System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving financial data input from a user; means for automatically updating a household account book based on the financial data; means for classifying and analyzing the updated household account book data; means for providing a saving suggestion to the user based on the analysis result; means for estimating an item that needs to be reordered based on a use frequency and a purchase history of daily necessities; and means for automatically ordering the estimated item in association with an online shopping platform.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In modern society, managing household finances and purchasing daily necessities are time-consuming and labor-intensive tasks. In many households, especially those with both spouses working, recording and analyzing household finances, ascertaining and purchasing necessities, can be cumbersome, resulting in oversights and wasteful spending. Furthermore, reordering daily necessities based on frequency of use and purchase history is time-consuming, making it difficult to secure supplies in a timely and efficient manner. Furthermore, it is difficult to provide customized shopping lists and money-saving suggestions tailored to each user's lifestyle and preferences. To address these challenges, a system is needed that enables efficient and optimal household finances and daily necessities management. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for receiving financial data entered by a user, a means for automatically updating a household ledger based on the financial data, a means for classifying and analyzing the updated household ledger data, and a means for providing the user with savings suggestions based on the analysis results. The system further includes a means for predicting items that need to be reordered based on the frequency of use and purchase history of daily necessities, and a means for automatically ordering the predicted items in cooperation with an online shopping platform. The system further includes a means for learning the user's preferences and lifestyle patterns and generating individually customized shopping lists and savings suggestions based thereon, and a means for utilizing a generative artificial intelligence model to respond to the user's questions and provide advice in real time. In this way, a system is provided that efficiently and optimally supports household management and automatic ordering of daily necessities.

[0006] "User" refers to an individual or organization that uses this System.

[0007] "Financial Data" means income, expenses, and associated transaction information relating to a User.

[0008] A "household account book" is a ledger used to record and manage a user's income and expenses.

[0009] "Update" means adding new information and updating existing information.

[0010] "Classification" refers to the act of separating collected data into specific categories or groups.

[0011] "Analysis" is the act of processing collected data to discover meaningful information and trends.

[0012] "Savings Suggestions" refers to specific advice to help users reduce their spending.

[0013] "Frequency of use" refers to how often a particular product or service is used.

[0014] "Purchase History" means a record of goods and services purchased by a User in the past.

[0015] "Reordering" refers to the act of ordering goods or services that have been previously purchased.

[0016] "Estimation" is the act of predicting future events or needs based on existing data.

[0017] "Online shopping platform" means a website or application for buying and selling goods and services over the Internet.

[0018] "Customization" is the act of tailoring a system or service to the preferences and requirements of an individual user.

[0019] A "generative artificial intelligence model" refers to an AI system that can learn from large amounts of data and generate, predict, and respond to new information. [Brief explanation of the drawings]

[0020] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6]FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0021] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0022] First, the terms used in the following description will be explained.

[0023] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0024] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0025] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0026] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0027] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 1, a 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.

[0031] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0032] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0033] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0034] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0035] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0038] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0039] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0040] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0041] This invention is a system that automates and streamlines the tedious tasks of managing household finances and purchasing everyday items. The system receives financial data entered by the user, automatically updates the household ledger based on that data, and also provides the functionality of categorizing and analyzing expenditures. This allows users to easily manage their expenditures. It also predicts items that need to be reordered based on the frequency of use and purchase history of everyday items, and automatically places orders in conjunction with an online shopping platform. These functions allow users to continuously obtain the items they need without missing them.

[0042] System configuration and functions

[0043] 1. Receiving financial data and updating your household accounts:

[0044] Server: Receives financial data entered by the user, including income, expenses, and transaction information.

[0045] Server: Automatically updates the household ledger based on the received data. This update includes adding new transactions and modifying existing transactions.

[0046] 2. Expenditure classification and analysis:

[0047] Server: Categorizes the updated household accounting data by category, such as food, transportation, entertainment, etc.

[0048] Server: Analyzes the categorized spending data to understand user spending patterns, including calculating totals, averages, frequency, etc.

[0049] 3. Providing savings offers:

[0050] Server: Based on the analysis of spending patterns, the server provides users with savings suggestions. For example, if spending in a particular category is high, the server provides advice on reducing spending in that category.

[0051] 4. Reorder Estimation and Execution:

[0052] Server: Based on the frequency of use and purchase history of everyday items, it estimates what items need to be reordered. Examples include paper or plastic consumables and food.

[0053] Server: Connects to online shopping platforms and automatically places orders for the estimated items, allowing users to obtain the items they need in a timely manner.

[0054] 5. Customized Lists and Suggestions:

[0055] Server: Learns the user's preferences and lifestyle patterns and generates customized shopping lists and savings suggestions based on them, using past purchase history and lifestyle data.

[0056] 6. Real-time response and advice:

[0057] Server: Utilizes generative artificial intelligence models to respond to user questions and provide advice in real time, providing quick solutions to user concerns and improving the efficiency of daily life.

[0058] Specific examples

[0059] User: At the beginning of each month, the user enters their bank transaction information into the system, including food and transportation expenses.

[0060] Terminal: The terminal transmits the entered transaction information to the server.

[0061] Server: The server receives the transaction information and updates the household ledger. The updated household ledger classifies the transaction information by category and generates analysis results.

[0062] Server: Based on the analysis results, the server provides users with money-saving suggestions such as, "Your food costs are high. You can save money by cutting down on eating out and cooking more at home."

[0063] Server: Learns from past purchase history how often the toothpaste purchased last time is used, and if it determines that a reorder is necessary, it automatically places the order.

[0064] Server: Further customizes and recommends the next shopping list based on the user's preferences and lifestyle patterns.

[0065] Server: Uses generative artificial intelligence models to provide appropriate advice in response to real-time questions from users.

[0066] This system allows users to automatically and efficiently manage their household finances and purchase everyday items, significantly reducing the time and effort required. It also provides customization based on the user's lifestyle, enabling support that meets individual needs.

[0067] The processing flow will be explained below.

[0068] Step 1:

[0069] The user enters bank transaction information and a new purchase history. For example, the transaction information includes a food expense of 50 yen and a transportation expense of 20 yen, and the new purchase history is recorded as "toothpaste."

[0070] Step 2:

[0071] The terminal sends the transaction information and purchase history entered by the user to the server. The transmitted data includes the date and time of the transaction, the amount, and the category.

[0072] Step 3:

[0073] The server stores the received transaction information as financial data and also stores the new purchase history in a purchase database.

[0074] Step 4:

[0075] The server updates the household ledger with the financial data, which includes adding new transactions and modifying existing transactions.

[0076] Step 5:

[0077] The server categorizes the household accounting data into categories, such as food, transportation, and entertainment expenses.

[0078] Step 6:

[0079] The server analyzes the classified household account data to understand the user's spending patterns, including total and average spending amounts and frequency of spending.

[0080] Step 7:

[0081] The server generates savings suggestions based on the analysis results. For example, if food expenses are high, it will suggest "cut down on eating out and cook more at home."

[0082] Step 8:

[0083] The server learns the user's purchase history and frequency of use and predicts which items need to be reordered. For example, it determines that toothpaste needs to be reordered based on how often it was used last time.

[0084] Step 9:

[0085] The server places an order for the estimated reorder items to the online shopping platform, utilizing an automatic ordering function to save the user the trouble of manually placing the order.

[0086] Step 10:

[0087] The server learns the user's behavioral patterns and preferences and generates customized shopping lists and savings suggestions, taking into account the user's past purchasing habits and lifestyle.

[0088] Step 11:

[0089] The server sends the generated customized shopping list and savings suggestions to the terminal, which displays them to the user.

[0090] Step 12:

[0091] When a user asks a question in real time, the server uses a generative artificial intelligence model to provide answers and advice to the user's questions.

[0092] Step 13:

[0093] The terminal displays the responses and advice received from the server to the user, thereby helping the user to efficiently manage their household finances and purchase everyday items.

[0094] Example 1

[0095] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0096] Conventional household management systems require users to manually input and manage data, which is cumbersome and time-consuming. Furthermore, they lack sufficient analysis of spending, making it difficult to provide efficient savings suggestions or reorder everyday items. Additionally, there was a lack of a system that allowed users to ask questions or seek advice in real time.

[0097] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0098] In this invention, the server includes: means for receiving financial data entered by a user; means for automatically updating a household ledger based on the financial data; means for categorizing the updated household ledger data; means for analyzing the categorized expenditure data to understand spending patterns; means for providing the user with money-saving suggestions based on the analysis results; means for predicting items that need to be reordered based on the frequency of use and purchase history of daily necessities; means for automatically ordering the predicted items in cooperation with an online shopping platform; and means for responding to questions from the user in real time using a generative artificial intelligence model. This enables automated and efficient household management and reordering of daily necessities. Furthermore, by providing users with advice in real time, it is possible to improve the efficiency of their daily lives.

[0099] "User" refers to any individual or group who uses this system.

[0100] "Financial data" refers to economic information necessary for managing household finances, such as income, expenditures, and transaction information.

[0101] A "household account book" refers to a ledger or collection of digital data that compiles records of income and expenses.

[0102] A "category" is a group name used to classify income and expenses, and mainly refers to general expenditure items such as food, transportation, and entertainment.

[0103] "Spending patterns" refers to a user's spending trends and habits over a specific period of time.

[0104] "Savings suggestions" refers to advice or specific recommended actions to reduce spending.

[0105] "Everyday items" are items that are frequently used in daily life, including consumables and food.

[0106] "Frequency of use" refers to the number of times a good or service is used within a specific period of time.

[0107] "Purchase history" refers to a record of products a user has purchased in the past.

[0108] "Online Shopping Platform" refers to a website or application for buying and selling goods and services over the Internet.

[0109] A "generative artificial intelligence model" refers to an AI system that generates text or responds based on a trained dataset, such as a natural language processing model like GPT-4 (registered trademark).

[0110] "Real-time response" refers to providing immediate answers to user inquiries and questions.

[0111] This invention is a system that automates and streamlines the tedious tasks of managing household finances and purchasing everyday items. The system receives financial data entered by the user, automatically updates the household ledger based on that data, and also provides the functionality of categorizing and analyzing expenditures. It also predicts items that need to be reordered based on the frequency of use and purchase history of everyday items, and automatically places orders in conjunction with an online shopping platform. This allows users to continuously obtain the items they need without missing them.

[0112] System Hardware and Software

[0113] Hardware

[0114] Server: The server acts as the central processing unit of the system and performs major tasks such as receiving data, analyzing, classifying, automatic ordering, and real-time response.

[0115] Device: The device on which a user enters data and receives notifications, such as a smartphone, tablet, or computer.

[0116] software

[0117] Database: Used within the server to store financial data, household accounting data, purchase history, etc. For example, MySQL (registered trademark) or PostgreSQL is used.

[0118] Analysis tools: Data analysis and statistical calculations are performed using Python's pandas library, etc.

[0119] Machine learning models: used to classify spending and generate customized recommendations. Using frameworks such as Scikit-learn and TENSORFLOW®.

[0120] Generative AI models: Used to respond to user questions in real time. Natural language processing models such as GPT-4 fall into this category.

[0121] API integration: To integrate with online shopping platforms, RESTful APIs are used to automate orders.

[0122] Specific examples

[0123] Example 1: Automating household accounting management

[0124] User: At the beginning of each month, the user enters their bank transaction information into the system, including food and transportation expenses.

[0125] Terminal: The terminal transmits the entered transaction information to the server.

[0126] Server: The server updates the household ledger based on the received transaction information. The updated household ledger classifies the transaction information by category and generates analysis results.

[0127] Server: Based on the analysis results, the server provides users with money-saving suggestions such as, "Your food costs are high. You can save money by cutting down on eating out and cooking more at home."

[0128] Example 2: Automatic reordering of everyday items

[0129] Server: Learns from past purchase history how often the toothpaste purchased last time is used, and if it determines that a reorder is necessary, it automatically places the order.

[0130] Server: Further customizes and recommends the next shopping list based on the user's preferences and lifestyle patterns.

[0131] Example 3: Real-time response

[0132] User: The user types a question: "What everyday item should I buy next?"

[0133] Server: The generative AI model analyzes this question and generates an appropriate answer, such as, "The next thing you should buy is toothpaste. Based on how quickly it's being consumed, it's estimated that a reorder will be necessary."

[0134] Specific prompt examples:

[0135] "What can I do to save money on food?"

[0136] "What everyday item should I buy next?"

[0137] "Tell me about your recent spending patterns."

[0138] In this way, the system of the present invention supports users' economic activities by streamlining and automating their household finances and purchasing everyday items. Furthermore, by using generative AI models, the system can provide advice and answers to questions in real time.

[0139] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0140] Step 1:

[0141] User financial data entry and submission

[0142] User: At the beginning of the month, users use devices such as smartphones or computers to enter financial data such as income, expenses, and transaction information. The data entered includes items such as food, transportation, and entertainment expenses.

[0143] Terminal: The terminal formats the entered financial data and sends it to the server.

[0144] Input: Income, expense, and transaction information entered by the user.

[0145] Output: The formatted financial data is sent to the server.

[0146] Specific operation: When a user opens the application, enters the required information into the form, and presses the submit button, the terminal sends the input data to the server.

[0147] Step 2:

[0148] Update household accounting data

[0149] Server: The server automatically updates the household ledger based on the received financial data, adding new transactions to the database and updating existing transactions.

[0150] Input: Financial data sent from the terminal.

[0151] Output: Updated household accounting data.

[0152] Specific operation: The server connects to a database (e.g., MySQL), adds new entries to the household ledger based on the received data, and modifies any necessary parts.

[0153] Step 3:

[0154] Classification of expenditure data

[0155] Server: The server analyzes the updated household accounting data and categorizes the transactions into categories, including food, transportation, entertainment, etc.

[0156] Input: Updated household accounting data.

[0157] Output: Spending data broken down by category.

[0158] How it works: The server uses machine learning models (e.g., Scikit-learn) to automatically classify spending items based on transaction content.

[0159] Step 4:

[0160] Analysis of spending data

[0161] Server: The server analyzes the categorized spending data and calculates the amount, average, and frequency of spending for each category.

[0162] Input: Expense data broken down by category.

[0163] Output: Analysis of spending patterns.

[0164] Specific operation: The server uses Python's pandas library to aggregate data and generate statistics, such as calculating the average monthly food expenses or the total transportation expenses.

[0165] Step 5:

[0166] Creating and notifying savings offers

[0167] Server: Based on the analysis, it creates savings suggestions to reduce spending in specific categories and notifies the user.

[0168] Input: Analysis of spending patterns.

[0169] Output: Notification of savings suggestions.

[0170] How it works: The server uses a predefined rule-based system to generate savings suggestions and send push notifications to the user's device.

[0171] Step 6:

[0172] Estimating reorders of everyday items

[0173] Server: Based on past purchase history and data on frequency of use of everyday items, estimates items that need to be reordered.

[0174] Input: Past purchase history, usage frequency data.

[0175] Output: A list of items that need to be reordered.

[0176] Specific operation: The server analyzes past purchase data, calculates the consumption rate of a particular product, and determines when to reorder.

[0177] Step 7:

[0178] Automated order execution

[0179] Server: Uses the API of an online shopping platform to automatically order the necessary items.

[0180] Input: A list of items that need to be reordered.

[0181] Output: Confirmation of order completion.

[0182] Specific operation: The server calls APIs such as Amazon and Rakuten, adds the estimated items to the order list, and executes the automatic order.

[0183] Step 8:

[0184] Generate customized lists and suggestions

[0185] Server: Learns the user's preferences and lifestyle patterns and generates customized shopping lists and savings suggestions.

[0186] Input: Past purchase history, lifestyle data.

[0187] Output: Customized shopping list, savings suggestions.

[0188] How it works: The server uses machine learning models (e.g., TensorFlow) to learn from the user's data and generate customized suggestions.

[0189] Step 9:

[0190] Real-time response and advice

[0191] User: The user types in a question.

[0192] Server: Uses a generative artificial intelligence model (e.g., GPT-4) to generate responses to user questions in real time.

[0193] Input: A question from the user.

[0194] Output: Real-time response.

[0195] How it works: When a user inputs a question such as "What everyday item should I buy next?", the server uses a generative AI model to generate an appropriate answer and provides it to the user.

[0196] (Application example 1)

[0197] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0198] Today's consumers spend a lot of time and effort managing their household finances and purchasing daily necessities. Therefore, they need a system that helps them efficiently manage their household finances and obtain the necessary consumables in a timely manner. However, physical stores lack the functionality to help users shop efficiently within their budget. Furthermore, the lack of real-time support based on savings suggestions and product guidance results in a suboptimal shopping experience.

[0199] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0200] In this invention, the server includes: means for receiving financial data entered by a user; means for automatically updating a household ledger based on the financial data; means for categorizing and analyzing the updated household ledger data; means for providing the user with savings suggestions based on the analysis results; means for predicting items that need to be reordered based on the frequency of use and purchase history of daily necessities; means for automatically ordering the predicted items in cooperation with an online shopping platform; means for synchronizing with the user's household data and purchase history and automatically generating a shopping list based on a budget when shopping in a physical store; and means for tracking in-store location information and using location information to guide the user to the appropriate shelves and sections. This allows users to shop efficiently within their budget even in physical stores and continuously obtain necessary items without missing them. Furthermore, the integration of home spending management and in-store shopping support provides comprehensive lifestyle support.

[0201] "Financial Data" means information relating to your finances, such as your income, expenses, and transaction information.

[0202] A "household account book" is a ledger that records a user's income and expenses and manages the status of assets and liabilities.

[0203] "Daily commodities" are items such as consumables and food that are used regularly in daily life.

[0204] An "online shopping platform" is an e-commerce venue where goods and services can be purchased via the Internet.

[0205] "Location tracking" is a technology that detects and tracks a user's current location.

[0206] A "generative artificial intelligence model" is an artificial intelligence technology that generates appropriate responses and suggestions based on input data.

[0207] A "shopping list" is a list of items that a user wants to purchase.

[0208] This invention is a comprehensive system that allows users to efficiently manage their household finances and purchase everyday items. The system has several main functions, each of which is designed to automate specific tasks and significantly reduce the burden on the user. Specific embodiments of the system are described below.

[0209] System configuration

[0210] The system mainly consists of a server, user terminals (smartphones, smart glasses, etc.), and in-store beacon devices.

[0211] 1. Receiving financial data and updating your household accounts:

[0212] The server receives financial data (income, expenses, and transaction information) entered by the user and automatically updates the household ledger based on that data.

[0213] This process uses a database management system (e.g., Firebase).

[0214] 2. Expenditure Classification and Analysis:

[0215] The server categorizes the updated household data and analyzes spending patterns, allowing it to calculate totals, averages, frequency, and other expenditures.

[0216] 3. Providing savings offers:

[0217] The server provides users with savings suggestions based on the analysis of their spending patterns, including advice on reducing spending in specific categories.

[0218] 4. Reorder Estimation and Auto Order:

[0219] The server learns the frequency of use and purchase history of everyday items and estimates which items need to be reordered.

[0220] Based on this estimation, the server will then work with an online shopping platform to automatically order the required items.

[0221] 5. In-store shopping assistance:

[0222] The user's device synchronizes with the server and automatically generates a shopping list based on the budget.

[0223] Using beacon devices in the store, the system tracks the user's location and guides them to the appropriate shelf or corner.

[0224] Example

[0225] Specifically, the following system can be implemented.

[0226] Enter financial data and update your household budget:

[0227] User: Enters bank transaction information into the system at the beginning of the month. Transaction information includes expenditures for food and transportation.

[0228] Server: Receives the entered transaction information and updates the household ledger. This update uses the Firebase database.

[0229] Expense classification and savings suggestions:

[0230] Server: Categorizes updated household accounting data by category and calculates total and average expenditures. Based on the analysis results, the server provides advice to the user, such as, "Your food expenses are high. You can save money by cutting down on eating out and cooking more at home."

[0231] Reordering everyday items:

[0232] Server: If it is estimated based on past purchase history that a consumable item (e.g., toothpaste) needs to be reordered, the server automatically places the order in cooperation with the online shopping platform.

[0233] In-store shopping assistance:

[0234] User device: Links with the beacon device in the store to identify the user's location and generates a real-time list of items that can be purchased within the user's specified budget.

[0235] In-store guidance: Beacon devices guide users to the shelves or corners where the products they are looking for are located, helping them shop more efficiently.

[0236] Examples of prompt statements

[0237] Based on the user's budget and recent purchase history, a generative AI model (e.g., GPT-4) is used to generate prompts such as:

[0238] Examples:

[0239] "User's budget is 10,000 yen, and their recent purchase history is as follows: Bread: 500 yen, Milk: 200 yen, Vegetables: 300 yen. Please provide some money-saving advice."

[0240] This system is expected to make household management and purchasing of everyday items more efficient, and to improve users' shopping experience in physical stores as well.

[0241] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0242] Step 1:

[0243] At the beginning of each month, users use a smartphone app to enter their banking information, which includes income and expenses such as food and transportation.

[0244] Input: Transaction information entered by the user

[0245] Output: Transaction information is sent to the server

[0246] Step 2:

[0247] The server receives the transaction information entered by the user and stores it in the Firebase database, which automatically updates the household account book based on this information.

[0248] Input: Transaction information sent by the user

[0249] Output: Updated household accounting data

[0250] Step 3:

[0251] The server categorizes the updated household budget data by category, such as food, transportation, entertainment, etc. It then analyzes spending patterns based on this data and calculates totals, averages, and frequency of spending for each category.

[0252] Input: Updated household accounting data

[0253] Output: Spending data broken down by category and analysis of spending patterns

[0254] Step 4:

[0255] The server generates saving suggestions for the user based on the analysis results. In this process, a generative artificial intelligence model (e.g., GPT-4) is used to generate specific advice prompts such as, "Your food costs are high. You can save money by cutting down on eating out and cooking more at home."

[0256] Input: Analysis of spending patterns

[0257] Output: Savings suggestions to the user

[0258] Step 5:

[0259] The server learns the frequency of use of everyday items and past purchase history, and predicts which items need to be reordered. For example, it learns how often toothpaste was used last time and predicts when it needs to be reordered.

[0260] Input: Frequency of use and purchase history of everyday items

[0261] Output: A list of items that need to be reordered

[0262] Step 6:

[0263] The server then connects with the online shopping platform to automatically place orders for items that are estimated to need reordering, a process that eliminates the need for users to manually place orders.

[0264] Input: List of items that need to be reordered

[0265] Output: Orders placed automatically

[0266] Step 7:

[0267] When a user shops in a physical store, the device synchronizes with the server and automatically generates a budget-based shopping list in real time.

[0268] Input: User budget information and real-time shopping data

[0269] Output: An automatically generated shopping list

[0270] Step 8:

[0271] Beacon devices in the store track users' location, and the terminal guides them to the appropriate shelf or section. For example, the beacon device identifies the user's location, and the smartphone notifies them that "there are discounted vegetables nearby."

[0272] Input: Location information from beacon device and shopping list

[0273] Output: Notification to guide the user to the product shelf or corner

[0274] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0275] This invention is a system that automates and streamlines the tedious tasks of managing household finances and purchasing everyday items. In particular, this system aims to provide more personalized services by incorporating an emotion engine that recognizes the user's emotions. The system receives financial data entered by the user, automatically updates the household ledger based on that data, and also provides the function of categorizing and analyzing expenses. This allows users to easily manage their expenses. It also predicts items that need to be reordered based on the frequency of use and purchase history of everyday items, and automatically places orders in conjunction with an online shopping platform, allowing users to continuously obtain necessary items without missing them. Furthermore, the system has the ability to recognize the user's emotions and adjust the provided savings suggestions and shopping list based on the user's emotions.

[0276] System configuration and functions

[0277] 1. Receiving financial data and updating your household accounts:

[0278] Server: Receives financial data entered by the user, including income, expenses, and transaction information.

[0279] Server: Automatically updates the household ledger based on the received data. This update includes adding new transactions and modifying existing transactions.

[0280] 2. Expenditure classification and analysis:

[0281] Server: Categorizes the updated household accounting data by category, such as food, transportation, entertainment, etc.

[0282] Server: Analyzes the categorized spending data to understand user spending patterns, including calculating totals, averages, frequency, etc.

[0283] 3. Providing savings offers:

[0284] Server: Based on the analysis of spending patterns, the server provides users with savings suggestions. For example, if spending in a particular category is high, the server provides advice on reducing spending in that category.

[0285] 4. Reorder Estimation and Execution:

[0286] Server: Based on the frequency of use and purchase history of everyday items, it estimates what items need to be reordered. Examples include paper or plastic consumables and food.

[0287] Server: Connects to online shopping platforms and automatically places orders for the estimated items, allowing users to obtain the items they need in a timely manner.

[0288] 5. Customized Lists and Suggestions:

[0289] Server: Learns the user's preferences and lifestyle patterns and generates customized shopping lists and savings suggestions based on them, using past purchase history and lifestyle data.

[0290] 6. Real-time response and advice:

[0291] Server: Utilizes generative artificial intelligence models to respond to user questions and provide advice in real time, providing quick solutions to user concerns and improving the efficiency of daily life.

[0292] 7. Use of Emotion Engine:

[0293] Server: Includes an emotion engine that recognizes the user's emotions. The emotion engine detects emotions from the user's facial expressions, tone of voice, input text, etc.

[0294] Server: Tailors customized savings suggestions and shopping lists based on the user's emotions detected by the emotion engine. For example, if the user is feeling stressed, it can recommend relaxation items to relieve stress.

[0295] Server: Based on the user's emotions detected by the emotion engine, the server adjusts responses and advice content in real time, thereby providing personalized advice according to the user's emotional state.

[0296] Specific examples

[0297] User: At the beginning of each month, the user enters their bank transaction information into the system, including food and transportation expenses.

[0298] Terminal: The terminal transmits the entered transaction information to the server.

[0299] Server: The server receives the transaction information and updates the household ledger. The updated household ledger classifies the transaction information by category and generates analysis results.

[0300] Server: Based on the analysis results, the server provides users with money-saving suggestions such as, "Your food costs are high. You can save money by cutting down on eating out and cooking more at home."

[0301] Server: Learns from past purchase history how often the toothpaste purchased last time is used, and if it determines that a reorder is necessary, it automatically places the order.

[0302] Server: Further customizes and recommends the next shopping list based on the user's preferences and lifestyle patterns.

[0303] Server: Uses generative artificial intelligence models to provide appropriate advice in response to real-time questions from users.

[0304] Server: Uses an emotion engine to sense the user's emotions and tailor savings suggestions and shopping lists accordingly. For example, if the user is tired, recommend items that will help reduce stress.

[0305] Server: Tailors real-time responses and advice based on the emotion engine, providing personalized support according to the user's emotional state.

[0306] The system enables automatic and efficient household management and daily necessities purchasing, and also provides personalized services based on users' emotions, significantly reducing users' time and effort and improving their quality of life.

[0307] The processing flow will be explained below.

[0308] Step 1:

[0309] The user enters bank transaction information and a new purchase history. For example, the transaction information includes a food expense of 50 yen and a transportation expense of 20 yen, and the new purchase history is recorded as "toothpaste."

[0310] Step 2:

[0311] The terminal sends the transaction information and purchase history entered by the user to the server. The transmitted data includes the date and time of the transaction, the amount, and the category.

[0312] Step 3:

[0313] The server stores the received transaction information as financial data and also stores the new purchase history in a purchase database.

[0314] Step 4:

[0315] The server updates the household ledger with the financial data, which includes adding new transactions and modifying existing transactions.

[0316] Step 5:

[0317] The server categorizes the household accounting data into categories, such as food, transportation, and entertainment expenses.

[0318] Step 6:

[0319] The server analyzes the classified household account data to understand the user's spending patterns, including total and average spending amounts and frequency of spending.

[0320] Step 7:

[0321] The server uses an emotion engine to recognize the user's emotions, using information such as the user's facial expression, tone of voice, and input text to determine the emotion.

[0322] Step 8:

[0323] The server generates money-saving suggestions based on the analysis results and the recognition results of the emotion engine. For example, if a user is feeling stressed because of high food expenses, the server will suggest, "Your food expenses are high. You can save money by cutting down on eating out and cooking more at home, which will also help reduce stress."

[0324] Step 9:

[0325] The server learns the user's purchase history and frequency of use and predicts which items need to be reordered. For example, it determines that a reorder is necessary based on how often toothpaste was used last time.

[0326] Step 10:

[0327] The server places an order for the estimated reorder items to the online shopping platform, utilizing an automatic ordering function to save the user the trouble of manually placing the order.

[0328] Step 11:

[0329] The server generates customized shopping lists and savings suggestions based on the results of the emotion engine. For example, if the user has the emotion of wanting to relax, it will recommend relaxation items.

[0330] Step 12:

[0331] The server sends the generated customized shopping list and savings suggestions to the terminal, which displays them to the user.

[0332] Step 13:

[0333] When a user asks a question in real time, the server uses a generative artificial intelligence model to provide answers and advice to the user's questions.

[0334] Step 14:

[0335] The server adjusts the content of real-time responses and advice based on the user's emotions detected by the emotion engine. For example, if the user is feeling irritated, the server will provide calm advice to calm the user.

[0336] Step 15:

[0337] The terminal displays the responses and advice received from the server to the user, thereby helping the user to efficiently manage their household finances and purchase everyday items.

[0338] Example 2

[0339] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0340] In modern life, managing household finances and purchasing everyday items requires a significant amount of time and effort. Furthermore, conventional household finance management and purchasing systems lack the ability to provide personalized services that take user emotions into account, making it difficult to increase user satisfaction. The present invention aims to solve these problems by streamlining and automating household finance management and providing personalized responses based on user emotions.

[0341] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0342] In this invention, the server includes: means for receiving financial data input by a user; means for automatically updating a household account book based on the financial data; means for classifying and analyzing the updated household account book data; means for providing the user with money-saving suggestions based on the analysis results; means for predicting items that need to be reordered based on the frequency of use and purchase history of daily necessities; means for automatically ordering the predicted items in cooperation with an e-commerce platform; means including an emotion engine that recognizes user emotions; and means for adjusting money-saving suggestions and a shopping list based on the user emotions sensed by the emotion engine. This allows the user to automatically manage their household finances, obtain necessary items in a timely manner, and receive personalized services according to their emotions.

[0343] "User" refers to any individual or organization that uses this system.

[0344] "Financial Data" refers to information related to a user's economic activities, such as income, expenses, and transaction information.

[0345] A "household account book" refers to a digital or physical ledger that allows a user to record and manage their income and expenses.

[0346] "Classification" refers to the process of separating household data into categories, such as food, transportation, and entertainment.

[0347] "Analysis" refers to the process of statistically analyzing household accounting data to identify spending patterns and unusual spending.

[0348] "Savings suggestions" refers to providing financial advice to users based on the analysis of their household accounting data.

[0349] "Frequency of use" refers to data indicating how often an everyday item is used.

[0350] "Purchase history" refers to data that records the items a user has previously purchased and their detailed information.

[0351] "Reordering" refers to the process of reordering needed items based on frequency of use and purchase history.

[0352] "E-commerce platform" refers to a website or application for buying and selling goods and services online.

[0353] An "emotion engine" refers to technology that detects emotions from a user's facial expressions, tone of voice, input text, etc.

[0354] "Personalization" refers to customizing services and offers based on the individual characteristics and circumstances of each user.

[0355] The present invention is a system that allows users to automate and streamline the tedious tasks of managing their household finances and purchasing everyday items. The system is designed to receive financial data, update household accounts, categorize and analyze expenses, provide savings suggestions, estimate and execute reorders for everyday items, and provide customized suggestions based on the user's emotions.

[0356] Receive financial data and update your household budget

[0357] At the beginning of each month, users enter financial data, such as bank transaction information and cash expenditure information, into the system. Specific examples include food expenditures of 1,000 yen and transportation expenditures of 3,000 yen. The data entered by the user is sent to the server via the terminal. Based on the received data, the server adds new transactions to the household accounting database and modifies existing transactions. For example, if the total food expenditures for August were 5,000 yen, a new expenditure of 1,000 yen would be added, bringing the total to 6,000 yen.

[0358] Expense classification and analysis

[0359] The server analyzes the updated household ledger data and classifies each transaction into a category. Specific examples include food expenses, transportation expenses, and entertainment expenses. Based on this, the server categorizes food-related transactions into the "food" category and transportation-related transactions into the "transportation" category. Based on the expenditure data for each category, the server calculates statistical information such as total expenditures, frequency, and average amounts. For example, it calculates the average monthly food expenses and compares them between years. The server detects spending trends and unusual spending patterns. For example, if transportation expenses spike in a particular month, it analyzes the cause.

[0360] Providing savings suggestions

[0361] The server generates savings suggestions tailored to the user based on the analysis of spending patterns. For example, a user with high transportation costs may be advised to consider commuting by bicycle. The generated savings suggestions are sent to the device, which then displays them to the user, suggesting specific ways to save money.

[0362] Reorder estimation and execution

[0363] Based on the frequency of use and purchase history of everyday items, the server estimates which items need to be reordered. As a specific example, it estimates when the next purchase will be based on the rate at which toilet paper was used the last time it was purchased. Information on items that are estimated to be needed is obtained by the server, and a decision is made as to whether to reorder them based on the user's purchase history. If it is determined that a reorder is necessary, the server will link with the e-commerce platform via API or other means to automatically place the order. After the order is completed, the server will notify the user of the order details.

[0364] Generate customized suggestions and lists

[0365] The server analyzes the user's past purchase history and lifestyle data to generate customized shopping lists and suggestions. For example, a user who buys a lot of ingredients on the weekend will be offered "recommended ingredients for this weekend." Savings suggestions tailored to the user's preferences are also offered. The customized lists and suggestions are displayed to the user through their device.

[0366] Real-time response and advice

[0367] A user inputs a question about household management into the system in real time. A specific example is, "How can I reduce my food expenses this month?" The device sends the question to the server, which uses a generative AI model (e.g., a generative AI model) to generate an appropriate answer to the user's question. The generated answer is sent to the device, which displays the generated answer to the user in real time.

[0368] Use of emotion engine

[0369] The system reads emotions from the user's tone of voice and input text. For example, if the input text is "tired," it will detect stress. Emotional data is sent to the server via the device, and the server uses an emotion engine to analyze the user's emotions. Based on the emotions, customized savings suggestions and shopping lists are adjusted. The response of the generative AI model is also customized based on the emotion data, providing personalized advice according to the user's current emotional state.

[0370] Prompt Sentence Examples

[0371] User: I want to enter my monthly expenses. How can I get the data reflected in my household ledger?

[0372] Terminal: Sends entered data to the server.

[0373] Server: Automatically updates the household account book based on bank transaction information and analyzes expenses.

[0374] This system allows users to efficiently manage their household finances, obtain necessary items in a timely manner, and receive personalized services based on their emotions, which can significantly reduce users' time and effort and improve their quality of life.

[0375] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0376] Step 1:

[0377] Entering and submitting financial data

[0378] At the beginning of each month, users enter their financial data, such as bank transaction information and cash expenditure information, into the system. For example, they enter 1,000 yen in food expenses and 3,000 yen in transportation expenses. The terminal then sends this input data to the server.

[0379] Input: Financial data such as food expenses, transportation expenses, etc.

[0380] Output: Financial data sent to the server

[0381] Step 2:

[0382] Receiving data and updating the household account book

[0383] The server receives the financial data sent from the device. Based on the received data, the server adds new transactions to the household accounting database and modifies existing transactions. For example, if the total food expenditure for August was 5,000 yen, it will add a new expenditure of 1,000 yen to update it to 6,000 yen.

[0384] Input: Financial data sent from the terminal

[0385] Processing: Update the household accounting database (add new transactions, modify existing transactions)

[0386] Output: Updated household account book

[0387] Step 3:

[0388] Expense Category Classification

[0389] The server categorizes the updated household accounting data into categories, such as food expenses, transportation expenses, and entertainment expenses.

[0390] Input: Updated household accounting data

[0391] Processing: Categorizing transaction data (e.g., food, transportation, entertainment)

[0392] Output: Household accounting data categorized by category

[0393] Step 4:

[0394] Analysis of spending patterns

[0395] The server calculates statistics such as total expenditures, frequency, and average amounts based on each category of expenditure data. For example, it calculates the average monthly food expenditure and compares it year-over-year. It also detects expenditure trends and unusual patterns.

[0396] Input: Household accounting data categorized by category

[0397] Processing: Calculating statistical information (total, frequency, average amount of expenditure)

[0398] Output: Spending statistics and analysis results

[0399] Step 5:

[0400] Generate and notify savings suggestions

[0401] The server generates savings suggestions tailored to the user based on the analysis of spending patterns. For example, it might suggest to a user with high transportation costs, "Consider commuting by bicycle." The generated savings suggestions are sent to the device, which then displays them to the user.

[0402] Input: Spending statistics and analysis results

[0403] Processing: Generate savings proposals

[0404] Output: Generated savings proposals

[0405] Step 6:

[0406] Estimating reorders of everyday items

[0407] The server estimates which items need to be reordered based on the frequency of use and purchase history of everyday items. For example, it estimates when the next purchase will be made based on the rate at which toilet paper was used last time.

[0408] Input: Usage frequency and purchase history data

[0409] Processing: Usage frequency analysis, reorder estimation

[0410] Output: List of items that need to be reordered

[0411] Step 7:

[0412] Automated order execution

[0413] If it is determined that a reorder is necessary, the server will automatically place the order by connecting with the e-commerce platform via API, etc. After the order is completed, the server will notify the user of the order details.

[0414] Input: List of items that need to be reordered

[0415] Processing: Integration with e-commerce platforms, automatic order execution

[0416] Output: Order details notification

[0417] Step 8:

[0418] Customization suggestions based on user preferences

[0419] The server analyzes the user's past purchase history and lifestyle data to generate customized shopping lists and savings suggestions. For example, it provides "recommended ingredients for this weekend" to users who buy a lot of ingredients on the weekend.

[0420] Input: Past purchase history, lifestyle data

[0421] Processing: Analysis of preferences and lifestyle patterns, generation of customization suggestions

[0422] Output: customized shopping list and savings suggestions

[0423] Step 9:

[0424] Real-time question responses

[0425] Users input questions about household finances into the system in real time. A typical example would be, "How can I reduce my food expenses this month?" The device sends the question to the server, which uses a generative AI model (e.g., a generative AI model) to generate an appropriate answer to the user's question. The generated answer is sent to the device and displayed to the user in real time.

[0426] Input: Real-time questions

[0427] Processing: Answer generation using generative AI models

[0428] Output: The generated answer

[0429] Step 10:

[0430] Receiving and analyzing emotion data

[0431] The system reads emotions from the user's tone of voice and input text. For example, if the input text is "tired," it will detect stress. Emotion data is sent to the server via the device, and the server uses an emotion engine to analyze the user's emotions.

[0432] Input: The user's tone of voice and input text

[0433] Processing: Emotion recognition and data generation

[0434] Output: User emotion data

[0435] Step 11:

[0436] Tailoring personalized suggestions based on emotions

[0437] Based on the emotional data, the server will tailor customized savings suggestions and shopping lists. For example, if the user is tired, it will add relaxation items to the shopping list. The emotional data will also customize the generative AI model's response, providing personalized advice based on the user's current emotional state.

[0438] Input: User emotion data

[0439] Processing: tailoring suggestions and customizing responses with generative AI models

[0440] Output: Tailored savings suggestions, shopping lists, personalized advice

[0441] (Application example 2)

[0442] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0443] Today's users are required to efficiently manage their household finances and purchase daily necessities amid their busy lives. However, these tasks are time-consuming and lack emotionally-sensitive personalized support, which increases user stress. Conventional systems have struggled to streamline household finances and purchase daily necessities, while providing personalized suggestions in a unified manner. Therefore, there is a need for the development of a system that automates and streamlines household finances and purchases while providing emotionally-sensitive support.

[0444] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving financial data input by a user, means for automatically updating the household account book based on the financial data, means for classifying and analyzing the updated household account book data, means for providing the user with money-saving suggestions based on the analysis results, means for predicting items that need to be reordered based on the frequency of use and purchase history of daily necessities, means for automatically ordering the predicted items in cooperation with an e-commerce platform, and means for recognizing the user's emotions using an emotion recognition engine and providing personalized suggestions based on the recognized emotions. This enables the user to efficiently manage their household finances and purchase daily necessities while receiving support based on their emotions.

[0445] "User" refers to an individual who uses the system to manage their household finances and purchase everyday items.

[0446] "Financial Data" refers to data related to economic activity, such as income, expenses, and transaction information entered by users.

[0447] A "household account book" refers to a ledger used to record and manage a user's income and expenses.

[0448] An "emotion recognition engine" refers to a system that detects emotions from a user's facial expressions, tone of voice, input text, etc.

[0449] "Savings Suggestions" refers to advice that analyzes a user's spending patterns and suggests ways to save money.

[0450] "Items that need to be reordered" refers to items that are determined to need to be purchased again based on the frequency of use and purchase history of everyday items.

[0451] "E-commerce platform" refers to a website or application that allows users to buy and sell goods and services online.

[0452] "Personalized suggestions" refers to providing specific advice or recommendations based on a user's emotions and preferences.

[0453] A "generative artificial intelligence model" refers to an artificial intelligence that generates answers and advice based on input data and questions.

[0454] This invention is a system that helps users manage their household finances and purchase everyday items efficiently. The system uses an emotion recognition engine and a generative artificial intelligence model to provide personalized suggestions based on the user's emotions.

[0455] The server first receives financial data entered by the user. Financial data includes income, expenses, and transaction information. For example, the user enters bank transaction information using a smartphone. This data is automatically updated in the household ledger.

[0456] The updated household accounting data is then classified and analyzed. Spending patterns are categorized and the total amount and frequency are calculated. Based on the results of this analysis, savings suggestions are provided to the user. For example, if the analysis shows that food expenses are high, the system will suggest "eating out less and cooking more at home."

[0457] Based on the frequency of use and purchase history of everyday items, the system predicts which items need to be reordered. For example, this applies to consumables such as paper products and food. The server then automatically orders these items in conjunction with the e-commerce platform, allowing users to obtain the items they need in a timely manner.

[0458] The emotion recognition engine recognizes emotions from the user's facial expressions, tone of voice, input text, etc. For example, if the user is feeling stressed, it will recommend relaxation items. Making suggestions based on emotions improves user satisfaction.

[0459] The generative AI model responds to real-time questions from users and generates appropriate advice based on the input data and questions. For example, if a user asks, "How can I reduce my food expenses this month?", the model will provide specific advice.

[0460] The hardware used includes a smartphone, the emotion recognition engine is Microsoft® Azure®'s Emotion API, and the generative artificial intelligence model is OpenAI®'s GPT.

[0461] Examples:

[0462] Users input financial data into the system via a smartphone app. The server receives the data and automatically updates the household ledger. Next, an emotion recognition engine detects stress levels from the user's facial expressions and suggests relaxation items. Meanwhile, a generative AI model provides real-time advice, such as "You can cut down on food costs by eating out less."

[0463] Example prompt sentence:

[0464] Consider user emotions and offer advice on buying and saving money on everyday items.

[0465] The user seems tired. Suggest items or foods that will help them relax.

[0466] The system allows users to efficiently manage their finances and purchase everyday items while receiving emotional support.

[0467] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0468] Step 1: Enter your financial data

[0469] A user uses a smartphone to input financial data such as income, expenses, and transaction information. This financial data is sent from the device to a server. The input data includes categories such as income, food expenses, and transportation expenses, along with the amounts for each. The server temporarily stores the received data.

[0470] Step 2: Update your household budget

[0471] The server automatically updates the household ledger based on the received financial data. Specifically, it analyzes transaction information and categorizes them. It adds and modifies new transactions to the previous household ledger to create a household ledger that reflects the user's latest financial situation. The updated household ledger is obtained as output.

[0472] Step 3: Categorize and analyze expenses

[0473] The server categorizes and analyzes the updated household accounting data. It categorizes income and expenses by category and calculates the total amount and frequency of spending for each category. The analysis results include total expenditures and spending patterns for each category, such as food, transportation, and entertainment. This allows users to understand their spending habits.

[0474] Step 4: Generate savings proposals

[0475] The server generates savings suggestions for the user based on the results of the expenditure analysis. For example, if expenditures in a particular category are high, specific advice on reducing spending in that category is provided. Saving suggestions are generated using a generative AI model and are tailored to the user's lifestyle. Saving suggestions are obtained as the output.

[0476] Step 5: Estimate reorders

[0477] The server estimates which items need to be reordered based on the frequency of use and purchase history of daily items. It analyzes purchase history data and predicts when repurchases will be necessary. For example, it estimates the timing of repurchase based on the period of use of toothpaste previously purchased. The output is a list of items that can be reordered.

[0478] Step 6: Execute an automatic order

[0479] The server automatically orders the estimated reorder candidate items in cooperation with the e-commerce platform. It checks the stock status and price of the necessary items and executes the order at the optimal time. This allows users to regularly secure the daily necessities they need. The output is confirmation data that the automatic order has been completed.

[0480] Step 7: Emotion Recognition and Custom Suggestions

[0481] The server uses an emotion recognition engine to recognize the user's emotions. It analyzes the input text, tone of voice, and facial expression data to determine the user's emotional state (e.g., stress or happiness). Based on the recognized emotions, it personalizes saving suggestions and shopping lists to provide suggestions that the user desires. The output is customized suggestions based on emotions.

[0482] Step 8: Real-time support

[0483] The server uses a generative AI model to respond to real-time questions from users. For example, in response to a question like, "How can I reduce my food expenses this month?", it will suggest detailed ways to save money. The AI ​​generates a response based on the prompt text, providing the user with timely and useful information. The output is specific advice.

[0484] Through these steps, users can manage their household finances and purchase everyday items efficiently and personalizedly.

[0485] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0486] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0487] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0488] [Second embodiment]

[0489] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0490] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0491] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0492] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0493] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0494] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0495] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0496] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0497] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0498] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0499] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0500] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0501] This invention is a system that automates and streamlines the tedious tasks of managing household finances and purchasing everyday items. The system receives financial data entered by the user, automatically updates the household ledger based on that data, and also provides the functionality of categorizing and analyzing expenditures. This allows users to easily manage their expenditures. It also predicts items that need to be reordered based on the frequency of use and purchase history of everyday items, and automatically places orders in conjunction with an online shopping platform. These functions allow users to continuously obtain the items they need without missing them.

[0502] System configuration and functions

[0503] 1. Receiving financial data and updating your household accounts:

[0504] Server: Receives financial data entered by the user, including income, expenses, and transaction information.

[0505] Server: Automatically updates the household ledger based on the received data. This update includes adding new transactions and modifying existing transactions.

[0506] 2. Expenditure classification and analysis:

[0507] Server: Categorizes the updated household accounting data by category, such as food, transportation, entertainment, etc.

[0508] Server: Analyzes the categorized spending data to understand user spending patterns, including calculating totals, averages, frequency, etc.

[0509] 3. Providing savings offers:

[0510] Server: Based on the analysis of spending patterns, the server provides users with savings suggestions. For example, if spending in a particular category is high, the server provides advice on reducing spending in that category.

[0511] 4. Reorder Estimation and Execution:

[0512] Server: Based on the frequency of use and purchase history of everyday items, it estimates what items need to be reordered. Examples include paper or plastic consumables and food.

[0513] Server: Connects to online shopping platforms and automatically places orders for the estimated items, allowing users to obtain the items they need in a timely manner.

[0514] 5. Customized Lists and Suggestions:

[0515] Server: Learns the user's preferences and lifestyle patterns and generates customized shopping lists and savings suggestions based on them, using past purchase history and lifestyle data.

[0516] 6. Real-time response and advice:

[0517] Server: Utilizes generative artificial intelligence models to respond to user questions and provide advice in real time, providing quick solutions to user concerns and improving the efficiency of daily life.

[0518] Specific examples

[0519] User: At the beginning of each month, the user enters their bank transaction information into the system, including food and transportation expenses.

[0520] Terminal: The terminal transmits the entered transaction information to the server.

[0521] Server: The server receives the transaction information and updates the household ledger. The updated household ledger classifies the transaction information by category and generates analysis results.

[0522] Server: Based on the analysis results, the server provides users with money-saving suggestions such as, "Your food costs are high. You can save money by cutting down on eating out and cooking more at home."

[0523] Server: Learns from past purchase history how often the toothpaste purchased last time is used, and if it determines that a reorder is necessary, it automatically places the order.

[0524] Server: Further customizes and recommends the next shopping list based on the user's preferences and lifestyle patterns.

[0525] Server: Uses generative artificial intelligence models to provide appropriate advice in response to real-time questions from users.

[0526] This system allows users to automatically and efficiently manage their household finances and purchase everyday items, significantly reducing the time and effort required. It also provides customization based on the user's lifestyle, enabling support that meets individual needs.

[0527] The processing flow will be explained below.

[0528] Step 1:

[0529] The user enters bank transaction information and a new purchase history. For example, the transaction information includes a food expense of 50 yen and a transportation expense of 20 yen, and the new purchase history is recorded as "toothpaste."

[0530] Step 2:

[0531] The terminal sends the transaction information and purchase history entered by the user to the server. The transmitted data includes the date and time of the transaction, the amount, and the category.

[0532] Step 3:

[0533] The server stores the received transaction information as financial data and also stores the new purchase history in a purchase database.

[0534] Step 4:

[0535] The server updates the household ledger with the financial data, which includes adding new transactions and modifying existing transactions.

[0536] Step 5:

[0537] The server categorizes the household accounting data into categories, such as food, transportation, and entertainment expenses.

[0538] Step 6:

[0539] The server analyzes the classified household account data to understand the user's spending patterns, including total and average spending amounts and frequency of spending.

[0540] Step 7:

[0541] The server generates savings suggestions based on the analysis results. For example, if food expenses are high, it will suggest "cut down on eating out and cook more at home."

[0542] Step 8:

[0543] The server learns the user's purchase history and frequency of use and predicts which items need to be reordered. For example, it determines that toothpaste needs to be reordered based on how often it was used last time.

[0544] Step 9:

[0545] The server places an order for the estimated reorder items to the online shopping platform, utilizing an automatic ordering function to save the user the trouble of manually placing the order.

[0546] Step 10:

[0547] The server learns the user's behavioral patterns and preferences and generates customized shopping lists and savings suggestions, taking into account the user's past purchasing habits and lifestyle.

[0548] Step 11:

[0549] The server sends the generated customized shopping list and savings suggestions to the terminal, which displays them to the user.

[0550] Step 12:

[0551] When a user asks a question in real time, the server uses a generative artificial intelligence model to provide answers and advice to the user's questions.

[0552] Step 13:

[0553] The terminal displays the responses and advice received from the server to the user, thereby helping the user to efficiently manage their household finances and purchase everyday items.

[0554] Example 1

[0555] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0556] Conventional household management systems require users to manually input and manage data, which is cumbersome and time-consuming. Furthermore, they lack sufficient analysis of spending, making it difficult to provide efficient savings suggestions or reorder everyday items. Additionally, there was a lack of a system that allowed users to ask questions or seek advice in real time.

[0557] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0558] In this invention, the server includes: means for receiving financial data entered by a user; means for automatically updating a household ledger based on the financial data; means for categorizing the updated household ledger data; means for analyzing the categorized expenditure data to understand spending patterns; means for providing the user with money-saving suggestions based on the analysis results; means for predicting items that need to be reordered based on the frequency of use and purchase history of daily necessities; means for automatically ordering the predicted items in cooperation with an online shopping platform; and means for responding to questions from the user in real time using a generative artificial intelligence model. This enables automated and efficient household management and reordering of daily necessities. Furthermore, by providing users with advice in real time, it is possible to improve the efficiency of their daily lives.

[0559] "User" refers to any individual or group who uses this system.

[0560] "Financial data" refers to economic information necessary for managing household finances, such as income, expenditures, and transaction information.

[0561] A "household account book" refers to a ledger or collection of digital data that compiles records of income and expenses.

[0562] A "category" is a group name used to classify income and expenses, and mainly refers to general expenditure items such as food, transportation, and entertainment.

[0563] "Spending patterns" refers to a user's spending trends and habits over a specific period of time.

[0564] "Savings suggestions" refers to advice and recommended specific actions to reduce spending.

[0565] "Everyday items" are items that are frequently used in daily life, including consumables and food.

[0566] "Frequency of use" refers to the number of times a good or service is used within a specific period of time.

[0567] "Purchase history" refers to a record of products a user has purchased in the past.

[0568] "Online Shopping Platform" refers to a website or application for buying and selling goods and services over the Internet.

[0569] A "generative artificial intelligence model" refers to an AI system that generates text or responses based on a trained dataset, such as a natural language processing model like GPT-4.

[0570] "Real-time response" refers to providing immediate answers to user inquiries and questions.

[0571] This invention is a system that automates and streamlines the tedious tasks of managing household finances and purchasing everyday items. The system receives financial data entered by the user, automatically updates the household ledger based on that data, and also provides the functionality of categorizing and analyzing expenditures. It also predicts items that need to be reordered based on the frequency of use and purchase history of everyday items, and automatically places orders in conjunction with an online shopping platform. This allows users to continuously obtain the items they need without missing them.

[0572] System Hardware and Software

[0573] Hardware

[0574] Server: The server acts as the central processing unit of the system and performs major tasks such as receiving data, analyzing, classifying, automatic ordering, and real-time response.

[0575] Device: The device on which a user enters data and receives notifications, such as a smartphone, tablet, or computer.

[0576] software

[0577] Database: Used within the server to store financial data, household accounting data, purchase history, etc. For example, MySQL or PostgreSQL is used.

[0578] Analysis tools: Data analysis and statistical calculations are performed using Python's pandas library, etc.

[0579] Machine learning models: Used to classify spending and generate customized recommendations. Use frameworks such as Scikit-learn and TensorFlow.

[0580] Generative AI models: Used to respond to user questions in real time. Natural language processing models such as GPT-4 fall into this category.

[0581] API integration: To integrate with online shopping platforms, RESTful APIs are used to automate orders.

[0582] Specific examples

[0583] Example 1: Automating household accounting management

[0584] User: At the beginning of each month, the user enters their bank transaction information into the system, including food and transportation expenses.

[0585] Terminal: The terminal transmits the entered transaction information to the server.

[0586] Server: The server updates the household ledger based on the received transaction information. The updated household ledger classifies the transaction information by category and generates analysis results.

[0587] Server: Based on the analysis results, the server provides users with money-saving suggestions such as, "Your food costs are high. You can save money by cutting down on eating out and cooking more at home."

[0588] Example 2: Automatic reordering of everyday items

[0589] Server: Learns from past purchase history how often the toothpaste purchased last time is used, and if it determines that a reorder is necessary, it automatically places the order.

[0590] Server: Further customizes and recommends the next shopping list based on the user's preferences and lifestyle patterns.

[0591] Example 3: Real-time response

[0592] User: The user types a question: "What everyday item should I buy next?"

[0593] Server: The generative AI model analyzes this question and generates an appropriate answer, such as, "The next thing you should buy is toothpaste. Based on how quickly it's being consumed, it's estimated that a reorder will be necessary."

[0594] Specific prompt examples:

[0595] "What can I do to save money on food?"

[0596] "What everyday item should I buy next?"

[0597] "Tell me about your recent spending patterns."

[0598] In this way, the system of the present invention supports users' economic activities by streamlining and automating their household finances and purchasing everyday items. Furthermore, by using generative AI models, the system can provide advice and answers to questions in real time.

[0599] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0600] Step 1:

[0601] User financial data entry and submission

[0602] User: At the beginning of the month, users use devices such as smartphones or computers to enter financial data such as income, expenses, and transaction information. The data entered includes items such as food, transportation, and entertainment expenses.

[0603] Terminal: The terminal formats the entered financial data and sends it to the server.

[0604] Input: Income, expense, and transaction information entered by the user.

[0605] Output: The formatted financial data is sent to the server.

[0606] Specific operation: When a user opens the application, enters the required information into the form, and presses the submit button, the terminal sends the input data to the server.

[0607] Step 2:

[0608] Update household accounting data

[0609] Server: The server automatically updates the household ledger based on the received financial data, adding new transactions to the database and updating existing transactions.

[0610] Input: Financial data sent from the terminal.

[0611] Output: Updated household accounting data.

[0612] Specific operation: The server connects to a database (e.g., MySQL), adds new entries to the household ledger based on the received data, and modifies any necessary parts.

[0613] Step 3:

[0614] Classification of expenditure data

[0615] Server: The server analyzes the updated household accounting data and categorizes the transactions into categories, including food, transportation, entertainment, etc.

[0616] Input: Updated household accounting data.

[0617] Output: Spending data broken down by category.

[0618] How it works: The server uses machine learning models (e.g., Scikit-learn) to automatically classify spending items based on transaction content.

[0619] Step 4:

[0620] Analysis of spending data

[0621] Server: The server analyzes the categorized spending data and calculates the amount, average, and frequency of spending for each category.

[0622] Input: Expense data broken down by category.

[0623] Output: Analysis of spending patterns.

[0624] Specific operation: The server uses the Python pandas library to aggregate data and generate statistics, such as calculating the average monthly food expenses or the total transportation expenses.

[0625] Step 5:

[0626] Creating and notifying savings offers

[0627] Server: Based on the analysis, it creates savings suggestions to reduce spending in specific categories and notifies the user.

[0628] Input: Analysis of spending patterns.

[0629] Output: Notification of savings suggestions.

[0630] How it works: The server uses a predefined rule-based system to generate savings suggestions and send push notifications to the user's device.

[0631] Step 6:

[0632] Estimating reorders of everyday items

[0633] Server: Based on past purchase history and data on frequency of use of everyday items, estimates items that need to be reordered.

[0634] Input: Past purchase history, usage frequency data.

[0635] Output: A list of items that need to be reordered.

[0636] Specific operation: The server analyzes past purchase data, calculates the consumption rate of a particular product, and determines when to reorder.

[0637] Step 7:

[0638] Automatic order execution

[0639] Server: Uses the API of an online shopping platform to automatically order the necessary items.

[0640] Input: A list of items that need to be reordered.

[0641] Output: Confirmation of order completion.

[0642] Specific operation: The server calls APIs such as Amazon and Rakuten, adds the estimated items to the order list, and executes the automatic order.

[0643] Step 8:

[0644] Generate customized lists and suggestions

[0645] Server: Learns the user's preferences and lifestyle patterns and generates customized shopping lists and savings suggestions.

[0646] Input: Past purchase history, lifestyle data.

[0647] Output: Customized shopping list, savings suggestions.

[0648] How it works: The server uses machine learning models (e.g., TensorFlow) to learn from the user's data and generate customized suggestions.

[0649] Step 9:

[0650] Real-time response and advice

[0651] User: The user types in a question.

[0652] Server: Uses a generative artificial intelligence model (e.g., GPT-4) to generate responses to user questions in real time.

[0653] Input: A question from the user.

[0654] Output: Real-time response.

[0655] How it works: When a user inputs a question such as "What everyday item should I buy next?", the server uses a generative AI model to generate an appropriate answer and provides it to the user.

[0656] (Application example 1)

[0657] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0658] Today's consumers spend a lot of time and effort managing their household finances and purchasing daily necessities. Therefore, they need a system that helps them efficiently manage their household finances and obtain the necessary consumables in a timely manner. However, physical stores lack the functionality to help users shop efficiently within their budget. Furthermore, the lack of real-time support based on savings suggestions and product guidance results in a suboptimal shopping experience.

[0659] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0660] In this invention, the server includes: means for receiving financial data entered by a user; means for automatically updating a household ledger based on the financial data; means for categorizing and analyzing the updated household ledger data; means for providing the user with savings suggestions based on the analysis results; means for predicting items that need to be reordered based on the frequency of use and purchase history of daily necessities; means for automatically ordering the predicted items in cooperation with an online shopping platform; means for synchronizing with the user's household data and purchase history and automatically generating a shopping list based on a budget when shopping in a physical store; and means for tracking in-store location information and using location information to guide the user to the appropriate shelves and sections. This allows users to shop efficiently within their budget even in physical stores and continuously obtain necessary items without missing them. Furthermore, the integration of home spending management and in-store shopping support provides comprehensive lifestyle support.

[0661] "Financial Data" means information relating to your finances, such as your income, expenses, and transaction information.

[0662] A "household account book" is a ledger that records a user's income and expenses and manages the status of assets and liabilities.

[0663] "Daily commodities" are items such as consumables and food that are used regularly in daily life.

[0664] An "online shopping platform" is an e-commerce venue where goods and services can be purchased via the Internet.

[0665] "Location tracking" is a technology that detects and tracks a user's current location.

[0666] A "generative artificial intelligence model" is an artificial intelligence technology that generates appropriate responses and suggestions based on input data.

[0667] A "shopping list" is a list of items that a user wants to purchase.

[0668] This invention is a comprehensive system that allows users to efficiently manage their household finances and purchase everyday items. The system has several main functions, each of which is designed to automate specific tasks and significantly reduce the burden on the user. Specific embodiments of the system are described below.

[0669] System configuration

[0670] The system mainly consists of a server, user terminals (smartphones, smart glasses, etc.), and in-store beacon devices.

[0671] 1. Receiving financial data and updating your household accounts:

[0672] The server receives financial data (income, expenses, and transaction information) entered by the user and automatically updates the household ledger based on that data.

[0673] This process uses a database management system (e.g., Firebase).

[0674] 2. Expenditure Classification and Analysis:

[0675] The server categorizes the updated household data and analyzes spending patterns, allowing it to calculate totals, averages, frequency, and other expenditures.

[0676] 3. Providing savings offers:

[0677] The server provides users with savings suggestions based on the analysis of their spending patterns, including advice on reducing spending in specific categories.

[0678] 4. Reorder Estimation and Auto Order:

[0679] The server learns the frequency of use and purchase history of everyday items and estimates which items need to be reordered.

[0680] Based on this estimation, the server will then work with an online shopping platform to automatically order the required items.

[0681] 5. In-store shopping assistance:

[0682] The user's device synchronizes with the server and automatically generates a shopping list based on the budget.

[0683] Using beacon devices in the store, the system tracks the user's location and guides them to the appropriate shelf or corner.

[0684] Example

[0685] Specifically, the following system can be implemented.

[0686] Enter financial data and update your household budget:

[0687] User: Enters bank transaction information into the system at the beginning of the month. Transaction information includes expenditures for food and transportation.

[0688] Server: Receives the entered transaction information and updates the household ledger. This update uses the Firebase database.

[0689] Expense classification and savings suggestions:

[0690] Server: Categorizes updated household accounting data by category and calculates total and average expenditures. Based on the analysis results, the server provides advice to the user, such as, "Your food expenses are high. You can save money by cutting down on eating out and cooking more at home."

[0691] Reordering everyday items:

[0692] Server: If it is estimated based on past purchase history that a consumable item (e.g., toothpaste) needs to be reordered, the server automatically places the order in cooperation with the online shopping platform.

[0693] In-store shopping assistance:

[0694] User device: Links with the beacon device in the store to identify the user's location and generates a real-time list of items that can be purchased within the user's specified budget.

[0695] In-store guidance: Beacon devices guide users to the shelves or corners where the products they are looking for are located, helping them shop more efficiently.

[0696] Examples of prompt statements

[0697] Based on the user's budget and recent purchase history, a generative AI model (e.g., GPT-4) is used to generate prompts such as:

[0698] Examples:

[0699] "User's budget is 10,000 yen, and their recent purchase history is as follows: Bread: 500 yen, Milk: 200 yen, Vegetables: 300 yen. Please provide some money-saving advice."

[0700] This system is expected to make household management and purchasing of everyday items more efficient, and to improve users' shopping experience in physical stores as well.

[0701] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0702] Step 1:

[0703] At the beginning of each month, users use a smartphone app to enter their banking information, which includes income and expenses such as food and transportation.

[0704] Input: Transaction information entered by the user

[0705] Output: Transaction information is sent to the server

[0706] Step 2:

[0707] The server receives the transaction information entered by the user and stores it in the Firebase database, which automatically updates the household account book based on this information.

[0708] Input: Transaction information sent by the user

[0709] Output: Updated household accounting data

[0710] Step 3:

[0711] The server categorizes the updated household budget data by category, such as food, transportation, entertainment, etc. It then analyzes spending patterns based on this data and calculates totals, averages, and frequency of spending for each category.

[0712] Input: Updated household accounting data

[0713] Output: Spending data broken down by category and analysis of spending patterns

[0714] Step 4:

[0715] The server generates saving suggestions for the user based on the analysis results. In this process, a generative artificial intelligence model (e.g., GPT-4) is used to generate specific advice prompts such as, "Your food costs are high. You can save money by cutting down on eating out and cooking more at home."

[0716] Input: Analysis of spending patterns

[0717] Output: Savings suggestions to the user

[0718] Step 5:

[0719] The server learns the frequency of use of everyday items and past purchase history, and predicts which items need to be reordered. For example, it learns how often toothpaste was used last time and predicts when it needs to be reordered.

[0720] Input: Frequency of use and purchase history of everyday items

[0721] Output: A list of items that need to be reordered

[0722] Step 6:

[0723] The server then connects with the online shopping platform to automatically place orders for items that are estimated to need reordering, a process that eliminates the need for users to manually place orders.

[0724] Input: List of items that need to be reordered

[0725] Output: Orders placed automatically

[0726] Step 7:

[0727] When a user shops in a physical store, the device synchronizes with the server and automatically generates a budget-based shopping list in real time.

[0728] Input: User budget information and real-time shopping data

[0729] Output: An automatically generated shopping list

[0730] Step 8:

[0731] Beacon devices in the store track users' location, and the terminal guides them to the appropriate shelf or section. For example, the beacon device identifies the user's location, and the smartphone notifies them that "there are discounted vegetables nearby."

[0732] Input: Location information from beacon device and shopping list

[0733] Output: Notification to guide the user to the product shelf or corner

[0734] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0735] This invention is a system that automates and streamlines the tedious tasks of managing household finances and purchasing everyday items. In particular, this system aims to provide more personalized services by incorporating an emotion engine that recognizes the user's emotions. The system receives financial data entered by the user, automatically updates the household ledger based on that data, and also provides the function of categorizing and analyzing expenses. This allows users to easily manage their expenses. It also predicts items that need to be reordered based on the frequency of use and purchase history of everyday items, and automatically places orders in conjunction with an online shopping platform, allowing users to continuously obtain necessary items without missing them. Furthermore, the system recognizes the user's emotions and adjusts the provided savings suggestions and shopping list based on the user's emotions.

[0736] System configuration and functions

[0737] 1. Receiving financial data and updating your household accounts:

[0738] Server: Receives financial data entered by the user, including income, expenses, and transaction information.

[0739] Server: Automatically updates the household ledger based on the received data. This update includes adding new transactions and modifying existing transactions.

[0740] 2. Expenditure classification and analysis:

[0741] Server: Categorizes the updated household accounting data by category, such as food, transportation, entertainment, etc.

[0742] Server: Analyzes the categorized spending data to understand user spending patterns, including calculating totals, averages, frequency, etc.

[0743] 3. Providing savings offers:

[0744] Server: Based on the analysis of spending patterns, the server provides users with savings suggestions. For example, if spending in a particular category is high, the server provides advice on reducing spending in that category.

[0745] 4. Reorder Estimation and Execution:

[0746] Server: Based on the frequency of use and purchase history of everyday items, it estimates what items need to be reordered. Examples include paper or plastic consumables and food.

[0747] Server: Connects to online shopping platforms and automatically places orders for the estimated items, allowing users to obtain the items they need in a timely manner.

[0748] 5. Customized Lists and Suggestions:

[0749] Server: Learns the user's preferences and lifestyle patterns and generates customized shopping lists and savings suggestions based on them, using past purchase history and lifestyle data.

[0750] 6. Real-time response and advice:

[0751] Server: Utilizes generative artificial intelligence models to respond to user questions and provide advice in real time, providing quick solutions to user concerns and improving the efficiency of daily life.

[0752] 7. Use of Emotion Engine:

[0753] Server: Includes an emotion engine that recognizes the user's emotions. The emotion engine detects emotions from the user's facial expressions, tone of voice, input text, etc.

[0754] Server: Tailors customized savings suggestions and shopping lists based on the user's emotions detected by the emotion engine. For example, if the user is feeling stressed, it can recommend relaxation items to relieve stress.

[0755] Server: Based on the user's emotions detected by the emotion engine, the server adjusts responses and advice content in real time, thereby providing personalized advice according to the user's emotional state.

[0756] Specific examples

[0757] User: At the beginning of each month, the user enters their bank transaction information into the system, including food and transportation expenses.

[0758] Terminal: The terminal transmits the entered transaction information to the server.

[0759] Server: The server receives the transaction information and updates the household ledger. The updated household ledger classifies the transaction information by category and generates analysis results.

[0760] Server: Based on the analysis results, the server provides users with money-saving suggestions such as, "Your food costs are high. You can save money by cutting down on eating out and cooking more at home."

[0761] Server: Learns from past purchase history how often the toothpaste purchased last time is used, and if it determines that a reorder is necessary, it automatically places the order.

[0762] Server: Further customizes and recommends the next shopping list based on the user's preferences and lifestyle patterns.

[0763] Server: Uses generative artificial intelligence models to provide appropriate advice in response to real-time questions from users.

[0764] Server: Uses an emotion engine to sense the user's emotions and tailor savings suggestions and shopping lists accordingly. For example, if the user is tired, recommend items that will help reduce stress.

[0765] Server: Tailors real-time responses and advice based on the emotion engine, providing personalized support according to the user's emotional state.

[0766] The system enables automatic and efficient household management and daily necessities purchasing, and also provides personalized services based on users' emotions, significantly reducing users' time and effort and improving their quality of life.

[0767] The processing flow will be explained below.

[0768] Step 1:

[0769] The user enters bank transaction information and a new purchase history. For example, the transaction information includes a food expense of 50 yen and a transportation expense of 20 yen, and the new purchase history is recorded as "toothpaste."

[0770] Step 2:

[0771] The terminal sends the transaction information and purchase history entered by the user to the server. The transmitted data includes the date and time of the transaction, the amount, and the category.

[0772] Step 3:

[0773] The server stores the received transaction information as financial data and also stores the new purchase history in a purchase database.

[0774] Step 4:

[0775] The server updates the household ledger with the financial data, which includes adding new transactions and modifying existing transactions.

[0776] Step 5:

[0777] The server categorizes the household accounting data into categories, such as food, transportation, and entertainment expenses.

[0778] Step 6:

[0779] The server analyzes the classified household account data to understand the user's spending patterns, including total and average spending amounts and frequency of spending.

[0780] Step 7:

[0781] The server uses an emotion engine to recognize the user's emotions, using information such as the user's facial expression, tone of voice, and input text to determine the emotion.

[0782] Step 8:

[0783] The server generates money-saving suggestions based on the analysis results and the recognition results of the emotion engine. For example, if a user is feeling stressed because of high food expenses, the server will suggest, "Your food expenses are high. You can save money by cutting down on eating out and cooking more at home, which will also help reduce stress."

[0784] Step 9:

[0785] The server learns the user's purchase history and frequency of use and predicts which items need to be reordered. For example, it determines that a reorder is necessary based on how often toothpaste was used last time.

[0786] Step 10:

[0787] The server places an order for the estimated reorder items to the online shopping platform, utilizing an automatic ordering function to save the user the trouble of manually placing the order.

[0788] Step 11:

[0789] The server generates customized shopping lists and savings suggestions based on the results of the emotion engine. For example, if the user has the emotion of wanting to relax, it will recommend relaxation items.

[0790] Step 12:

[0791] The server sends the generated customized shopping list and savings suggestions to the terminal, which displays them to the user.

[0792] Step 13:

[0793] When a user asks a question in real time, the server uses a generative artificial intelligence model to provide answers and advice to the user's questions.

[0794] Step 14:

[0795] The server adjusts its real-time responses and advice based on the user's emotions detected by the emotion engine. For example, if the user is feeling irritated, the server will provide calm advice to calm the user.

[0796] Step 15:

[0797] The terminal displays the responses and advice received from the server to the user, thereby helping the user to efficiently manage their household finances and purchase everyday items.

[0798] Example 2

[0799] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0800] In modern life, managing household finances and purchasing everyday items requires a significant amount of time and effort. Furthermore, conventional household finance management and purchasing systems lack the ability to provide personalized services that take user emotions into account, making it difficult to increase user satisfaction. The present invention aims to solve these problems by streamlining and automating household finance management and providing personalized responses based on user emotions.

[0801] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0802] In this invention, the server includes: means for receiving financial data input by a user; means for automatically updating a household account book based on the financial data; means for classifying and analyzing the updated household account book data; means for providing the user with money-saving suggestions based on the analysis results; means for predicting items that need to be reordered based on the frequency of use and purchase history of daily necessities; means for automatically ordering the predicted items in cooperation with an e-commerce platform; means including an emotion engine that recognizes user emotions; and means for adjusting money-saving suggestions and a shopping list based on the user emotions sensed by the emotion engine. This allows the user to automatically manage their household finances, obtain necessary items in a timely manner, and receive personalized services according to their emotions.

[0803] "User" refers to any individual or organization that uses this system.

[0804] "Financial Data" refers to information related to a user's economic activities, such as income, expenses, and transaction information.

[0805] A "household account book" refers to a digital or physical ledger that allows a user to record and manage their income and expenses.

[0806] "Classification" refers to the process of separating household data into categories, such as food, transportation, and entertainment.

[0807] "Analysis" refers to the process of statistically analyzing household accounting data to identify spending patterns and unusual spending.

[0808] "Savings suggestions" refers to providing financial advice to users based on the analysis of their household accounting data.

[0809] "Frequency of use" refers to data indicating how often an everyday item is used.

[0810] "Purchase history" refers to data that records the items a user has previously purchased and their detailed information.

[0811] "Reordering" refers to the process of reordering needed items based on frequency of use and purchase history.

[0812] "E-commerce platform" refers to a website or application for buying and selling goods and services online.

[0813] An "emotion engine" refers to technology that detects emotions from a user's facial expressions, tone of voice, input text, etc.

[0814] "Personalization" refers to customizing services and offers based on the individual characteristics and circumstances of each user.

[0815] The present invention is a system that allows users to automate and streamline the tedious tasks of managing their household finances and purchasing everyday items. The system is designed to receive financial data, update household accounts, categorize and analyze expenses, provide savings suggestions, estimate and execute reorders for everyday items, and provide customized suggestions based on the user's emotions.

[0816] Receive financial data and update your household budget

[0817] At the beginning of each month, users enter financial data, such as bank transaction information and cash expenditure information, into the system. Specific examples include food expenditures of 1,000 yen and transportation expenditures of 3,000 yen. The data entered by the user is sent to the server via the terminal. Based on the received data, the server adds new transactions to the household accounting database and modifies existing transactions. For example, if the total food expenditures for August were 5,000 yen, a new expenditure of 1,000 yen would be added, bringing the total to 6,000 yen.

[0818] Expense classification and analysis

[0819] The server analyzes the updated household ledger data and classifies each transaction into a category. Specific examples include food expenses, transportation expenses, and entertainment expenses. Based on this, the server categorizes food-related transactions into the "food" category and transportation-related transactions into the "transportation" category. Based on the expenditure data for each category, the server calculates statistical information such as total expenditures, frequency, and average amounts. For example, it calculates the average monthly food expenses and compares them between years. The server detects spending trends and unusual spending patterns. For example, if transportation expenses spike in a particular month, it analyzes the cause.

[0820] Providing savings suggestions

[0821] The server generates savings suggestions tailored to the user based on the analysis of spending patterns. For example, a user with high transportation costs may be advised to consider commuting by bicycle. The generated savings suggestions are sent to the device, which then displays them to the user, suggesting specific ways to save money.

[0822] Reorder estimation and execution

[0823] Based on the frequency of use and purchase history of everyday items, the server estimates which items need to be reordered. As a specific example, it estimates when the next purchase will be based on the rate at which toilet paper was used the last time it was purchased. Information on items that are estimated to be needed is obtained by the server, and a decision is made as to whether to reorder them based on the user's purchase history. If it is determined that a reorder is necessary, the server will link with the e-commerce platform via API or other means to automatically place the order. After the order is completed, the server will notify the user of the order details.

[0824] Generate customized suggestions and lists

[0825] The server analyzes the user's past purchase history and lifestyle data to generate customized shopping lists and suggestions. For example, a user who buys a lot of ingredients on the weekend will be offered "recommended ingredients for this weekend." Savings suggestions tailored to the user's preferences are also offered. The customized lists and suggestions are displayed to the user through their device.

[0826] Real-time response and advice

[0827] A user inputs a question about household management into the system in real time. A specific example is, "How can I reduce my food expenses this month?" The device sends the question to the server, which uses a generative AI model (e.g., a generative AI model) to generate an appropriate answer to the user's question. The generated answer is sent to the device, which displays the generated answer to the user in real time.

[0828] Use of emotion engine

[0829] The system reads emotions from the user's tone of voice and input text. For example, if the input text is "tired," it will detect stress. Emotional data is sent to the server via the device, and the server uses an emotion engine to analyze the user's emotions. Based on the emotions, customized savings suggestions and shopping lists are adjusted. The response of the generative AI model is also customized based on the emotion data, providing personalized advice according to the user's current emotional state.

[0830] Prompt Sentence Examples

[0831] User: I want to enter my monthly expenses. How can I get the data reflected in my household ledger?

[0832] Terminal: Sends entered data to the server.

[0833] Server: Automatically updates the household account book based on bank transaction information and analyzes expenses.

[0834] This system allows users to efficiently manage their household finances, obtain necessary items in a timely manner, and receive personalized services based on their emotions, which can significantly reduce users' time and effort and improve their quality of life.

[0835] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0836] Step 1:

[0837] Entering and submitting financial data

[0838] At the beginning of each month, users enter their financial data, such as bank transaction information and cash expenditure information, into the system. For example, they enter 1,000 yen in food expenses and 3,000 yen in transportation expenses. The terminal then sends this input data to the server.

[0839] Input: Financial data such as food expenses, transportation expenses, etc.

[0840] Output: Financial data sent to the server

[0841] Step 2:

[0842] Receiving data and updating the household account book

[0843] The server receives the financial data sent from the device. Based on the received data, the server adds new transactions to the household accounting database and modifies existing transactions. For example, if the total food expenditure for August was 5,000 yen, it will add a new expenditure of 1,000 yen to update it to 6,000 yen.

[0844] Input: Financial data sent from the terminal

[0845] Processing: Update the household accounting database (add new transactions, modify existing transactions)

[0846] Output: Updated household account book

[0847] Step 3:

[0848] Expense Category Classification

[0849] The server categorizes the updated household accounting data into categories, such as food expenses, transportation expenses, and entertainment expenses.

[0850] Input: Updated household accounting data

[0851] Processing: Categorizing transaction data (e.g., food, transportation, entertainment)

[0852] Output: Household accounting data categorized by category

[0853] Step 4:

[0854] Analysis of spending patterns

[0855] The server calculates statistics such as total expenditures, frequency, and average amounts based on each category of expenditure data. For example, it calculates the average monthly food expenditure and compares it year-over-year. It also detects expenditure trends and unusual patterns.

[0856] Input: Household accounting data categorized by category

[0857] Processing: Calculating statistical information (total, frequency, average amount of expenditure)

[0858] Output: Spending statistics and analysis results

[0859] Step 5:

[0860] Generate and notify savings suggestions

[0861] The server generates savings suggestions tailored to the user based on the analysis of spending patterns. For example, it might suggest to a user with high transportation costs, "Consider commuting by bicycle." The generated savings suggestions are sent to the device, which then displays them to the user.

[0862] Input: Spending statistics and analysis results

[0863] Processing: Generate savings proposals

[0864] Output: Generated savings proposals

[0865] Step 6:

[0866] Estimating reorders of everyday items

[0867] The server estimates which items need to be reordered based on the frequency of use and purchase history of everyday items. For example, it estimates when the next purchase will be made based on the rate at which toilet paper was used last time.

[0868] Input: Usage frequency and purchase history data

[0869] Processing: Usage frequency analysis, reorder estimation

[0870] Output: List of items that need to be reordered

[0871] Step 7:

[0872] Automatic order execution

[0873] If it is determined that a reorder is necessary, the server will automatically place the order by connecting with the e-commerce platform via API, etc. After the order is completed, the server will notify the user of the order details.

[0874] Input: List of items that need to be reordered

[0875] Processing: Integration with e-commerce platforms, automatic order execution

[0876] Output: Order details notification

[0877] Step 8:

[0878] Customization suggestions based on user preferences

[0879] The server analyzes the user's past purchase history and lifestyle data to generate customized shopping lists and savings suggestions. For example, it provides "recommended ingredients for this weekend" to users who buy a lot of ingredients on the weekend.

[0880] Input: Past purchase history, lifestyle data

[0881] Processing: Analysis of preferences and lifestyle patterns, generation of customization suggestions

[0882] Output: customized shopping list and savings suggestions

[0883] Step 9:

[0884] Real-time question responses

[0885] Users input questions about household finances into the system in real time. A typical example is, "How can I reduce my food expenses this month?" The device sends the question to the server, which uses a generative AI model (e.g., a generative AI model) to generate an appropriate answer to the user's question. The generated answer is sent to the device and displayed to the user in real time.

[0886] Input: Real-time questions

[0887] Processing: Answer generation using generative AI models

[0888] Output: The generated answer

[0889] Step 10:

[0890] Receiving and analyzing emotion data

[0891] The system reads emotions from the user's tone of voice and input text. For example, if the input text is "tired," it will detect stress. Emotion data is sent to the server via the device, and the server uses an emotion engine to analyze the user's emotions.

[0892] Input: The user's tone of voice and input text

[0893] Processing: Emotion recognition and data generation

[0894] Output: User emotion data

[0895] Step 11:

[0896] Tailoring personalized suggestions based on emotions

[0897] Based on the emotional data, the server will tailor customized savings suggestions and shopping lists. For example, if the user is tired, it will add relaxation items to the shopping list. The emotional data will also customize the generative AI model's response, providing personalized advice based on the user's current emotional state.

[0898] Input: User emotion data

[0899] Processing: tailoring suggestions and customizing responses with generative AI models

[0900] Output: Tailored savings suggestions, shopping lists, personalized advice

[0901] (Application example 2)

[0902] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0903] Today's users are required to efficiently manage their household finances and purchase daily necessities amid their busy lives. However, these tasks are time-consuming and lack emotionally-sensitive personalized support, which increases user stress. Conventional systems have struggled to streamline household finances and purchase daily necessities, while providing personalized suggestions in a unified manner. Therefore, there is a need for the development of a system that automates and streamlines household finances and purchases while providing emotionally-sensitive support.

[0904] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving financial data input by a user, means for automatically updating the household account book based on the financial data, means for classifying and analyzing the updated household account book data, means for providing the user with money-saving suggestions based on the analysis results, means for predicting items that need to be reordered based on the frequency of use and purchase history of daily necessities, means for automatically ordering the predicted items in cooperation with an e-commerce platform, and means for recognizing the user's emotions using an emotion recognition engine and providing personalized suggestions based on the recognized emotions. This enables the user to efficiently manage their household finances and purchase daily necessities while receiving support based on their emotions.

[0905] "User" refers to an individual who uses the system to manage their household finances and purchase everyday items.

[0906] "Financial Data" refers to data related to economic activity, such as income, expenses, and transaction information entered by users.

[0907] A "household account book" refers to a ledger used to record and manage a user's income and expenses.

[0908] An "emotion recognition engine" refers to a system that detects emotions from a user's facial expressions, tone of voice, input text, etc.

[0909] "Savings Suggestions" refers to advice that analyzes a user's spending patterns and suggests ways to save money.

[0910] "Items that need to be reordered" refers to items that are determined to need to be purchased again based on the frequency of use and purchase history of everyday items.

[0911] "E-commerce platform" refers to a website or application that allows users to buy and sell goods and services online.

[0912] "Personalized suggestions" refers to providing specific advice or recommendations based on a user's emotions and preferences.

[0913] A "generative artificial intelligence model" refers to an artificial intelligence that generates answers and advice based on input data and questions.

[0914] This invention is a system that helps users manage their household finances and purchase everyday items efficiently. The system uses an emotion recognition engine and a generative artificial intelligence model to provide personalized suggestions based on the user's emotions.

[0915] The server first receives financial data entered by the user. Financial data includes income, expenses, and transaction information. For example, the user enters bank transaction information using a smartphone. This data is automatically updated in the household ledger.

[0916] The updated household accounting data is then classified and analyzed. Spending patterns are categorized and the total amount and frequency are calculated. Based on the results of this analysis, savings suggestions are provided to the user. For example, if the analysis shows that food expenses are high, the system will suggest "eating out less and cooking more at home."

[0917] Based on the frequency of use and purchase history of everyday items, the system predicts which items need to be reordered. For example, this applies to consumables such as paper products and food. The server then automatically orders these items in conjunction with the e-commerce platform, allowing users to obtain the items they need in a timely manner.

[0918] The emotion recognition engine recognizes emotions from the user's facial expressions, tone of voice, input text, etc. For example, if the user is feeling stressed, it will recommend relaxation items. Making suggestions based on emotions improves user satisfaction.

[0919] The generative AI model responds to real-time questions from users and generates appropriate advice based on the input data and questions. For example, if a user asks, "How can I reduce my food expenses this month?", the model will provide specific advice.

[0920] The hardware used includes a smartphone, the emotion recognition engine is Microsoft Azure's Emotion API, and the generative artificial intelligence model is OpenAI's GPT.

[0921] Examples:

[0922] Users input financial data into the system via a smartphone app. The server receives the data and automatically updates the household ledger. Next, an emotion recognition engine detects stress levels from the user's facial expressions and suggests relaxation items. Meanwhile, a generative AI model provides real-time advice, such as "You can cut down on food costs by eating out less."

[0923] Example prompt sentence:

[0924] Consider user emotions and offer advice on buying and saving money on everyday items.

[0925] The user seems tired. Suggest items or foods that will help them relax.

[0926] The system allows users to efficiently manage their finances and purchase everyday items while receiving emotional support.

[0927] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0928] Step 1: Enter your financial data

[0929] A user uses a smartphone to input financial data such as income, expenses, and transaction information. This financial data is sent from the device to a server. The input data includes categories such as income, food expenses, and transportation expenses, along with the amounts for each. The server temporarily stores the received data.

[0930] Step 2: Update your household budget

[0931] The server automatically updates the household ledger based on the received financial data. Specifically, it analyzes transaction information and categorizes them. It adds and modifies new transactions to the previous household ledger to create a household ledger that reflects the user's latest financial situation. The updated household ledger is obtained as output.

[0932] Step 3: Categorize and analyze expenses

[0933] The server categorizes and analyzes the updated household accounting data. It categorizes income and expenses by category and calculates the total amount and frequency of spending for each category. The analysis results include total expenditures and spending patterns for each category, such as food, transportation, and entertainment. This allows users to understand their spending habits.

[0934] Step 4: Generate savings proposals

[0935] The server generates savings suggestions for the user based on the results of the expenditure analysis. For example, if expenditures in a particular category are high, specific advice on reducing spending in that category is provided. Saving suggestions are generated using a generative AI model and are tailored to the user's lifestyle. Saving suggestions are obtained as the output.

[0936] Step 5: Estimate reorders

[0937] The server estimates which items need to be reordered based on the frequency of use and purchase history of daily items. It analyzes purchase history data and predicts when repurchases will be necessary. For example, it estimates the timing of repurchase based on the period of use of toothpaste previously purchased. The output is a list of items that can be reordered.

[0938] Step 6: Execute an automatic order

[0939] The server automatically orders the estimated reorder candidate items in cooperation with the e-commerce platform. It checks the stock status and price of the necessary items and executes the order at the optimal time. This allows users to regularly secure the daily necessities they need. The output is confirmation data that the automatic order has been completed.

[0940] Step 7: Emotion Recognition and Custom Suggestions

[0941] The server uses an emotion recognition engine to recognize the user's emotions. It analyzes the input text, tone of voice, and facial expression data to determine the user's emotional state (e.g., stress or happiness). Based on the recognized emotions, it personalizes saving suggestions and shopping lists to provide suggestions that the user desires. The output is customized suggestions based on emotions.

[0942] Step 8: Real-time support

[0943] The server uses a generative AI model to respond to real-time questions from users. For example, in response to a question like, "How can I reduce my food expenses this month?", it will suggest detailed ways to save money. The AI ​​generates a response based on the prompt text, providing the user with timely and useful information. The output is specific advice.

[0944] Through these steps, users can manage their household finances and purchase everyday items efficiently and personalizedly.

[0945] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0946] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0947] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0948] [Third embodiment]

[0949] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0950] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0951] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0952] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0953] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0954] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0955] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0956] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0957] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0958] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0959] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0960] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0961] This invention is a system that automates and streamlines the tedious tasks of managing household finances and purchasing everyday items. The system receives financial data entered by the user, automatically updates the household ledger based on that data, and also provides the functionality of categorizing and analyzing expenditures. This allows users to easily manage their expenditures. It also predicts items that need to be reordered based on the frequency of use and purchase history of everyday items, and automatically places orders in conjunction with an online shopping platform. These functions allow users to continuously obtain the items they need without missing them.

[0962] System configuration and functions

[0963] 1. Receiving financial data and updating your household accounts:

[0964] Server: Receives financial data entered by the user, including income, expenses, and transaction information.

[0965] Server: Automatically updates the household ledger based on the received data. This update includes adding new transactions and modifying existing transactions.

[0966] 2. Expenditure classification and analysis:

[0967] Server: Categorizes the updated household accounting data by category, such as food, transportation, entertainment, etc.

[0968] Server: Analyzes the categorized spending data to understand user spending patterns, including calculating totals, averages, frequency, etc.

[0969] 3. Providing savings offers:

[0970] Server: Based on the analysis of spending patterns, the server provides users with savings suggestions. For example, if spending in a particular category is high, the server provides advice on reducing spending in that category.

[0971] 4. Reorder Estimation and Execution:

[0972] Server: Based on the frequency of use and purchase history of everyday items, it estimates what items need to be reordered. Examples include paper or plastic consumables and food.

[0973] Server: Connects to online shopping platforms and automatically places orders for the estimated items, allowing users to obtain the items they need in a timely manner.

[0974] 5. Customized Lists and Suggestions:

[0975] Server: Learns the user's preferences and lifestyle patterns and generates customized shopping lists and savings suggestions based on them, using past purchase history and lifestyle data.

[0976] 6. Real-time response and advice:

[0977] Server: Utilizes generative artificial intelligence models to respond to user questions and provide advice in real time, providing quick solutions to user concerns and improving the efficiency of daily life.

[0978] Specific examples

[0979] User: At the beginning of each month, the user enters their bank transaction information into the system, including food and transportation expenses.

[0980] Terminal: The terminal transmits the entered transaction information to the server.

[0981] Server: The server receives the transaction information and updates the household ledger. The updated household ledger classifies the transaction information by category and generates analysis results.

[0982] Server: Based on the analysis results, the server provides users with money-saving suggestions such as, "Your food costs are high. You can save money by cutting down on eating out and cooking more at home."

[0983] Server: Learns from past purchase history how often the toothpaste purchased last time is used, and if it determines that a reorder is necessary, it automatically places the order.

[0984] Server: Further customizes and recommends the next shopping list based on the user's preferences and lifestyle patterns.

[0985] Server: Uses generative artificial intelligence models to provide appropriate advice in response to real-time questions from users.

[0986] This system allows users to automatically and efficiently manage their household finances and purchase everyday items, significantly reducing the time and effort required. It also provides customization based on the user's lifestyle, enabling support that meets individual needs.

[0987] The processing flow will be explained below.

[0988] Step 1:

[0989] The user enters bank transaction information and a new purchase history. For example, the transaction information includes a food expense of 50 yen and a transportation expense of 20 yen, and the new purchase history is recorded as "toothpaste."

[0990] Step 2:

[0991] The terminal sends the transaction information and purchase history entered by the user to the server. The transmitted data includes the date and time of the transaction, the amount, and the category.

[0992] Step 3:

[0993] The server stores the received transaction information as financial data and also stores the new purchase history in a purchase database.

[0994] Step 4:

[0995] The server updates the household ledger with the financial data, which includes adding new transactions and modifying existing transactions.

[0996] Step 5:

[0997] The server categorizes the household accounting data into categories, such as food, transportation, and entertainment expenses.

[0998] Step 6:

[0999] The server analyzes the classified household account data to understand the user's spending patterns, including total and average spending amounts and frequency of spending.

[1000] Step 7:

[1001] The server generates savings suggestions based on the analysis results. For example, if food expenses are high, it will suggest "cut down on eating out and cook more at home."

[1002] Step 8:

[1003] The server learns the user's purchase history and frequency of use and predicts which items need to be reordered. For example, it determines that toothpaste needs to be reordered based on how often it was used last time.

[1004] Step 9:

[1005] The server places an order for the estimated reorder items to the online shopping platform, utilizing an automatic ordering function to save the user the trouble of manually placing the order.

[1006] Step 10:

[1007] The server learns the user's behavioral patterns and preferences and generates customized shopping lists and savings suggestions, taking into account the user's past purchasing habits and lifestyle.

[1008] Step 11:

[1009] The server sends the generated customized shopping list and savings suggestions to the terminal, which displays them to the user.

[1010] Step 12:

[1011] When a user asks a question in real time, the server uses a generative artificial intelligence model to provide answers and advice to the user's questions.

[1012] Step 13:

[1013] The terminal displays the responses and advice received from the server to the user, thereby helping the user to efficiently manage their household finances and purchase everyday items.

[1014] Example 1

[1015] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1016] Conventional household management systems require users to manually input and manage data, which is cumbersome and time-consuming. Furthermore, they lack sufficient analysis of spending, making it difficult to provide efficient savings suggestions or reorder everyday items. Additionally, there was a lack of a system that allowed users to ask questions or seek advice in real time.

[1017] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1018] In this invention, the server includes: means for receiving financial data entered by a user; means for automatically updating a household ledger based on the financial data; means for categorizing the updated household ledger data; means for analyzing the categorized expenditure data to understand spending patterns; means for providing the user with money-saving suggestions based on the analysis results; means for predicting items that need to be reordered based on the frequency of use and purchase history of daily necessities; means for automatically ordering the predicted items in cooperation with an online shopping platform; and means for responding to questions from the user in real time using a generative artificial intelligence model. This enables automated and efficient household management and reordering of daily necessities. Furthermore, by providing users with advice in real time, it is possible to improve the efficiency of their daily lives.

[1019] "User" refers to any individual or group who uses this system.

[1020] "Financial data" refers to economic information necessary for managing household finances, such as income, expenditures, and transaction information.

[1021] A "household account book" refers to a ledger or collection of digital data that compiles records of income and expenses.

[1022] A "category" is a group name used to classify income and expenses, and mainly refers to general expenditure items such as food, transportation, and entertainment.

[1023] "Spending patterns" refers to a user's spending trends and habits over a specific period of time.

[1024] "Savings suggestions" refers to advice and recommended specific actions to reduce spending.

[1025] "Everyday items" are items that are frequently used in daily life, including consumables and food.

[1026] "Frequency of use" refers to the number of times a good or service is used within a specific period of time.

[1027] "Purchase history" refers to a record of products a user has purchased in the past.

[1028] "Online Shopping Platform" refers to a website or application for buying and selling goods and services over the Internet.

[1029] A "generative artificial intelligence model" refers to an AI system that generates text or responses based on a trained dataset, such as a natural language processing model like GPT-4.

[1030] "Real-time response" refers to providing immediate answers to user inquiries and questions.

[1031] This invention is a system that automates and streamlines the tedious tasks of managing household finances and purchasing everyday items. The system receives financial data entered by the user, automatically updates the household ledger based on that data, and also provides the functionality of categorizing and analyzing expenditures. It also predicts items that need to be reordered based on the frequency of use and purchase history of everyday items, and automatically places orders in conjunction with an online shopping platform. This allows users to continuously obtain the items they need without missing them.

[1032] System Hardware and Software

[1033] Hardware

[1034] Server: The server acts as the central processing unit of the system and performs major tasks such as receiving data, analyzing, classifying, automatic ordering, and real-time response.

[1035] Device: The device on which a user enters data and receives notifications, such as a smartphone, tablet, or computer.

[1036] software

[1037] Database: Used within the server to store financial data, household accounting data, purchase history, etc. For example, MySQL or PostgreSQL is used.

[1038] Analysis tools: Data analysis and statistical calculations are performed using Python's pandas library, etc.

[1039] Machine learning models: Used to classify spending and generate customized recommendations. Use frameworks such as Scikit-learn and TensorFlow.

[1040] Generative AI models: Used to respond to user questions in real time. Natural language processing models such as GPT-4 fall into this category.

[1041] API integration: To integrate with online shopping platforms, RESTful APIs are used to automate orders.

[1042] Specific examples

[1043] Example 1: Automating household accounting management

[1044] User: At the beginning of each month, the user enters their bank transaction information into the system, including food and transportation expenses.

[1045] Terminal: The terminal transmits the entered transaction information to the server.

[1046] Server: The server updates the household ledger based on the received transaction information. The updated household ledger classifies the transaction information by category and generates analysis results.

[1047] Server: Based on the analysis results, the server provides users with money-saving suggestions such as, "Your food costs are high. You can save money by cutting down on eating out and cooking more at home."

[1048] Example 2: Automatic reordering of everyday items

[1049] Server: Learns from past purchase history how often the toothpaste purchased last time is used, and if it determines that a reorder is necessary, it automatically places the order.

[1050] Server: Further customizes and recommends the next shopping list based on the user's preferences and lifestyle patterns.

[1051] Example 3: Real-time response

[1052] User: The user types a question: "What everyday item should I buy next?"

[1053] Server: The generative AI model analyzes this question and generates an appropriate answer, such as, "The next thing you should buy is toothpaste. Based on how quickly it's being consumed, it's estimated that a reorder will be necessary."

[1054] Specific prompt examples:

[1055] "What can I do to save money on food?"

[1056] "What everyday item should I buy next?"

[1057] "Tell me about your recent spending patterns."

[1058] In this way, the system of the present invention supports users' economic activities by streamlining and automating their household finances and purchasing everyday items. Furthermore, by using generative AI models, the system can provide advice and answers to questions in real time.

[1059] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1060] Step 1:

[1061] User financial data entry and submission

[1062] User: At the beginning of the month, users use devices such as smartphones or computers to enter financial data such as income, expenses, and transaction information. The data entered includes items such as food, transportation, and entertainment expenses.

[1063] Terminal: The terminal formats the entered financial data and sends it to the server.

[1064] Input: Income, expense, and transaction information entered by the user.

[1065] Output: The formatted financial data is sent to the server.

[1066] Specific operation: When a user opens the application, enters the required information into the form, and presses the submit button, the terminal sends the input data to the server.

[1067] Step 2:

[1068] Update household accounting data

[1069] Server: The server automatically updates the household ledger based on the received financial data, adding new transactions to the database and updating existing transactions.

[1070] Input: Financial data sent from the terminal.

[1071] Output: Updated household accounting data.

[1072] Specific operation: The server connects to a database (e.g., MySQL), adds new entries to the household ledger based on the received data, and modifies any necessary parts.

[1073] Step 3:

[1074] Classification of expenditure data

[1075] Server: The server analyzes the updated household accounting data and categorizes the transactions into categories, including food, transportation, entertainment, etc.

[1076] Input: Updated household accounting data.

[1077] Output: Spending data broken down by category.

[1078] How it works: The server uses machine learning models (e.g., Scikit-learn) to automatically classify spending items based on transaction content.

[1079] Step 4:

[1080] Analysis of spending data

[1081] Server: The server analyzes the categorized spending data and calculates the amount, average, and frequency of spending for each category.

[1082] Input: Expense data broken down by category.

[1083] Output: Analysis of spending patterns.

[1084] Specific operation: The server uses the Python pandas library to aggregate data and generate statistics, such as calculating the average monthly food expenses or the total transportation expenses.

[1085] Step 5:

[1086] Creating and notifying savings offers

[1087] Server: Based on the analysis, it creates savings suggestions to reduce spending in specific categories and notifies the user.

[1088] Input: Analysis of spending patterns.

[1089] Output: Notification of savings suggestions.

[1090] How it works: The server uses a predefined rule-based system to generate savings suggestions and send push notifications to the user's device.

[1091] Step 6:

[1092] Estimating reorders of everyday items

[1093] Server: Based on past purchase history and data on frequency of use of everyday items, estimates items that need to be reordered.

[1094] Input: Past purchase history, usage frequency data.

[1095] Output: A list of items that need to be reordered.

[1096] Specific operation: The server analyzes past purchase data, calculates the consumption rate of a particular product, and determines when to reorder.

[1097] Step 7:

[1098] Automatic order execution

[1099] Server: Uses the API of an online shopping platform to automatically order the necessary items.

[1100] Input: A list of items that need to be reordered.

[1101] Output: Confirmation of order completion.

[1102] Specific operation: The server calls APIs such as Amazon and Rakuten, adds the estimated items to the order list, and executes the automatic order.

[1103] Step 8:

[1104] Generate customized lists and suggestions

[1105] Server: Learns the user's preferences and lifestyle patterns and generates customized shopping lists and savings suggestions.

[1106] Input: Past purchase history, lifestyle data.

[1107] Output: Customized shopping list, savings suggestions.

[1108] How it works: The server uses machine learning models (e.g., TensorFlow) to learn from the user's data and generate customized suggestions.

[1109] Step 9:

[1110] Real-time response and advice

[1111] User: The user types in a question.

[1112] Server: Uses a generative artificial intelligence model (e.g., GPT-4) to generate responses to user questions in real time.

[1113] Input: A question from the user.

[1114] Output: Real-time response.

[1115] How it works: When a user inputs a question such as "What everyday item should I buy next?", the server uses a generative AI model to generate an appropriate answer and provides it to the user.

[1116] (Application example 1)

[1117] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1118] Today's consumers spend a lot of time and effort managing their household finances and purchasing daily necessities. Therefore, they need a system that helps them efficiently manage their household finances and obtain the necessary consumables in a timely manner. However, physical stores lack the functionality to help users shop efficiently within their budget. Furthermore, the lack of real-time support based on savings suggestions and product guidance results in a suboptimal shopping experience.

[1119] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1120] In this invention, the server includes: means for receiving financial data entered by a user; means for automatically updating a household ledger based on the financial data; means for categorizing and analyzing the updated household ledger data; means for providing the user with savings suggestions based on the analysis results; means for predicting items that need to be reordered based on the frequency of use and purchase history of daily necessities; means for automatically ordering the predicted items in cooperation with an online shopping platform; means for synchronizing with the user's household data and purchase history and automatically generating a shopping list based on a budget when shopping in a physical store; and means for tracking in-store location information and using location information to guide the user to the appropriate shelves and sections. This allows users to shop efficiently within their budget even in physical stores and continuously obtain necessary items without missing them. Furthermore, the integration of home spending management and in-store shopping support provides comprehensive lifestyle support.

[1121] "Financial Data" means information relating to your finances, such as your income, expenses, and transaction information.

[1122] A "household account book" is a ledger that records a user's income and expenses and manages the status of assets and liabilities.

[1123] "Daily commodities" are items such as consumables and food that are used regularly in daily life.

[1124] An "online shopping platform" is an e-commerce venue where goods and services can be purchased via the Internet.

[1125] "Location tracking" is a technology that detects and tracks a user's current location.

[1126] A "generative artificial intelligence model" is an artificial intelligence technology that generates appropriate responses and suggestions based on input data.

[1127] A "shopping list" is a list of items that a user wants to purchase.

[1128] This invention is a comprehensive system that allows users to efficiently manage their household finances and purchase everyday items. The system has several main functions, each of which is designed to automate specific tasks and significantly reduce the burden on the user. Specific embodiments of the system are described below.

[1129] System configuration

[1130] The system mainly consists of a server, user terminals (smartphones, smart glasses, etc.), and in-store beacon devices.

[1131] 1. Receiving financial data and updating your household accounts:

[1132] The server receives financial data (income, expenses, and transaction information) entered by the user and automatically updates the household ledger based on that data.

[1133] This process uses a database management system (e.g., Firebase).

[1134] 2. Expenditure Classification and Analysis:

[1135] The server categorizes the updated household data and analyzes spending patterns, allowing it to calculate totals, averages, frequency, and other expenditures.

[1136] 3. Providing savings offers:

[1137] The server provides users with savings suggestions based on the analysis of their spending patterns, including advice on reducing spending in specific categories.

[1138] 4. Reorder Estimation and Auto Order:

[1139] The server learns the frequency of use and purchase history of everyday items and estimates which items need to be reordered.

[1140] Based on this estimation, the server will then work with an online shopping platform to automatically order the required items.

[1141] 5. In-store shopping assistance:

[1142] The user's device synchronizes with the server and automatically generates a shopping list based on the budget.

[1143] Using beacon devices in the store, the system tracks the user's location and guides them to the appropriate shelf or corner.

[1144] Example

[1145] Specifically, the following system can be implemented.

[1146] Enter financial data and update your household budget:

[1147] User: Enters bank transaction information into the system at the beginning of the month. Transaction information includes expenditures for food and transportation.

[1148] Server: Receives the entered transaction information and updates the household ledger. This update uses the Firebase database.

[1149] Expense classification and savings suggestions:

[1150] Server: Categorizes updated household accounting data by category and calculates total and average expenditures. Based on the analysis results, the server provides advice to the user, such as, "Your food expenses are high. You can save money by cutting down on eating out and cooking more at home."

[1151] Reordering everyday items:

[1152] Server: If it is estimated based on past purchase history that a consumable item (e.g., toothpaste) needs to be reordered, the server automatically places the order in cooperation with the online shopping platform.

[1153] In-store shopping assistance:

[1154] User device: Links with the beacon device in the store to identify the user's location and generates a real-time list of items that can be purchased within the user's specified budget.

[1155] In-store guidance: Beacon devices guide users to the shelves or corners where the products they are looking for are located, helping them shop more efficiently.

[1156] Examples of prompt statements

[1157] Based on the user's budget and recent purchase history, a generative AI model (e.g., GPT-4) is used to generate prompts such as:

[1158] Examples:

[1159] "User's budget is 10,000 yen, and their recent purchase history is as follows: Bread: 500 yen, Milk: 200 yen, Vegetables: 300 yen. Please provide some money-saving advice."

[1160] This system is expected to make household management and purchasing of everyday items more efficient, and to improve users' shopping experience in physical stores as well.

[1161] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1162] Step 1:

[1163] At the beginning of each month, users use a smartphone app to enter their banking information, which includes income and expenses such as food and transportation.

[1164] Input: Transaction information entered by the user

[1165] Output: Transaction information is sent to the server

[1166] Step 2:

[1167] The server receives the transaction information entered by the user and stores it in the Firebase database, which automatically updates the household account book based on this information.

[1168] Input: Transaction information sent by the user

[1169] Output: Updated household accounting data

[1170] Step 3:

[1171] The server categorizes the updated household budget data by category, such as food, transportation, entertainment, etc. It then analyzes spending patterns based on this data and calculates totals, averages, and frequency of spending for each category.

[1172] Input: Updated household accounting data

[1173] Output: Spending data broken down by category and analysis of spending patterns

[1174] Step 4:

[1175] The server generates saving suggestions for the user based on the analysis results. In this process, a generative artificial intelligence model (e.g., GPT-4) is used to generate specific advice prompts such as, "Your food costs are high. You can save money by cutting down on eating out and cooking more at home."

[1176] Input: Analysis of spending patterns

[1177] Output: Savings suggestions to the user

[1178] Step 5:

[1179] The server learns the frequency of use of everyday items and past purchase history, and predicts which items need to be reordered. For example, it learns how often toothpaste was used last time and predicts when it needs to be reordered.

[1180] Input: Frequency of use and purchase history of everyday items

[1181] Output: A list of items that need to be reordered

[1182] Step 6:

[1183] The server then connects with the online shopping platform to automatically place orders for items that are estimated to need reordering, a process that eliminates the need for users to manually place orders.

[1184] Input: List of items that need to be reordered

[1185] Output: Orders placed automatically

[1186] Step 7:

[1187] When a user shops in a physical store, the device synchronizes with the server and automatically generates a budget-based shopping list in real time.

[1188] Input: User budget information and real-time shopping data

[1189] Output: An automatically generated shopping list

[1190] Step 8:

[1191] Beacon devices in the store track users' location, and the terminal guides them to the appropriate shelf or section. For example, the beacon device identifies the user's location, and the smartphone notifies them that "there are discounted vegetables nearby."

[1192] Input: Location information from beacon device and shopping list

[1193] Output: Notification to guide the user to the product shelf or corner

[1194] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1195] This invention is a system that automates and streamlines the tedious tasks of managing household finances and purchasing everyday items. In particular, this system aims to provide more personalized services by incorporating an emotion engine that recognizes the user's emotions. The system receives financial data entered by the user, automatically updates the household ledger based on that data, and also provides the function of categorizing and analyzing expenses. This allows users to easily manage their expenses. It also predicts items that need to be reordered based on the frequency of use and purchase history of everyday items, and automatically places orders in conjunction with an online shopping platform, allowing users to continuously obtain necessary items without missing them. Furthermore, the system recognizes the user's emotions and adjusts the provided savings suggestions and shopping list based on the user's emotions.

[1196] System configuration and functions

[1197] 1. Receiving financial data and updating your household accounts:

[1198] Server: Receives financial data entered by the user, including income, expenses, and transaction information.

[1199] Server: Automatically updates the household ledger based on the received data. This update includes adding new transactions and modifying existing transactions.

[1200] 2. Expenditure classification and analysis:

[1201] Server: Categorizes the updated household accounting data by category, such as food, transportation, entertainment, etc.

[1202] Server: Analyzes the categorized spending data to understand user spending patterns, including calculating totals, averages, frequency, etc.

[1203] 3. Providing savings offers:

[1204] Server: Based on the analysis of spending patterns, the server provides users with savings suggestions. For example, if spending in a particular category is high, the server provides advice on reducing spending in that category.

[1205] 4. Reorder Estimation and Execution:

[1206] Server: Based on the frequency of use and purchase history of everyday items, it estimates what items need to be reordered. Examples include paper or plastic consumables and food.

[1207] Server: Connects to online shopping platforms and automatically places orders for the estimated items, allowing users to obtain the items they need in a timely manner.

[1208] 5. Customized Lists and Suggestions:

[1209] Server: Learns the user's preferences and lifestyle patterns and generates customized shopping lists and savings suggestions based on them, using past purchase history and lifestyle data.

[1210] 6. Real-time response and advice:

[1211] Server: Utilizes generative artificial intelligence models to respond to user questions and provide advice in real time, providing quick solutions to user concerns and improving the efficiency of daily life.

[1212] 7. Use of Emotion Engine:

[1213] Server: Includes an emotion engine that recognizes the user's emotions. The emotion engine detects emotions from the user's facial expressions, tone of voice, input text, etc.

[1214] Server: Tailors customized savings suggestions and shopping lists based on the user's emotions detected by the emotion engine. For example, if the user is feeling stressed, it can recommend relaxation items to relieve stress.

[1215] Server: Based on the user's emotions detected by the emotion engine, the server adjusts responses and advice content in real time, thereby providing personalized advice according to the user's emotional state.

[1216] Specific examples

[1217] User: At the beginning of each month, the user enters their bank transaction information into the system, including food and transportation expenses.

[1218] Terminal: The terminal transmits the entered transaction information to the server.

[1219] Server: The server receives the transaction information and updates the household ledger. The updated household ledger classifies the transaction information by category and generates analysis results.

[1220] Server: Based on the analysis results, the server provides users with money-saving suggestions such as, "Your food costs are high. You can save money by cutting down on eating out and cooking more at home."

[1221] Server: Learns from past purchase history how often the toothpaste purchased last time is used, and if it determines that a reorder is necessary, it automatically places the order.

[1222] Server: Further customizes and recommends the next shopping list based on the user's preferences and lifestyle patterns.

[1223] Server: Uses generative artificial intelligence models to provide appropriate advice in response to real-time questions from users.

[1224] Server: Uses an emotion engine to sense the user's emotions and tailor savings suggestions and shopping lists accordingly. For example, if the user is tired, recommend items that will help reduce stress.

[1225] Server: Tailors real-time responses and advice based on the emotion engine, providing personalized support according to the user's emotional state.

[1226] The system enables automatic and efficient household management and daily necessities purchasing, and also provides personalized services based on users' emotions, significantly reducing users' time and effort and improving their quality of life.

[1227] The processing flow will be explained below.

[1228] Step 1:

[1229] The user enters bank transaction information and a new purchase history. For example, the transaction information includes a food expense of 50 yen and a transportation expense of 20 yen, and the new purchase history is recorded as "toothpaste."

[1230] Step 2:

[1231] The terminal sends the transaction information and purchase history entered by the user to the server. The transmitted data includes the date and time of the transaction, the amount, and the category.

[1232] Step 3:

[1233] The server stores the received transaction information as financial data and also stores the new purchase history in a purchase database.

[1234] Step 4:

[1235] The server updates the household ledger with the financial data, which includes adding new transactions and modifying existing transactions.

[1236] Step 5:

[1237] The server categorizes the household accounting data into categories, such as food, transportation, and entertainment expenses.

[1238] Step 6:

[1239] The server analyzes the classified household account data to understand the user's spending patterns, including total and average spending amounts and frequency of spending.

[1240] Step 7:

[1241] The server uses an emotion engine to recognize the user's emotions, using information such as the user's facial expression, tone of voice, and input text to determine the emotion.

[1242] Step 8:

[1243] The server generates money-saving suggestions based on the analysis results and the recognition results of the emotion engine. For example, if a user is feeling stressed because of high food expenses, the server will suggest, "Your food expenses are high. You can save money by cutting down on eating out and cooking more at home, which will also help reduce stress."

[1244] Step 9:

[1245] The server learns the user's purchase history and frequency of use and predicts which items need to be reordered. For example, it determines that a reorder is necessary based on how often toothpaste was used last time.

[1246] Step 10:

[1247] The server places an order for the estimated reorder items to the online shopping platform, utilizing an automatic ordering function to save the user the trouble of manually placing the order.

[1248] Step 11:

[1249] The server generates customized shopping lists and savings suggestions based on the results of the emotion engine. For example, if the user has the emotion of wanting to relax, it will recommend relaxation items.

[1250] Step 12:

[1251] The server sends the generated customized shopping list and savings suggestions to the terminal, which displays them to the user.

[1252] Step 13:

[1253] When a user asks a question in real time, the server uses a generative artificial intelligence model to provide answers and advice to the user's questions.

[1254] Step 14:

[1255] The server adjusts its real-time responses and advice based on the user's emotions detected by the emotion engine. For example, if the user is feeling irritated, the server will provide calm advice to calm the user.

[1256] Step 15:

[1257] The terminal displays the responses and advice received from the server to the user, thereby helping the user to efficiently manage their household finances and purchase everyday items.

[1258] Example 2

[1259] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1260] In modern life, managing household finances and purchasing everyday items requires a significant amount of time and effort. Furthermore, conventional household finance management and purchasing systems lack the ability to provide personalized services that take user emotions into account, making it difficult to increase user satisfaction. The present invention aims to solve these problems by streamlining and automating household finance management and providing personalized responses based on user emotions.

[1261] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1262] In this invention, the server includes: means for receiving financial data input by a user; means for automatically updating a household account book based on the financial data; means for classifying and analyzing the updated household account book data; means for providing the user with money-saving suggestions based on the analysis results; means for predicting items that need to be reordered based on the frequency of use and purchase history of daily necessities; means for automatically ordering the predicted items in cooperation with an e-commerce platform; means including an emotion engine that recognizes user emotions; and means for adjusting money-saving suggestions and a shopping list based on the user emotions sensed by the emotion engine. This allows the user to automatically manage their household finances, obtain necessary items in a timely manner, and receive personalized services according to their emotions.

[1263] "User" refers to any individual or organization that uses this system.

[1264] "Financial Data" refers to information related to a user's economic activities, such as income, expenses, and transaction information.

[1265] A "household account book" refers to a digital or physical ledger that allows a user to record and manage their income and expenses.

[1266] "Classification" refers to the process of separating household data into categories, such as food, transportation, and entertainment.

[1267] "Analysis" refers to the process of statistically analyzing household accounting data to identify spending patterns and unusual spending.

[1268] "Savings suggestions" refers to providing financial advice to users based on the analysis of their household accounting data.

[1269] "Frequency of use" refers to data indicating how often an everyday item is used.

[1270] "Purchase history" refers to data that records the items a user has previously purchased and their detailed information.

[1271] "Reordering" refers to the process of reordering needed items based on frequency of use and purchase history.

[1272] "E-commerce platform" refers to a website or application for buying and selling goods and services online.

[1273] An "emotion engine" refers to technology that detects emotions from a user's facial expressions, tone of voice, input text, etc.

[1274] "Personalization" refers to customizing services and offers based on the individual characteristics and circumstances of each user.

[1275] The present invention is a system that allows users to automate and streamline the tedious tasks of managing their household finances and purchasing everyday items. The system is designed to receive financial data, update household accounts, categorize and analyze expenses, provide savings suggestions, estimate and execute reorders for everyday items, and provide customized suggestions based on the user's emotions.

[1276] Receive financial data and update your household budget

[1277] At the beginning of each month, users enter financial data, such as bank transaction information and cash expenditure information, into the system. Specific examples include food expenditures of 1,000 yen and transportation expenditures of 3,000 yen. The data entered by the user is sent to the server via the terminal. Based on the received data, the server adds new transactions to the household accounting database and modifies existing transactions. For example, if the total food expenditures for August were 5,000 yen, a new expenditure of 1,000 yen would be added, bringing the total to 6,000 yen.

[1278] Expense classification and analysis

[1279] The server analyzes the updated household ledger data and classifies each transaction into a category. Specific examples include food expenses, transportation expenses, and entertainment expenses. Based on this, the server categorizes food-related transactions into the "food" category and transportation-related transactions into the "transportation" category. Based on the expenditure data for each category, the server calculates statistical information such as total expenditures, frequency, and average amounts. For example, it calculates the average monthly food expenses and compares them between years. The server detects spending trends and unusual spending patterns. For example, if transportation expenses spike in a particular month, it analyzes the cause.

[1280] Providing savings suggestions

[1281] The server generates savings suggestions tailored to the user based on the analysis of spending patterns. For example, a user with high transportation costs may be advised to consider commuting by bicycle. The generated savings suggestions are sent to the device, which then displays them to the user, suggesting specific ways to save money.

[1282] Reorder estimation and execution

[1283] Based on the frequency of use and purchase history of everyday items, the server estimates which items need to be reordered. As a specific example, it estimates when the next purchase will be based on the rate at which toilet paper was used the last time it was purchased. Information on items that are estimated to be needed is obtained by the server, and a decision is made as to whether to reorder them based on the user's purchase history. If it is determined that a reorder is necessary, the server will link with the e-commerce platform via API or other means to automatically place the order. After the order is completed, the server will notify the user of the order details.

[1284] Generate customized suggestions and lists

[1285] The server analyzes the user's past purchase history and lifestyle data to generate customized shopping lists and suggestions. For example, a user who buys a lot of ingredients on the weekend will be offered "recommended ingredients for this weekend." Savings suggestions tailored to the user's preferences are also offered. The customized lists and suggestions are displayed to the user through their device.

[1286] Real-time response and advice

[1287] A user inputs a question about household management into the system in real time. A specific example is, "How can I reduce my food expenses this month?" The device sends the question to the server, which uses a generative AI model (e.g., a generative AI model) to generate an appropriate answer to the user's question. The generated answer is sent to the device, which displays the generated answer to the user in real time.

[1288] Use of emotion engine

[1289] The system reads emotions from the user's tone of voice and input text. For example, if the input text is "tired," it will detect stress. Emotional data is sent to the server via the device, and the server uses an emotion engine to analyze the user's emotions. Based on the emotions, customized savings suggestions and shopping lists are adjusted. The response of the generative AI model is also customized based on the emotion data, providing personalized advice according to the user's current emotional state.

[1290] Prompt Sentence Examples

[1291] User: I want to enter my monthly expenses. How can I get the data reflected in my household ledger?

[1292] Terminal: Sends entered data to the server.

[1293] Server: Automatically updates the household account book based on bank transaction information and analyzes expenses.

[1294] This system allows users to efficiently manage their household finances, obtain necessary items in a timely manner, and receive personalized services based on their emotions, which can significantly reduce users' time and effort and improve their quality of life.

[1295] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1296] Step 1:

[1297] Entering and submitting financial data

[1298] At the beginning of each month, users enter their financial data, such as bank transaction information and cash expenditure information, into the system. For example, they enter 1,000 yen in food expenses and 3,000 yen in transportation expenses. The terminal then sends this input data to the server.

[1299] Input: Financial data such as food expenses, transportation expenses, etc.

[1300] Output: Financial data sent to the server

[1301] Step 2:

[1302] Receiving data and updating the household account book

[1303] The server receives the financial data sent from the device. Based on the received data, the server adds new transactions to the household accounting database and modifies existing transactions. For example, if the total food expenditure for August was 5,000 yen, it will add a new expenditure of 1,000 yen to update it to 6,000 yen.

[1304] Input: Financial data sent from the terminal

[1305] Processing: Update the household accounting database (add new transactions, modify existing transactions)

[1306] Output: Updated household account book

[1307] Step 3:

[1308] Expense Category Classification

[1309] The server categorizes the updated household accounting data into categories, such as food expenses, transportation expenses, and entertainment expenses.

[1310] Input: Updated household accounting data

[1311] Processing: Categorizing transaction data (e.g., food, transportation, entertainment)

[1312] Output: Household accounting data categorized by category

[1313] Step 4:

[1314] Analysis of spending patterns

[1315] The server calculates statistics such as total expenditures, frequency, and average amounts based on each category of expenditure data. For example, it calculates the average monthly food expenditure and compares it year-over-year. It also detects expenditure trends and unusual patterns.

[1316] Input: Household accounting data categorized by category

[1317] Processing: Calculating statistical information (total, frequency, average amount of expenditure)

[1318] Output: Spending statistics and analysis results

[1319] Step 5:

[1320] Generate and notify savings suggestions

[1321] The server generates savings suggestions tailored to the user based on the analysis of spending patterns. For example, it might suggest to a user with high transportation costs, "Consider commuting by bicycle." The generated savings suggestions are sent to the device, which then displays them to the user.

[1322] Input: Spending statistics and analysis results

[1323] Processing: Generate savings proposals

[1324] Output: Generated savings proposals

[1325] Step 6:

[1326] Estimating reorders of everyday items

[1327] The server estimates which items need to be reordered based on the frequency of use and purchase history of everyday items. For example, it estimates when the next purchase will be made based on the rate at which toilet paper was used last time.

[1328] Input: Usage frequency and purchase history data

[1329] Processing: Usage frequency analysis, reorder estimation

[1330] Output: List of items that need to be reordered

[1331] Step 7:

[1332] Automatic order execution

[1333] If it is determined that a reorder is necessary, the server will automatically place the order by connecting with the e-commerce platform via API, etc. After the order is completed, the server will notify the user of the order details.

[1334] Input: List of items that need to be reordered

[1335] Processing: Integration with e-commerce platforms, automatic order execution

[1336] Output: Order details notification

[1337] Step 8:

[1338] Customization suggestions based on user preferences

[1339] The server analyzes the user's past purchase history and lifestyle data to generate customized shopping lists and savings suggestions. For example, it provides "recommended ingredients for this weekend" to users who buy a lot of ingredients on the weekend.

[1340] Input: Past purchase history, lifestyle data

[1341] Processing: Analysis of preferences and lifestyle patterns, generation of customization suggestions

[1342] Output: customized shopping list and savings suggestions

[1343] Step 9:

[1344] Real-time question responses

[1345] Users input questions about household finances into the system in real time. A typical example is, "How can I reduce my food expenses this month?" The device sends the question to the server, which uses a generative AI model (e.g., a generative AI model) to generate an appropriate answer to the user's question. The generated answer is sent to the device and displayed to the user in real time.

[1346] Input: Real-time questions

[1347] Processing: Answer generation using generative AI models

[1348] Output: The generated answer

[1349] Step 10:

[1350] Receiving and analyzing emotion data

[1351] The system reads emotions from the user's tone of voice and input text. For example, if the input text is "tired," it will detect stress. Emotion data is sent to the server via the device, and the server uses an emotion engine to analyze the user's emotions.

[1352] Input: The user's tone of voice and input text

[1353] Processing: Emotion recognition and data generation

[1354] Output: User emotion data

[1355] Step 11:

[1356] Tailoring personalized suggestions based on emotions

[1357] Based on the emotional data, the server will tailor customized savings suggestions and shopping lists. For example, if the user is tired, it will add relaxation items to the shopping list. The emotional data will also customize the generative AI model's response, providing personalized advice based on the user's current emotional state.

[1358] Input: User emotion data

[1359] Processing: tailoring suggestions and customizing responses with generative AI models

[1360] Output: Tailored savings suggestions, shopping lists, personalized advice

[1361] (Application example 2)

[1362] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1363] Today's users are required to efficiently manage their household finances and purchase daily necessities amid their busy lives. However, these tasks are time-consuming and lack emotionally-sensitive personalized support, which increases user stress. Conventional systems have struggled to streamline household finances and purchase daily necessities, while providing personalized suggestions in a unified manner. Therefore, there is a need for the development of a system that automates and streamlines household finances and purchases while providing emotionally-sensitive support.

[1364] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving financial data input by a user, means for automatically updating the household account book based on the financial data, means for classifying and analyzing the updated household account book data, means for providing the user with money-saving suggestions based on the analysis results, means for predicting items that need to be reordered based on the frequency of use and purchase history of daily necessities, means for automatically ordering the predicted items in cooperation with an e-commerce platform, and means for recognizing the user's emotions using an emotion recognition engine and providing personalized suggestions based on the recognized emotions. This enables the user to efficiently manage their household finances and purchase daily necessities while receiving support based on their emotions.

[1365] "User" refers to an individual who uses the system to manage their household finances and purchase everyday items.

[1366] "Financial Data" refers to data related to economic activity, such as income, expenses, and transaction information entered by users.

[1367] A "household account book" refers to a ledger used to record and manage a user's income and expenses.

[1368] An "emotion recognition engine" refers to a system that detects emotions from a user's facial expressions, tone of voice, input text, etc.

[1369] "Savings Suggestions" refers to advice that analyzes a user's spending patterns and suggests ways to save money.

[1370] "Items that need to be reordered" refers to items that are determined to need to be purchased again based on the frequency of use and purchase history of everyday items.

[1371] "E-commerce platform" refers to a website or application that allows users to buy and sell goods and services online.

[1372] "Personalized suggestions" refers to providing specific advice or recommendations based on a user's emotions and preferences.

[1373] A "generative artificial intelligence model" refers to an artificial intelligence that generates answers and advice based on input data and questions.

[1374] This invention is a system that helps users manage their household finances and purchase everyday items efficiently. The system uses an emotion recognition engine and a generative artificial intelligence model to provide personalized suggestions based on the user's emotions.

[1375] The server first receives financial data entered by the user. Financial data includes income, expenses, and transaction information. For example, the user enters bank transaction information using a smartphone. This data is automatically updated in the household ledger.

[1376] The updated household accounting data is then classified and analyzed. Spending patterns are categorized and the total amount and frequency are calculated. Based on the results of this analysis, savings suggestions are provided to the user. For example, if the analysis shows that food expenses are high, the system will suggest "eating out less and cooking more at home."

[1377] Based on the frequency of use and purchase history of everyday items, the system predicts which items need to be reordered. For example, this applies to consumables such as paper products and food. The server then automatically orders these items in conjunction with the e-commerce platform, allowing users to obtain the items they need in a timely manner.

[1378] The emotion recognition engine recognizes emotions from the user's facial expressions, tone of voice, input text, etc. For example, if the user is feeling stressed, it will recommend relaxation items. Making suggestions based on emotions improves user satisfaction.

[1379] The generative AI model responds to real-time questions from users and generates appropriate advice based on the input data and questions. For example, if a user asks, "How can I reduce my food expenses this month?", the model will provide specific advice.

[1380] The hardware used includes a smartphone, the emotion recognition engine is Microsoft Azure's Emotion API, and the generative artificial intelligence model is OpenAI's GPT.

[1381] Examples:

[1382] Users input financial data into the system via a smartphone app. The server receives the data and automatically updates the household ledger. Next, an emotion recognition engine detects stress levels from the user's facial expressions and suggests relaxation items. Meanwhile, a generative AI model provides real-time advice, such as "You can cut down on food costs by eating out less."

[1383] Example prompt sentence:

[1384] Consider user emotions and offer advice on buying and saving money on everyday items.

[1385] The user seems tired. Suggest items or foods that will help them relax.

[1386] The system allows users to efficiently manage their finances and purchase everyday items while receiving emotional support.

[1387] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1388] Step 1: Enter your financial data

[1389] A user uses a smartphone to input financial data such as income, expenses, and transaction information. This financial data is sent from the device to a server. The input data includes categories such as income, food expenses, and transportation expenses, along with the amounts for each. The server temporarily stores the received data.

[1390] Step 2: Update your household budget

[1391] The server automatically updates the household ledger based on the received financial data. Specifically, it analyzes transaction information and categorizes them. It adds and modifies new transactions to the previous household ledger to create a household ledger that reflects the user's latest financial situation. The updated household ledger is obtained as output.

[1392] Step 3: Categorize and analyze expenses

[1393] The server categorizes and analyzes the updated household accounting data. It categorizes income and expenses by category and calculates the total amount and frequency of spending for each category. The analysis results include total expenditures and spending patterns for each category, such as food, transportation, and entertainment. This allows users to understand their spending habits.

[1394] Step 4: Generate savings proposals

[1395] The server generates savings suggestions for the user based on the results of the expenditure analysis. For example, if expenditures in a particular category are high, specific advice on reducing spending in that category is provided. Saving suggestions are generated using a generative AI model and are tailored to the user's lifestyle. Saving suggestions are obtained as the output.

[1396] Step 5: Estimate reorders

[1397] The server estimates which items need to be reordered based on the frequency of use and purchase history of daily items. It analyzes purchase history data and predicts when repurchases will be necessary. For example, it estimates the timing of repurchase based on the period of use of toothpaste previously purchased. The output is a list of items that can be reordered.

[1398] Step 6: Execute an automatic order

[1399] The server automatically orders the estimated reorder candidate items in cooperation with the e-commerce platform. It checks the stock status and price of the necessary items and executes the order at the optimal time. This allows users to regularly secure the daily necessities they need. The output is confirmation data that the automatic order has been completed.

[1400] Step 7: Emotion Recognition and Custom Suggestions

[1401] The server uses an emotion recognition engine to recognize the user's emotions. It analyzes the input text, tone of voice, and facial expression data to determine the user's emotional state (e.g., stress or happiness). Based on the recognized emotions, it personalizes saving suggestions and shopping lists to provide suggestions that the user desires. The output is customized suggestions based on emotions.

[1402] Step 8: Real-time support

[1403] The server uses a generative AI model to respond to real-time questions from users. For example, in response to a question like, "How can I reduce my food expenses this month?", it will suggest detailed ways to save money. The AI ​​generates a response based on the prompt text, providing the user with timely and useful information. The output is specific advice.

[1404] Through these steps, users can manage their household finances and purchase everyday items efficiently and personalizedly.

[1405] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1406] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1407] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1408] [Fourth embodiment]

[1409] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1410] 7, a 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.

[1411] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1412] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1413] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1414] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1415] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1416] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1417] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1418] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1419] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1420] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1421] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1422] This invention is a system that automates and streamlines the tedious tasks of managing household finances and purchasing everyday items. The system receives financial data entered by the user, automatically updates the household ledger based on that data, and also provides the functionality of categorizing and analyzing expenditures. This allows users to easily manage their expenditures. It also predicts items that need to be reordered based on the frequency of use and purchase history of everyday items, and automatically places orders in conjunction with an online shopping platform. These functions allow users to continuously obtain the items they need without missing them.

[1423] System configuration and functions

[1424] 1. Receiving financial data and updating your household accounts:

[1425] Server: Receives financial data entered by the user, including income, expenses, and transaction information.

[1426] Server: Automatically updates the household ledger based on the received data. This update includes adding new transactions and modifying existing transactions.

[1427] 2. Expenditure classification and analysis:

[1428] Server: Categorizes the updated household accounting data by category, such as food, transportation, entertainment, etc.

[1429] Server: Analyzes the categorized spending data to understand user spending patterns, including calculating totals, averages, frequency, etc.

[1430] 3. Providing savings offers:

[1431] Server: Based on the analysis of spending patterns, the server provides users with savings suggestions. For example, if spending in a particular category is high, the server provides advice on reducing spending in that category.

[1432] 4. Reorder Estimation and Execution:

[1433] Server: Based on the frequency of use and purchase history of everyday items, it estimates what items need to be reordered. Examples include paper or plastic consumables and food.

[1434] Server: Connects to online shopping platforms and automatically places orders for the estimated items, allowing users to obtain the items they need in a timely manner.

[1435] 5. Customized Lists and Suggestions:

[1436] Server: Learns the user's preferences and lifestyle patterns and generates customized shopping lists and savings suggestions based on them, using past purchase history and lifestyle data.

[1437] 6. Real-time response and advice:

[1438] Server: Utilizes generative artificial intelligence models to respond to user questions and provide advice in real time, providing quick solutions to user concerns and improving the efficiency of daily life.

[1439] Specific examples

[1440] User: At the beginning of each month, the user enters their bank transaction information into the system, including food and transportation expenses.

[1441] Terminal: The terminal transmits the entered transaction information to the server.

[1442] Server: The server receives the transaction information and updates the household ledger. The updated household ledger classifies the transaction information by category and generates analysis results.

[1443] Server: Based on the analysis results, the server provides users with money-saving suggestions such as, "Your food costs are high. You can save money by cutting down on eating out and cooking more at home."

[1444] Server: Learns from past purchase history how often the toothpaste purchased last time is used, and if it determines that a reorder is necessary, it automatically places the order.

[1445] Server: Further customizes and recommends the next shopping list based on the user's preferences and lifestyle patterns.

[1446] Server: Uses generative artificial intelligence models to provide appropriate advice in response to real-time questions from users.

[1447] This system allows users to automatically and efficiently manage their household finances and purchase everyday items, significantly reducing the time and effort required. It also provides customization based on the user's lifestyle, enabling support that meets individual needs.

[1448] The processing flow will be explained below.

[1449] Step 1:

[1450] The user enters bank transaction information and a new purchase history. For example, the transaction information includes a food expense of 50 yen and a transportation expense of 20 yen, and the new purchase history is recorded as "toothpaste."

[1451] Step 2:

[1452] The terminal sends the transaction information and purchase history entered by the user to the server. The transmitted data includes the date and time of the transaction, the amount, and the category.

[1453] Step 3:

[1454] The server stores the received transaction information as financial data and also stores the new purchase history in a purchase database.

[1455] Step 4:

[1456] The server updates the household ledger with the financial data, which includes adding new transactions and modifying existing transactions.

[1457] Step 5:

[1458] The server categorizes the household accounting data into categories, such as food, transportation, and entertainment expenses.

[1459] Step 6:

[1460] The server analyzes the classified household account data to understand the user's spending patterns, including total and average spending amounts and frequency of spending.

[1461] Step 7:

[1462] The server generates savings suggestions based on the analysis results. For example, if food expenses are high, it will suggest "cut down on eating out and cook more at home."

[1463] Step 8:

[1464] The server learns the user's purchase history and frequency of use and predicts which items need to be reordered. For example, it determines that toothpaste needs to be reordered based on how often it was used last time.

[1465] Step 9:

[1466] The server places an order for the estimated reorder items to the online shopping platform, utilizing an automatic ordering function to save the user the trouble of manually placing the order.

[1467] Step 10:

[1468] The server learns the user's behavioral patterns and preferences and generates customized shopping lists and savings suggestions, taking into account the user's past purchasing habits and lifestyle.

[1469] Step 11:

[1470] The server sends the generated customized shopping list and savings suggestions to the terminal, which displays them to the user.

[1471] Step 12:

[1472] When a user asks a question in real time, the server uses a generative artificial intelligence model to provide answers and advice to the user's questions.

[1473] Step 13:

[1474] The terminal displays the responses and advice received from the server to the user, thereby helping the user to efficiently manage their household finances and purchase everyday items.

[1475] Example 1

[1476] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1477] Conventional household management systems require users to manually input and manage data, which is cumbersome and time-consuming. Furthermore, they lack sufficient analysis of spending, making it difficult to provide efficient savings suggestions or reorder everyday items. Additionally, there was a lack of a system that allowed users to ask questions or seek advice in real time.

[1478] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1479] In this invention, the server includes: means for receiving financial data entered by a user; means for automatically updating a household ledger based on the financial data; means for categorizing the updated household ledger data; means for analyzing the categorized expenditure data to understand spending patterns; means for providing the user with money-saving suggestions based on the analysis results; means for predicting items that need to be reordered based on the frequency of use and purchase history of daily necessities; means for automatically ordering the predicted items in cooperation with an online shopping platform; and means for responding to questions from the user in real time using a generative artificial intelligence model. This enables automated and efficient household management and reordering of daily necessities. Furthermore, by providing users with advice in real time, it is possible to improve the efficiency of their daily lives.

[1480] "User" refers to any individual or group who uses this system.

[1481] "Financial data" refers to economic information necessary for managing household finances, such as income, expenditures, and transaction information.

[1482] A "household account book" refers to a ledger or collection of digital data that compiles records of income and expenses.

[1483] A "category" is a group name used to classify income and expenses, and mainly refers to general expenditure items such as food, transportation, and entertainment.

[1484] "Spending patterns" refers to a user's spending trends and habits over a specific period of time.

[1485] "Savings suggestions" refers to advice and recommended specific actions to reduce spending.

[1486] "Everyday items" are items that are frequently used in daily life, including consumables and food.

[1487] "Frequency of use" refers to the number of times a good or service is used within a specific period of time.

[1488] "Purchase history" refers to a record of products a user has purchased in the past.

[1489] "Online Shopping Platform" refers to a website or application for buying and selling goods and services over the Internet.

[1490] A "generative artificial intelligence model" refers to an AI system that generates text or responses based on a trained dataset, such as a natural language processing model like GPT-4.

[1491] "Real-time response" refers to providing immediate answers to user inquiries and questions.

[1492] This invention is a system that automates and streamlines the tedious tasks of managing household finances and purchasing everyday items. The system receives financial data entered by the user, automatically updates the household ledger based on that data, and also provides the functionality of categorizing and analyzing expenditures. It also predicts items that need to be reordered based on the frequency of use and purchase history of everyday items, and automatically places orders in conjunction with an online shopping platform. This allows users to continuously obtain the items they need without missing them.

[1493] System Hardware and Software

[1494] Hardware

[1495] Server: The server acts as the central processing unit of the system and performs major tasks such as receiving data, analyzing, classifying, automatic ordering, and real-time response.

[1496] Device: The device on which a user enters data and receives notifications, such as a smartphone, tablet, or computer.

[1497] software

[1498] Database: Used within the server to store financial data, household accounting data, purchase history, etc. For example, MySQL or PostgreSQL is used.

[1499] Analysis tools: Data analysis and statistical calculations are performed using Python's pandas library, etc.

[1500] Machine learning models: Used to classify spending and generate customized recommendations. Use frameworks such as Scikit-learn and TensorFlow.

[1501] Generative AI models: Used to respond to user questions in real time. Natural language processing models such as GPT-4 fall into this category.

[1502] API integration: To integrate with online shopping platforms, RESTful APIs are used to automate orders.

[1503] Specific examples

[1504] Example 1: Automating household accounting management

[1505] User: At the beginning of each month, the user enters their bank transaction information into the system, including food and transportation expenses.

[1506] Terminal: The terminal transmits the entered transaction information to the server.

[1507] Server: The server updates the household ledger based on the received transaction information. The updated household ledger classifies the transaction information by category and generates analysis results.

[1508] Server: Based on the analysis results, the server provides users with money-saving suggestions such as, "Your food costs are high. You can save money by cutting down on eating out and cooking more at home."

[1509] Example 2: Automatic reordering of everyday items

[1510] Server: Learns from past purchase history how often the toothpaste purchased last time is used, and if it determines that a reorder is necessary, it automatically places the order.

[1511] Server: Further customizes and recommends the next shopping list based on the user's preferences and lifestyle patterns.

[1512] Example 3: Real-time response

[1513] User: The user types a question: "What everyday item should I buy next?"

[1514] Server: The generative AI model analyzes this question and generates an appropriate answer, such as, "The next thing you should buy is toothpaste. Based on how quickly it's being consumed, it's estimated that a reorder will be necessary."

[1515] Specific prompt examples:

[1516] "What can I do to save money on food?"

[1517] "What everyday item should I buy next?"

[1518] "Tell me about your recent spending patterns."

[1519] In this way, the system of the present invention supports users' economic activities by streamlining and automating their household finances and purchasing everyday items. Furthermore, by using generative AI models, the system can provide advice and answers to questions in real time.

[1520] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1521] Step 1:

[1522] User financial data entry and submission

[1523] User: At the beginning of the month, users use devices such as smartphones or computers to enter financial data such as income, expenses, and transaction information. The data entered includes items such as food, transportation, and entertainment expenses.

[1524] Terminal: The terminal formats the entered financial data and sends it to the server.

[1525] Input: Income, expense, and transaction information entered by the user.

[1526] Output: The formatted financial data is sent to the server.

[1527] Specific operation: When a user opens the application, enters the required information into the form, and presses the submit button, the terminal sends the input data to the server.

[1528] Step 2:

[1529] Update household accounting data

[1530] Server: The server automatically updates the household ledger based on the received financial data, adding new transactions to the database and updating existing transactions.

[1531] Input: Financial data sent from the terminal.

[1532] Output: Updated household accounting data.

[1533] Specific operation: The server connects to a database (e.g., MySQL), adds new entries to the household ledger based on the received data, and modifies any necessary parts.

[1534] Step 3:

[1535] Classification of expenditure data

[1536] Server: The server analyzes the updated household accounting data and categorizes the transactions into categories, including food, transportation, entertainment, etc.

[1537] Input: Updated household accounting data.

[1538] Output: Spending data broken down by category.

[1539] How it works: The server uses machine learning models (e.g., Scikit-learn) to automatically classify spending items based on transaction content.

[1540] Step 4:

[1541] Analysis of spending data

[1542] Server: The server analyzes the categorized spending data and calculates the amount, average, and frequency of spending for each category.

[1543] Input: Expense data broken down by category.

[1544] Output: Analysis of spending patterns.

[1545] Specific operation: The server uses the Python pandas library to aggregate data and generate statistics, such as calculating the average monthly food expenses or the total transportation expenses.

[1546] Step 5:

[1547] Creating and notifying savings offers

[1548] Server: Based on the analysis, it creates savings suggestions to reduce spending in specific categories and notifies the user.

[1549] Input: Analysis of spending patterns.

[1550] Output: Notification of savings suggestions.

[1551] How it works: The server uses a predefined rule-based system to generate savings suggestions and send push notifications to the user's device.

[1552] Step 6:

[1553] Estimating reorders of everyday items

[1554] Server: Based on past purchase history and data on frequency of use of everyday items, estimates items that need to be reordered.

[1555] Input: Past purchase history, usage frequency data.

[1556] Output: A list of items that need to be reordered.

[1557] Specific operation: The server analyzes past purchase data, calculates the consumption rate of a particular product, and determines when to reorder.

[1558] Step 7:

[1559] Automatic order execution

[1560] Server: Uses the API of an online shopping platform to automatically order the necessary items.

[1561] Input: A list of items that need to be reordered.

[1562] Output: Confirmation of order completion.

[1563] Specific operation: The server calls APIs such as Amazon and Rakuten, adds the estimated items to the order list, and executes the automatic order.

[1564] Step 8:

[1565] Generate customized lists and suggestions

[1566] Server: Learns the user's preferences and lifestyle patterns and generates customized shopping lists and savings suggestions.

[1567] Input: Past purchase history, lifestyle data.

[1568] Output: Customized shopping list, savings suggestions.

[1569] How it works: The server uses machine learning models (e.g., TensorFlow) to learn from the user's data and generate customized suggestions.

[1570] Step 9:

[1571] Real-time response and advice

[1572] User: The user types in a question.

[1573] Server: Uses a generative artificial intelligence model (e.g., GPT-4) to generate responses to user questions in real time.

[1574] Input: A question from the user.

[1575] Output: Real-time response.

[1576] How it works: When a user inputs a question such as "What everyday item should I buy next?", the server uses a generative AI model to generate an appropriate answer and provides it to the user.

[1577] (Application example 1)

[1578] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1579] Today's consumers spend a lot of time and effort managing their household finances and purchasing daily necessities. Therefore, they need a system that helps them efficiently manage their household finances and obtain the necessary consumables in a timely manner. However, physical stores lack the functionality to help users shop efficiently within their budget. Furthermore, the lack of real-time support based on savings suggestions and product guidance results in a suboptimal shopping experience.

[1580] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1581] In this invention, the server includes: means for receiving financial data entered by a user; means for automatically updating a household ledger based on the financial data; means for categorizing and analyzing the updated household ledger data; means for providing the user with savings suggestions based on the analysis results; means for predicting items that need to be reordered based on the frequency of use and purchase history of daily necessities; means for automatically ordering the predicted items in cooperation with an online shopping platform; means for synchronizing with the user's household data and purchase history and automatically generating a shopping list based on a budget when shopping in a physical store; and means for tracking in-store location information and using location information to guide the user to the appropriate shelves and sections. This allows users to shop efficiently within their budget even in physical stores and continuously obtain necessary items without missing them. Furthermore, the integration of home spending management and in-store shopping support provides comprehensive lifestyle support.

[1582] "Financial Data" means information relating to your finances, such as your income, expenses, and transaction information.

[1583] A "household account book" is a ledger that records a user's income and expenses and manages the status of assets and liabilities.

[1584] "Daily commodities" are items such as consumables and food that are used regularly in daily life.

[1585] An "online shopping platform" is an e-commerce venue where goods and services can be purchased via the Internet.

[1586] "Location tracking" is a technology that detects and tracks a user's current location.

[1587] A "generative artificial intelligence model" is an artificial intelligence technology that generates appropriate responses and suggestions based on input data.

[1588] A "shopping list" is a list of items that a user wants to purchase.

[1589] This invention is a comprehensive system that allows users to efficiently manage their household finances and purchase everyday items. The system has several main functions, each of which is designed to automate specific tasks and significantly reduce the burden on the user. Specific embodiments of the system are described below.

[1590] System configuration

[1591] The system mainly consists of a server, user terminals (smartphones, smart glasses, etc.), and in-store beacon devices.

[1592] 1. Receiving financial data and updating your household accounts:

[1593] The server receives financial data (income, expenses, and transaction information) entered by the user and automatically updates the household ledger based on that data.

[1594] This process uses a database management system (e.g., Firebase).

[1595] 2. Expenditure Classification and Analysis:

[1596] The server categorizes the updated household data and analyzes spending patterns, allowing it to calculate totals, averages, frequency, and other expenditures.

[1597] 3. Providing savings offers:

[1598] The server provides users with savings suggestions based on the analysis of their spending patterns, including advice on reducing spending in specific categories.

[1599] 4. Reorder Estimation and Auto Order:

[1600] The server learns the frequency of use and purchase history of everyday items and estimates which items need to be reordered.

[1601] Based on this estimation, the server will then work with an online shopping platform to automatically order the required items.

[1602] 5. In-store shopping assistance:

[1603] The user's device synchronizes with the server and automatically generates a shopping list based on the budget.

[1604] Using beacon devices in the store, the system tracks the user's location and guides them to the appropriate shelf or corner.

[1605] Example

[1606] Specifically, the following system can be implemented.

[1607] Enter financial data and update your household budget:

[1608] User: Enters bank transaction information into the system at the beginning of the month. Transaction information includes expenditures for food and transportation.

[1609] Server: Receives the entered transaction information and updates the household ledger. This update uses the Firebase database.

[1610] Expense classification and savings suggestions:

[1611] Server: Categorizes updated household accounting data by category and calculates total and average expenditures. Based on the analysis results, the server provides advice to the user, such as, "Your food expenses are high. You can save money by cutting down on eating out and cooking more at home."

[1612] Reordering everyday items:

[1613] Server: If it is estimated based on past purchase history that a consumable item (e.g., toothpaste) needs to be reordered, the server automatically places the order in cooperation with the online shopping platform.

[1614] In-store shopping assistance:

[1615] User device: Links with the beacon device in the store to identify the user's location and generates a real-time list of items that can be purchased within the user's specified budget.

[1616] In-store guidance: Beacon devices guide users to the shelves or corners where the products they are looking for are located, helping them shop more efficiently.

[1617] Examples of prompt statements

[1618] Based on the user's budget and recent purchase history, a generative AI model (e.g., GPT-4) is used to generate prompts such as:

[1619] Examples:

[1620] "User's budget is 10,000 yen, and their recent purchase history is as follows: Bread: 500 yen, Milk: 200 yen, Vegetables: 300 yen. Please provide some money-saving advice."

[1621] This system is expected to make household management and purchasing of everyday items more efficient, and to improve users' shopping experience in physical stores as well.

[1622] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1623] Step 1:

[1624] At the beginning of each month, users use a smartphone app to enter their banking information, which includes income and expenses such as food and transportation.

[1625] Input: Transaction information entered by the user

[1626] Output: Transaction information is sent to the server

[1627] Step 2:

[1628] The server receives the transaction information entered by the user and stores it in the Firebase database, which automatically updates the household account book based on this information.

[1629] Input: Transaction information sent by the user

[1630] Output: Updated household accounting data

[1631] Step 3:

[1632] The server categorizes the updated household budget data by category, such as food, transportation, entertainment, etc. It then analyzes spending patterns based on this data and calculates totals, averages, and frequency of spending for each category.

[1633] Input: Updated household accounting data

[1634] Output: Spending data broken down by category and analysis of spending patterns

[1635] Step 4:

[1636] The server generates saving suggestions for the user based on the analysis results. In this process, a generative artificial intelligence model (e.g., GPT-4) is used to generate specific advice prompts such as, "Your food costs are high. You can save money by cutting down on eating out and cooking more at home."

[1637] Input: Analysis of spending patterns

[1638] Output: Savings suggestions to the user

[1639] Step 5:

[1640] The server learns the frequency of use of everyday items and past purchase history, and predicts which items need to be reordered. For example, it learns how often toothpaste was used last time and predicts when it needs to be reordered.

[1641] Input: Frequency of use and purchase history of everyday items

[1642] Output: A list of items that need to be reordered

[1643] Step 6:

[1644] The server then connects with the online shopping platform to automatically place orders for items that are estimated to need reordering, a process that eliminates the need for users to manually place orders.

[1645] Input: List of items that need to be reordered

[1646] Output: Orders placed automatically

[1647] Step 7:

[1648] When a user shops in a physical store, the device synchronizes with the server and automatically generates a budget-based shopping list in real time.

[1649] Input: User budget information and real-time shopping data

[1650] Output: An automatically generated shopping list

[1651] Step 8:

[1652] Beacon devices in the store track users' location, and the terminal guides them to the appropriate shelf or section. For example, the beacon device identifies the user's location, and the smartphone notifies them that "there are discounted vegetables nearby."

[1653] Input: Location information from beacon device and shopping list

[1654] Output: Notification to guide the user to the product shelf or corner

[1655] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1656] This invention is a system that automates and streamlines the tedious tasks of managing household finances and purchasing everyday items. In particular, this system aims to provide more personalized services by incorporating an emotion engine that recognizes the user's emotions. The system receives financial data entered by the user, automatically updates the household ledger based on that data, and also provides the function of categorizing and analyzing expenses. This allows users to easily manage their expenses. It also predicts items that need to be reordered based on the frequency of use and purchase history of everyday items, and automatically places orders in conjunction with an online shopping platform, allowing users to continuously obtain necessary items without missing them. Furthermore, the system recognizes the user's emotions and adjusts the provided savings suggestions and shopping list based on the user's emotions.

[1657] System configuration and functions

[1658] 1. Receiving financial data and updating your household accounts:

[1659] Server: Receives financial data entered by the user, including income, expenses, and transaction information.

[1660] Server: Automatically updates the household ledger based on the received data. This update includes adding new transactions and modifying existing transactions.

[1661] 2. Expenditure classification and analysis:

[1662] Server: Categorizes the updated household accounting data by category, such as food, transportation, entertainment, etc.

[1663] Server: Analyzes the categorized spending data to understand user spending patterns, including calculating totals, averages, frequency, etc.

[1664] 3. Providing savings offers:

[1665] Server: Based on the analysis of spending patterns, the server provides users with savings suggestions. For example, if spending in a particular category is high, the server provides advice on reducing spending in that category.

[1666] 4. Reorder Estimation and Execution:

[1667] Server: Based on the frequency of use and purchase history of everyday items, it estimates what items need to be reordered. Examples include paper or plastic consumables and food.

[1668] Server: Connects to online shopping platforms and automatically places orders for the estimated items, allowing users to obtain the items they need in a timely manner.

[1669] 5. Customized Lists and Suggestions:

[1670] Server: Learns the user's preferences and lifestyle patterns and generates customized shopping lists and savings suggestions based on them, using past purchase history and lifestyle data.

[1671] 6. Real-time response and advice:

[1672] Server: Utilizes generative artificial intelligence models to respond to user questions and provide advice in real time, providing quick solutions to user concerns and improving the efficiency of daily life.

[1673] 7. Use of Emotion Engine:

[1674] Server: Includes an emotion engine that recognizes the user's emotions. The emotion engine detects emotions from the user's facial expressions, tone of voice, input text, etc.

[1675] Server: Tailors customized savings suggestions and shopping lists based on the user's emotions detected by the emotion engine. For example, if the user is feeling stressed, it can recommend relaxation items to relieve stress.

[1676] Server: Based on the user's emotions detected by the emotion engine, the server adjusts responses and advice content in real time, thereby providing personalized advice according to the user's emotional state.

[1677] Specific examples

[1678] User: At the beginning of each month, the user enters their bank transaction information into the system, including food and transportation expenses.

[1679] Terminal: The terminal transmits the entered transaction information to the server.

[1680] Server: The server receives the transaction information and updates the household ledger. The updated household ledger classifies the transaction information by category and generates analysis results.

[1681] Server: Based on the analysis results, the server provides users with money-saving suggestions such as, "Your food costs are high. You can save money by cutting down on eating out and cooking more at home."

[1682] Server: Learns from past purchase history how often the toothpaste purchased last time is used, and if it determines that a reorder is necessary, it automatically places the order.

[1683] Server: Further customizes and recommends the next shopping list based on the user's preferences and lifestyle patterns.

[1684] Server: Uses generative artificial intelligence models to provide appropriate advice in response to real-time questions from users.

[1685] Server: Uses an emotion engine to sense the user's emotions and tailor savings suggestions and shopping lists accordingly. For example, if the user is tired, recommend items that will help reduce stress.

[1686] Server: Tailors real-time responses and advice based on the emotion engine, providing personalized support according to the user's emotional state.

[1687] The system enables automatic and efficient household management and daily necessities purchasing, and also provides personalized services based on users' emotions, significantly reducing users' time and effort and improving their quality of life.

[1688] The processing flow will be explained below.

[1689] Step 1:

[1690] The user enters bank transaction information and a new purchase history. For example, the transaction information includes a food expense of 50 yen and a transportation expense of 20 yen, and the new purchase history is recorded as "toothpaste."

[1691] Step 2:

[1692] The terminal sends the transaction information and purchase history entered by the user to the server. The transmitted data includes the date and time of the transaction, the amount, and the category.

[1693] Step 3:

[1694] The server stores the received transaction information as financial data and also stores the new purchase history in a purchase database.

[1695] Step 4:

[1696] The server updates the household ledger with the financial data, which includes adding new transactions and modifying existing transactions.

[1697] Step 5:

[1698] The server categorizes the household accounting data into categories, such as food, transportation, and entertainment expenses.

[1699] Step 6:

[1700] The server analyzes the classified household account data to understand the user's spending patterns, including total and average spending amounts and frequency of spending.

[1701] Step 7:

[1702] The server uses an emotion engine to recognize the user's emotions, using information such as the user's facial expression, tone of voice, and input text to determine the emotion.

[1703] Step 8:

[1704] The server generates money-saving suggestions based on the analysis results and the recognition results of the emotion engine. For example, if a user is feeling stressed because of high food expenses, the server will suggest, "Your food expenses are high. You can save money by cutting down on eating out and cooking more at home, which will also help reduce stress."

[1705] Step 9:

[1706] The server learns the user's purchase history and frequency of use and predicts which items need to be reordered. For example, it determines that a reorder is necessary based on how often toothpaste was used last time.

[1707] Step 10:

[1708] The server places an order for the estimated reorder items to the online shopping platform, utilizing an automatic ordering function to save the user the trouble of manually placing the order.

[1709] Step 11:

[1710] The server generates customized shopping lists and savings suggestions based on the results of the emotion engine. For example, if the user has the emotion of wanting to relax, it will recommend relaxation items.

[1711] Step 12:

[1712] The server sends the generated customized shopping list and savings suggestions to the terminal, which displays them to the user.

[1713] Step 13:

[1714] When a user asks a question in real time, the server uses a generative artificial intelligence model to provide answers and advice to the user's questions.

[1715] Step 14:

[1716] The server adjusts its real-time responses and advice based on the user's emotions detected by the emotion engine. For example, if the user is feeling irritated, the server will provide calm advice to calm the user.

[1717] Step 15:

[1718] The terminal displays the responses and advice received from the server to the user, thereby helping the user to efficiently manage their household finances and purchase everyday items.

[1719] Example 2

[1720] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1721] In modern life, managing household finances and purchasing everyday items requires a significant amount of time and effort. Furthermore, conventional household finance management and purchasing systems lack the ability to provide personalized services that take user emotions into account, making it difficult to increase user satisfaction. The present invention aims to solve these problems by streamlining and automating household finance management and providing personalized responses based on user emotions.

[1722] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1723] In this invention, the server includes: means for receiving financial data input by a user; means for automatically updating a household account book based on the financial data; means for classifying and analyzing the updated household account book data; means for providing the user with money-saving suggestions based on the analysis results; means for predicting items that need to be reordered based on the frequency of use and purchase history of daily necessities; means for automatically ordering the predicted items in cooperation with an e-commerce platform; means including an emotion engine that recognizes user emotions; and means for adjusting money-saving suggestions and a shopping list based on the user emotions sensed by the emotion engine. This allows the user to automatically manage their household finances, obtain necessary items in a timely manner, and receive personalized services according to their emotions.

[1724] "User" refers to any individual or organization that uses this system.

[1725] "Financial Data" refers to information related to a user's economic activities, such as income, expenses, and transaction information.

[1726] A "household account book" refers to a digital or physical ledger that allows a user to record and manage their income and expenses.

[1727] "Classification" refers to the process of separating household data into categories, such as food, transportation, and entertainment.

[1728] "Analysis" refers to the process of statistically analyzing household accounting data to identify spending patterns and unusual spending.

[1729] "Savings suggestions" refers to providing financial advice to users based on the analysis of their household accounting data.

[1730] "Frequency of use" refers to data indicating how often an everyday item is used.

[1731] "Purchase history" refers to data that records the items a user has previously purchased and their detailed information.

[1732] "Reordering" refers to the process of reordering needed items based on frequency of use and purchase history.

[1733] "E-commerce platform" refers to a website or application for buying and selling goods and services online.

[1734] An "emotion engine" refers to technology that detects emotions from a user's facial expressions, tone of voice, input text, etc.

[1735] "Personalization" refers to customizing services and offers based on the individual characteristics and circumstances of each user.

[1736] The present invention is a system that allows users to automate and streamline the tedious tasks of managing their household finances and purchasing everyday items. The system is designed to receive financial data, update household accounts, categorize and analyze expenses, provide savings suggestions, estimate and execute reorders for everyday items, and provide customized suggestions based on the user's emotions.

[1737] Receive financial data and update your household budget

[1738] At the beginning of each month, users enter financial data, such as bank transaction information and cash expenditure information, into the system. Specific examples include food expenditures of 1,000 yen and transportation expenditures of 3,000 yen. The data entered by the user is sent to the server via the terminal. Based on the received data, the server adds new transactions to the household accounting database and modifies existing transactions. For example, if the total food expenditures for August were 5,000 yen, a new expenditure of 1,000 yen would be added, bringing the total to 6,000 yen.

[1739] Expense classification and analysis

[1740] The server analyzes the updated household ledger data and classifies each transaction into a category. Specific examples include food expenses, transportation expenses, and entertainment expenses. Based on this, the server categorizes food-related transactions into the "food" category and transportation-related transactions into the "transportation" category. Based on the expenditure data for each category, the server calculates statistical information such as total expenditures, frequency, and average amounts. For example, it calculates the average monthly food expenses and compares them between years. The server detects spending trends and unusual spending patterns. For example, if transportation expenses spike in a particular month, it analyzes the cause.

[1741] Providing savings suggestions

[1742] The server generates savings suggestions tailored to the user based on the analysis of spending patterns. For example, a user with high transportation costs may be advised to consider commuting by bicycle. The generated savings suggestions are sent to the device, which then displays them to the user, suggesting specific ways to save money.

[1743] Reorder estimation and execution

[1744] Based on the frequency of use and purchase history of everyday items, the server estimates which items need to be reordered. As a specific example, it estimates when the next purchase will be based on the rate at which toilet paper was used the last time it was purchased. Information on items that are estimated to be needed is obtained by the server, and a decision is made as to whether to reorder them based on the user's purchase history. If it is determined that a reorder is necessary, the server will link with the e-commerce platform via API or other means to automatically place the order. After the order is completed, the server will notify the user of the order details.

[1745] Generate customized suggestions and lists

[1746] The server analyzes the user's past purchase history and lifestyle data to generate customized shopping lists and suggestions. For example, a user who buys a lot of ingredients on the weekend will be offered "recommended ingredients for this weekend." Savings suggestions tailored to the user's preferences are also offered. The customized lists and suggestions are displayed to the user through their device.

[1747] Real-time response and advice

[1748] A user inputs a question about household management into the system in real time. A specific example is, "How can I reduce my food expenses this month?" The device sends the question to the server, which uses a generative AI model (e.g., a generative AI model) to generate an appropriate answer to the user's question. The generated answer is sent to the device, which displays the generated answer to the user in real time.

[1749] Use of emotion engine

[1750] The system reads emotions from the user's tone of voice and input text. For example, if the input text is "tired," it will detect stress. Emotional data is sent to the server via the device, and the server uses an emotion engine to analyze the user's emotions. Based on the emotions, customized savings suggestions and shopping lists are adjusted. The response of the generative AI model is also customized based on the emotion data, providing personalized advice according to the user's current emotional state.

[1751] Prompt Sentence Examples

[1752] User: I want to enter my monthly expenses. How can I get the data reflected in my household ledger?

[1753] Terminal: Sends entered data to the server.

[1754] Server: Automatically updates the household account book based on bank transaction information and analyzes expenses.

[1755] This system allows users to efficiently manage their household finances, obtain necessary items in a timely manner, and receive personalized services based on their emotions, which can significantly reduce users' time and effort and improve their quality of life.

[1756] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1757] Step 1:

[1758] Entering and submitting financial data

[1759] At the beginning of each month, users enter their financial data, such as bank transaction information and cash expenditure information, into the system. For example, they enter 1,000 yen in food expenses and 3,000 yen in transportation expenses. The terminal then sends this input data to the server.

[1760] Input: Financial data such as food expenses, transportation expenses, etc.

[1761] Output: Financial data sent to the server

[1762] Step 2:

[1763] Receiving data and updating the household account book

[1764] The server receives the financial data sent from the device. Based on the received data, the server adds new transactions to the household accounting database and modifies existing transactions. For example, if the total food expenditure for August was 5,000 yen, it will add a new expenditure of 1,000 yen to update it to 6,000 yen.

[1765] Input: Financial data sent from the terminal

[1766] Processing: Update the household accounting database (add new transactions, modify existing transactions)

[1767] Output: Updated household account book

[1768] Step 3:

[1769] Expense Category Classification

[1770] The server categorizes the updated household accounting data into categories, such as food expenses, transportation expenses, and entertainment expenses.

[1771] Input: Updated household accounting data

[1772] Processing: Categorizing transaction data (e.g., food, transportation, entertainment)

[1773] Output: Household accounting data categorized by category

[1774] Step 4:

[1775] Analysis of spending patterns

[1776] The server calculates statistics such as total expenditures, frequency, and average amounts based on each category of expenditure data. For example, it calculates the average monthly food expenditure and compares it year-over-year. It also detects expenditure trends and unusual patterns.

[1777] Input: Household accounting data categorized by category

[1778] Processing: Calculating statistical information (total, frequency, average amount of expenditure)

[1779] Output: Spending statistics and analysis results

[1780] Step 5:

[1781] Generate and notify savings suggestions

[1782] The server generates savings suggestions tailored to the user based on the analysis of spending patterns. For example, it might suggest to a user with high transportation costs, "Consider commuting by bicycle." The generated savings suggestions are sent to the device, which then displays them to the user.

[1783] Input: Spending statistics and analysis results

[1784] Processing: Generate savings proposals

[1785] Output: Generated savings proposals

[1786] Step 6:

[1787] Estimating reorders of everyday items

[1788] The server estimates which items need to be reordered based on the frequency of use and purchase history of everyday items. For example, it estimates when the next purchase will be made based on the rate at which toilet paper was used last time.

[1789] Input: Usage frequency and purchase history data

[1790] Processing: Usage frequency analysis, reorder estimation

[1791] Output: List of items that need to be reordered

[1792] Step 7:

[1793] Automatic order execution

[1794] If it is determined that a reorder is necessary, the server will automatically place the order by connecting with the e-commerce platform via API, etc. After the order is completed, the server will notify the user of the order details.

[1795] Input: List of items that need to be reordered

[1796] Processing: Integration with e-commerce platforms, automatic order execution

[1797] Output: Order details notification

[1798] Step 8:

[1799] Customization suggestions based on user preferences

[1800] The server analyzes the user's past purchase history and lifestyle data to generate customized shopping lists and savings suggestions. For example, it provides "recommended ingredients for this weekend" to users who buy a lot of ingredients on the weekend.

[1801] Input: Past purchase history, lifestyle data

[1802] Processing: Analysis of preferences and lifestyle patterns, generation of customization suggestions

[1803] Output: customized shopping list and savings suggestions

[1804] Step 9:

[1805] Real-time question responses

[1806] Users input questions about household finances into the system in real time. A typical example is, "How can I reduce my food expenses this month?" The device sends the question to the server, which uses a generative AI model (e.g., a generative AI model) to generate an appropriate answer to the user's question. The generated answer is sent to the device and displayed to the user in real time.

[1807] Input: Real-time questions

[1808] Processing: Answer generation using generative AI models

[1809] Output: The generated answer

[1810] Step 10:

[1811] Receiving and analyzing emotion data

[1812] The system reads emotions from the user's tone of voice and input text. For example, if the input text is "tired," it will detect stress. Emotion data is sent to the server via the device, and the server uses an emotion engine to analyze the user's emotions.

[1813] Input: The user's tone of voice and input text

[1814] Processing: Emotion recognition and data generation

[1815] Output: User emotion data

[1816] Step 11:

[1817] Tailoring personalized suggestions based on emotions

[1818] Based on the emotional data, the server will tailor customized savings suggestions and shopping lists. For example, if the user is tired, it will add relaxation items to the shopping list. The emotional data will also customize the generative AI model's response, providing personalized advice based on the user's current emotional state.

[1819] Input: User emotion data

[1820] Processing: tailoring suggestions and customizing responses with generative AI models

[1821] Output: Tailored savings suggestions, shopping lists, personalized advice

[1822] (Application example 2)

[1823] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1824] Today's users are required to efficiently manage their household finances and purchase daily necessities amid their busy lives. However, these tasks are time-consuming and lack emotionally-sensitive personalized support, which increases user stress. Conventional systems have struggled to streamline household finances and purchase daily necessities, while providing personalized suggestions in a unified manner. Therefore, there is a need for the development of a system that automates and streamlines household finances and purchases while providing emotionally-sensitive support.

[1825] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving financial data input by a user, means for automatically updating the household account book based on the financial data, means for classifying and analyzing the updated household account book data, means for providing the user with money-saving suggestions based on the analysis results, means for predicting items that need to be reordered based on the frequency of use and purchase history of daily necessities, means for automatically ordering the predicted items in cooperation with an e-commerce platform, and means for recognizing the user's emotions using an emotion recognition engine and providing personalized suggestions based on the recognized emotions. This enables the user to efficiently manage their household finances and purchase daily necessities while receiving support based on their emotions.

[1826] "User" refers to an individual who uses the system to manage their household finances and purchase everyday items.

[1827] "Financial Data" refers to data related to economic activity, such as income, expenses, and transaction information entered by users.

[1828] A "household account book" refers to a ledger used to record and manage a user's income and expenses.

[1829] An "emotion recognition engine" refers to a system that detects emotions from a user's facial expressions, tone of voice, input text, etc.

[1830] "Savings Suggestions" refers to advice that analyzes a user's spending patterns and suggests ways to save money.

[1831] "Items that need to be reordered" refers to items that are determined to need to be purchased again based on the frequency of use and purchase history of everyday items.

[1832] "E-commerce platform" refers to a website or application that allows users to buy and sell goods and services online.

[1833] "Personalized suggestions" refers to providing specific advice or recommendations based on a user's emotions and preferences.

[1834] A "generative artificial intelligence model" refers to an artificial intelligence that generates answers and advice based on input data and questions.

[1835] This invention is a system that helps users manage their household finances and purchase everyday items efficiently. The system uses an emotion recognition engine and a generative artificial intelligence model to provide personalized suggestions based on the user's emotions.

[1836] The server first receives financial data entered by the user. Financial data includes income, expenses, and transaction information. For example, the user enters bank transaction information using a smartphone. This data is automatically updated in the household ledger.

[1837] The updated household accounting data is then classified and analyzed. Spending patterns are categorized and the total amount and frequency are calculated. Based on the results of this analysis, savings suggestions are provided to the user. For example, if the analysis shows that food expenses are high, the system will suggest "eating out less and cooking more at home."

[1838] Based on the frequency of use and purchase history of everyday items, the system predicts which items need to be reordered. For example, this applies to consumables such as paper products and food. The server then automatically orders these items in conjunction with the e-commerce platform, allowing users to obtain the items they need in a timely manner.

[1839] The emotion recognition engine recognizes emotions from the user's facial expressions, tone of voice, input text, etc. For example, if the user is feeling stressed, it will recommend relaxation items. Making suggestions based on emotions improves user satisfaction.

[1840] The generative AI model responds to real-time questions from users and generates appropriate advice based on the input data and questions. For example, if a user asks, "How can I reduce my food expenses this month?", the model will provide specific advice.

[1841] The hardware used includes a smartphone, the emotion recognition engine is Microsoft Azure's Emotion API, and the generative artificial intelligence model is OpenAI's GPT.

[1842] Examples:

[1843] Users input financial data into the system via a smartphone app. The server receives the data and automatically updates the household ledger. Next, an emotion recognition engine detects stress levels from the user's facial expressions and suggests relaxation items. Meanwhile, a generative AI model provides real-time advice, such as "You can cut down on food costs by eating out less."

[1844] Example prompt sentence:

[1845] Consider user emotions and offer advice on buying and saving money on everyday items.

[1846] The user seems tired. Suggest items or foods that will help them relax.

[1847] The system allows users to efficiently manage their finances and purchase everyday items while receiving emotional support.

[1848] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1849] Step 1: Enter your financial data

[1850] A user uses a smartphone to input financial data such as income, expenses, and transaction information. This financial data is sent from the device to a server. The input data includes categories such as income, food expenses, and transportation expenses, along with the amounts for each. The server temporarily stores the received data.

[1851] Step 2: Update your household budget

[1852] The server automatically updates the household ledger based on the received financial data. Specifically, it analyzes transaction information and categorizes them. It adds and modifies new transactions to the previous household ledger to create a household ledger that reflects the user's latest financial situation. The updated household ledger is obtained as output.

[1853] Step 3: Categorize and analyze expenses

[1854] The server categorizes and analyzes the updated household accounting data. It categorizes income and expenses by category and calculates the total amount and frequency of spending for each category. The analysis results include total expenditures and spending patterns for each category, such as food, transportation, and entertainment. This allows users to understand their spending habits.

[1855] Step 4: Generate savings proposals

[1856] The server generates savings suggestions for the user based on the results of the expenditure analysis. For example, if expenditures in a particular category are high, specific advice on reducing spending in that category is provided. Saving suggestions are generated using a generative AI model and are tailored to the user's lifestyle. Saving suggestions are obtained as the output.

[1857] Step 5: Estimate reorders

[1858] The server estimates which items need to be reordered based on the frequency of use and purchase history of daily items. It analyzes purchase history data and predicts when repurchases will be necessary. For example, it estimates the timing of repurchase based on the period of use of toothpaste previously purchased. The output is a list of items that can be reordered.

[1859] Step 6: Execute an automatic order

[1860] The server automatically orders the estimated reorder candidate items in cooperation with the e-commerce platform. It checks the stock status and price of the necessary items and executes the order at the optimal time. This allows users to regularly secure the daily necessities they need. The output is confirmation data that the automatic order has been completed.

[1861] Step 7: Emotion Recognition and Custom Suggestions

[1862] The server uses an emotion recognition engine to recognize the user's emotions. It analyzes the input text, tone of voice, and facial expression data to determine the user's emotional state (e.g., stress or happiness). Based on the recognized emotions, it personalizes saving suggestions and shopping lists to provide suggestions that the user desires. The output is customized suggestions based on emotions.

[1863] Step 8: Real-time support

[1864] The server uses a generative AI model to respond to real-time questions from users. For example, in response to a question like, "How can I reduce my food expenses this month?", it will suggest detailed ways to save money. The AI ​​generates a response based on the prompt text, providing the user with timely and useful information. The output is specific advice.

[1865] Through these steps, users can manage their household finances and purchase everyday items efficiently and personalizedly.

[1866] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1867] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1868] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1869] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1870] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1871] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1872] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1873] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1874] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1875] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1876] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1877] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1878] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1879] 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.

[1880] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1881] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1882] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1883] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1884] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1885] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1886] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1887] The following is further disclosed regarding the above embodiment.

[1888] (Claim 1)

[1889] means for receiving financial...

Claims

1. means for receiving financial data input from a user; means for automatically updating a household account book based on said financial data; means for classifying and analyzing the updated household accounting data; means for providing a user with savings suggestions based on the analysis results; A means for estimating items that need to be reordered based on the frequency of use and purchase history of everyday items; means for automatically ordering the estimated item in cooperation with an online shopping platform; A system including:

2. The system of claim 1 , further comprising means for learning a user's preferences and lifestyle patterns and generating individually customized shopping lists and savings suggestions based thereon.

3. The system of claim 1 , further comprising means for utilizing a generative artificial intelligence model to respond to user questions and provide advice in real time.

Images