system

Abstract

We provide the system. [Solution] In an information processing device, means for acquiring user identification information, Means for collecting user transaction history, A means for applying a generative model that generates product candidates based on acquired user identification information and collected transaction history, A means of providing the generated list of product candidates to the user terminal, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the hometown tax payment service, it is difficult to select the optimal one from a large number of local specialties, which requires a lot of time. In particular, it is a problem that users have to spend a lot of effort to find local specialties that suit their preferences.

Means for Solving the Problems

[0005] The present invention provides a system that enables an information processing device to acquire user identification information and transaction history, apply a generation model based on these data to generate product candidates, and provide a list of optimal local specialties for the user. With this system, users can efficiently select local specialties that suit their preferences, and the hometown tax payment procedure can proceed smoothly.

[0006] An "information processing device" is a computer system that acquires, analyzes, and outputs data.

[0007] "User identification information" refers to data used to uniquely identify a specific user, and includes login information and IDs.

[0008] "Transaction history" refers to a record of purchases and payments made by a user in the past.

[0009] A "generative model" is an algorithm or machine learning model that generates the optimal output based on the input data.

[0010] The "product suggestion list" is a list of local specialty products suggested based on the user's preferences and history.

[0011] A "user terminal" is an electronic device that can receive or display information through user operation. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This 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. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

MODE FOR CARRYING OUT THE INVENTION

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

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

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

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

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

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

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when three or more matters are connected and expressed by "and / or", the same concept as "A and / or B" is applied.

[0020] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0033] The present invention's system assists users in efficiently selecting the most suitable local specialty products when using the Furusato Nozei (hometown tax donation) service. This system uses an information processing device to utilize user identification information and transaction history to generate a list of optimal product candidates. Specifically, a server collects user identification information and transaction history, and proposes candidate local specialty products using a generative model.

[0034] When a user logs in, their device communicates with the server to send and receive necessary information. The server applies a generative model based on the user's preferences and past transaction data to create a list of specialty products best suited to the user. This list is displayed on the user's device, and the user makes a selection based on it.

[0035] For example, if a user has previously purchased wine using electronic payment, the server will use this information to suggest high-quality local wines as specialty products. This allows users to easily find products that suit their interests, significantly reducing the time and effort required for selection. Another example is when a user who frequently purchases seafood is suggested fresh, locally sourced seafood.

[0036] In this way, the system of the present invention enhances the user experience by providing personalized suggestions using data, thereby improving the convenience of the hometown tax donation system.

[0037] The following describes the processing flow.

[0038] Step 1:

[0039] The user logs into the Furusato Nozei (hometown tax donation) service using their device. Upon login, the device initiates a process to link the user's Yahoo! ID with their electronic payment-related accounts, with the user's consent.

[0040] Step 2:

[0041] The device sends the Yahoo! ID and recent electronic payment transaction history to the server. This allows the server to receive the user's individual information.

[0042] Step 3:

[0043] The server stores the received user identification information and transaction history in a database. This allows for the management of each user's data.

[0044] Step 4:

[0045] The server provides the stored data as input to a generative model for analysis. The generative model then calculates product candidates that take user preferences into account.

[0046] Step 5:

[0047] The server sends the generated list of potential products to the user's terminal. This list includes local specialties tailored to the user's needs.

[0048] Step 6:

[0049] The terminal displays a list of the local specialty products the user has received. The user selects their desired product from the displayed list of options and proceeds with the hometown tax donation process.

[0050] Step 7:

[0051] Once the user completes their selection, the device notifies the server of the final tax payment procedures and proceeds with the necessary steps. This completes the tax payment process.

[0052] (Example 1)

[0053] 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."

[0054] When users utilize the Furusato Nozei (hometown tax donation) service, a challenge arises in efficiently selecting the most suitable products that match their preferences and interests from a vast array of local specialties. In particular, the time-consuming and laborious process of discovering products based on past transaction history and preferences is a significant problem.

[0055] 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.

[0056] In this invention, the server includes means for acquiring identification information, means for collecting transaction history, and means for applying a generative model based on the acquired identification information and collected transaction history to generate candidate items. This makes it possible to efficiently suggest specialty products that match the user's preferences from a vast number of products, and to significantly reduce the time and effort required for selection.

[0057] An "information processing system" is a system consisting of devices or networks that collect, process, analyze, and output data.

[0058] "Identification information" refers to information used to identify individual users, including user IDs and other individual identifiers.

[0059] "Transaction history" refers to a record of purchases and contracts made by a user in the past, and usually includes detailed information such as the date, product name, and amount.

[0060] A "generative model" is an algorithm or framework that generates results or predictions from input data based on machine learning or statistical methods.

[0061] "Product candidates" are a list of products that should be suggested to the user, and are selected based on the user's preferences and past history.

[0062] A "device" is an electronic device that a user directly operates, and includes computers, smartphones, and tablets.

[0063] "Personalization" is the process of optimizing content and suggestions based on the preferences and needs of individual users.

[0064] This invention is a system that assists users in efficiently selecting local specialty products when using the Furusato Nozei (hometown tax donation) service. The system consists of a server, which is an information processing system, and terminals for direct user operation. The server runs on a suitable platform for implementing a generative AI model, which is used for selecting local specialty products.

[0065] The server first obtains user identification information using a security protocol when a user logs in. This identification information is stored in a database and collected by the server along with past transaction history. Transaction history is recorded through communication and payment technology and includes information such as past purchases and amounts spent.

[0066] The acquired data is input into a generative AI model, where product candidates are selected for the first time. Based on the identification information and transaction history, the generative AI model generates prompts such as "User's past purchase history: wine, seafood," and creates a list of local specialties that match the user's preferences.

[0067] The terminal displays a list of potential products sent from the server on the user interface. At this stage, the user can select a local specialty that suits their preferences and interests based on the displayed list. For example, if the server suggests locally renowned wines or fresh seafood based on past data, the user can easily select them.

[0068] This personalized selection process significantly reduces the time and effort users spend choosing products. The overall system aims to improve the convenience and customer satisfaction of the Furusato Nozei (hometown tax donation) program by providing a suggestion-based selection method utilizing a generative AI model.

[0069] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0070] Step 1:

[0071] The server obtains identification information when a user logs in. This input information includes a user ID and authentication token, and is sent to the server for security reasons. The server compares this identification information with the database to search for the user's past transaction history. The transaction history includes data such as past purchases, purchase dates, and amounts.

[0072] Step 2:

[0073] The server prepares to apply the generated AI model based on the acquired identification information and transaction history. Specifically, it processes the data to generate prompt messages that reflect the user's preferences. The user's past purchase history is used as input information. Based on this information, prompt messages such as "User's past purchase history: Wine, seafood" are generated. The generated prompt messages serve as the starting point for analysis by the AI ​​model.

[0074] Step 3:

[0075] The server inputs the generated prompt text into the AI ​​model and performs data calculations. Specifically, the AI ​​model calculates a list of item candidates that take user preferences into account based on the prompt text. The input is the prompt text, and the output is the generated list of specialty product candidates. This candidate list includes specialty products based on past usage history and trends.

[0076] Step 4:

[0077] The server sends a generated list of potential local products to the user's device. The device receives this list and displays it on the user interface. The user scrolls through the displayed list and selects local products that suit their interests and needs.

[0078] Step 5:

[0079] The user makes a selection from the displayed list of options. This involves tapping or clicking on a specific product on the device. The selected data is sent back to the server and used for order processing and history updates. The specialty product selected by the user then proceeds to the order process.

[0080] (Application Example 1)

[0081] 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."

[0082] When users utilize the Furusato Nozei (hometown tax donation) service, they face challenges in efficiently selecting the most suitable local products based on their preferences and past purchase history, resulting in time-consuming and cumbersome selection processes. Furthermore, there is difficulty in providing personalized product suggestions by leveraging users' past purchase data.

[0083] 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.

[0084] In this invention, the server includes means for acquiring user identification information, means for collecting the user's transaction history, means for applying a generative model that generates product candidates based on the acquired user identification information and transaction history, means for generating relevant product suggestions based on the user's past transaction history using a generative AI model, and means for displaying the suggested product list on the user's terminal. This makes it possible to personalize and suggest the most suitable local products to the user.

[0085] "User identification information" refers to information used to uniquely identify a specific user.

[0086] "Transaction history" refers to information that records details of purchases and transactions made by a user in the past.

[0087] A "generative model" is a computational algorithm used to create new information or patterns based on data.

[0088] A "generative AI model" is a model that uses artificial intelligence technology to make effective suggestions and predictions from user data.

[0089] "Personalization" refers to customizing specific information or services based on the individual user's preferences and behavioral patterns.

[0090] "Product candidates" are the options of products or services that may be offered to the user.

[0091] A "user terminal" is a device that a user directly operates and uses to receive information.

[0092] An "electronic payment system" is a mechanism that uses digital technology to allow people to pay for goods and services online.

[0093] The system implementing this invention is designed to personalize and suggest local specialty products for hometown tax donations based on the user's purchase history and preferences. The system consists of the following hardware and software.

[0094] The servers are built on cloud platforms, utilizing Amazon Web Services (AWS®) and Google Cloud Platform (GCP). MySQL® is used for database management, storing user identification information and transaction history. Google's Tensorflow® is used for the generative AI model. The generative AI model predicts the most suitable local products based on the user's transaction history and creates a list of candidates.

[0095] A terminal is a device used by a user to receive information, such as a smartphone or personal computer. When a user logs in, the application on the terminal communicates with the server and sends the user's identification information. Based on this information, the server retrieves the user's past transaction data and uses a generative AI model to create a list of potential products.

[0096] As a concrete example, consider a user who has previously purchased apples from Aomori Prefecture. This user will then be offered related products such as Aomori cider and apple jam as local specialties. This allows users to efficiently find local products that match their preferences.

[0097] An example of a prompt is: "Generate text that suggests additional local products based on the user's past purchase history. If the user has purchased apples from Aomori Prefecture, suggest a new product that uses those apples." This prompt allows the AI ​​model to generate specific product suggestions.

[0098] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0099] Step 1:

[0100] A user logs into an application on their smartphone or computer. During this process, the user's identification information is sent from the device to the server. The input is the user's login information, and the output is permission to communicate with the server.

[0101] Step 2:

[0102] The server retrieves the transaction history of the corresponding user from the database based on the received user identification information. In this step, the input is the user identification information, and the output is the user's transaction history data. The information is extracted using database queries.

[0103] Step 3:

[0104] The server inputs the acquired transaction history into a generating AI model to analyze user preferences and past purchase patterns. The input is the user's transaction history data, and the output is the analyzed preferences and patterns. TensorFlow is used to apply machine learning algorithms.

[0105] Step 4:

[0106] The generative AI model generates a list of optimal local specialty product candidates based on the analysis results. The input is the analyzed preferences and patterns, and the output is the list of specialty product candidates. The model performs inference and selects product candidates according to the prompt.

[0107] Step 5:

[0108] The server sends the generated list of specialty product candidates to the user's terminal. The input is the list of specialty product candidates, and the output is delivery to the user's terminal. The transfer of the list is performed using a data transmission protocol.

[0109] Step 6:

[0110] The user terminal displays the received list of local specialty product candidates on the application. The input is the list of local specialty product candidates sent from the server, and the output is the display on the user interface. The user can confirm the local specialty product through screen rendering.

[0111] 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.

[0112] The system of the present invention provides efficient, emotion-based, and personalized product suggestions to users of the Furusato Nozei (hometown tax donation) service. In addition to a generative model that generates product candidates based on user identification information and transaction history, this system incorporates an emotion engine that recognizes the user's emotions.

[0113] When a user logs into the service, the terminal sends user identification information and electronic payment history to the server. The server receives this information and uses a generative model to create initial product candidates tailored to the user's preferences. Next, the emotion engine analyzes the user's current emotional state from their facial expressions and voice, and combines this emotional data with the generative model to refine the optimal product candidate list.

[0114] For example, if a user has recently been feeling stressed, the emotion engine will prioritize adding products with relaxing effects (e.g., aromatherapy oils or massage devices) to the list. Based on the emotion recognition by the emotion engine, the service can flexibly change its product recommendations according to the user's emotional state.

[0115] The server sends a finalized list of product candidates to the user's terminal, and the user selects a product from that list. This allows the user to efficiently choose local products that match their emotions and preferences, and to comfortably proceed with the hometown tax donation process. In this way, the system of the present invention achieves advanced personalization by utilizing emotion recognition technology to improve the user experience.

[0116] The following describes the processing flow.

[0117] Step 1:

[0118] The user logs into the hometown tax donation service via their device. Using the login information, the device collects the user's identification information and begins sending data to the server.

[0119] Step 2:

[0120] The terminal sends user identification information, including Yahoo! ID and electronic payment history, to the server. The server receives this information and stores it in its database.

[0121] Step 3:

[0122] The server uses stored user identification information and transaction history to apply a generative model and generate an initial list of specialty products.

[0123] Step 4:

[0124] The user accesses the emotion engine through the device's camera and microphone. The emotion engine analyzes the user's facial expressions and voice information to identify their current emotional state.

[0125] Step 5:

[0126] The server uses emotion data obtained from the emotion engine to adjust the initial list of candidates that has been generated. The adjustment optimizes the list to prioritize products that match the user's emotions.

[0127] Step 6:

[0128] The server then creates a new list of product suggestions optimized based on the user's emotional state and provides it to the user's terminal.

[0129] Step 7:

[0130] The device displays a list of local specialty products to the user. The user selects a product from the displayed list that matches their feelings and preferences, and then proceeds with the hometown tax donation process.

[0131] Step 8:

[0132] To complete the tax payment process for the selected items, the terminal sends the necessary information to the server and concludes the process. The user's selection is complete, and satisfactory items are chosen.

[0133] (Example 2)

[0134] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0135] Traditional hometown tax donation services offered product suggestions based on user preferences, but they lacked sufficient personalization that considered the user's current emotional state, resulting in a limited user experience. Furthermore, conventional systems struggled to provide appropriate product suggestions that reflected the user's emotions, such as stress or relaxation.

[0136] 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.

[0137] In this invention, the server includes means for acquiring user identification information, means for collecting the user's transaction history, means for generating product candidates by applying a generative model, means for acquiring emotional data using an emotional engine and adjusting the product candidate list, and means for providing the generated product candidate list to the user terminal. This enables personalized product suggestions based on the user's preferences and emotional state.

[0138] An "information processing device" is a device that acquires, processes, and analyzes data to provide useful information to users.

[0139] "User identification information" refers to identification data used to recognize a specific user, and includes user IDs and authentication tokens.

[0140] "Transaction history" refers to records of purchases and payments made by a user in the past.

[0141] A "generative model" is a model that uses machine learning algorithms to suggest products based on user preferences.

[0142] An "emotion engine" is a software component that analyzes a user's emotional state from their facial expressions and voice.

[0143] A "product candidate list" is a list of products selected to be proposed to users.

[0144] An "electronic payment system" is a digital payment system used to record a user's payment history.

[0145] A "user terminal" refers to an electronic device that the user directly operates, and includes PCs, smartphones, and other similar devices.

[0146] This invention utilizes a system centered around an information processing device. The user first logs into the hometown tax donation service using a terminal. At this time, the terminal acquires user identification information and electronic payment history and transmits them to the server.

[0147] The server uses the received user identification information and transaction history to apply a generative AI model utilizing machine learning frameworks such as TensorFlow and PyTorch to generate product candidates tailored to the user's preferences. The prompt message used for this process might be something like, "Analyze the user's preferences based on their past purchase history and suggest relevant products."

[0148] Next, the user's device uses its camera and microphone to capture the user's facial expressions and voice in real time, which are then analyzed by an emotion engine. The emotion engine uses OpenCV to analyze facial expressions and voice analysis software to evaluate voice data, thereby understanding the user's emotional state. This emotion data is sent to a server and combined with a generative AI model to adjust the product candidate list.

[0149] For example, if a user is feeling stressed, the server can prioritize including products with relaxing effects, such as aromatherapy oils or massage devices, in the list. Finally, the server returns the adjusted list of product suggestions to the user's terminal, and the user selects the desired product from that list.

[0150] This system allows users to efficiently and comfortably select products that match their preferences and feelings, and to smoothly complete the process of making hometown tax donations.

[0151] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0152] Step 1:

[0153] The user logs into the hometown tax donation service using their device. The device retrieves user identification information and electronic payment history and sends it to the server. This input data includes the user ID and past electronic payment history.

[0154] Step 2:

[0155] The server uses user identification information and transaction history received from the terminal as input to generate product candidates using a machine learning model. The generation AI model uses TensorFlow and PyTorch, and generates an initial list of specialty product candidates based on the user's past transaction data. This list is then output.

[0156] Step 3:

[0157] The user's device uses its built-in camera and microphone to capture the user's facial expressions and voice. This data is sent to a server in the form of image and audio data for sentiment analysis.

[0158] Step 4:

[0159] The server utilizes an emotion engine to analyze the received image and audio data. It processes information obtained from facial expressions using OpenCV and audio data obtained using voice analysis software. Through this process, the user's current emotional state is identified and output as emotion data.

[0160] Step 5:

[0161] The server provides emotional data as input to the generating AI model, which then readjusts the initial list of candidate products. Based on the emotional data, products that are appropriate to the user's current state are prioritized in the list. This adjusted product list is then output.

[0162] Step 6:

[0163] Finally, the server sends the adjusted list of product candidates to the user's terminal. The user reviews this list on their terminal and selects the desired product.

[0164] (Application Example 2)

[0165] 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".

[0166] In modern e-commerce, users are often overwhelmed by the sheer number of choices available, and it's particularly difficult for them to receive optimal product recommendations tailored to their current emotional state. Furthermore, there is no system that efficiently provides personalized product recommendations that take user emotions into account. Solving this challenge and improving the user experience is crucial.

[0167] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0168] In this invention, the server includes means for acquiring user identification information, means for collecting the user's transaction history, means for applying a generation function that generates product candidates based on the acquired user identification information and the collected transaction history, means for analyzing the user's emotional state from their facial expressions and voice using an emotion analysis function, means for adjusting the generated product candidate list based on the emotional state, and means for providing the adjusted product candidate list to the user's device. This enables highly personalized product suggestions based on the user's preferences and emotional state.

[0169] "User identification information" refers to information used to uniquely identify a specific user.

[0170] "Transaction history" refers to information that shows the history of e-commerce transactions and payments that a user has made in the past.

[0171] The "generation function" is a technology that automatically creates product candidates based on the user's identification information and transaction history.

[0172] "Emotion analysis function" is a technology that analyzes the user's facial expressions and voice to understand their emotional state at that time.

[0173] A "product candidate list" is a collection of products suggested to the user, and is created using a generation function.

[0174] "User equipment" refers to information terminals or devices used by users, specifically those used to display a list of product candidates.

[0175] "Personalized product suggestions" refer to unique product suggestions tailored to the individual preferences and emotional state of the user.

[0176] The system for realizing this invention includes a user terminal, a server, and a computing environment equipped with the necessary analytical functions. Its outline is described below.

[0177] First, a smartphone is used as the user's terminal. The smartphone is equipped with a camera and microphone, and these sensors are used to capture the user's facial expressions and voice. The acquired data is sent to the emotion analysis function. Emotion analysis uses facial recognition technology with TensorFlow and voice analysis technology with PyTorch.

[0178] The server receives user identification information and electronic payment history, and uses a generative AI model to generate an initial list of specialty product candidates. This generative AI model uses machine learning algorithms to analyze the user's past preferences and selection patterns, listing the most relevant products. The generated list is then refined in combination with analyzed sentiment data. For example, if the user indicates a desire to relax, aromatherapy oils and relaxation products will be given higher priority.

[0179] The finalized list of product candidates is provided to the user's terminal, from which the user can select a product. In this way, personalized product suggestions based on emotional state become possible.

[0180] For example, if a user receives the prompt "Tell us how you've been feeling lately. What kind of products are you looking for?", and the user answers "I'm tired," that emotion will be analyzed, and relaxation products will be moved to the top of the list.

[0181] With the above configuration, this invention can provide flexible product suggestions that adapt to the user's current emotions, thereby improving the user experience.

[0182] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0183] Step 1:

[0184] The user terminal acquires the user's facial expressions and voice data. It uses a camera and microphone as inputs, collecting real-time data from these sensors. The output consists of video and audio data.

[0185] Step 2:

[0186] The user terminal sends the acquired facial expressions and audio data to the server. In this transmission process, the terminal compresses the data and sends it to the server via a secure network. The input is the video and audio data acquired earlier, and the output is the data ready for use on the server.

[0187] Step 3:

[0188] The server applies emotion analysis functionality to analyze the user's emotional state from the transmitted data. It uses TensorFlow for facial recognition and PyTorch for voice analysis to analyze the user's facial expressions and voice. The input is the data received in step 2, and the output is the analyzed emotion information.

[0189] Step 4:

[0190] The server retrieves user identification information and electronic payment history, and generates a list of product candidates using a generative AI model. At this stage, the user's past purchase history and preferences are taken into consideration. The input is user identification information and electronic payment history, and the output is the generated initial list of product candidates.

[0191] Step 5:

[0192] Based on the results of the emotion analysis, the server adjusts the generated list of candidate products. If an emotion indicating a desire for relaxation is detected, relaxation products are prioritized. This process is performed by data calculations combining emotion information and the candidate product list. The input is emotion information and the initial candidate product list, and the output is an optimized candidate product list.

[0193] Step 6:

[0194] The server sends an optimized list of product candidates to the user's terminal. The input is the optimized list of product candidates, and the output is a product list converted into a format that can be displayed on the user's terminal.

[0195] Step 7:

[0196] The user terminal presents the user with a list of received product candidates. The user can select a product from the provided list and make a decision. The input is the product list sent from the server, and the output is the selection information based on the user's decision.

[0197] 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.

[0198] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0199] 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.

[0200] [Second Embodiment]

[0201] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0202] 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.

[0203] 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).

[0204] 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.

[0205] 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.

[0206] 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).

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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".

[0213] The present invention's system assists users in efficiently selecting the most suitable local specialty products when using the Furusato Nozei (hometown tax donation) service. This system uses an information processing device to utilize user identification information and transaction history to generate a list of optimal product candidates. Specifically, a server collects user identification information and transaction history, and proposes candidate local specialty products using a generative model.

[0214] When a user logs in, their device communicates with the server to send and receive necessary information. The server applies a generative model based on the user's preferences and past transaction data to create a list of specialty products best suited to the user. This list is displayed on the user's device, and the user makes a selection based on it.

[0215] For example, if a user has previously purchased wine using electronic payment, the server will use this information to suggest high-quality local wines as specialty products. This allows users to easily find products that suit their interests, significantly reducing the time and effort required for selection. Another example is when a user who frequently purchases seafood is suggested fresh, locally sourced seafood.

[0216] In this way, the system of the present invention enhances the user experience by providing personalized suggestions using data, thereby improving the convenience of the hometown tax donation system.

[0217] The following describes the processing flow.

[0218] Step 1:

[0219] The user logs into the Furusato Nozei (hometown tax donation) service using their device. Upon login, the device initiates a process to link the user's Yahoo! ID with their electronic payment-related accounts, with the user's consent.

[0220] Step 2:

[0221] The device sends the Yahoo! ID and recent electronic payment transaction history to the server. This allows the server to receive the user's individual information.

[0222] Step 3:

[0223] The server stores the received user identification information and transaction history in a database. This allows for the management of each user's data.

[0224] Step 4:

[0225] The server provides the stored data as input to a generative model for analysis. The generative model then calculates product candidates that take user preferences into account.

[0226] Step 5:

[0227] The server sends the generated list of potential products to the user's terminal. This list includes local specialties tailored to the user's needs.

[0228] Step 6:

[0229] The terminal displays a list of the local specialty products the user has received. The user selects their desired product from the displayed list of options and proceeds with the hometown tax donation process.

[0230] Step 7:

[0231] Once the user completes their selection, the device notifies the server of the final tax payment procedures and proceeds with the necessary steps. This completes the tax payment process.

[0232] (Example 1)

[0233] 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."

[0234] When users utilize the Furusato Nozei (hometown tax donation) service, a challenge arises in efficiently selecting the most suitable products that match their preferences and interests from a vast array of local specialties. In particular, the time-consuming and laborious process of discovering products based on past transaction history and preferences is a significant problem.

[0235] 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.

[0236] In this invention, the server includes means for acquiring identification information, means for collecting transaction history, and means for applying a generative model based on the acquired identification information and collected transaction history to generate candidate items. This makes it possible to efficiently suggest specialty products that match the user's preferences from a vast number of products, and to significantly reduce the time and effort required for selection.

[0237] An "information processing system" is a system consisting of devices or networks that collect, process, analyze, and output data.

[0238] "Identification information" refers to information used to identify individual users, including user IDs and other individual identifiers.

[0239] "Transaction history" refers to a record of purchases and contracts made by a user in the past, and usually includes detailed information such as the date, product name, and amount.

[0240] A "generative model" is an algorithm or framework that generates results or predictions from input data based on machine learning or statistical methods.

[0241] "Product candidates" are a list of products that should be suggested to the user, and are selected based on the user's preferences and past history.

[0242] A "device" is an electronic device that a user directly operates, and includes computers, smartphones, and tablets.

[0243] "Personalization" is the process of optimizing content and suggestions based on the preferences and needs of individual users.

[0244] This invention is a system that assists users in efficiently selecting local specialty products when using the Furusato Nozei (hometown tax donation) service. The system consists of a server, which is an information processing system, and terminals for direct user operation. The server runs on a suitable platform for implementing a generative AI model, which is used for selecting local specialty products.

[0245] The server first obtains user identification information using a security protocol when a user logs in. This identification information is stored in a database and collected by the server along with past transaction history. Transaction history is recorded through communication and payment technology and includes information such as past purchases and amounts spent.

[0246] The acquired data is input into a generative AI model, where product candidates are selected for the first time. Based on the identification information and transaction history, the generative AI model generates prompts such as "User's past purchase history: wine, seafood," and creates a list of local specialties that match the user's preferences.

[0247] The terminal displays a list of potential products sent from the server on the user interface. At this stage, the user can select a local specialty that suits their preferences and interests based on the displayed list. For example, if the server suggests locally renowned wines or fresh seafood based on past data, the user can easily select them.

[0248] This personalized selection process significantly reduces the time and effort users spend choosing products. The overall system aims to improve the convenience and customer satisfaction of the Furusato Nozei (hometown tax donation) program by providing a suggestion-based selection method utilizing a generative AI model.

[0249] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0250] Step 1:

[0251] The server obtains identification information when a user logs in. This input information includes a user ID and authentication token, and is sent to the server for security reasons. The server compares this identification information with the database to search for the user's past transaction history. The transaction history includes data such as past purchases, purchase dates, and amounts.

[0252] Step 2:

[0253] The server prepares to apply the generated AI model based on the acquired identification information and transaction history. Specifically, it processes the data to generate prompt messages that reflect the user's preferences. The user's past purchase history is used as input information. Based on this information, prompt messages such as "User's past purchase history: Wine, seafood" are generated. The generated prompt messages serve as the starting point for analysis by the AI ​​model.

[0254] Step 3:

[0255] The server inputs the generated prompt text into the AI ​​model and performs data calculations. Specifically, the AI ​​model calculates a list of item candidates that take user preferences into account based on the prompt text. The input is the prompt text, and the output is the generated list of specialty product candidates. This candidate list includes specialty products based on past usage history and trends.

[0256] Step 4:

[0257] The server sends a generated list of potential local products to the user's device. The device receives this list and displays it on the user interface. The user scrolls through the displayed list and selects local products that suit their interests and needs.

[0258] Step 5:

[0259] The user makes a selection from the displayed list of options. This involves tapping or clicking on a specific product on the device. The selected data is sent back to the server and used for order processing and history updates. The specialty product selected by the user then proceeds to the order process.

[0260] (Application Example 1)

[0261] 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."

[0262] When users utilize the Furusato Nozei (hometown tax donation) service, they face challenges in efficiently selecting the most suitable local products based on their preferences and past purchase history, resulting in time-consuming and cumbersome selection processes. Furthermore, there is difficulty in providing personalized product suggestions by leveraging users' past purchase data.

[0263] 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.

[0264] In this invention, the server includes means for acquiring user identification information, means for collecting the user's transaction history, means for applying a generative model that generates product candidates based on the acquired user identification information and transaction history, means for generating relevant product suggestions based on the user's past transaction history using a generative AI model, and means for displaying the suggested product list on the user's terminal. This makes it possible to personalize and suggest the most suitable local products to the user.

[0265] "User identification information" refers to information used to uniquely identify a specific user.

[0266] "Transaction history" refers to information that records details of purchases and transactions made by a user in the past.

[0267] A "generative model" is a computational algorithm used to create new information or patterns based on data.

[0268] A "generative AI model" is a model that uses artificial intelligence technology to make effective suggestions and predictions from user data.

[0269] "Personalization" refers to customizing specific information or services based on the individual user's preferences and behavioral patterns.

[0270] "Product candidates" are the options of products or services that may be offered to the user.

[0271] A "user terminal" is a device that a user directly operates and uses to receive information.

[0272] An "electronic payment system" is a mechanism that uses digital technology to allow people to pay for goods and services online.

[0273] The system implementing this invention is designed to personalize and suggest local specialty products for hometown tax donations to users based on their purchase history and preferences. The system consists of the following hardware and software.

[0274] The servers are built on cloud platforms, utilizing Amazon Web Services (AWS) and Google Cloud Platform (GCP). MySQL is used for database management, storing user identification information and transaction history. Google's TensorFlow is used for the generative AI model. The generative AI model predicts the most suitable local products based on the user's transaction history and creates a list of candidates.

[0275] A terminal is a device used by a user to receive information, such as a smartphone or personal computer. When a user logs in, the application on the terminal communicates with the server and sends the user's identification information. Based on this information, the server retrieves the user's past transaction data and creates a list of potential products using a generative AI model.

[0276] As a concrete example, consider a user who has previously purchased apples from Aomori Prefecture. This user will then be offered related products such as Aomori cider and apple jam as local specialties. This allows users to efficiently find local products that match their preferences.

[0277] An example of a prompt is: "Generate text that suggests additional local products based on the user's past purchase history. If the user has purchased apples from Aomori Prefecture, suggest a new product that uses those apples." This prompt allows the AI ​​model to generate specific product suggestions.

[0278] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0279] Step 1:

[0280] A user logs into an application on their smartphone or computer. During this process, the user's identification information is sent from the device to the server. The input is the user's login information, and the output is permission to communicate with the server.

[0281] Step 2:

[0282] The server retrieves the transaction history of the corresponding user from the database based on the received user identification information. In this step, the input is the user identification information, and the output is the user's transaction history data. The information is extracted using database queries.

[0283] Step 3:

[0284] The server inputs the obtained transaction history into the generative AI model to analyze the user's preferences and past purchase patterns. The input is the user's transaction history data, and the output is the analyzed preferences and patterns. An operation of applying a machine learning algorithm using TensorFlow is performed.

[0285] Step 4:

[0286] The generative AI model generates a list of candidate specialty products based on the analysis results. The input is the analyzed preferences and patterns, and the output is the list of specialty product candidates. An operation of performing inference according to the prompt text and selecting product candidates is performed.

[0287] Step 5:

[0288] The server sends the generated list of specialty product candidates to the user's terminal. The input is the list of specialty product candidates, and the output is the delivery to the user terminal. An operation of transferring the list using a data transmission protocol is performed.

[0289] Step 6:

[0290] The user terminal displays the received list of specialty product candidates on the application. The input is the list of specialty product candidates sent from the server, and the output is the display on the user interface. An operation is performed such that the user can check the specialty products by screen rendering.

[0291] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion.

[0292] The system of the present invention provides efficient, emotion-based, and personalized product suggestions to users of the Furusato Nozei (hometown tax donation) service. In addition to a generative model that generates product candidates based on user identification information and transaction history, this system incorporates an emotion engine that recognizes the user's emotions.

[0293] When a user logs into the service, the terminal sends user identification information and electronic payment history to the server. The server receives this information and uses a generative model to create initial product candidates tailored to the user's preferences. Next, the emotion engine analyzes the user's current emotional state from their facial expressions and voice, and combines this emotional data with the generative model to refine the optimal product candidate list.

[0294] For example, if a user has recently been feeling stressed, the emotion engine will prioritize adding products with relaxing effects (e.g., aromatherapy oils or massage devices) to the list. Based on the emotion recognition by the emotion engine, the service can flexibly change its product recommendations according to the user's emotional state.

[0295] The server sends a finalized list of product candidates to the user's terminal, and the user selects a product from that list. This allows the user to efficiently choose local products that match their emotions and preferences, and to comfortably proceed with the hometown tax donation process. In this way, the system of the present invention achieves advanced personalization by utilizing emotion recognition technology to improve the user experience.

[0296] The following describes the processing flow.

[0297] Step 1:

[0298] The user logs into the hometown tax donation service via their device. Using the login information, the device collects the user's identification information and begins sending data to the server.

[0299] Step 2:

[0300] The terminal sends the user's identification information including the Yahoo ID and the electronic payment history to the server. The server receives this information and stores it in the database.

[0301] Step 3:

[0302] Based on the stored user identification information and transaction history, the server applies a generation model to generate an initial candidate list of specialty products.

[0303] Step 4:

[0304] The user accesses the emotion engine through the terminal's camera or microphone. The emotion engine analyzes the emotion from the user's facial expression and voice information to identify the current emotional state.

[0305] Step 5:

[0306] The server uses the emotion data obtained from the emotion engine to adjust the generated initial candidate list. The adjustment content optimizes the list to preferentially include products that match the user's emotion.

[0307] Step 6:

[0308] The server re-creates the optimized product candidate list based on the emotional state and provides it to the user's terminal.

[0309] Step 7:

[0310] The terminal displays the candidate list of specialty products to the user. The user selects a product that matches their emotion and preference from the displayed list and proceeds with the hometown tax payment procedure.

[0311] Step 8:

[0312] To complete the tax payment procedure for the selected product, the terminal sends the necessary information to the server to finalize the process. The user's selection is completed, and a satisfactory product is selected.

[0313] (Example 2)

[0314] 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".

[0315] Traditional hometown tax donation services offered product suggestions based on user preferences, but they lacked sufficient personalization that considered the user's current emotional state, resulting in a limited user experience. Furthermore, conventional systems struggled to provide appropriate product suggestions that reflected the user's emotions, such as stress or relaxation.

[0316] 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.

[0317] In this invention, the server includes means for acquiring user identification information, means for collecting the user's transaction history, means for generating product candidates by applying a generative model, means for acquiring emotional data using an emotional engine and adjusting the product candidate list, and means for providing the generated product candidate list to the user terminal. This enables personalized product suggestions based on the user's preferences and emotional state.

[0318] An "information processing device" is a device that acquires, processes, and analyzes data to provide useful information to users.

[0319] "User identification information" refers to identification data used to recognize a specific user, and includes user IDs and authentication tokens.

[0320] "Transaction history" refers to records of purchases and payments made by a user in the past.

[0321] A "generative model" is a model that uses machine learning algorithms to suggest products based on user preferences.

[0322] An "emotion engine" is a software component that analyzes a user's emotional state from their facial expressions and voice.

[0323] A "product candidate list" is a list of products selected to be proposed to users.

[0324] An "electronic payment system" is a digital payment system used to record a user's payment history.

[0325] A "user terminal" refers to an electronic device that the user directly operates, and includes PCs, smartphones, and other similar devices.

[0326] This invention utilizes a system centered around an information processing device. The user first logs into the hometown tax donation service using a terminal. At this time, the terminal acquires user identification information and electronic payment history and transmits them to the server.

[0327] The server uses the received user identification information and transaction history to apply a generative AI model utilizing machine learning frameworks such as TensorFlow and PyTorch to generate product candidates tailored to the user's preferences. The prompt message used for this process might be something like, "Analyze the user's preferences based on their past purchase history and suggest relevant products."

[0328] Next, the user's device uses its camera and microphone to capture the user's facial expressions and voice in real time, which are then analyzed by an emotion engine. The emotion engine uses OpenCV to analyze facial expressions and voice analysis software to evaluate voice data, thereby understanding the user's emotional state. This emotion data is sent to a server and combined with a generative AI model to adjust the product candidate list.

[0329] For example, if a user is feeling stressed, the server can prioritize including products with relaxing effects, such as aromatherapy oils or massage devices, in the list. Finally, the server returns the adjusted list of product suggestions to the user's terminal, and the user selects the desired product from that list.

[0330] This system allows users to efficiently and comfortably select products that match their preferences and feelings, and to smoothly complete the process of making hometown tax donations.

[0331] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0332] Step 1:

[0333] The user logs into the hometown tax donation service using their device. The device retrieves user identification information and electronic payment history and sends it to the server. This input data includes the user ID and past electronic payment history.

[0334] Step 2:

[0335] The server uses user identification information and transaction history received from the terminal as input to generate product candidates using a machine learning model. The generation AI model uses TensorFlow and PyTorch, and generates an initial list of specialty product candidates based on the user's past transaction data. This list is then output.

[0336] Step 3:

[0337] The user's device uses its built-in camera and microphone to capture the user's facial expressions and voice. This data is sent to a server in the form of image and audio data for sentiment analysis.

[0338] Step 4:

[0339] The server utilizes an emotion engine to analyze the received image and audio data. It processes information obtained from facial expressions using OpenCV and audio data obtained using voice analysis software. Through this process, the user's current emotional state is identified and output as emotion data.

[0340] Step 5:

[0341] The server provides emotional data as input to the generating AI model, which then readjusts the initial list of candidate products. Based on the emotional data, products that are appropriate to the user's current state are prioritized in the list. This adjusted product list is then output.

[0342] Step 6:

[0343] Finally, the server sends the adjusted list of product candidates to the user's terminal. The user reviews this list on their terminal and selects the desired product.

[0344] (Application Example 2)

[0345] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0346] In modern e-commerce, users are often overwhelmed by the sheer number of choices available, and it's particularly difficult for them to receive optimal product recommendations tailored to their current emotional state. Furthermore, there is no system that efficiently provides personalized product recommendations that take user emotions into account. Solving this challenge and improving the user experience is crucial.

[0347] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0348] In this invention, the server includes means for acquiring user identification information, means for collecting the user's transaction history, means for applying a generation function that generates product candidates based on the acquired user identification information and the collected transaction history, means for analyzing the user's emotional state from their facial expressions and voice using an emotion analysis function, means for adjusting the generated product candidate list based on the emotional state, and means for providing the adjusted product candidate list to the user's device. This enables highly personalized product suggestions based on the user's preferences and emotional state.

[0349] "User identification information" refers to information used to uniquely identify a specific user.

[0350] "Transaction history" refers to information that shows the history of e-commerce transactions and payments that a user has made in the past.

[0351] The "generation function" is a technology that automatically creates product candidates based on the user's identification information and transaction history.

[0352] "Emotion analysis function" is a technology that analyzes the user's facial expressions and voice to understand their emotional state at that time.

[0353] A "product candidate list" is a collection of products suggested to the user, and is created using a generation function.

[0354] "User equipment" refers to information terminals or devices used by users, specifically those used to display a list of product candidates.

[0355] "Personalized product suggestions" refer to unique product suggestions tailored to the individual preferences and emotional state of the user.

[0356] The system for realizing this invention includes a user terminal, a server, and a computing environment equipped with the necessary analytical functions. Its outline is described below.

[0357] First, a smartphone is used as the user's terminal. The smartphone is equipped with a camera and microphone, and these sensors are used to capture the user's facial expressions and voice. The acquired data is sent to the emotion analysis function. Emotion analysis uses facial recognition technology with TensorFlow and voice analysis technology with PyTorch.

[0358] The server receives user identification information and electronic payment history, and uses a generative AI model to generate an initial list of specialty product candidates. This generative AI model uses machine learning algorithms to analyze the user's past preferences and selection patterns, listing the most relevant products. The generated list is then refined in combination with analyzed sentiment data. For example, if the user indicates a desire to relax, aromatherapy oils and relaxation products will be given higher priority.

[0359] The finalized list of product candidates is provided to the user's terminal, from which the user can select a product. In this way, personalized product suggestions based on emotional state become possible.

[0360] For example, if a user receives the prompt "Tell us how you've been feeling lately. What kind of products are you looking for?", and the user answers "I'm tired," that emotion will be analyzed, and relaxation products will be moved to the top of the list.

[0361] With the above configuration, this invention can provide flexible product suggestions that adapt to the user's current emotions, thereby improving the user experience.

[0362] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0363] Step 1:

[0364] The user terminal acquires the user's facial expressions and voice data. It uses a camera and microphone as inputs, collecting real-time data from these sensors. The output consists of video and audio data.

[0365] Step 2:

[0366] The user terminal sends the acquired facial expressions and audio data to the server. In this transmission process, the terminal compresses the data and sends it to the server via a secure network. The input is the video and audio data acquired earlier, and the output is the data ready for use on the server.

[0367] Step 3:

[0368] The server applies emotion analysis functionality to analyze the user's emotional state from the transmitted data. It uses TensorFlow for facial recognition and PyTorch for voice analysis to analyze the user's facial expressions and voice. The input is the data received in step 2, and the output is the analyzed emotion information.

[0369] Step 4:

[0370] The server retrieves user identification information and electronic payment history, and generates a list of product candidates using a generative AI model. At this stage, the user's past purchase history and preferences are taken into consideration. The input is user identification information and electronic payment history, and the output is the generated initial list of product candidates.

[0371] Step 5:

[0372] Based on the results of the emotion analysis, the server adjusts the generated list of product candidates. If an emotion indicating a desire for relaxation is detected, relaxation products are prioritized. This process is performed by data calculations combining the emotion information and the list of product candidates. The input is the emotion information and the initial list of product candidates, and the output is the optimized list of product candidates.

[0373] Step 6:

[0374] The server sends an optimized list of product candidates to the user's terminal. The input is the optimized list of product candidates, and the output is a product list converted into a format that can be displayed on the user's terminal.

[0375] Step 7:

[0376] The user terminal presents the user with a list of received product candidates. The user can select a product from the provided list and make a decision. The input is the product list sent from the server, and the output is the selection information based on the user's decision.

[0377] 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.

[0378] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0379] 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.

[0380] [Third Embodiment]

[0381] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0382] 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.

[0383] 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).

[0384] 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.

[0385] 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.

[0386] 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).

[0387] 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.

[0388] 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.

[0389] 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.

[0390] 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.

[0391] 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.

[0392] 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".

[0393] The present invention's system assists users in efficiently selecting the most suitable local specialty products when using the Furusato Nozei (hometown tax donation) service. This system uses an information processing device to utilize user identification information and transaction history to generate a list of optimal product candidates. Specifically, a server collects user identification information and transaction history, and proposes candidate local specialty products using a generative model.

[0394] When a user logs in, their device communicates with the server to send and receive necessary information. The server applies a generative model based on the user's preferences and past transaction data to create a list of specialty products best suited to the user. This list is displayed on the user's device, and the user makes a selection based on it.

[0395] For example, if a user has previously purchased wine using electronic payment, the server will use this information to suggest high-quality local wines as specialty products. This allows users to easily find products that suit their interests, significantly reducing the time and effort required for selection. Another example is when a user who frequently purchases seafood is suggested fresh, locally sourced seafood.

[0396] In this way, the system of the present invention enhances the user experience by providing personalized suggestions using data, thereby improving the convenience of the hometown tax donation system.

[0397] The following describes the processing flow.

[0398] Step 1:

[0399] The user logs into the Furusato Nozei (hometown tax donation) service using their device. Upon login, the device initiates a process to link the user's Yahoo! ID with their electronic payment-related accounts, with the user's consent.

[0400] Step 2:

[0401] The device sends the Yahoo! ID and recent electronic payment transaction history to the server. This allows the server to receive the user's individual information.

[0402] Step 3:

[0403] The server stores the received user identification information and transaction history in a database. This allows for the management of each user's data.

[0404] Step 4:

[0405] The server provides the stored data as input to a generative model for analysis. The generative model then calculates product candidates that take user preferences into account.

[0406] Step 5:

[0407] The server sends the generated list of potential products to the user's terminal. This list includes local specialties tailored to the user's needs.

[0408] Step 6:

[0409] The terminal displays a list of the local specialty products the user has received. The user selects their desired product from the displayed list of options and proceeds with the hometown tax donation process.

[0410] Step 7:

[0411] Once the user completes their selection, the device notifies the server of the final tax payment procedures and proceeds with the necessary steps. This completes the tax payment process.

[0412] (Example 1)

[0413] 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."

[0414] When users utilize the Furusato Nozei (hometown tax donation) service, a challenge arises in efficiently selecting the most suitable products that match their preferences and interests from a vast array of local specialties. In particular, the time-consuming and laborious process of discovering products based on past transaction history and preferences is a significant problem.

[0415] 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.

[0416] In this invention, the server includes means for acquiring identification information, means for collecting transaction history, and means for applying a generative model based on the acquired identification information and collected transaction history to generate candidate items. This makes it possible to efficiently suggest specialty products that match the user's preferences from a vast number of products, and to significantly reduce the time and effort required for selection.

[0417] An "information processing system" is a system consisting of devices or networks that collect, process, analyze, and output data.

[0418] "Identification information" refers to information used to identify individual users, including user IDs and other individual identifiers.

[0419] "Transaction history" refers to a record of purchases and contracts made by a user in the past, and usually includes detailed information such as the date, product name, and amount.

[0420] A "generative model" is an algorithm or framework that generates results or predictions from input data based on machine learning or statistical methods.

[0421] "Product candidates" are a list of products that should be suggested to the user, and are selected based on the user's preferences and past history.

[0422] A "device" is an electronic device that a user directly operates, and includes computers, smartphones, and tablets.

[0423] "Personalization" is the process of optimizing content and suggestions based on the preferences and needs of individual users.

[0424] This invention is a system that assists users in efficiently selecting local specialty products when using the Furusato Nozei (hometown tax donation) service. The system consists of a server, which is an information processing system, and terminals for direct user operation. The server runs on a suitable platform for implementing a generative AI model, which is used for selecting local specialty products.

[0425] The server first obtains user identification information using a security protocol when a user logs in. This identification information is stored in a database and collected by the server along with past transaction history. Transaction history is recorded through communication and payment technology and includes information such as past purchases and amounts spent.

[0426] The acquired data is input into a generative AI model, where product candidates are selected for the first time. Based on the identification information and transaction history, the generative AI model generates prompts such as "User's past purchase history: wine, seafood," and creates a list of local specialties that match the user's preferences.

[0427] The terminal displays a list of potential products sent from the server on the user interface. At this stage, the user can select a local specialty that suits their preferences and interests based on the displayed list. For example, if the server suggests locally renowned wines or fresh seafood based on past data, the user can easily select them.

[0428] This personalized selection process significantly reduces the time and effort users spend choosing products. The overall system aims to improve the convenience and customer satisfaction of the Furusato Nozei (hometown tax donation) program by providing a suggestion-based selection method utilizing a generative AI model.

[0429] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0430] Step 1:

[0431] The server obtains identification information when a user logs in. This input information includes a user ID and authentication token, and is sent to the server for security reasons. The server compares this identification information with the database to search for the user's past transaction history. The transaction history includes data such as past purchases, purchase dates, and amounts.

[0432] Step 2:

[0433] The server prepares to apply the generated AI model based on the acquired identification information and transaction history. Specifically, it processes the data to generate prompt messages that reflect the user's preferences. The user's past purchase history is used as input information. Based on this information, prompt messages such as "User's past purchase history: Wine, seafood" are generated. The generated prompt messages serve as the starting point for analysis by the AI ​​model.

[0434] Step 3:

[0435] The server inputs the generated prompt text into the AI ​​model and performs data calculations. Specifically, the AI ​​model calculates a list of item candidates that take user preferences into account based on the prompt text. The input is the prompt text, and the output is the generated list of specialty product candidates. This candidate list includes specialty products based on past usage history and trends.

[0436] Step 4:

[0437] The server sends a generated list of potential local products to the user's device. The device receives this list and displays it on the user interface. The user scrolls through the displayed list and selects local products that suit their interests and needs.

[0438] Step 5:

[0439] The user makes a selection from the displayed list of options. This involves tapping or clicking on a specific product on the device. The selected data is sent back to the server and used for order processing and history updates. The specialty product selected by the user then proceeds to the order process.

[0440] (Application Example 1)

[0441] 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."

[0442] When users utilize the Furusato Nozei (hometown tax donation) service, they face challenges in efficiently selecting the most suitable local products based on their preferences and past purchase history, resulting in time-consuming and cumbersome selection processes. Furthermore, there is difficulty in providing personalized product suggestions by leveraging users' past purchase data.

[0443] 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.

[0444] In this invention, the server includes means for acquiring user identification information, means for collecting the user's transaction history, means for applying a generative model that generates product candidates based on the acquired user identification information and transaction history, means for generating relevant product suggestions based on the user's past transaction history using a generative AI model, and means for displaying the suggested product list on the user's terminal. This makes it possible to personalize and suggest the most suitable local products to the user.

[0445] "User identification information" refers to information used to uniquely identify a specific user.

[0446] "Transaction history" refers to information that records details of purchases and transactions made by a user in the past.

[0447] A "generative model" is a computational algorithm used to create new information or patterns based on data.

[0448] A "generative AI model" is a model that uses artificial intelligence technology to make effective suggestions and predictions from user data.

[0449] "Personalization" refers to customizing specific information or services based on the individual user's preferences and behavioral patterns.

[0450] "Product candidates" are the options of products or services that may be offered to the user.

[0451] A "user terminal" is a device that a user directly operates and uses to receive information.

[0452] An "electronic payment system" is a mechanism that uses digital technology to allow people to pay for goods and services online.

[0453] The system implementing this invention is designed to personalize and suggest local specialty products for hometown tax donations to users based on their purchase history and preferences. The system consists of the following hardware and software.

[0454] The servers are built on cloud platforms, utilizing Amazon Web Services (AWS) and Google Cloud Platform (GCP). MySQL is used for database management, storing user identification information and transaction history. Google's TensorFlow is used for the generative AI model. The generative AI model predicts the most suitable local products based on the user's transaction history and creates a list of candidates.

[0455] A terminal is a device used by a user to receive information, such as a smartphone or personal computer. When a user logs in, the application on the terminal communicates with the server and sends the user's identification information. Based on this information, the server retrieves the user's past transaction data and creates a list of potential products using a generative AI model.

[0456] As a concrete example, consider a user who has previously purchased apples from Aomori Prefecture. This user will then be offered related products such as Aomori cider and apple jam as local specialties. This allows users to efficiently find local products that match their preferences.

[0457] An example of a prompt is: "Generate text that suggests additional local products based on the user's past purchase history. If the user has purchased apples from Aomori Prefecture, suggest a new product that uses those apples." This prompt allows the AI ​​model to generate specific product suggestions.

[0458] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0459] Step 1:

[0460] A user logs into an application on their smartphone or computer. During this process, the user's identification information is sent from the device to the server. The input is the user's login information, and the output is permission to communicate with the server.

[0461] Step 2:

[0462] The server retrieves the transaction history of the corresponding user from the database based on the received user identification information. In this step, the input is the user identification information, and the output is the user's transaction history data. The information is extracted using database queries.

[0463] Step 3:

[0464] The server inputs the acquired transaction history into a generating AI model to analyze user preferences and past purchase patterns. The input is the user's transaction history data, and the output is the analyzed preferences and patterns. TensorFlow is used to apply machine learning algorithms.

[0465] Step 4:

[0466] The generative AI model generates a list of optimal local specialty product candidates based on the analysis results. The input is the analyzed preferences and patterns, and the output is the list of specialty product candidates. The model performs inference and selects product candidates according to the prompt.

[0467] Step 5:

[0468] The server sends the generated list of specialty product candidates to the user's terminal. The input is the list of specialty product candidates, and the output is delivery to the user's terminal. The transfer of the list is performed using a data transmission protocol.

[0469] Step 6:

[0470] The user terminal displays the received list of local specialty product candidates on the application. The input is the list of local specialty product candidates sent from the server, and the output is the display on the user interface. The user can confirm the local specialty product through screen rendering.

[0471] 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.

[0472] The system of the present invention provides efficient, emotion-based, and personalized product suggestions to users of the Furusato Nozei (hometown tax donation) service. In addition to a generative model that generates product candidates based on user identification information and transaction history, this system incorporates an emotion engine that recognizes the user's emotions.

[0473] When a user logs into the service, the terminal sends user identification information and electronic payment history to the server. The server receives this information and uses a generative model to create initial product candidates tailored to the user's preferences. Next, the emotion engine analyzes the user's current emotional state from their facial expressions and voice, and combines this emotional data with the generative model to refine the optimal product candidate list.

[0474] For example, if a user has recently been feeling stressed, the emotion engine will prioritize adding products with relaxing effects (e.g., aromatherapy oils or massage devices) to the list. Based on the emotion recognition by the emotion engine, the service can flexibly change its product recommendations according to the user's emotional state.

[0475] The server sends a finalized list of product candidates to the user's terminal, and the user selects a product from that list. This allows the user to efficiently choose local products that match their emotions and preferences, and to comfortably proceed with the hometown tax donation process. In this way, the system of the present invention achieves advanced personalization by utilizing emotion recognition technology to improve the user experience.

[0476] The following describes the processing flow.

[0477] Step 1:

[0478] The user logs into the hometown tax donation service via their device. Using the login information, the device collects the user's identification information and begins sending data to the server.

[0479] Step 2:

[0480] The terminal sends user identification information, including Yahoo! ID and electronic payment history, to the server. The server receives this information and stores it in its database.

[0481] Step 3:

[0482] The server uses stored user identification information and transaction history to apply a generative model and generate an initial list of specialty products.

[0483] Step 4:

[0484] The user accesses the emotion engine through the device's camera and microphone. The emotion engine analyzes the user's facial expressions and voice information to identify their current emotional state.

[0485] Step 5:

[0486] The server uses emotion data obtained from the emotion engine to adjust the initial list of candidates that has been generated. The adjustment optimizes the list to prioritize products that match the user's emotions.

[0487] Step 6:

[0488] The server then creates a new list of product suggestions optimized based on the user's emotional state and provides it to the user's terminal.

[0489] Step 7:

[0490] The device displays a list of local specialty products to the user. The user selects a product from the displayed list that matches their feelings and preferences, and then proceeds with the hometown tax donation process.

[0491] Step 8:

[0492] To complete the tax payment process for the selected items, the terminal sends the necessary information to the server and concludes the process. The user's selection is complete, and satisfactory items are chosen.

[0493] (Example 2)

[0494] 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."

[0495] Traditional hometown tax donation services offered product suggestions based on user preferences, but they lacked sufficient personalization that considered the user's current emotional state, resulting in a limited user experience. Furthermore, conventional systems struggled to provide appropriate product suggestions that reflected the user's emotions, such as stress or relaxation.

[0496] 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.

[0497] In this invention, the server includes means for acquiring user identification information, means for collecting the user's transaction history, means for generating product candidates by applying a generative model, means for acquiring emotional data using an emotional engine and adjusting the product candidate list, and means for providing the generated product candidate list to the user terminal. This enables personalized product suggestions based on the user's preferences and emotional state.

[0498] An "information processing device" is a device that acquires, processes, and analyzes data to provide useful information to users.

[0499] "User identification information" refers to identification data used to recognize a specific user, and includes user IDs and authentication tokens.

[0500] "Transaction history" refers to records of purchases and payments made by a user in the past.

[0501] A "generative model" is a model that uses machine learning algorithms to suggest products based on user preferences.

[0502] An "emotion engine" is a software component that analyzes a user's emotional state from their facial expressions and voice.

[0503] A "product candidate list" is a list of products selected to be proposed to users.

[0504] An "electronic payment system" is a digital payment system used to record a user's payment history.

[0505] A "user terminal" refers to an electronic device that the user directly operates, and includes PCs, smartphones, and other similar devices.

[0506] This invention utilizes a system centered around an information processing device. The user first logs into the hometown tax donation service using a terminal. At this time, the terminal obtains user identification information and electronic payment history and transmits them to the server.

[0507] The server uses the received user identification information and transaction history to apply a generative AI model utilizing machine learning frameworks such as TensorFlow and PyTorch to generate product candidates tailored to the user's preferences. The prompt message used for this process might be something like, "Analyze the user's preferences based on their past purchase history and suggest relevant products."

[0508] Next, the user's device uses its camera and microphone to capture the user's facial expressions and voice in real time, which are then analyzed by an emotion engine. The emotion engine uses OpenCV to analyze facial expressions and voice analysis software to evaluate voice data, thereby understanding the user's emotional state. This emotion data is sent to a server and combined with a generative AI model to adjust the product candidate list.

[0509] For example, if a user is feeling stressed, the server can prioritize including products with relaxing effects, such as aromatherapy oils or massage devices, in the list. Finally, the server returns the adjusted list of product suggestions to the user's terminal, and the user selects the desired product from that list.

[0510] This system allows users to efficiently and comfortably select products that match their preferences and feelings, and to smoothly complete the process of making hometown tax donations.

[0511] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0512] Step 1:

[0513] The user logs into the hometown tax donation service using their device. The device retrieves user identification information and electronic payment history and sends it to the server. This input data includes the user ID and past electronic payment history.

[0514] Step 2:

[0515] The server uses user identification information and transaction history received from the terminal as input to generate product candidates using a machine learning model. The generation AI model uses TensorFlow and PyTorch, and generates an initial list of specialty product candidates based on the user's past transaction data. This list is then output.

[0516] Step 3:

[0517] The user's device uses its built-in camera and microphone to capture the user's facial expressions and voice. This data is sent to a server in the form of image and audio data for sentiment analysis.

[0518] Step 4:

[0519] The server utilizes an emotion engine to analyze the received image and audio data. It processes information obtained from facial expressions using OpenCV and audio data obtained using voice analysis software. Through this process, the user's current emotional state is identified and output as emotion data.

[0520] Step 5:

[0521] The server provides emotional data as input to the generating AI model, which then readjusts the initial list of candidate products. Based on the emotional data, products that are appropriate to the user's current state are prioritized in the list. This adjusted product list is then output.

[0522] Step 6:

[0523] Finally, the server sends the adjusted list of product candidates to the user's terminal. The user reviews this list on their terminal and selects the desired product.

[0524] (Application Example 2)

[0525] 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."

[0526] In modern e-commerce, users are often overwhelmed by the sheer number of choices available, and it's particularly difficult for them to receive optimal product recommendations tailored to their current emotional state. Furthermore, there is no system that efficiently provides personalized product recommendations that take user emotions into account. Solving this challenge and improving the user experience is crucial.

[0527] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0528] In this invention, the server includes means for acquiring user identification information, means for collecting the user's transaction history, means for applying a generation function that generates product candidates based on the acquired user identification information and the collected transaction history, means for analyzing the user's emotional state from their facial expressions and voice using an emotion analysis function, means for adjusting the generated product candidate list based on the emotional state, and means for providing the adjusted product candidate list to the user's device. This enables highly personalized product suggestions based on the user's preferences and emotional state.

[0529] "User identification information" refers to information used to uniquely identify a specific user.

[0530] "Transaction history" refers to information that shows the history of e-commerce transactions and payments that a user has made in the past.

[0531] The "generation function" is a technology that automatically creates product candidates based on the user's identification information and transaction history.

[0532] "Emotion analysis function" is a technology that analyzes the user's facial expressions and voice to understand their emotional state at that time.

[0533] A "product candidate list" is a collection of products suggested to the user, and is created using a generation function.

[0534] "User equipment" refers to information terminals or devices used by users, specifically those used to display a list of product candidates.

[0535] "Personalized product suggestions" refer to unique product suggestions tailored to the individual preferences and emotional state of the user.

[0536] The system for realizing this invention includes a user terminal, a server, and a computing environment equipped with the necessary analytical functions. Its outline is described below.

[0537] First, a smartphone is used as the user's terminal. The smartphone is equipped with a camera and microphone, and these sensors are used to capture the user's facial expressions and voice. The acquired data is sent to the emotion analysis function. Emotion analysis uses facial recognition technology with TensorFlow and voice analysis technology with PyTorch.

[0538] The server receives user identification information and electronic payment history, and uses a generative AI model to generate an initial list of specialty product candidates. This generative AI model uses machine learning algorithms to analyze the user's past preferences and selection patterns, listing the most relevant products. The generated list is then refined in combination with analyzed sentiment data. For example, if the user indicates a desire to relax, aromatherapy oils and relaxation products will be given higher priority.

[0539] The finalized list of product candidates is provided to the user's terminal, from which the user can select a product. In this way, personalized product suggestions based on emotional state become possible.

[0540] For example, if a user receives the prompt "Tell us how you've been feeling lately. What kind of products are you looking for?", and the user answers "I'm tired," that emotion will be analyzed, and relaxation products will be moved to the top of the list.

[0541] With the above configuration, this invention can provide flexible product suggestions that adapt to the user's current emotions, thereby improving the user experience.

[0542] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0543] Step 1:

[0544] The user terminal acquires the user's facial expressions and voice data. It uses a camera and microphone as inputs, collecting real-time data from these sensors. The output consists of video and audio data.

[0545] Step 2:

[0546] The user terminal sends the acquired facial expressions and audio data to the server. In this transmission process, the terminal compresses the data and sends it to the server via a secure network. The input is the video and audio data acquired earlier, and the output is the data ready for use on the server.

[0547] Step 3:

[0548] The server applies emotion analysis functionality to analyze the user's emotional state from the transmitted data. It uses TensorFlow for facial recognition and PyTorch for voice analysis to analyze the user's facial expressions and voice. The input is the data received in step 2, and the output is the analyzed emotion information.

[0549] Step 4:

[0550] The server retrieves user identification information and electronic payment history, and generates a list of product candidates using a generative AI model. At this stage, the user's past purchase history and preferences are taken into consideration. The input is user identification information and electronic payment history, and the output is the generated initial list of product candidates.

[0551] Step 5:

[0552] Based on the results of the emotion analysis, the server adjusts the generated list of candidate products. If an emotion indicating a desire for relaxation is detected, relaxation products are prioritized. This process is performed by data calculations combining emotion information and the candidate product list. The input is emotion information and the initial candidate product list, and the output is an optimized candidate product list.

[0553] Step 6:

[0554] The server sends an optimized list of product candidates to the user's terminal. The input is the optimized list of product candidates, and the output is a product list converted into a format that can be displayed on the user's terminal.

[0555] Step 7:

[0556] The user terminal presents the user with a list of received product candidates. The user can select a product from the provided list and make a decision. The input is the product list sent from the server, and the output is the selection information based on the user's decision.

[0557] 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.

[0558] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0559] 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.

[0560] [Fourth Embodiment]

[0561] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0562] 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.

[0563] 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).

[0564] 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.

[0565] 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.

[0566] 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).

[0567] 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.

[0568] 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.

[0569] 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.

[0570] 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.

[0571] 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.

[0572] 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.

[0573] 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".

[0574] The present invention's system assists users in efficiently selecting the most suitable local specialty products when using the Furusato Nozei (hometown tax donation) service. This system uses an information processing device to utilize user identification information and transaction history to generate a list of optimal product candidates. Specifically, a server collects user identification information and transaction history, and proposes candidate local specialty products using a generative model.

[0575] When a user logs in, their device communicates with the server to send and receive necessary information. The server applies a generative model based on the user's preferences and past transaction data to create a list of specialty products best suited to the user. This list is displayed on the user's device, and the user makes a selection based on it.

[0576] For example, if a user has previously purchased wine using electronic payment, the server will use this information to suggest high-quality local wines as specialty products. This allows users to easily find products that suit their interests, significantly reducing the time and effort required for selection. Another example is when a user who frequently purchases seafood is suggested fresh, locally sourced seafood.

[0577] In this way, the system of the present invention enhances the user experience by providing personalized suggestions using data, thereby improving the convenience of the hometown tax donation system.

[0578] The following describes the processing flow.

[0579] Step 1:

[0580] The user logs into the Furusato Nozei (hometown tax donation) service using their device. Upon login, the device initiates a process to link the user's Yahoo! ID with their electronic payment-related accounts, with the user's consent.

[0581] Step 2:

[0582] The device sends the Yahoo! ID and recent electronic payment transaction history to the server. This allows the server to receive the user's individual information.

[0583] Step 3:

[0584] The server stores the received user identification information and transaction history in a database. This allows for the management of each user's data.

[0585] Step 4:

[0586] The server provides the stored data as input to a generative model for analysis. The generative model then calculates product candidates that take user preferences into account.

[0587] Step 5:

[0588] The server sends the generated list of potential products to the user's terminal. This list includes local specialties tailored to the user's needs.

[0589] Step 6:

[0590] The terminal displays a list of the local specialty products the user has received. The user selects their desired product from the displayed list of options and proceeds with the hometown tax donation process.

[0591] Step 7:

[0592] Once the user completes their selection, the device notifies the server of the final tax payment procedures and proceeds with the necessary steps. This completes the tax payment process.

[0593] (Example 1)

[0594] 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".

[0595] When users utilize the Furusato Nozei (hometown tax donation) service, a challenge arises in efficiently selecting the most suitable products that match their preferences and interests from a vast array of local specialties. In particular, the time-consuming and laborious process of discovering products based on past transaction history and preferences is a significant problem.

[0596] 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.

[0597] In this invention, the server includes means for acquiring identification information, means for collecting transaction history, and means for applying a generative model based on the acquired identification information and collected transaction history to generate candidate items. This makes it possible to efficiently suggest specialty products that match the user's preferences from a vast number of products, and to significantly reduce the time and effort required for selection.

[0598] An "information processing system" is a system consisting of devices or networks that collect, process, analyze, and output data.

[0599] "Identification information" refers to information used to identify individual users, including user IDs and other individual identifiers.

[0600] "Transaction history" refers to a record of purchases and contracts made by a user in the past, and usually includes detailed information such as the date, product name, and amount.

[0601] A "generative model" is an algorithm or framework that generates results or predictions from input data based on machine learning or statistical methods.

[0602] "Product candidates" are a list of products that should be suggested to the user, and are selected based on the user's preferences and past history.

[0603] A "device" is an electronic device that a user directly operates, and includes computers, smartphones, and tablets.

[0604] "Personalization" is the process of optimizing content and suggestions based on the preferences and needs of individual users.

[0605] This invention is a system that assists users in efficiently selecting local specialty products when using the Furusato Nozei (hometown tax donation) service. The system consists of a server, which is an information processing system, and terminals for direct user operation. The server runs on a suitable platform for implementing a generative AI model, which is used for selecting local specialty products.

[0606] The server first obtains user identification information using a security protocol when a user logs in. This identification information is stored in a database and collected by the server along with past transaction history. Transaction history is recorded through communication and payment technology and includes information such as past purchases and amounts spent.

[0607] The acquired data is input into a generative AI model, where product candidates are selected for the first time. Based on the identification information and transaction history, the generative AI model generates prompts such as "User's past purchase history: wine, seafood," and creates a list of local specialties that match the user's preferences.

[0608] The terminal displays a list of potential products sent from the server on the user interface. At this stage, the user can select a local specialty that suits their preferences and interests based on the displayed list. For example, if the server suggests locally renowned wines or fresh seafood based on past data, the user can easily select them.

[0609] This personalized selection process significantly reduces the time and effort users spend choosing products. The overall system aims to improve the convenience and customer satisfaction of the Furusato Nozei (hometown tax donation) program by providing a suggestion-based selection method utilizing a generative AI model.

[0610] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0611] Step 1:

[0612] The server obtains identification information when a user logs in. This input information includes a user ID and authentication token, and is sent to the server for security reasons. The server compares this identification information with the database to search for the user's past transaction history. The transaction history includes data such as past purchases, purchase dates, and amounts.

[0613] Step 2:

[0614] The server prepares to apply the generated AI model based on the acquired identification information and transaction history. Specifically, it processes the data to generate prompt messages that reflect the user's preferences. The user's past purchase history is used as input information. Based on this information, prompt messages such as "User's past purchase history: Wine, seafood" are generated. The generated prompt messages serve as the starting point for analysis by the AI ​​model.

[0615] Step 3:

[0616] The server inputs the generated prompt text into the AI ​​model and performs data calculations. Specifically, the AI ​​model calculates a list of item candidates that take user preferences into account based on the prompt text. The input is the prompt text, and the output is the generated list of specialty product candidates. This candidate list includes specialty products based on past usage history and trends.

[0617] Step 4:

[0618] The server sends a generated list of potential local products to the user's device. The device receives this list and displays it on the user interface. The user scrolls through the displayed list and selects local products that suit their interests and needs.

[0619] Step 5:

[0620] The user makes a selection from the displayed list of options. This involves tapping or clicking on a specific product on the device. The selected data is sent back to the server and used for order processing and history updates. The specialty product selected by the user then proceeds to the order process.

[0621] (Application Example 1)

[0622] 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".

[0623] When users utilize the Furusato Nozei (hometown tax donation) service, they face challenges in efficiently selecting the most suitable local products based on their preferences and past purchase history, resulting in time-consuming and cumbersome selection processes. Furthermore, there is difficulty in providing personalized product suggestions by leveraging users' past purchase data.

[0624] 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.

[0625] In this invention, the server includes means for acquiring user identification information, means for collecting the user's transaction history, means for applying a generative model that generates product candidates based on the acquired user identification information and transaction history, means for generating relevant product suggestions based on the user's past transaction history using a generative AI model, and means for displaying the suggested product list on the user's terminal. This makes it possible to personalize and suggest the most suitable local products to the user.

[0626] "User identification information" refers to information used to uniquely identify a specific user.

[0627] "Transaction history" refers to information that records details of purchases and transactions made by a user in the past.

[0628] A "generative model" is a computational algorithm used to create new information or patterns based on data.

[0629] A "generative AI model" is a model that uses artificial intelligence technology to make effective suggestions and predictions from user data.

[0630] "Personalization" refers to customizing specific information or services based on the individual user's preferences and behavioral patterns.

[0631] "Product candidates" are the options of products or services that may be offered to the user.

[0632] A "user terminal" is a device that a user directly operates and uses to receive information.

[0633] An "electronic payment system" is a mechanism that uses digital technology to allow people to pay for goods and services online.

[0634] The system implementing this invention is designed to personalize and suggest local specialty products for hometown tax donations to users based on their purchase history and preferences. The system consists of the following hardware and software.

[0635] The servers are built on cloud platforms, utilizing Amazon Web Services (AWS) and Google Cloud Platform (GCP). MySQL is used for database management, storing user identification information and transaction history. Google's TensorFlow is used for the generative AI model. The generative AI model predicts the most suitable local products based on the user's transaction history and creates a list of candidates.

[0636] A terminal is a device used by a user to receive information, such as a smartphone or personal computer. When a user logs in, the application on the terminal communicates with the server and sends the user's identification information. Based on this information, the server retrieves the user's past transaction data and creates a list of potential products using a generative AI model.

[0637] As a concrete example, consider a user who has previously purchased apples from Aomori Prefecture. This user will then be offered related products such as Aomori cider and apple jam as local specialties. This allows users to efficiently find local products that match their preferences.

[0638] An example of a prompt is: "Generate text that suggests additional local products based on the user's past purchase history. If the user has purchased apples from Aomori Prefecture, suggest a new product that uses those apples." This prompt allows the AI ​​model to generate specific product suggestions.

[0639] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0640] Step 1:

[0641] A user logs into an application on their smartphone or computer. During this process, the user's identification information is sent from the device to the server. The input is the user's login information, and the output is permission to communicate with the server.

[0642] Step 2:

[0643] The server retrieves the transaction history of the corresponding user from the database based on the received user identification information. In this step, the input is the user identification information, and the output is the user's transaction history data. The information is extracted using database queries.

[0644] Step 3:

[0645] The server inputs the acquired transaction history into a generating AI model to analyze user preferences and past purchase patterns. The input is the user's transaction history data, and the output is the analyzed preferences and patterns. TensorFlow is used to apply machine learning algorithms.

[0646] Step 4:

[0647] The generative AI model generates a list of optimal local specialty product candidates based on the analysis results. The input is the analyzed preferences and patterns, and the output is the list of specialty product candidates. The model performs inference and selects product candidates according to the prompt.

[0648] Step 5:

[0649] The server sends the generated list of specialty product candidates to the user's terminal. The input is the list of specialty product candidates, and the output is delivery to the user's terminal. The transfer of the list is performed using a data transmission protocol.

[0650] Step 6:

[0651] The user terminal displays the received list of local specialty product candidates on the application. The input is the list of local specialty product candidates sent from the server, and the output is the display on the user interface. The user can confirm the local specialty product through screen rendering.

[0652] 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.

[0653] The system of the present invention provides efficient, emotion-based, and personalized product suggestions to users of the Furusato Nozei (hometown tax donation) service. In addition to a generative model that generates product candidates based on user identification information and transaction history, this system incorporates an emotion engine that recognizes the user's emotions.

[0654] When a user logs into the service, the terminal sends user identification information and electronic payment history to the server. The server receives this information and uses a generative model to create initial product candidates tailored to the user's preferences. Next, the emotion engine analyzes the user's current emotional state from their facial expressions and voice, and combines this emotional data with the generative model to refine the optimal product candidate list.

[0655] For example, if a user has recently been feeling stressed, the emotion engine will prioritize adding products with relaxing effects (e.g., aromatherapy oils or massage devices) to the list. Based on the emotion recognition by the emotion engine, the service can flexibly change its product recommendations according to the user's emotional state.

[0656] The server sends a finalized list of product candidates to the user's terminal, and the user selects a product from that list. This allows the user to efficiently choose local products that match their emotions and preferences, and to comfortably proceed with the hometown tax donation process. In this way, the system of the present invention achieves advanced personalization by utilizing emotion recognition technology to improve the user experience.

[0657] The following describes the processing flow.

[0658] Step 1:

[0659] The user logs into the hometown tax donation service via their device. Using the login information, the device collects the user's identification information and begins sending data to the server.

[0660] Step 2:

[0661] The terminal sends user identification information, including Yahoo! ID and electronic payment history, to the server. The server receives this information and stores it in its database.

[0662] Step 3:

[0663] The server uses stored user identification information and transaction history to apply a generative model and generate an initial list of specialty products.

[0664] Step 4:

[0665] The user accesses the emotion engine through the device's camera and microphone. The emotion engine analyzes the user's facial expressions and voice information to identify their current emotional state.

[0666] Step 5:

[0667] The server uses emotion data obtained from the emotion engine to adjust the initial list of candidates that has been generated. The adjustment optimizes the list to prioritize products that match the user's emotions.

[0668] Step 6:

[0669] The server then creates a new list of product suggestions optimized based on the user's emotional state and provides it to the user's terminal.

[0670] Step 7:

[0671] The device displays a list of local specialty products to the user. The user selects a product from the displayed list that matches their feelings and preferences, and then proceeds with the hometown tax donation process.

[0672] Step 8:

[0673] To complete the tax payment process for the selected items, the terminal sends the necessary information to the server and concludes the process. The user's selection is complete, and satisfactory items are chosen.

[0674] (Example 2)

[0675] 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".

[0676] Traditional hometown tax donation services offered product suggestions based on user preferences, but they lacked sufficient personalization that considered the user's current emotional state, resulting in a limited user experience. Furthermore, conventional systems struggled to provide appropriate product suggestions that reflected the user's emotions, such as stress or relaxation.

[0677] 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.

[0678] In this invention, the server includes means for acquiring user identification information, means for collecting the user's transaction history, means for generating product candidates by applying a generative model, means for acquiring emotional data using an emotional engine and adjusting the product candidate list, and means for providing the generated product candidate list to the user terminal. This enables personalized product suggestions based on the user's preferences and emotional state.

[0679] An "information processing device" is a device that acquires, processes, and analyzes data to provide useful information to users.

[0680] "User identification information" refers to identification data used to recognize a specific user, and includes user IDs and authentication tokens.

[0681] "Transaction history" refers to records of purchases and payments made by a user in the past.

[0682] A "generative model" is a model that uses machine learning algorithms to suggest products based on user preferences.

[0683] An "emotion engine" is a software component that analyzes a user's emotional state from their facial expressions and voice.

[0684] A "product candidate list" is a list of products selected to be proposed to users.

[0685] An "electronic payment system" is a digital payment system used to record a user's payment history.

[0686] A "user terminal" refers to an electronic device that the user directly operates, and includes PCs, smartphones, and other similar devices.

[0687] This invention utilizes a system centered around an information processing device. The user first logs into the hometown tax donation service using a terminal. At this time, the terminal obtains user identification information and electronic payment history and transmits them to the server.

[0688] The server uses the received user identification information and transaction history to apply a generative AI model utilizing machine learning frameworks such as TensorFlow and PyTorch to generate product candidates tailored to the user's preferences. The prompt message used for this process might be something like, "Analyze the user's preferences based on their past purchase history and suggest relevant products."

[0689] Next, the user's device uses its camera and microphone to capture the user's facial expressions and voice in real time, which are then analyzed by an emotion engine. The emotion engine uses OpenCV to analyze facial expressions and voice analysis software to evaluate voice data, thereby understanding the user's emotional state. This emotion data is sent to a server and combined with a generative AI model to adjust the product candidate list.

[0690] For example, if a user is feeling stressed, the server can prioritize including products with relaxing effects, such as aromatherapy oils or massage devices, in the list. Finally, the server returns the adjusted list of product suggestions to the user's terminal, and the user selects the desired product from that list.

[0691] This system allows users to efficiently and comfortably select products that match their preferences and feelings, and to smoothly complete the process of making hometown tax donations.

[0692] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0693] Step 1:

[0694] The user logs into the hometown tax donation service using their device. The device retrieves user identification information and electronic payment history and sends it to the server. This input data includes the user ID and past electronic payment history.

[0695] Step 2:

[0696] The server uses user identification information and transaction history received from the terminal as input to generate product candidates using a machine learning model. The generation AI model uses TensorFlow and PyTorch, and generates an initial list of specialty product candidates based on the user's past transaction data. This list is then output.

[0697] Step 3:

[0698] The user's device uses its built-in camera and microphone to capture the user's facial expressions and voice. This data is sent to a server in the form of image and audio data for sentiment analysis.

[0699] Step 4:

[0700] The server utilizes an emotion engine to analyze the received image and audio data. It processes information obtained from facial expressions using OpenCV and audio data obtained using voice analysis software. Through this process, the user's current emotional state is identified and output as emotion data.

[0701] Step 5:

[0702] The server provides emotional data as input to the generating AI model, which then readjusts the initial list of candidate products. Based on the emotional data, products that are appropriate to the user's current state are prioritized in the list. This adjusted product list is then output.

[0703] Step 6:

[0704] Finally, the server sends the adjusted list of product candidates to the user's terminal. The user reviews this list on their terminal and selects the desired product.

[0705] (Application Example 2)

[0706] 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".

[0707] In modern e-commerce, users are often overwhelmed by the sheer number of choices available, and it's particularly difficult for them to receive optimal product recommendations tailored to their current emotional state. Furthermore, there is no system that efficiently provides personalized product recommendations that take user emotions into account. Solving this challenge and improving the user experience is crucial.

[0708] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0709] In this invention, the server includes means for acquiring user identification information, means for collecting the user's transaction history, means for applying a generation function that generates product candidates based on the acquired user identification information and the collected transaction history, means for analyzing the user's emotional state from their facial expressions and voice using an emotion analysis function, means for adjusting the generated product candidate list based on the emotional state, and means for providing the adjusted product candidate list to the user's device. This enables highly personalized product suggestions based on the user's preferences and emotional state.

[0710] "User identification information" refers to information used to uniquely identify a specific user.

[0711] "Transaction history" refers to information that shows the history of e-commerce transactions and payments that a user has made in the past.

[0712] The "generation function" is a technology that automatically creates product candidates based on the user's identification information and transaction history.

[0713] "Emotion analysis function" is a technology that analyzes the user's facial expressions and voice to understand their emotional state at that time.

[0714] A "product candidate list" is a collection of products suggested to the user, and is created using a generation function.

[0715] "User equipment" refers to information terminals or devices used by users, specifically those used to display a list of product candidates.

[0716] "Personalized product suggestions" refer to unique product suggestions tailored to the individual preferences and emotional state of the user.

[0717] The system for realizing this invention includes a user terminal, a server, and a computing environment equipped with the necessary analytical functions. Its outline is described below.

[0718] First, a smartphone is used as the user's terminal. The smartphone is equipped with a camera and microphone, and these sensors are used to capture the user's facial expressions and voice. The acquired data is sent to the emotion analysis function. Emotion analysis uses facial recognition technology with TensorFlow and voice analysis technology with PyTorch.

[0719] The server receives user identification information and electronic payment history, and uses a generative AI model to generate an initial list of specialty product candidates. This generative AI model uses machine learning algorithms to analyze the user's past preferences and selection patterns, listing the most relevant products. The generated list is then refined in combination with analyzed sentiment data. For example, if the user indicates a desire to relax, aromatherapy oils and relaxation products will be given higher priority.

[0720] The finalized list of product candidates is provided to the user's terminal, from which the user can select a product. In this way, personalized product suggestions based on emotional state become possible.

[0721] For example, if a user receives the prompt "Tell us how you've been feeling lately. What kind of products are you looking for?", and the user answers "I'm tired," that emotion will be analyzed, and relaxation products will be moved to the top of the list.

[0722] With the above configuration, this invention can provide flexible product suggestions that adapt to the user's current emotions, thereby improving the user experience.

[0723] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0724] Step 1:

[0725] The user terminal acquires the user's facial expressions and voice data. It uses a camera and microphone as inputs, collecting real-time data from these sensors. The output consists of video and audio data.

[0726] Step 2:

[0727] The user terminal sends the acquired facial expressions and audio data to the server. In this transmission process, the terminal compresses the data and sends it to the server via a secure network. The input is the video and audio data acquired earlier, and the output is the data ready for use on the server.

[0728] Step 3:

[0729] The server applies emotion analysis functionality to analyze the user's emotional state from the transmitted data. It uses TensorFlow for facial recognition and PyTorch for voice analysis to analyze the user's facial expressions and voice. The input is the data received in step 2, and the output is the analyzed emotion information.

[0730] Step 4:

[0731] The server retrieves user identification information and electronic payment history, and generates a list of product candidates using a generative AI model. At this stage, the user's past purchase history and preferences are taken into consideration. The input is user identification information and electronic payment history, and the output is the generated initial list of product candidates.

[0732] Step 5:

[0733] Based on the results of the emotion analysis, the server adjusts the generated list of candidate products. If an emotion indicating a desire for relaxation is detected, relaxation products are prioritized. This process is performed by data calculations combining emotion information and the candidate product list. The input is emotion information and the initial candidate product list, and the output is an optimized candidate product list.

[0734] Step 6:

[0735] The server sends an optimized list of product candidates to the user's terminal. The input is the optimized list of product candidates, and the output is a product list converted into a format that can be displayed on the user's terminal.

[0736] Step 7:

[0737] The user terminal presents the user with a list of received product candidates. The user can select a product from the provided list and make a decision. The input is the product list sent from the server, and the output is the selection information based on the user's decision.

[0738] 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.

[0739] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0740] 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.

[0741] 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.

[0742] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0743] 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.

[0744] 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.

[0745] 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.

[0746] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0747] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0748] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0749] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0750] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0751] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0752] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0753] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0754] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0755] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0756] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0757] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0758] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0759] The following is further disclosed regarding the embodiments described above.

[0760] (Claim 1)

[0761] In an information processing device, means for acquiring user identification information,

[0762] Means for collecting user transaction history,

[0763] A means for applying a generative model that generates product candidates based on acquired user identification information and collected transaction history,

[0764] A means of providing the generated list of product candidates to the user terminal,

[0765] A system that includes this.

[0766] (Claim 2)

[0767] The system according to claim 1, wherein the user's transaction history is a history recorded by an electronic payment system.

[0768] (Claim 3)

[0769] The system according to claim 1, wherein a list of product candidates is personalized and displayed based on the user's preferences.

[0770] "Example 1"

[0771] (Claim 1)

[0772] In an information processing system, means for acquiring identification information,

[0773] Means of collecting transaction history,

[0774] A means for applying a generative model to generate candidate items based on acquired identification information and collected transaction history,

[0775] A means for providing the generated list of candidate items to the terminal,

[0776] A means of making a selection based on a list of item candidates displayed on the user's terminal,

[0777] A system that includes this.

[0778] (Claim 2)

[0779] The system according to claim 1, wherein the transaction history is a history recorded by communication settlement technology.

[0780] (Claim 3)

[0781] The system according to claim 1, wherein a list of potential items is presented in an individualized manner based on the user's preferences.

[0782] "Application Example 1"

[0783] (Claim 1)

[0784] Means for obtaining user identification information,

[0785] Means for collecting user transaction history,

[0786] A means for applying a generative model that generates product candidates based on acquired user identification information and collected transaction history,

[0787] A means of providing the generated list of product candidates to the user terminal,

[0788] A means for generating relevant product suggestions based on a user's past transaction history using a generative AI model,

[0789] A means of displaying the proposed product list on the user's terminal,

[0790] A system that includes this.

[0791] (Claim 2)

[0792] The system according to claim 1, wherein the user's transaction history is a history recorded by an electronic payment system, and includes product suggestions based on a generative AI model.

[0793] (Claim 3)

[0794] The system according to claim 1, in which a list of product candidates is personalized based on the user's preferences and displayed using a generative AI model.

[0795] "Example 2 of combining an emotion engine"

[0796] (Claim 1)

[0797] In an information processing device, means for acquiring user identification information,

[0798] Means for collecting user transaction history,

[0799] A means for applying a generative model that generates product candidates based on acquired user identification information and collected transaction history,

[0800] A means of acquiring emotional data using an emotion engine that analyzes the user's emotional state and adjusting the product candidate list,

[0801] A means of providing the generated list of product candidates to the user terminal,

[0802] A system that includes this.

[0803] (Claim 2)

[0804] The system according to claim 1, wherein the user's transaction history is a history recorded by an electronic payment system, and the user's emotional state is analyzed from image and audio data.

[0805] (Claim 3)

[0806] The system according to claim 1, wherein a list of product candidates is personalized and displayed based on the user's preferences and emotional state.

[0807] "Application example 2 when combining with an emotional engine"

[0808] (Claim 1)

[0809] Means for obtaining user identification information,

[0810] Means for collecting user transaction history,

[0811] A means for applying a generation function that generates product candidates based on acquired user identification information and collected transaction history,

[0812] A means of analyzing the user's emotional state from their facial expressions and voice using an emotion analysis function,

[0813] A means of adjusting the generated list of product candidates based on emotional state,

[0814] Means for providing a user device with a refined list of candidate products,

[0815] A system that includes this.

[0816] (Claim 2)

[0817] The system according to claim 1, wherein the user's transaction history is a history recorded by an electronic payment method.

[0818] (Claim 3)

[0819] The system according to claim 1, wherein a list of product candidates is personalized and displayed based on the user's preferences and emotional state. [Explanation of Symbols]

[0820] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. In an information processing device, means for acquiring user identification information, Means for collecting user transaction history, A means for applying a generative model that generates product candidates based on acquired user identification information and collected transaction history, A means of providing the generated list of product candidates to the user terminal, A system that includes this.

2. The system according to claim 1, wherein the user's transaction history is a history recorded by an electronic payment system.

3. The system according to claim 1, wherein a list of product candidates is personalized and displayed based on the user's preferences.

Images