorFlow to extract product specifications based on user requests. The input data consists of responses and sentiment data, and the output is the extracted product specifications.

[1150] Step 9:

[1151] The server lists the most suitable products based on the analysis results and sends the top candidate products to the user's terminal. Specifically, it searches the database for products that meet the criteria based on the extracted product specifications and lists the best ones. The input data is product specifications, and the output is a list of optimal products.

[1152] Step 10:

[1153] The terminal displays a list of optimal products to the user. The user can select from the presented products, and detailed product information and purchase links are also displayed. The input data is the list of optimal products, and the output is the display of the products.

[1154] Step 11:

[1155] If a user enters an additional request (for example, "a model that can be operated with a smartphone"), that request is sent to the server via the device. The input data is the additional request, and the output is the transmission of that data to the server.

[1156] Step 12:

[1157] The server analyzes the additional request information and incorporates it into the initial analysis results to re-evaluate the products. Specifically, it re-evaluates the product list based on the new conditions derived from the additional requests. The aforementioned AI model is used again for the analysis. The input data is the additional requests, and the output is the updated product list.

[1158] Step 13:

[1159] The terminal displays updated suggested products to the user again. The user can then review the new best product. The input data is the updated product list, and the output is a redisplay of the products.

[1160] (Application Example 2)

[1161] 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."

[1162] In traditional e-commerce sites, product suggestions were based solely on basic information and answers to questions, making it difficult to adequately reflect users' emotions and true desires. This resulted in users spending considerable time and effort finding the most suitable product from a wide range of options.

[1163] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving basic information from a user, means for generating a list of questions based on the basic information, means for presenting the generated list of questions to the user, means for receiving the user's answers and analyzing those answers to select the optimal product, means including an emotion engine for analyzing emotion data from the user's answers, means for optimizing the product selection process using the emotion data, and means for presenting the selected product to the user. This makes it possible to propose the optimal product that reflects the user's emotions and true feelings.

[1164] "User information" refers to basic information that users provide when selecting electronic products or home appliances, such as their budget, room size, and intended use.

[1165] A "question list" is a list of questions generated based on the user's basic information and presented to the user.

[1166] "Answer" refers to the response entered by the user based on the list of questions.

[1167] The "emotion engine" is a part of the system that includes an algorithm for analyzing emotions from user response data.

[1168] "Emotional data" is data that represents the user's emotional state (e.g., satisfaction, dissatisfaction, excitement, indecision, etc.) generated by the emotion engine through analysis of the user's responses.

[1169] The "product selection process" is a series of procedures that analyze data from the user's basic information and responses to determine the most suitable product.

[1170] "Product specifications" refer to a list of specific features and performance characteristics of a product, extracted based on user needs.

[1171] The "optimal product" is the product that best matches the user's needs and emotions, selected based on the user's basic information, responses, and sentiment data.

[1172] A "server" is a core computer system that receives basic user information, generates a list of questions, collects and analyzes responses, and selects and suggests the most suitable products.

[1173] System Overview

[1174] This invention relates to a system that uses an emotion engine to analyze user emotional data during the process of selecting electronic products and home appliances, and then proposes the most suitable product based on that analysis. The system performs user information input, generates a list of questions, collects responses, performs emotion analysis, selects products, and proposes the most suitable product.

[1175] Hardware and software configuration

[1176] server:

[1177] Hardware: High-performance computer (such as AWS EC2)

[1178] software:

[1179] Operating System: Linux

[1180] Application server: Node.js

[1181] Database: MySQL

[1182] Sentiment analysis engine: Natural language processing API (Google Cloud Natural Language API)

[1183] AI Analysis Module: Python-based machine learning models

[1184] User terminal:

[1185] Hardware: Smartphone, tablet, or PC

[1186] software:

[1187] Operating system (e.g., iOS, Android, Windows)

[1188] Browser or dedicated application

[1189] Processing flow

[1190] 1. Enter user information

[1191] The user uses a terminal to select the product category they wish to purchase. Next, they enter basic information such as their budget, room size, and intended use. This information is sent to the server and stored in the database.

[1192] 2. Generating a list of questions

[1193] The server analyzes the received basic information and generates a custom list of questions based on the relevant product category. For example, in the case of an air conditioner, it generates questions such as room size, monthly electricity cost, initial purchase cost, and whether it can be operated with a smart device.

[1194] 3. Displaying questions and collecting answers

[1195] A list of questions is displayed sequentially on the user's terminal, and the user answers them. The answers are sent to the server in real time.

[1196] 4. Emotional analysis using an emotion engine

[1197] The server analyzes each response using an emotion engine (Google Cloud Natural Language API) to identify the user's emotions (satisfied, dissatisfied, excited, confused, etc.). This emotion data is also stored in a database.

[1198] 5. AI-driven analysis of responses and selection of optimal products

[1199] The server integrates and analyzes user responses and sentiment data to extract product specifications. A Python-based machine learning model is used to narrow down the database to the most suitable products.

[1200] 6. Proposal of the optimal product

[1201] An optimal product list is generated and sent to the user's terminal. The user reviews it and enters additional information if they have any further requests.

[1202] 7. Processing of additional requests

[1203] When a user enters additional requests (e.g., a model that can be operated via smartphone), the server re-evaluates and presents the updated product list to the user.

[1204] Specific example

[1205] Example 1: The user selects a refrigerator category and enters a specific budget. The server generates questions about the refrigerator (e.g., energy efficiency, quietness, design), and the user answers them sequentially. The emotion engine analyzes these answers to gather emotional data and suggests the most suitable product.

[1206] Example 2: The user selects a PC category and enters their primary use (e.g., gaming, video editing, etc.) and budget. The server generates questions tailored to the user's purpose, and the user answers them. Using the sentiment data analyzed by the emotion engine and the user's response data, the server selects the most suitable PC and presents it to the user.

[1207] Example of a prompt

[1208] "What is your budget?"

[1209] "Is energy efficiency important for a refrigerator? (Please rate on a scale of 1-5)"

[1210] "Do you care about the design of your refrigerator? (Yes / No)"

[1211] The above describes a specific embodiment of the present invention system. By using this system, users can receive optimal product suggestions that reflect their own emotions, thereby improving the efficiency of the selection process and increasing satisfaction.

[1212] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1213] Step 1: Enter user information

[1214] Subject: User

[1215] Specific operation: The user accesses the system via a smartphone application or browser and selects the product category they wish to purchase. Next, they enter basic information such as budget, room size, and intended use. This information is sent from the device to the server.

[1216] Input: Desired product category, budget, room size, purpose of use

[1217] Output: Basic information is sent to the server.

[1218] Step 2: Generate the question list

[1219] Subject: Server

[1220] Specific operation: The server analyzes the received user's basic information and generates a list of questions corresponding to the relevant product category. The generated question list is stored in the database and sent to the user's terminal.

[1221] Input: User's basic information

[1222] Data processing / calculation: Analyze basic information and generate a list of questions.

[1223] Output: A provisional list of questions is displayed on the user's terminal.

[1224] Step 3: Display the questions and collect the answers.

[1225] Subject: User

[1226] Specific operation: A list of questions is displayed on the user's terminal, and the user answers them sequentially. The user's response data is sent to the server in real time.

[1227] Input: List of questions sent from the server

[1228] Output: Response data is sent to the server.

[1229] Step 4: Emotional analysis using the emotion engine

[1230] Subject: Server

[1231] Specific operation: The server uses an emotion engine to analyze user response data in real time and generate emotion data. Emotion data is data that indicates the user's emotional state, such as satisfaction, dissatisfaction, excitement, and indecision. Emotion data is also stored in a database.

[1232] Input: User response data

[1233] Data processing / calculation: Emotion analysis is performed using an emotion engine to generate emotion data.

[1234] Output: Emotional data is generated and stored in the database.

[1235] Step 5: AI-driven analysis of responses and selection of optimal products

[1236] Subject: Server

[1237] Specific operation: The server integrates user response data and sentiment data and performs analysis using an AI model (a Python-based machine learning model). This analysis extracts product specifications, and the server selects the product best suited to the user's needs from the database.

[1238] Input: Response data, sentiment data

[1239] Data processing / calculation: Analyze data using an AI model and extract product specifications.

[1240] Output: The optimal product is generated.

[1241] Step 6: Proposing the optimal product

[1242] Subject: Server

[1243] Specific operation: The server selects the most suitable product list, which is then sent to the user's terminal and displayed to the user. The user then reviews the displayed product list.

[1244] Input: List of products selected by the server

[1245] Output: A list of products best suited to the user's terminal is displayed.

[1246] Step 7: Processing additional requests

[1247] Subject: User

[1248] Specific operation: When a user enters an additional request (for example, a model that can be operated with a smartphone) from the displayed product list, the additional information is sent from the device to the server. The server re-analyzes the newly added request and proposes an updated product list.

[1249] Input: Additional request information

[1250] Output: The updated product list is redisplayed on the user's terminal.

[1251] 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.

[1252] 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 those described above. 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 shown 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.

[1253] 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.

[1254] [Fourth Embodiment]

[1255] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1256] 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.

[1257] 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).

[1258] 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.

[1259] 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.

[1260] 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).

[1261] 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.

[1262] 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.

[1263] 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.

[1264] 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.

[1265] 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.

[1266] 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.

[1267] 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".

[1268] This invention relates to a system for assisting users in the process of selecting expensive electronic products and home appliances. This system receives basic information from the user, and based on the user's answers to a generated list of questions, selects and suggests the most suitable products. The program processing of this system is described below in natural language.

[1269] Program Processing Description

[1270] Initial setup

[1271] The server stores selection criteria and question lists for each product category in its database. Product categories include, for example, refrigerators, personal computers, and air conditioners.

[1272] Entering user information

[1273] The user uses their device to first select the product category they wish to purchase. Next, the user enters basic information such as their budget, room size, and intended use.

[1274] Generating a list of questions

[1275] Based on the basic information received, the server generates a list of questions tailored to the relevant product category. For example, in the case of an air conditioner, the server lists questions such as room size, monthly electricity costs, initial purchase cost, and whether the customer wants to control it via smartphone.

[1276] Displaying questions and collecting answers

[1277] A list of questions is displayed to the user sequentially on their device. The user answers these questions, and the answers are sent to the server in real time.

[1278] AI-powered analysis of responses

[1279] The server analyzes the responses received from the user and extracts product specifications. Based on these product specifications, it narrows down the database to the most suitable product.

[1280] Suggesting the optimal product

[1281] Based on the analysis results, the server lists the most suitable products and sends the top-ranked candidate product to the user's terminal. The optimal product is then displayed to the user on the terminal.

[1282] Additional questions and reassessment

[1283] If the user enters additional requests, such as whether the product is operable on a smartphone, the server will incorporate this information into its analysis and perform a re-evaluation. The updated list of candidate products will then be displayed on the user's device.

[1284] Specific example

[1285] Specific example 1: Air conditioner selection

[1286] The user selects an air conditioner category and enters basic information such as budget and room size. The server generates a list of questions about air conditioners based on this information and sends it to the user's device. The user answers whether they prioritize electricity costs or initial costs, etc. The server analyzes the answers, selects air conditioners with high energy efficiency, and presents them to the user. The user then enters a request for a "model that can be operated with a smartphone," and the server re-evaluates and presents updated air conditioner models.

[1287] Example 2: Choosing a PC

[1288] The user selects a PC category and enters their primary use (e.g., video editing, gaming) and budget. The server generates a list of questions based on this information and sends them to the terminal. The user answers questions about "CPU performance" and "storage capacity." The server analyzes the answers, selects a high-performance PC that meets the user's needs, and presents it to the user. Furthermore, if the user wants to see a second option, the server relaxes the settings, re-evaluates, and presents the second PC as well.

[1289] As described above, the present invention allows consumers to easily choose the optimal product that suits their needs.

[1290] The following describes the processing flow.

[1291] Program execution flow

[1292] Initial setup

[1293] Step 1:

[1294] The server stores selection criteria and question lists for each product category in its database. For example, different criteria are set for each category, such as refrigerators, personal computers, and air conditioners.

[1295] Entering user information

[1296] Step 2:

[1297] The user uses their device to select the product category they wish to purchase. Users can choose from options such as refrigerators, computers, and air conditioners.

[1298] Step 3:

[1299] The user fills in the required information in a form, including basic details such as budget, room size, and purpose of use. Once completed, they press the submit button.

[1300] Generating a list of questions

[1301] Step 4:

[1302] The server analyzes the received basic information and generates a list of questions tailored to the relevant product category. For example, for an air conditioner, it would prepare questions such as room size, monthly electricity costs, initial purchase cost, and whether the customer wants to control it with their smartphone.

[1303] Displaying questions and collecting answers

[1304] Step 5:

[1305] The server sends the generated list of questions to the user's terminal. On the user's terminal, the list of questions is displayed sequentially in an easy-to-understand format.

[1306] Step 6:

[1307] The user sequentially enters answers to the displayed questions. For example, they might enter information such as the room size being "20 square meters" and whether they prioritize electricity costs.

[1308] Step 7:

[1309] User responses are sent to the server in real time and stored in the database.

[1310] AI-powered analysis of responses

[1311] Step 8:

[1312] The server analyzes the user's responses and extracts the corresponding product specifications. The analysis uses an algorithm based on the user's response data.

[1313] Step 9:

[1314] The server narrows down the database to the most suitable products based on the extracted product specifications. It then lists the most appropriate products as a result of this filtering.

[1315] Suggesting the optimal product

[1316] Step 10:

[1317] The server prepares detailed information on the listed optimal products and sends it to the user's terminal.

[1318] Step 11:

[1319] The user terminal presents the optimal product to the user in a visually easy-to-understand format. For example, it might display something like "Air conditioner A with high energy efficiency."

[1320] Additional questions and reassessment

[1321] Step 12:

[1322] If a user has additional requests (e.g., a model that can be operated via smartphone), they will enter the information using an additional question form on their device. Once they have finished entering the information, they will press the submit button again.

[1323] Step 13:

[1324] The server analyzes the additional request information and incorporates it into the initial analysis results to re-evaluate the product. A new algorithm that takes the added requests into account is used for the re-evaluation.

[1325] Step 14:

[1326] The updated list of candidate products resulting from the re-evaluation is sent to the user's terminal, which then presents them to the user.

[1327] Confirmation of the second candidate

[1328] Step 15:

[1329] If the user is not satisfied with the first recommended product, they can press the "View Second Choice" button.

[1330] Step 16:

[1331] The server uses the initial responses as a basis, but slightly relaxes the criteria and selects products again. Different algorithms can be used for this process.

[1332] Step 17:

[1333] The server re-analyzes the data and selects a second-choice product. This information is then sent to the user's terminal, which then presents the second-choice product to the user.

[1334] Through these steps, users can effectively select the product that best suits their needs. This system significantly simplifies the product selection process.

[1335] (Example 1)

[1336] 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".

[1337] Traditional product selection systems suggest the most suitable products based on the user's basic information, but they have the problem of not being able to flexibly respond to additional requests or changes. Furthermore, the generated list of questions is limited and sometimes does not adequately reflect the user's needs. As a result, it was difficult for users to select a product that perfectly matched their requirements.

[1338] 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.

[1339] In this invention, the server includes means for receiving basic information from a user, means for generating a list of questions based on the basic information, means for presenting the generated list of questions to the user, means for receiving the user's answers, analyzing those answers, and selecting the most suitable product, means for presenting the selected product to the user, and means for re-evaluating the product based on the user's additional requests and presenting updated candidate products. This enables product selection that more accurately reflects the user's needs and can quickly respond to additional requests and changes.

[1340] A "user" is an individual or organization that uses the system to input basic information and additional requests in order to select products.

[1341] "Basic information" refers to initial information such as the user's desired product category, budget, space size, and intended use, and is used by the system to generate appropriate question lists and product suggestions.

[1342] A "question list" is a series of questions generated based on a user's basic information, designed to gain a more detailed understanding of their needs and requests.

[1343] "Answers" refer to the selections and text information that users enter based on a list of questions, providing data for the system to analyze and select products.

[1344] "Product specifications" refer to the specific specifications and characteristics required for a product, extracted based on user responses.

[1345] A "selected product" is a product that the server has determined to be optimal after analyzing the user's basic information and responses.

[1346] "Additional requests" are new conditions or preferences that users would like to consider, separate from the initial information and responses.

[1347] "Re-evaluation" is the process by which the server incorporates additional requests into its analysis, re-evaluates existing data and conditions, and updates the list of potential products.

[1348] This invention relates to a system for assisting users in the process of selecting expensive electronic products and home appliances. This system receives basic information from the user and, based on the user's answers to a generated list of questions, selects and suggests the most suitable products. Specific embodiments of this system are described below.

[1349] Initial setup

[1350] server

[1351] The server stores selection criteria and question lists for each product category in a database. Product categories include refrigerators, personal computers, air conditioners, etc. For example, the server uses a MySQL database and stores the selection criteria and corresponding question lists for each product category in database tables. These question lists and selection criteria include specific items such as "energy efficiency" and "cooling capacity."

[1352] Entering user information

[1353] User

[1354] The user selects the product category they wish to purchase using their device. For example, using a smartphone app, they might select "air conditioner" on the category selection screen. Next, the user enters information such as "budget of 50,000 yen" and "room size of 15 tatami mats."

[1355] Generating a list of questions

[1356] server

[1357] The server generates a list of questions corresponding to the relevant product category based on the user's basic information received. The server uses Python to dynamically generate a list of questions for air conditioners from the given basic information. For example, it might prepare questions such as, "Your room is 15 tatami mats in size, what are your expectations for your monthly electricity bill?"

[1358] Displaying questions and collecting answers

[1359] terminal

[1360] A list of questions is displayed sequentially to the user on their device. The user answers these questions, and the answers are sent to the server in real time. For example, a smartphone app displays a list of questions retrieved from the server based on the information entered by the user, and each time the user taps an option, the answer data is sent to the server.

[1361] AI-powered analysis of responses

[1362] server

[1363] The server analyzes the user's responses using an AI model. The server uses TensorFlow to build a generative AI model and analyze the user's responses. For example, if the server receives a response indicating that "electricity costs are a priority," the model will narrow down the candidates to air conditioners with particularly excellent energy-saving performance.

[1364] Suggesting the optimal product

[1365] server

[1366] Based on the analysis results, the system lists the most suitable products and sends the top-ranked candidate product to the user's device. The server generates a list of recommended products and sends the most suitable product from that list to the user's smartphone app in JSON format.

[1367] terminal

[1368] The most suitable products are displayed to the user. The smartphone app displays product details to the user based on the data received.

[1369] Additional questions and reassessment

[1370] User

[1371] The user enters any additional requests. For example, if the user wants a model that can be operated with a smartphone, they enter that request from their device.

[1372] server

[1373] The server incorporates the additional requests into its analysis and performs a re-evaluation. Once the analysis is complete, it resends the updated list of candidate products to the user's device. The smartphone app immediately reflects the changes to the user.

[1374] Specific example

[1375] Specific example 1: Air conditioner selection

[1376] The user selects an air conditioner category and enters basic information such as budget and room size. The server generates a list of questions about air conditioners based on this information and sends it to the user's device. The user answers whether they prioritize electricity costs or initial costs, etc. The server analyzes the answers, selects air conditioners with high energy efficiency, and presents them to the user. If the user adds a request for a "model that can be operated with a smartphone," the server re-evaluates and presents updated air conditioner models.

[1377] Example of a prompt

[1378] Please simulate the process a user goes through when selecting an air conditioner. The budget is 50,000 yen, the room size is 15 tatami mats, the purpose is heating and cooling, and the additional request is for a model that can be controlled via smartphone.

[1379] Example 2: Choosing a PC

[1380] The user selects a PC category and enters their primary use (e.g., video editing, gaming) and budget. The server generates a list of questions based on this information and sends them to the terminal. The user answers questions about "CPU performance" and "storage capacity." The server analyzes the answers, selects a high-performance PC that meets the user's needs, and presents it to the user. Furthermore, if the user wants to see a second option, the server relaxes the settings, re-evaluates, and presents the second PC as well.

[1381] Example of a prompt

[1382] Please simulate the process a user goes through when selecting a PC. The purpose is video editing, the budget is 150,000 yen, and additional requirements include a high-performance CPU and storage capacity of 1TB or more. Please provide an example of this scenario.

[1383] As described above, the present invention allows consumers to easily choose the optimal product that suits their needs.

[1384] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1385] Step 1: Database Setup

[1386] The server stores selection criteria and question lists for each product category in a database. The server uses a MySQL database and stores the selection criteria and corresponding question lists in database tables for each product category (refrigerators, personal computers, air conditioners, etc.). For example, the refrigerator category includes criteria such as "overall capacity" and "energy efficiency." Input is the data for the selection criteria and question lists, and output is the selection criteria and question lists stored in the database.

[1387] Step 2: Enter user information

[1388] The user selects the product category they wish to purchase using their device. Next, the user enters basic information such as budget, space size, and intended use. This information is entered using the smartphone app interface, and the entered information is sent from the device to the server. The input is the user's basic information, and the output is the basic information sent to the server.

[1389] Step 3: Generate the question list

[1390] The server generates a list of questions corresponding to the product category based on the user's basic information received. The server executes a Python script to dynamically generate the necessary questions from the basic information. For example, in the case of the air conditioner category, questions such as "room size," "budget," and "desire for smartphone control" are created. The input is the user's basic information, and the output is the generated list of questions.

[1391] Step 4: Display the questions and collect the answers.

[1392] A list of questions generated for the user is displayed sequentially on the terminal. The user answers the questions as they appear, and the answers are sent to the server in real time. For example, if the terminal interface displays the question "Are you thinking about your monthly electricity bill?", and the user enters an answer, that answer is sent to the server. The input is the list of questions and the user's answers, and the output is the user's answers sent to the server.

[1393] Step 5: AI-driven analysis of the response

[1394] The server analyzes the user's responses using an AI model. The server uses TensorFlow to build a generative AI model and extracts product specifications from the user's responses. For example, if it receives a response indicating a focus on electricity costs, it will narrow down the candidates to products with high energy efficiency. The input is the user's response data, and the output is the analyzed product specifications.

[1395] Step 6: Proposing the optimal product

[1396] The server lists the most suitable products based on the analysis results and sends the top-ranked candidate product to the user's terminal. The server generates a list of recommended products and sends it to the user's smartphone app in JSON format. The smartphone app displays product details to the user based on the received data. The input is the analyzed product specifications, and the output is the list of optimal products sent to the user's terminal.

[1397] Step 7: Additional questions and reassessment

[1398] The user enters additional requests. For example, if they want a "model that can be operated with a smartphone," they enter that request from their device. The server incorporates the additional requests into its analysis and performs a re-evaluation. After the re-evaluation, the updated list of candidate products is resent to the user's device. The smartphone app immediately reflects the changes to the user. The input consists of the additional requests and existing data, and the output is the re-evaluated, updated product list.

[1399] (Application Example 1)

[1400] 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".

[1401] Modern consumers face the challenge of quickly selecting the optimal product to suit their specific needs in a physical store with numerous options. In particular, they require selection support that addresses not only basic information such as budget and intended use, but also specific factors like electricity costs and ease of use. Furthermore, a lack of adequate means to provide product and location information within physical stores can cause consumers to become lost. It is necessary to address these challenges and provide consumers with an efficient and intuitive product selection support system.

[1402] 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.

[1403] In this invention, the server includes means for receiving basic information from a user, means for generating a list of questions based on the basic information, means for presenting the generated list of questions to the user, means for receiving the user's answers and analyzing those answers to select the optimal product, means for presenting the selected product to the user, means for providing product information and location information available in the store to the user in the physical store, and means for providing product selection support using a smartphone-based user interface. This makes it possible for consumers to efficiently select the optimal product even in a physical store.

[1404] "Basic information" refers to initial settings such as budget, room size, and intended use that users enter when selecting a product.

[1405] A "question list" is a collection of specific questions necessary for product selection, generated based on the user's basic information.

[1406] "User response" refers to the specific content of the user's response to the list of questions.

[1407] The "optimal product" is the product that best suits the user's needs, selected based on the user's basic information and responses.

[1408] "Selected products" refer to specific products that are recommended to the user based on the analysis results.

[1409] A "physical store" is a physical sales location where consumers can go in person and purchase products.

[1410] "Product information" refers to detailed data about a product, such as its characteristics, specifications, and price.

[1411] "Location information" refers to information used to identify the location of a product within a physical store.

[1412] A "user interface" refers to the operating screen and display functions used for exchanging information between the user and the system.

[1413] A "smartphone" is a portable mobile terminal device that provides a variety of operating applications in addition to the functions of a mobile phone.

[1414] This invention is a system that helps consumers efficiently select the most suitable products in a physical store. This system is realized using a server, terminals such as smartphones, a database, and an AI model.

[1415] First, the server stores selection criteria and question lists for each product category in a database. Product categories include refrigerators, personal computers, air conditioners, etc. Next, the user launches the application using their smartphone in a physical store and selects the product category they wish to purchase. The user enters basic information such as budget, room size, and intended use. The server then generates a question list corresponding to the product category based on the received basic information and sends it to the terminal. For example, for an air conditioner, the list would include questions such as room size, monthly electricity costs, initial purchase cost, and whether the user wants to control it with a smartphone.

[1416] The terminal displays a list of questions to the user sequentially, and the user answers them. The answers are sent to the server in real time. The server analyzes the answers and uses an AI model to extract product specifications. Generative AI models such as TensorFlow are used for this analysis process. Based on the extracted product specifications, the server narrows down the best products from the database and lists candidate products. This list of candidate products is sent to the terminal and presented to the user.

[1417] Furthermore, product information and location data are provided to make it easier for users to check potential products within physical stores. Users can check the specific location and detailed information of products through their smartphone interface.

[1418] As a concrete example, consider a case where a user purchases a refrigerator at a physical electronics store. In this example, the user selects a category, then enters their budget, room size, and intended use. The server generates a list of questions for the refrigerator and sends it to the user's terminal. The user answers the questions, and the server analyzes them using a generated AI model. Based on the analysis results, the server selects the most suitable refrigerator and provides the user with its product information and location.

[1419] Example of a prompt message: "My budget is 200,000 yen. I'm looking for a refrigerator. The room size is 3m x 3m. I prioritize low monthly electricity costs, a standard size is fine, and I don't have a preference for the door opening direction. Please recommend a refrigerator."

[1420] This system configuration allows users to efficiently and intuitively select the most suitable products even within a physical store.

[1421] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1422] Step 1:

[1423] The server stores selection criteria and question lists for each product category in a database. This process adds information such as product characteristics, usage scenarios, and price ranges to the database. The input is detailed information for each product category, and the output is the selection criteria and question lists stored in the database. Specifically, it creates appropriate question lists for each category, such as refrigerators, personal computers, and air conditioners.

[1424] Step 2:

[1425] The user launches the application using their smartphone while in a physical store. Next, they select the product category they wish to purchase and enter basic information such as their budget, room size, and intended use. This basic information is sent to the server. The input is the basic information such as budget and intended use entered by the user, and the output is the basic information sent to the server. Specifically, the user selects the refrigerator category and enters information such as "budget is 200,000 yen" and "intended use is for home use."

[1426] Step 3:

[1427] The server generates a list of questions corresponding to the relevant product category based on the basic information received and sends it to the terminal. The input is the basic information received from the user, and the output is the generated list of questions. Specifically, for the refrigerator category, questions such as "Are you concerned about monthly electricity costs?" and "What size refrigerator do you need?" are generated.

[1428] Step 4:

[1429] The terminal displays a generated list of questions to the user sequentially. The user answers these questions, and the answers are sent to the server in real time. The input is the list of questions sent from the server and the user's answers, and the output is the answer data for analysis sent to the server. Specifically, the user answers questions such as "I prioritize electricity costs" and "I want a standard-sized refrigerator."

[1430] Step 5:

[1431] The server uses a generative AI model to analyze user responses and extract product specifications. The input is user response data, and the output is the extracted product specifications. Specifically, a generative AI model using TensorFlow extracts the specifications "prioritizing low electricity consumption" and "standard size."

[1432] Step 6:

[1433] The server narrows down the database to the most suitable products based on the extracted product specifications, lists the candidate products, and sends them to the terminal. The input is the extracted product specifications, and the output is the list of candidate products presented to the user. Specifically, refrigerators that meet the conditions of "budget under 200,000 yen," "prioritizing low electricity consumption," and "standard size" are listed.

[1434] Step 7:

[1435] Within the physical store, users are provided with information on selected products and their locations. Input consists of a list of candidate products sent from the server and the product locations within the store; output consists of detailed product information and location information displayed on the terminal. Specifically, the detailed specifications of the listed refrigerators and their location within the store are presented.

[1436] Step 8:

[1437] Users check the specific location and details of products through their smartphone's user interface. Input is the product location and details displayed on the device, while output is the user's action based on their purchasing decision. Specifically, users check the location of listed refrigerators within a physical store, check the products on the spot, and decide to purchase them.

[1438] 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.

[1439] This invention combines an emotion engine with a system designed to assist users in the process of selecting electronic products and home appliances. This system receives basic information from the user, analyzes the user's emotions based on their answers to a generated list of questions using the emotion engine, and then selects and suggests the most suitable products based on that analysis. The following describes the program's processing in natural language.

[1440] Program Processing Description

[1441] Initial setup

[1442] The server stores selection criteria and question lists for each product category in a database. Product categories include, for example, refrigerators, personal computers, and air conditioners. The emotion engine includes algorithms that analyze user emotions from text and voice data.

[1443] Entering user information

[1444] The user uses their device to first select the product category they wish to purchase. Next, they enter basic information such as their budget, room size, and intended use.

[1445] Generating a list of questions

[1446] The server analyzes the received basic information and generates a list of questions tailored to the relevant product category. For example, for an air conditioner, it would prepare questions such as room size, monthly electricity costs, initial purchase cost, and whether the customer wants to control it with their smartphone.

[1447] Displaying questions and collecting answers

[1448] A list of questions is displayed to the user sequentially on their device. The user answers these questions, and the answers are sent to the server in real time.

[1449] Emotional analysis using an emotion engine

[1450] The emotion engine analyzes the user's response text and voice data to identify the user's emotions (e.g., satisfaction, dissatisfaction, excitement, indecision, etc.).

[1451] AI-powered analysis of responses

[1452] The server integrates responses received from the user with sentiment data from the sentiment engine and extracts product specifications. Based on these product specifications, it narrows down the database to the most suitable product.

[1453] Suggesting the optimal product

[1454] Based on the analysis results, the server lists the most suitable products and sends the top-ranked candidate product to the user's terminal. The optimal product is then displayed to the user on the terminal.

[1455] Additional questions and reassessment

[1456] If a user has additional requests (e.g., a model that can be operated via smartphone), they will enter the information using an additional question form on their device. Once they have finished entering the information, they will press the submit button again.

[1457] The server analyzes the additional request information and incorporates it into the initial analysis results to re-evaluate the products. A new algorithm based on the added requests is used for the re-evaluation. The updated candidate products are then displayed on the user's device.

[1458] Specific example

[1459] Specific example 1: Air conditioner selection

[1460] The user selects an air conditioner category and enters basic information such as budget and room size. The server generates a list of questions about air conditioners based on this information and sends it to the user's device. The user answers whether they prioritize electricity costs or initial costs, etc. As soon as the answers are sent to the server, an emotion engine analyzes the user's responses to identify their emotions, satisfaction level, and level of excitement. The server comprehensively analyzes this data to select and present air conditioners with high energy efficiency. If the user requests an additional model that can be operated via smartphone, the server re-evaluates and presents updated air conditioner models.

[1461] Example 2: Choosing a PC

[1462] The user selects a PC category and enters their primary use (e.g., video editing, gaming) and budget. The server generates a list of questions based on this information and sends them to the terminal. The user answers questions about "CPU performance" and "storage capacity." The emotion engine analyzes the user's responses to identify their stress level and level of interest. Based on the responses and emotion data, the server analyzes and selects a high-performance PC that meets the user's needs and presents it to the user. If the user wants to see a second option, the server relaxes the settings, re-evaluates, and presents the second PC.

[1463] As described above, the system of the present invention, by combining an emotion engine that analyzes the user's emotions, more accurately reflects the user's true needs and enables optimal product recommendations. As a result, users can find products that are more satisfying to them during the selection process.

[1464] The following describes the processing flow.

[1465] Program execution flow

[1466] Initial setup

[1467] Step 1:

[1468] The server stores selection criteria, question lists, and sentiment analysis algorithms for each product category in its database. For example, different criteria and sentiment analysis settings are prepared for each category, such as refrigerators, personal computers, and air conditioners.

[1469] Entering user information

[1470] Step 2:

[1471] The user uses their device to select the product category they wish to purchase. Categories include refrigerators, computers, air conditioners, and so on.

[1472] Step 3:

[1473] The user enters basic information such as budget, room size, and purpose of use into a form and presses the submit button.

[1474] Generating a list of questions

[1475] Step 4:

[1476] The server analyzes the basic information it receives and generates a list of questions based on that information, corresponding to the relevant product category. For example, in the case of an air conditioner, the server lists questions such as room size, monthly electricity costs, initial purchase cost, and whether the customer wants to control it with their smartphone.

[1477] Displaying questions and collecting answers

[1478] Step 5:

[1479] The server sends the generated list of questions to the user's terminal. On the user's terminal, the list of questions is displayed sequentially in an easy-to-understand format.

[1480] Step 6:

[1481] The user sequentially enters answers to the displayed questions. For example, they might enter information such as the room size being "20 square meters" and whether they prioritize electricity costs.

[1482] Step 7:

[1483] User responses are sent to the server in real time and stored in a database. Simultaneously, an emotion engine analyzes the response text and audio data.

[1484] Emotional analysis using an emotion engine

[1485] Step 8:

[1486] The emotion engine built into the server analyzes emotions based on the user's response text and voice data. For example, it uses natural language processing technology to identify emotions such as how satisfied, excited, or anxious the user is.

[1487] AI-powered analysis of responses

[1488] Step 9:

[1489] The server integrates the responses received from the user with sentiment data from the sentiment engine and extracts product specifications. The extracted product specifications are then compared with candidate products in the database.

[1490] Step 10:

[1491] The server narrows down the database to the most suitable products based on the extracted product specifications and sentiment data. It then lists the most appropriate products as a result of this filtering.

[1492] Suggesting the optimal product

[1493] Step 11:

[1494] The server prepares detailed information on the listed optimal products and sends it to the user's terminal.

[1495] Step 12:

[1496] The user terminal presents the optimal product to the user in a visually easy-to-understand format. For example, it might display something like "Air conditioner A with high energy efficiency."

[1497] Additional questions and reassessment

[1498] Step 13:

[1499] If a user has additional requests (e.g., a model that can be operated via smartphone), they will enter the information using an additional question form on their device. Once they have finished entering the information, they will press the submit button again.

[1500] Step 14:

[1501] The server analyzes the additional request information and incorporates it into the initial analysis results to re-evaluate the product. The re-evaluation utilizes a new algorithm based on the added requests.

[1502] Step 15:

[1503] The updated list of candidate products is displayed on the user's device. The user's device then presents the user with new, optimal products that reflect the additional requests.

[1504] Confirmation of the second candidate

[1505] Step 16:

[1506] If the user is not satisfied with the first recommended product, they can press the "View Second Choice" button.

[1507] Step 17:

[1508] The server selects products again, based on the initial responses and sentiment data, but with slightly relaxed criteria. Different algorithms can be used for this process.

[1509] Step 18:

[1510] The server re-analyzes the data and selects a second-choice product. This information is then sent to the user's terminal, which then presents the second-choice product to the user.

[1511] By following these steps, users can effectively select the product that best suits their needs. This system also takes user emotions into consideration, resulting in a more satisfying product selection process.

[1512] (Example 2)

[1513] 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".

[1514] Traditional selection processes for electronic products and home appliances often relied solely on user information and responses, failing to consider user emotions and thus making it difficult to meet true user needs. Furthermore, selection based solely on responses can overlook important factors that users may not be aware of. As a result, users are more likely to make unsatisfactory choices, increasing the risk of post-purchase regret.

[1515] 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.

[1516] In this invention, the server includes means for receiving basic information from the user, means for generating a list of questions based on the basic information, means for presenting the generated list of questions to the user, means for receiving the user's answers and analyzing those answers to identify the user's emotions, means for selecting the optimal product based on the analyzed emotion information and answer information, and means for presenting the selected product to the user. This enables comprehensive analysis of the user's answers and emotion data, making it possible to propose the optimal product that reflects the user's true needs.

[1517] "Basic information" refers to information necessary for product selection, such as the user's budget, the size of the environment, and the purpose of use.

[1518] A "question list" is a series of questions generated based on the user's basic information and presented to the user.

[1519] "Sentiment analysis" is the process of analyzing user response text and voice data to identify emotions such as satisfaction, dissatisfaction, excitement, and indecision.

[1520] "Product specifications" refer to detailed information about the product's performance and functions, extracted based on the user's responses and sentiment analysis results.

[1521] The "optimal product" is the product that best meets the user's needs, selected based on the user's basic information, responses, and sentiment analysis results.

[1522] A "terminal" is a device used by a user to input information, answer questions, and be presented with the most suitable products, and includes smartphones, PCs, and other similar devices.

[1523] A "server" is a computer device that receives basic information, generates a list of questions, analyzes responses and emotions, and selects the most suitable product.

[1524] This invention combines an emotion engine with a system designed to assist users in the process of selecting electronic products and home appliances. The system receives basic information from the user, analyzes the user's emotions based on their responses to a generated list of questions using the emotion engine, and then selects and suggests the most suitable products based on that analysis.

[1525] The server stores selection criteria for each product category (e.g., refrigerators, personal computers, air conditioners) and corresponding question lists in a database. The sentiment engine is configured to analyze user response text and audio data using Google Cloud Natural Language API and IBM Watson's sentiment analysis capabilities. This configuration includes setting up API keys and importing model training data.

[1526] The user uses a device (such as a smartphone or PC) to select the product category they wish to purchase and enters basic information such as their budget, room size, and intended use. This prepares the system to generate a list of questions tailored to the user.

[1527] The server analyzes the received basic information and generates a list of questions corresponding to the relevant product category. For example, in the air conditioner category, it dynamically creates relevant questions based on clues such as room size and desired functions (energy-saving mode, remote control operation, etc.).

[1528] The terminal displays a list of questions sent from the server to the user, one by one. The user answers each question, and the answers are sent to the server in real time. For example, if the user is asked "What is the size of the room?" in the air conditioner question list, and answers "20m²", the user will answer "20m²". 2 When you answer "Yes," the response is immediately sent to the server.

[1529] The emotion engine on the server analyzes the user's response text and audio data. Based on the analysis, it identifies the user's emotions (e.g., satisfaction, dissatisfaction, excitement, indecision, etc.). For example, if a user answers, "I'm concerned about the electricity bill, but does it have energy-saving features?", the emotion engine will analyze the word "concerned" to identify the emotion of "worry."

[1530] The server integrates responses and sentiment data received from users and extracts product specifications using high-performance AI. This involves using machine learning models (e.g., scikit-learn or TensorFlow) to gain a deep understanding of user needs. For example, if a user prioritizes "energy efficiency," the server will narrow down the search to products with high energy efficiency.

[1531] The server lists the most suitable products based on the analysis results and sends the top candidate product to the user's terminal. The product is then displayed to the user on the terminal. For example, it might display "highly energy-efficient air conditioners" and provide detailed information and a purchase link for that product.

[1532] When a user enters additional requests, such as "models that can be operated with a smartphone," the device sends the new information to the server. The server then re-evaluates the product list based on this information and sends the results back to the device. For example, if the user adds "smartphone controllable" as a condition, the server will display air conditioner models that meet that condition again.

[1533] Specific example

[1534] Specific example 1: Air conditioner selection

[1535] The user selects an air conditioner category and enters basic information such as budget and room size. The server generates a list of questions about air conditioners based on this information and sends it to the user's device. The user answers whether they prioritize electricity costs or initial costs and sends their answer to the server. Simultaneously, an emotion engine analyzes emotions such as "satisfied" or "concerned." The server integrates this data to select and present air conditioners with high energy efficiency. If the user requests an additional model that can be operated via smartphone, the server re-evaluates and presents a new air conditioner model.

[1536] Example of a prompt

[1537] 1. "I'm thinking of buying an air conditioner. The room is 20m²." 2 So, I want to keep my monthly electricity bill down. I prioritize running costs over initial costs."

[1538] 2. "I want an air conditioner that I can control with my smartphone."

[1539] Example 2: Choosing a PC

[1540] The user selects a PC category and enters their primary use (e.g., video editing, gaming) and budget. The server generates a list of questions based on this information and sends it to the terminal. The user answers questions about "CPU performance" and "storage capacity," and an emotion engine analyzes their "interests" and "stress levels." Based on the answers and emotion data, the server performs an analysis to select and present a high-performance PC that meets the user's needs. If the user wants to see a second option, the server relaxes the settings, re-evaluates, and presents another PC.

[1541] Example of a prompt

[1542] 1. "I'm considering buying a computer. My budget is 150,000 yen, and my main purpose is video editing. A large storage capacity would be ideal."

[1543] 2. "I want a model with a high CPU performance for video editing."

[1544] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1545] Step 1:

[1546] The server stores selection criteria and question lists for each product category in a database. Specifically, for each category such as refrigerators, personal computers, and air conditioners, it sets criteria related to budget and intended use, as well as question lists based on those criteria. A database system such as Google Cloud Firestore or MySQL is used for this setup. The input data consists of product categories, their selection criteria, and question lists, and the output is storage in the database.

[1547] Step 2:

[1548] The user uses a terminal to select the product category they wish to purchase. Specifically, they select one from a list of product categories displayed on the terminal screen, such as air conditioners, refrigerators, or personal computers. The user's input data is the selected product category, and the output is the transmission of the selection information to the server.

[1549] Step 3:

[1550] The user uses a terminal to input basic information such as budget, room size, and purpose of use. Specifically, they enter the necessary information in fields such as budget (amount), room size (square meters), and purpose of use (cooling, heating, other). This information is sent to the server. The input data is basic information, and the output is the transmission of this data to the server.

[1551] Step 4:

[1552] The server analyzes the received basic information and generates a list of questions tailored to the relevant product category. For example, in the case of an air conditioner, it generates questions about electricity costs, energy efficiency, and whether it can be controlled via smartphone, based on room size and budget. The analysis is performed using Python scripts or Node.js, and the algorithm is executed. The input data is basic information, and the output is the generated list of questions.

[1553] Step 5:

[1554] The terminal displays a list of questions sent from the server to the user in sequence. Specifically, each question is displayed on the terminal screen, prompting the user to input. The input data is the list of questions, and the output is the presentation of these questions to the user.

[1555] Step 6:

[1556] The user answers each question and sends the answers to the server in real time via their device. For example, to the question "What is the size of the room?", the answer might be "20m 2 The system provides responses such as "[...]". The input data is the user's response, and the output is the transmission of that response data to the server.

[1557] Step 7:

[1558] The emotion engine on the server analyzes the text and audio data submitted by the user. Specifically, it uses the Google Cloud Natural Language API for text analysis and IBM Watson's emotion analysis function for audio data analysis. The emotion engine identifies emotions such as satisfaction, dissatisfaction, excitement, and indecision from the user's statements. The input data is the user's response, and the output is the analyzed emotion information.

[1559] Step 8:

[1560] The server integrates responses and sentiment data received from users and extracts product specifications using high-performance AI. For example, it creates an analysis model using Python libraries such as scikit-learn and TensorFlow to extract product specifications based on user requests. The input data consists of responses and sentiment data, and the output is the extracted product specifications.

[1561] Step 9:

[1562] The server lists the most suitable products based on the analysis results and sends the top candidate products to the user's terminal. Specifically, it searches the database for products that meet the criteria based on the extracted product specifications and lists the best ones. The input data is product specifications, and the output is a list of optimal products.

[1563] Step 10:

[1564] The terminal displays a list of optimal products to the user. The user can select from the presented products, and detailed product information and purchase links are also displayed. The input data is the list of optimal products, and the output is the display of the products.

[1565] Step 11:

[1566] If a user enters an additional request (for example, "a model that can be operated with a smartphone"), that request is sent to the server via the device. The input data is the additional request, and the output is the transmission of that data to the server.

[1567] Step 12:

[1568] The server analyzes the additional request information and incorporates it into the initial analysis results to re-evaluate the products. Specifically, it re-evaluates the product list based on the new conditions derived from the additional requests. The aforementioned AI model is used again for the analysis. The input data is the additional requests, and the output is the updated product list.

[1569] Step 13:

[1570] The terminal displays updated suggested products to the user again. The user can then review the new best product. The input data is the updated product list, and the output is a redisplay of the products.

[1571] (Application Example 2)

[1572] 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".

[1573] In traditional e-commerce sites, product suggestions were based solely on basic information and answers to questions, making it difficult to adequately reflect users' emotions and true desires. This resulted in users spending considerable time and effort finding the most suitable product from a wide range of options.

[1574] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving basic information from a user, means for generating a list of questions based on the basic information, means for presenting the generated list of questions to the user, means for receiving the user's answers and analyzing those answers to select the optimal product, means including an emotion engine for analyzing emotion data from the user's answers, means for optimizing the product selection process using the emotion data, and means for presenting the selected product to the user. This makes it possible to propose the optimal product that reflects the user's emotions and true feelings.

[1575] "User information" refers to basic information that users provide when selecting electronic products or home appliances, such as their budget, room size, and intended use.

[1576] A "question list" is a list of questions generated based on the user's basic information and presented to the user.

[1577] "Answer" refers to the response entered by the user based on the list of questions.

[1578] The "emotion engine" is a part of the system that includes an algorithm for analyzing emotions from user response data.

[1579] "Emotional data" is data that represents the user's emotional state (e.g., satisfaction, dissatisfaction, excitement, indecision, etc.) generated by the emotion engine through analysis of the user's responses.

[1580] The "product selection process" is a series of procedures that analyze data from the user's basic information and responses to determine the most suitable product.

[1581] "Product specifications" refer to a list of specific features and performance characteristics of a product, extracted based on user needs.

[1582] The "optimal product" is the product that best matches the user's needs and emotions, selected based on the user's basic information, responses, and sentiment data.

[1583] A "server" is a core computer system that receives basic user information, generates a list of questions, collects and analyzes responses, and selects and suggests the most suitable products.

[1584] System Overview

[1585] This invention relates to a system that uses an emotion engine to analyze user emotional data during the process of selecting electronic products and home appliances, and then proposes the most suitable product based on that analysis. The system performs user information input, generates a list of questions, collects responses, performs emotion analysis, selects products, and proposes the most suitable product.

[1586] Hardware and software configuration

[1587] server:

[1588] Hardware: High-performance computer (such as AWS EC2)

[1589] software:

[1590] Operating System: Linux

[1591] Application server: Node.js

[1592] Database: MySQL

[1593] Sentiment analysis engine: Natural language processing API (Google Cloud Natural Language API)

[1594] AI Analysis Module: Python-based machine learning models

[1595] User terminal:

[1596] Hardware: Smartphone, tablet, or PC

[1597] software:

[1598] Operating system (e.g., iOS, Android, Windows)

[1599] Browser or dedicated application

[1600] Processing flow

[1601] 1. Enter user information

[1602] The user uses a terminal to select the product category they wish to purchase. Next, they enter basic information such as their budget, room size, and intended use. This information is sent to the server and stored in the database.

[1603] 2. Generating a list of questions

[1604] The server analyzes the received basic information and generates a custom list of questions based on the relevant product category. For example, in the case of an air conditioner, it generates questions such as room size, monthly electricity cost, initial purchase cost, and whether it can be operated with a smart device.

[1605] 3. Displaying questions and collecting answers

[1606] A list of questions is displayed sequentially on the user's terminal, and the user answers them. The answers are sent to the server in real time.

[1607] 4. Emotional analysis using an emotion engine

[1608] The server analyzes each response using an emotion engine (Google Cloud Natural Language API) to identify the user's emotions (satisfied, dissatisfied, excited, confused, etc.). This emotion data is also stored in a database.

[1609] 5. AI-driven analysis of responses and selection of optimal products

[1610] The server integrates and analyzes user responses and sentiment data to extract product specifications. A Python-based machine learning model is used to narrow down the database to the most suitable products.

[1611] 6. Proposal of the optimal product

[1612] An optimal product list is generated and sent to the user's terminal. The user reviews it and enters additional information if they have any further requests.

[1613] 7. Processing of additional requests

[1614] When a user enters additional requests (e.g., a model that can be operated via smartphone), the server re-evaluates and presents the updated product list to the user.

[1615] Specific example

[1616] Example 1: The user selects a refrigerator category and enters a specific budget. The server generates questions about the refrigerator (e.g., energy efficiency, quietness, design), and the user answers them sequentially. The emotion engine analyzes these answers to gather emotional data and suggests the most suitable product.

[1617] Example 2: The user selects a PC category and enters their primary use (e.g., gaming, video editing, etc.) and budget. The server generates questions tailored to the user's purpose, and the user answers them. Using the sentiment data analyzed by the emotion engine and the user's response data, the server selects the most suitable PC and presents it to the user.

[1618] Example of a prompt

[1619] "What is your budget?"

[1620] "Is energy efficiency important for a refrigerator? (Please rate on a scale of 1-5)"

[1621] "Do you care about the design of your refrigerator? (Yes / No)"

[1622] The above describes a specific embodiment of the present invention system. By using this system, users can receive optimal product suggestions that reflect their own emotions, thereby improving the efficiency of the selection process and increasing satisfaction.

[1623] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1624] Step 1: Enter user information

[1625] Subject: User

[1626] Specific operation: The user accesses the system via a smartphone application or browser and selects the product category they wish to purchase. Next, they enter basic information such as budget, room size, and intended use. This information is sent from the device to the server.

[1627] Input: Desired product category, budget, room size, purpose of use

[1628] Output: Basic information is sent to the server.

[1629] Step 2: Generate the question list

[1630] Subject: Server

[1631] Specific operation: The server analyzes the received user's basic information and generates a list of questions corresponding to the relevant product category. The generated question list is stored in the database and sent to the user's terminal.

[1632] Input: User's basic information

[1633] Data processing / calculation: Analyze basic information and generate a list of questions.

[1634] Output: A provisional list of questions is displayed on the user's terminal.

[1635] Step 3: Display the questions and collect the answers.

[1636] Subject: User

[1637] Specific operation: A list of questions is displayed on the user's terminal, and the user answers them sequentially. The user's response data is sent to the server in real time.

[1638] Input: List of questions sent from the server

[1639] Output: Response data is sent to the server.

[1640] Step 4: Emotional analysis using the emotion engine

[1641] Subject: Server

[1642] Specific operation: The server uses an emotion engine to analyze user response data in real time and generate emotion data. Emotion data is data that indicates the user's emotional state, such as satisfaction, dissatisfaction, excitement, and indecision. Emotion data is also stored in a database.

[1643] Input: User response data

[1644] Data processing / calculation: Emotion analysis is performed using an emotion engine to generate emotion data.

[1645] Output: Emotional data is generated and stored in the database.

[1646] Step 5: AI-driven analysis of responses and selection of optimal products

[1647] Subject: Server

[1648] Specific operation: The server integrates user response data and sentiment data and performs analysis using an AI model (a Python-based machine learning model). This analysis extracts product specifications, and the server selects the product best suited to the user's needs from the database.

[1649] Input: Response data, sentiment data

[1650] Data processing / calculation: Analyze data using an AI model and extract product specifications.

[1651] Output: The optimal product is generated.

[1652] Step 6: Proposing the optimal product

[1653] Subject: Server

[1654] Specific operation: The server selects the most suitable product list, which is then sent to the user's terminal and displayed to the user. The user then reviews the displayed product list.

[1655] Input: List of products selected by the server

[1656] Output: A list of products best suited to the user's terminal is displayed.

[1657] Step 7: Processing additional requests

[1658] Subject: User

[1659] Specific operation: When a user enters an additional request (for example, a model that can be operated with a smartphone) from the displayed product list, the additional information is sent from the device to the server. The server re-analyzes the newly added request and proposes an updated product list.

[1660] Input: Additional request information

[1661] Output: The updated product list is redisplayed on the user's terminal.

[1662] 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.

[1663] 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 those described above. 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 shown 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.

[1664] In the above embodiment, an example was given in which the 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.

[1665] 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.

[1666] 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. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, 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.

[1667] 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.

[1668] 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.

[1669] 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.

[1670] 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" ...

Claims

1. A means of receiving basic information from the user, A means for generating a list of questions based on the aforementioned basic information, A means for presenting the generated list of questions to the user, A means for receiving the user's response, analyzing that response, and selecting the most suitable product, A means for presenting the selected product to the user, A system that includes this.

2. The system according to claim 1, which accepts information including budget, room size, and purpose of use as the basic information.

3. The system according to claim 1, which extracts product specifications and lists the most suitable products based on the user's answers to the generated list of questions.

4. It provides a means for users to input additional requests for the optimal product. The system according to claim 1, which re-evaluates products based on the aforementioned additional requests and presents updated candidate products.

5. After presenting the aforementioned optimal product, the system provides a means for the user to input the instruction to "view the second option". The system according to claim 1, which re-evaluates the ranking of candidate products based on the aforementioned instructions and presents a second candidate product.

Images