System

Abstract

A system is provided.SOLUTION: The system includes an input means for inputting household account information, a normalization means for normalizing the household account information received from the input means, an analysis means for analyzing the data normalized by the normalization means, an advice generation means for generating advice on the household account based on the analysis means, and a display means for displaying the advice generated by the advice generation means.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, many individuals and families face challenges in managing their household finances. Specifically, the balance between income and expenditures is unclear, making it difficult to avoid wasteful spending and develop effective savings plans. In particular, when there are multiple expenditure items, it is not easy to properly analyze the expenditure ratio for each item and find specific improvement measures. There is a need for a system that can solve these problems and allow users to efficiently manage their household finances. [Means for solving the problem]

[0005] In order to solve the above-mentioned problems, there is provided a system including an input means for inputting household information, a normalization means for normalizing the household information received from the input means, an analysis means for analyzing the data normalized by the normalization means, an advice generation means for generating advice regarding household finances based on the analysis means, and a display means for displaying the advice generated by the advice generation means. This system enables a user to efficiently manage their household finances and is able to support reducing wasteful spending and achieving savings goals.

[0006] "Household Information" means information that includes income, expenses, and related financial data.

[0007] "Input means" refers to the interface or device that allows a user to input information. Examples include a keyboard, mouse, and touch screen.

[0008] "Normalization" is the process of converting input data into a form that is easier to analyze and removing outliers and missing values.

[0009] The "normalization means" refers to a program or function for normalizing the household information.

[0010] "Analysis tools" are functions or programs that analyze normalized data and find specific patterns or trends.

[0011] "Advice generation means" refers to a function or program for creating specific advice on household management based on the analyzed data.

[0012] The "display means" refers to an interface or device that visually presents the generated advice to the user. Specifically, it includes a display, a monitor, a mobile screen, and the like. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] The present invention relates to a system that provides advice based on input household finance information. Specific embodiments of the present invention will be described below.

[0035] System Overview

[0036] Users input household information into an application on their device (PC or smartphone). Specifically, they input items such as monthly income, rent, food expenses, and transportation expenses. This information is sent to the server via the device.

[0037] The server normalizes the received household information. For example, if there are abnormal values, it detects them and provides feedback. It also imputes missing values.

[0038] The server then analyzes the normalized data, calculating the income and expenditure items to arrive at a balance, and assessing the percentage of each expenditure category.

[0039] The server generates specific advice for the user's household finances based on the analysis results. For example, if food expenses are high, it will suggest "cooking more at home." If the balance is positive, it will provide a specific plan for achieving future savings goals.

[0040] Finally, the server sends the generated advice to the terminal and displays it to the user, who can then take specific actions to improve their household finances.

[0041] Specific examples

[0042] Suppose a user launches the application and enters the following household information:

[0043] Monthly salary: 500,000 yen

[0044] Rent: 100,000 yen

[0045] Food expenses: 50,000 yen

[0046] Transportation fee: 30,000 yen

[0047] Other expenses: 50,000 yen

[0048] The device sends this information to a server, which then receives the data and first normalizes it, taking into account, for example, unusually high food values ​​or unusually low values ​​for other expenditure items.

[0049] Next, the server analyzes the normalized data. Calculating the balance, the server finds that the monthly income is 500,000 yen and the expenditure is 230,000 yen, resulting in a positive balance of 270,000 yen. It also calculates the percentage of each expenditure item and finds that food expenses account for 10%.

[0050] The server generates advice based on the results of this analysis. For example, it could say, "Your food expenses are high. Cook more meals at home to save money," or "You can save 270,000 yen per month. Keep saving and get closer to your future goal."

[0051] Finally, the server sends the generated advice to the terminal, which displays it to the user, who can then take specific actions to improve their household finances.

[0052] This embodiment allows users to efficiently manage their household finances, reduce wasteful spending, and receive support in achieving their savings goals.

[0053] The processing flow will be explained below.

[0054] Step 1:

[0055] The user operates the device and launches the application. The user enters household information such as monthly income, rent, food expenses, and transportation expenses. After confirming that the input data is correct, the user clicks the send button.

[0056] Step 2:

[0057] The terminal sends the household information entered by the user to the server. The sent data includes detailed information on income and various expenses.

[0058] Step 3:

[0059] The server first validates the household information received from the device, checking that all data is entered in the correct format (e.g., numeric format), and returns feedback to the user if any data is invalid.

[0060] Step 4:

[0061] The server normalizes the received data. If the data contains abnormal values ​​(e.g., monthly income is extremely high or low), it detects this and asks the user to re-enter the data. It also imputes missing values.

[0062] Step 5:

[0063] The server analyzes the normalized data, calculating the balance by subtracting all expenses from income, and calculating the percentage of each expense item relative to monthly income.

[0064] Step 6:

[0065] The server generates specific advice based on the analysis results. For example, if the proportion of food expenses is high, it will suggest "cooking more meals at home to save money," and if there is a positive balance, it will display the amount of savings.

[0066] Step 7:

[0067] The server transmits the generated advice to the terminal, which includes a suggestion of what specific action the user should take.

[0068] Step 8:

[0069] The device receives the advice sent from the server and visually displays it to the user, who can then review the advice and take action to improve their household finances.

[0070] Example 1

[0071] 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."

[0072] Conventional household management systems often require users to manually input data, without providing sufficient analysis or advice. This makes it difficult for users to accurately grasp their own household situation and find appropriate improvement measures. Furthermore, the lack of accurate correction for data containing outliers or missing values ​​also creates a problem of low reliability in the analysis results.

[0073] 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.

[0074] In this invention, the server includes input means for inputting household information, normalization means for normalizing the household information received from the input means, analysis means for analyzing the data normalized by the normalization means, advice generation means for generating advice regarding household finances based on the analysis means, and display means for displaying the advice generated by the advice generation means. This allows a user to receive an accurate and reliable household analysis and easily obtain advice on specific improvement measures.

[0075] "Household information" is data relating to the user's income and expenses, specifically information consisting of income, rent, food expenses, transportation expenses, and other expense items.

[0076] "Input means" refers to the interface and device through which users input household information, including applications on smartphones and PCs.

[0077] "Normalization means" refers to functions for normalizing household information received from input means through the detection of outliers and completion of missing values, and includes data processing libraries such as Python's Pandas and NumPy.

[0078] "Analysis tools" refers to functions for calculating income and expenditure balances and evaluating the proportions of each expenditure category based on data normalized by the normalization tools, and includes the Python Scikit-learn library.

[0079] "Advice generation means" refers to a function for generating specific advice for improving household finances based on data obtained from the analysis means, and uses a generative AI model (e.g., GPT-3 (registered trademark)).

[0080] The "display means" refers to a function for displaying the advice generated by the advice generating means to the user, and includes an application interface on a smartphone or PC.

[0081] "Generative AI model" refers to an artificial intelligence model that generates advice in natural language based on an input prompt, and includes OpenAI's (registered trademark) GPT series.

[0082] A "prompt" refers to a specific instruction to be input into the generative AI model, and is text used to generate advice based on the user's household financial information.

[0083] This invention relates to a system that provides advice based on input household information. This system allows users to input household information using a terminal (PC or smartphone), and the information is processed and analyzed by a server, which then generates and provides advice to the user. Specifically, this system is implemented using the following hardware and software.

[0084] Hardware used

[0085] 1. Terminal: A device such as a PC or smartphone

[0086] 2. Server: A remote server for data processing and analysis.

[0087] Software used

[0088] 1. Application: Software that runs on a device and provides an interface for users to enter household information.

[0089] 2. Data processing library: Use Python's Pandas or NumPy to normalize the data

[0090] 3. Data Analysis Library: Analyze data using Python's Scikit-learn

[0091] 4. Generative AI model: Uses OpenAI's GPT series to generate advice from analysis results.

[0092] Overview of program processing

[0093] The user launches the application on their device and enters their monthly income and expenses (rent, food, transportation, and other expenses). This household information is sent from the device to the server in JSON format. The server then normalizes the received household information using Python's Pandas and NumPy. Specifically, it detects outliers and completes missing values.

[0094] The server then analyzes the normalized data using Python's Scikit-learn. This analysis includes calculating the balance of income and expenditures and assessing the percentage of each expenditure category. For example, if income is ¥500,000 and expenditures are ¥230,000, the balance will be ¥270,000, with food spending accounting for 10%.

[0095] Based on the analysis results, the advice generator uses a generative AI model (GPT-3) to generate specific advice. An example of a prompt sentence to be input to the generative AI model is as follows:

[0096] The user's monthly income is 500,000 yen, rent is 100,000 yen, food is 50,000 yen, transportation is 30,000 yen, and other expenses are 50,000 yen. Please provide specific advice for their current financial situation.

[0097] The generated advice is sent from the server to the device and displayed on the device's application interface. Based on this advice, the user can take specific actions to improve their household finances. For example, advice could be, "Cook more meals at home to save money on food," or "You can save 270,000 yen each month. Keep saving and get closer to your future goal."

[0098] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0099] Step 1:

[0100] The user enters household information into an application on the terminal.

[0101] The user launches the application on their device and enters household information such as income, rent, food, transportation, and other expenses. The entered information is properly formatted and verified by the application. The input data format is numeric data for income and each expense item.

[0102] Step 2:

[0103] The terminal transmits the input information to the server.

[0104] The terminal converts the household information entered by the user into JSON format and sends it to the server using the HTTPS protocol. For example, the following data is sent:

[0105] json

[0106] {

[0107] "income": 500000,

[0108] "rent": 100000,

[0109] "food": 50000,

[0110] "transport": 30000,

[0111] "other": 50000

[0112] }

[0113] This data is input to and received by the server.

[0114] Step 3:

[0115] The server normalizes the data it receives.

[0116] The server converts the received JSON data into a data frame using Python's Pandas library and normalizes the data. Specifically, it detects outliers and imputes missing values. For example, if the food expenses figure is abnormally high, it will be determined to be an outlier and generate a notification to the user. Additionally, if there are missing values, they will be imputed using the average or median of past data. The input data is household information, and the output is normalized data.

[0117] Step 4:

[0118] The server analyzes the normalized data.

[0119] The server calculates the income and expenditure balance based on the normalized data. Specifically, it uses Python's Scikit-learn library to calculate the sum of the user's income and expenses and calculate the net balance. It also evaluates the percentage of each expenditure category. For example, if a monthly income is 500,000 yen and expenses are 230,000 yen, the balance will be positive 270,000 yen. The input data is normalized household information, and the output is the income and expenditure balance and the percentage of each expenditure category.

[0120] Step 5:

[0121] The server generates advice based on the analysis results.

[0122] The server generates advice using a generative AI model (e.g., GPT-3) based on the data on income and expenditure balance and expenditure ratio. A prompt sentence is constructed and input into the generative AI model. An example of a prompt sentence is as follows:

[0123] The user's monthly income is 500,000 yen, rent is 100,000 yen, food is 50,000 yen, transportation is 30,000 yen, and other expenses are 50,000 yen. Please provide specific advice for their current financial situation.

[0124] The generative AI model uses this prompt to generate specific advice for improving household finances. The input data is the numerical data from the analysis results and the prompt, and the output is the generated advice.

[0125] Step 6:

[0126] The server transmits the generated advice to the terminal.

[0127] The server converts the generated advice into JSON format and sends it to the device using the HTTPS protocol. For example, the following advice is sent:

[0128] json

[0129] {

[0130] "advice": "Food costs are high. Cook more meals at home and save money. You can save 270,000 yen per month. Keep saving and get closer to your future goal."

[0131] }

[0132] This data is entered into the terminal.

[0133] Step 7:

[0134] The terminal displays the advice to the user.

[0135] The device displays the advice received from the server on the application interface. The user can check the advice and take specific actions based on it. For example, they might cook more meals at home or create a savings plan. The input data is the advice received from the server, and the output is what is displayed to the user.

[0136] (Application example 1)

[0137] 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."

[0138] Conventional household management systems require users to manually input household information, which is time-consuming and can lead to input errors or missing information. Furthermore, the lack of automatic acquisition of expenditure information using electronic payment services makes comprehensive household management difficult.

[0139] 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.

[0140] In this invention, the server includes input means for inputting household information, normalization means for normalizing the household information received from the input means, analysis means for analyzing the data normalized by the normalization means, expenditure data acquisition means for automatically acquiring expenditure information from electronic payment services, advice generation means for generating advice regarding household finances based on the analysis means, and display means for displaying the advice generated by the advice generation means. This makes it possible to automatically acquire, normalize, and analyze expenditure information from electronic payment services that a user uses on a daily basis, and to provide highly accurate advice regarding household finances.

[0141] "Household information" is data regarding a user's income, fixed expenses, variable expenses, and other expenditure items.

[0142] "Input means" refers to an interface that allows a user to input household information into the system, and includes devices such as a keyboard, a touch screen, and voice input.

[0143] "Normalization means" refers to processes and functions for detecting and correcting outliers in the input household information and arranging it into an accurate format.

[0144] "Analysis tools" is a function that calculates and evaluates the ratio of income to each expenditure category and the overall balance of income and expenditure based on normalized data.

[0145] The "advice generation means" is a function for creating specific advice for improving household finances based on the analysis results of the analysis means.

[0146] The "expenditure data acquisition means" is a function for automatically acquiring user expenditure information from the electronic payment service.

[0147] The "display means" is an interface for displaying generated advice and analysis results to the user, and includes a smartphone screen, a computer display, a notification function, etc.

[0148] A system for implementing this invention includes an input means for inputting household information, a normalization means for normalizing the household information received from the input means, an analysis means for performing analysis based on the normalized data, an expenditure data acquisition means for automatically acquiring expenditure information from an electronic payment service, an advice generation means for generating specific advice based on the analysis results, and a display means for displaying the generated advice.

[0149] First, the user inputs household information using a device such as a smartphone or PC. This includes data on income, fixed expenses (e.g., rent), and variable expenses (e.g., food and transportation costs). The device then sends this information to the server.

[0150] The server detects outliers and fills in missing values ​​in the received household information to normalize it. The normalized data is then analyzed by analytical tools to calculate income, expenses, and the percentage of each expense category. For example, if monthly income is 500,000 yen, rent is 100,000 yen, food expenses are 50,000 yen, and transportation expenses are 30,000 yen, total expenses are calculated as 180,000 yen, and the income and expenditure balance is calculated.

[0151] At the same time, the server automatically obtains expenditure information from the API of electronic payment services (e.g., PayPal and Stripe) through expenditure data acquisition means. This eliminates the need for users to manually enter the information, enabling accurate data collection. More detailed expenditure information can also be collected using the smartphone's GPS and camera.

[0152] Once the analysis is complete, the server generates specific advice using an advice generation means. For example, based on the data analysis, the server may generate a suggestion such as "Your food expenses are high. Cook more meals at home to save money," or goal-setting advice such as "You can save 270,000 yen per month. Keep saving and get closer to your future goal."

[0153] The generated advice is sent to the user's terminal via the display means and displayed within the application, allowing the user to check the advice and use it to improve their household finance management.

[0154] Furthermore, the system can leverage generative AI models to provide more specific and personalized advice to users, who can input prompts to receive more detailed suggestions.

[0155] As a concrete example, the following prompt sentences can be input into a generative AI model to elicit optimal advice for the user:

[0156] Based on this month's household financial information, please give some specific advice on how to improve your lifestyle.

[0157] Monthly salary: 500,000 yen

[0158] Rent: 100,000 yen

[0159] Food expenses: 70,000 yen

[0160] Transportation fee: 30,000 yen

[0161] Other expenses: 50,000 yen

[0162] Other income and expenditure data: ...

[0163] Also consider the data you can get from electronic payment service APIs.

[0164] This allows users to get a complete picture of their household finances, cut down on wasteful spending, and create concrete action plans to achieve their savings goals.

[0165] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0166] Step 1:

[0167] Users enter household information using a smartphone or PC. Input items include income, rent, food, transportation, and other expenses. This information is structured in JSON format or similar and sent from the device to the server. The input at this stage is recorded as household information.

[0168] Input: Household information entered by the user (income, rent, food, transportation, and other expenses)

[0169] Output: The entered household information is sent to the server.

[0170] Step 2:

[0171] The server normalizes the received household information. This process involves detecting outliers and filling in missing values. For example, if the food expense value is abnormally high, a notification is sent to the user requesting reconfirmation. If no outliers are detected, missing values ​​are filled in with predicted values ​​or average values.

[0172] Input: Household information received from the device

[0173] Output: Normalized household data

[0174] Step 3:

[0175] The server then analyzes the normalized household data. Using analytical tools, it calculates the balance between income and expenditure, and calculates the percentage of each expenditure category. Based on the analysis results, the expenditure percentage and income / expense balance can be determined.

[0176] Input: Normalized household data

[0177] Output: Income and percentage of each expenditure category, balance

[0178] Step 4:

[0179] The server uses the expenditure data acquisition means to automatically acquire the user's expenditure information from the API of the electronic payment service. The API is called, and the acquired data is aggregated on the server. This information is added to the household information.

[0180] Input: Spending information obtained from the API of the electronic payment service

[0181] Output: Added expenditure information

[0182] Step 5:

[0183] The server then integrates the added spending information with the household data based on analytical methods to form a final data set, which accurately calculates the overall spending amount and the percentage of spending by category.

[0184] Input: Household data, expenditure information from electronic payment services

[0185] Output: Final merged dataset

[0186] Step 6:

[0187] The server uses the advice generation means to generate specific advice from the analysis results based on the final dataset. For example, the advice generated might be, "Your food expenses are high at 70,000 yen, so consider cooking more at home to save money."

[0188] Input: Final merged dataset

[0189] Output: Specific advice

[0190] Step 7:

[0191] Finally, the generated advice is transmitted from the server to the terminal and notified to the user using a display means, so that the user can check the generated advice within the application.

[0192] Input: Generated specific advice

[0193] Output: Advice displayed on the user's terminal

[0194] Through the above process, the user can efficiently manage daily household finance information and improve their household finances based on specific advice.

[0195] 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.

[0196] The present invention combines a system that provides advice based on input household finance information with an emotion engine that recognizes the user's emotions. An embodiment of the present invention will now be described in detail.

[0197] System Overview

[0198] Users input household information into an application on their device (PC or smartphone). Specifically, they input items such as monthly income, rent, food expenses, and transportation expenses. This information is sent to the server via the device.

[0199] The server normalizes the received household information. For example, if there are abnormal values, it detects them and provides feedback. It also imputes missing values.

[0200] The server then analyzes the normalized data, calculating the income and expenditure items to arrive at a balance, and assessing the percentage of each expenditure category.

[0201] The server generates specific advice for the user's household finances based on the analysis results. For example, if food expenses are high, it will suggest "cooking more at home." If the balance is positive, it will also display the amount of savings.

[0202] Furthermore, the present invention recognizes the user's emotions using an emotion engine, which identifies the user's emotions (joy, sadness, anger, stress, etc.) through, for example, the user's facial expressions, tone of voice, and content analysis of input content.

[0203] The server adjusts the content and presentation of advice based on the emotional information provided by the emotion engine. For example, if the user is feeling stressed, the server generates advice that contains more encouraging content.

[0204] Finally, the server sends the generated advice to the terminal and displays it to the user, who can then take specific actions to improve their household finances.

[0205] Specific examples

[0206] The user enters financial information using the application

[0207] Suppose a user launches the application and enters the following household information:

[0208] Monthly salary: 500,000 yen

[0209] Rent: 100,000 yen

[0210] Food expenses: 50,000 yen

[0211] Transportation fee: 30,000 yen

[0212] Other expenses: 50,000 yen

[0213] The device sends this information to a server, which then receives the data and first normalizes it, taking into account, for example, unusually high food values ​​or unusually low values ​​for other expenditure items.

[0214] Server analysis and advice generation

[0215] Next, the server analyzes the normalized data. Calculating the balance, the server finds that the monthly income is 500,000 yen and the expenditure is 230,000 yen, resulting in a positive balance of 270,000 yen. It also calculates the percentage of each expenditure item and finds that food expenses account for 10%.

[0216] The server generates advice based on the results of this analysis. For example, it could say, "Your food expenses are high. Cook more meals at home to save money," or "You can save 270,000 yen per month. Keep saving and get closer to your future goal."

[0217] Utilizing the Emotion Engine

[0218] If the emotion engine recognizes the user's emotions (e.g., the user is feeling stressed), the server adds encouraging advice such as, "This is a difficult situation, but let's work together to improve it little by little."

[0219] Displaying Advice

[0220] Finally, the server sends the generated advice to the terminal, which displays it to the user, who can then review the advice and take specific actions to improve their household finances.

[0221] This embodiment allows users to efficiently manage their household finances, reduce wasteful spending, and receive support in achieving their savings goals. Furthermore, by providing detailed advice based on the user's emotions, more effective household finance management is possible.

[0222] The processing flow will be explained below.

[0223] Step 1:

[0224] The user operates the device and launches the application. The user enters household information such as monthly income, rent, food expenses, and transportation expenses. After confirming that the input data is correct, the user clicks the send button.

[0225] Step 2:

[0226] The terminal sends the household information entered by the user to the server. The sent data includes detailed information on income and various expenses.

[0227] Step 3:

[0228] The server first validates the household information received from the device, checking that all data is entered in the correct format (e.g., numeric format), and returns feedback to the user if any data is invalid.

[0229] Step 4:

[0230] The server normalizes the received data. If the data contains abnormal values ​​(e.g., monthly income is extremely high or low), it detects this and asks the user to re-enter the data. It also imputes missing values.

[0231] Step 5:

[0232] The server analyzes the normalized data, calculating the balance by subtracting all expenses from income, and calculating the percentage of each expense item relative to monthly income.

[0233] Step 6:

[0234] The server generates specific advice based on the analysis results. For example, if the proportion of food expenses is high, it will suggest "cooking more meals at home to save money," and if there is a positive balance, it will display the amount of savings.

[0235] Step 7:

[0236] The user can input additional emotional information by operating the device. For example, the user can convey their emotional state (such as stress or satisfaction) to the emotion engine using text input or voice input.

[0237] Step 8:

[0238] The terminal transmits the user's emotional information to the server, which provides the emotional information together with the user's household financial information.

[0239] Step 9:

[0240] The emotion engine analyzes the user's emotion information and identifies the emotional state. For example, if the user inputs "I'm feeling stressed," the emotion engine will recognize that the user is feeling stressed.

[0241] Step 10:

[0242] The server adjusts the content and presentation of advice based on the emotional information provided by the emotion engine. For example, if the user is feeling stressed, the server will add encouraging advice such as, "This is a difficult situation, but let's work hard together to improve it little by little."

[0243] Step 11:

[0244] The server transmits the generated advice to the terminal, which includes a suggestion of what specific action the user should take.

[0245] Step 12:

[0246] The device receives the advice sent from the server and visually displays it to the user, who can then review the advice and take action to improve their household finances.

[0247] Example 2

[0248] 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."

[0249] Conventional household management systems are unable to consider the user's emotions when analyzing household information and providing advice. As a result, it is difficult to provide detailed advice based on the user's emotions, and appropriate support cannot be provided when the user is stressed or unmotivated.

[0250] 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.

[0251] In this invention, the server includes input means for inputting household information, normalization means for normalizing the information, analysis means for analyzing the information, advice generation means for generating advice, an emotion engine for adjustment, adjustment means for adjusting the content of the advice based on the emotion information, and display means for displaying the information, thereby making it possible to accurately analyze the user's household information and provide appropriate advice taking the user's emotions into consideration.

[0252] "Input means" refers to a device or mechanism that allows a user to input household information.

[0253] The "normalization means" is a device or mechanism that normalizes the household information received from the input means by complementing abnormal values ​​and missing values.

[0254] The "analysis means" is a device or mechanism that calculates the balance of income and expenditure and the proportion of each expenditure item based on the data normalized by the normalization means.

[0255] The "advice generating means" is a device or mechanism that generates specific advice regarding household finances based on the data obtained by the analysis means.

[0256] An "emotion engine" is a device or mechanism that analyzes facial expressions, voice tone, input content, etc. to recognize the user's emotional state.

[0257] The "adjustment means" is a device or mechanism that appropriately adjusts the content and expression of advice based on the emotion information obtained from the emotion engine.

[0258] The "display means" is a device or mechanism that displays the advice generated by the advice generating means and the adjustment means to the user.

[0259] System Overview

[0260] This system allows users to input household finance information and provides advice based on that information. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide advice that corresponds to the user's emotional state.

[0261] Users input household information into the application using devices such as PCs or smartphones. Examples of items include monthly income, rent, food expenses, and transportation expenses. This information is sent to the server via the device.

[0262] Data Receipt and Normalization

[0263] The server normalizes the household information received from the device. For example, if there are abnormal values, it detects and corrects them. It also completes any missing values. This ensures the consistency and reliability of the data.

[0264] Analyzing the data

[0265] The server then analyzes the normalized data, calculating income and each expense item to calculate the balance, and assessing the percentage of each expense category. This process is carried out using specialized analytical software installed on the server.

[0266] Generating Advice

[0267] The server generates specific advice for the user's household finances based on the analysis results. For example, if food expenses are high, it will suggest "cook more at home." If the balance is positive, it will also display the amount of savings. This process uses a generative AI model that is installed on the server.

[0268] Utilizing the Emotion Engine

[0269] Furthermore, the present invention uses an emotion engine to recognize the user's emotions. The emotion engine identifies the user's emotions through, for example, analyzing the user's facial expressions, tone of voice, and input content. The server adjusts the content and presentation of advice based on the emotion information provided by the emotion engine. For example, if the user is feeling stressed, the server generates advice that includes more encouraging content.

[0270] Displaying Advice

[0271] Finally, the server sends the generated advice to the terminal and displays it to the user, who can then take specific actions to improve their household finances.

[0272] Specific examples

[0273] Suppose a user launches the application and enters the following household information:

[0274] Monthly salary: 500,000 yen

[0275] Rent: 100,000 yen

[0276] Food expenses: 50,000 yen

[0277] Transportation fee: 30,000 yen

[0278] Other expenses: 50,000 yen

[0279] The device sends this information to a server, which then receives the data and first normalizes it, taking into account, for example, unusually high food values ​​or unusually low values ​​for other expenditure items.

[0280] Next, the server analyzes the normalized data. Calculating the balance, the server finds that the monthly income is 500,000 yen and the expenditure is 230,000 yen, resulting in a positive balance of 270,000 yen. It also calculates the percentage of each expenditure item and finds that food expenses account for 10%.

[0281] The server generates advice based on the results of this analysis. For example, it could say, "Your food expenses are high. Cook more meals at home to save money," or "You can save 270,000 yen per month. Keep saving and get closer to your future goal."

[0282] If the emotion engine recognizes the user's emotions (e.g., the user is feeling stressed), the server adds encouraging advice such as, "This is a difficult situation, but let's work together to improve it little by little."

[0283] Finally, the server sends the generated advice to the terminal, which displays it to the user, who can then review the advice and take specific actions to improve their household finances.

[0284] Example prompts for generative AI models

[0285] "This is an application that allows you to enter your monthly household finances. Based on the data you enter, it calculates your balance and provides you with the percentage of each expense item. It also recognizes your emotions and generates more personalized advice. Please enter your household finances below:

[0286] Monthly salary: 500,000 yen

[0287] Rent: 100,000 yen

[0288] Food expenses: 50,000 yen

[0289] Transportation fee: 30,000 yen

[0290] Other expenses: 50,000 yen

[0291] Emotional data: users are stressed

[0292] Please generate advice."

[0293]

[0294] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0295] Step 1: User enters household information

[0296] The user launches the application on their PC or smartphone and enters household information such as monthly income, rent, food expenses, and transportation costs. The user fills in this information in the input form and clicks the submit button.

[0297] Input: Household information such as monthly income, rent, food, transportation, and other expenses

[0298] Output: Input household information data

[0299] Step 2: The device sends the data to the server

[0300] The device parses the household information entered by the user into JSON format and sends it to the server via an HTTP POST request.

[0301] Input: Entered household information data

[0302] Output: Household information data sent to the server

[0303] Step 3: The server receives and normalizes the data

[0304] The server parses and normalizes the received household information data. Specifically, it detects outliers and missing values ​​and corrects or imputes them. For example, if monthly income is extremely high or food expenses are abnormally low, it generates a warning and imputes them with reasonable values.

[0305] Input: Household information data sent to the server

[0306] Output: Normalized household information data

[0307] Step 4: The server analyzes the data

[0308] The server analyzes the normalized data and calculates the balance and percentage of each expense item (for example, subtracting each expense from monthly income to get the remaining amount), as well as the percentage of total income each expense item contributes to.

[0309] Input: Normalized household information data

[0310] Output: Analysis result data (income and expenditure balance, expenditure ratio, etc.)

[0311] Step 5: Server generates advice

[0312] The server generates advice for improving household finances based on the analysis results data, using a generative AI model to create specific advice such as "Food costs are high, so cook more at home" or "Continue saving money to work toward your future goals."

[0313] Input: Analysis result data

[0314] Output: Generated advice

[0315] Step 6: The server uses the emotion engine

[0316] The server uses an emotion engine to recognize the user's emotions. It analyzes the text data, facial images, and voice data entered by the user to identify their emotional state. For example, if it determines that the user is feeling stressed, it adjusts the content of the advice.

[0317] Input: User's text data, facial images, voice data, and other emotional data

[0318] Output: User's emotional state data

[0319] Step 7: The server adjusts the advice

[0320] The server adjusts the content and presentation of the generated advice based on the user's emotional state data obtained from the emotion engine. For example, if the user is feeling stressed, the server adds encouraging words such as, "It's a tough situation, but let's try to improve it little by little."

[0321] Input: Generated advice, user emotional state data

[0322] Output: Adjusted advice

[0323] Step 8: The server sends the advice to the device

[0324] The server sends the finalized advice to the device, which converts the advice into JSON format and returns it to the device as an HTTP response.

[0325] Input: Tailored Advice

[0326] Output: Advice sent to terminal

[0327] Step 9: The device displays the advice to the user

[0328] The device parses the advice received from the server and displays it on the user's application screen. The user can then review the advice and take specific actions to improve their household finances.

[0329] Input: Advice sent to terminal

[0330] Output: Advice displayed to the user

[0331] (Application example 2)

[0332] 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."

[0333] In modern society, managing one's finances and receiving appropriate financial advice are becoming increasingly important. However, while many existing financial management systems allow users to input and analyze their financial information, they do not consider the user's emotional state. As a result, if the advice provided is not appropriate for the user's psychological state, it often does not lead to actual behavioral change. Furthermore, effective support is required, especially in emotionally stressful situations. Furthermore, the cumbersome interfaces of existing financial management systems often result in a lack of motivation for users to use them regularly.

[0334] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0335] In this invention, the server includes an input means for inputting household information, a normalization means for normalizing the household information received from the input means, an analysis means for analyzing the data normalized by the normalization means, an advice generation means for generating advice about household finances based on the analysis means, a recognition means for recognizing a user's emotions, and an adjustment means for adjusting the content and presentation of the advice based on the emotional information recognized by the recognition means. This makes it possible to provide advice based on the user's household information tailored to the user's emotional state at any given time. Furthermore, using an interface such as a robot enables natural dialogue with the user, thereby increasing motivation to use the household finance management system.

[0336] "Household information" refers to detailed data on the income and expenditure of individuals and households, such as monthly income, rent, food expenses, and transportation costs.

[0337] "Input means" refers to the device or interface that a user uses to input household information. Examples include smartphones and computer applications.

[0338] "Normalization measures" refer to processes or algorithms used to correct, amend, and transform input household information into a form suitable for analysis.

[0339] "Analytical tools" refers to processes and systems for analyzing normalized household information data and calculating income and expenditure balances and expenditure ratios.

[0340] The "advice generation means" refers to a system for forming specific advice and suggestions regarding the user's household finances based on the data obtained by the analysis means.

[0341] The term "display means" refers to a device or method for visually or audibly presenting the generated advice to the user. Specific examples include a display and a speaker.

[0342] "Recognition means" refers to technology for identifying a user's emotions. Specific examples include voice analysis and facial expression recognition.

[0343] "Adjustment means" refers to a process or algorithm that adjusts the content and expression of generated advice based on the recognized user's emotional information.

[0344] This invention combines a system that provides advice based on input household finance information with an emotion engine that recognizes the user's emotions. Specific embodiments for carrying out this invention will be described below.

[0345] System Overview

[0346] Users input household information into an application on their device (smartphone or computer), such as monthly income, rent, food expenses, and transportation expenses. This household information is then sent to a server via the device.

[0347] The server normalizes the household information it receives, a process that detects outliers and imputes missing values. Once normalization is complete, the server then analyzes the data, which includes calculating income and expenditure balances and assessing the percentages of each expenditure category.

[0348] The server generates specific advice for the user's household finances based on the analysis results. For example, it may suggest cooking more meals at home if food costs are high. If the balance is positive, the amount of savings will be displayed.

[0349] The system also recognizes the user's emotions. The emotion engine identifies emotions such as stress or joy through content analysis of the user's facial expressions, tone of voice, and input. The server adjusts the content and presentation of advice based on this emotional information. For example, if the user is feeling stressed, it generates advice that includes encouraging content.

[0350] Finally, the server sends the generated advice to the terminal and displays it to the user.

[0351] Hardware and software configuration

[0352] Hardware: smartphones, computers, robots (smart home assistants), microphones, cameras (for facial recognition)

[0353] Software: Python, Emotion Recognition API, Financial Management API

[0354] Data processing flow

[0355] 1. Enter user's household information:

[0356] The user enters household information and uses a prompt such as, "My monthly income is $500,000. My rent is $100,000 and my food expenses are $50,000. What is the balance?"

[0357] 2. Emotion recognition:

[0358] The emotion engine (Emotion Recognition API) analyzes the user's voice and facial expressions and generates messages based on their emotions, such as "Please do your best. We understand your situation."

[0359] 3. Data normalization and analysis:

[0360] The Financial Management API normalizes household information and analyzes income and expenditure balances and expenditure ratios.

[0361] 4. Advice Generation:

[0362] Based on the analysis results, specific advice tailored to the user's emotional state is generated.

[0363] 5. Display Advice:

[0364] The generated advice is provided to the user in an audio or visual manner.

[0365] This system allows users to efficiently manage their household finances and receive detailed support tailored to their emotions.

[0366] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0367] Step 1:

[0368] The user enters household information.

[0369] Input: Household information such as monthly income, rent, food expenses, and transportation costs. An example prompt is, "My monthly income is 500,000 yen. My rent is 100,000 yen, and my food expenses are 50,000 yen. Please tell me the balance of income and expenses."

[0370] Specific operation: The user uses a smartphone or computer to enter each item on the household information input screen. The device then sends the entered data to the server.

[0371] Step 2:

[0372] The server normalizes the household information.

[0373] Input: Household information data sent from the device.

[0374] Data processing: Detect outliers and correct or impute missing values ​​as necessary.

[0375] Output: Normalized household information data.

[0376] Specific operation: The server receives household information data and stores the normalized information in an internal database.

[0377] Step 3:

[0378] The server analyzes the normalized data.

[0379] Input: Normalized household information data.

[0380] Data calculation: Calculate income and expenditure balances and evaluate the percentage of each expenditure category.

[0381] Output: Analysis results (e.g. income / expense balance, percentage of each expenditure item).

[0382] Specific operation: The server aggregates the income and expenditure for each item, calculates the income and expenditure balance and expenditure ratio, and saves the results.

[0383] Step 4:

[0384] Recognize user emotions.

[0385] Input: User voice and facial expression data. An example prompt is "I've entered my financial information, what should I do next?"

[0386] Data processing: Using voice analysis and facial expression recognition technology to identify emotional states (e.g., joy, sadness, stress).

[0387] Output: User's emotion information.

[0388] Specific operation: The emotion engine analyzes the user's voice or facial expressions obtained from the camera, generates emotion data, and sends it to the server.

[0389] Step 5:

[0390] The server generates the advice.

[0391] Input: Analysis results and user sentiment information.

[0392] Data calculations: Generate tailored advice based on the user's financial situation and emotions. Example: "Cook more at home and save money on food."

[0393] Output: Specific advice on improving your finances.

[0394] Specific operation: The server uses a generative AI model to generate advice in text format based on analytical data and emotional data.

[0395] Step 6:

[0396] The server transmits the generated advice to the terminal.

[0397] Input: The generated advice.

[0398] Data processing: Converting advice content into a format that is easy for users to read.

[0399] Output: Advice displayed on the user's terminal.

[0400] Specific operation: The server sends the generated advice to the terminal, and the terminal displays it on the display screen.

[0401] 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.

[0402] 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.

[0403] 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.

[0404] [Second embodiment]

[0405] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0406] 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.

[0407] 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).

[0408] 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.

[0409] 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.

[0410] 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).

[0411] 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. 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.

[0412] 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.

[0413] 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.

[0414] 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.

[0415] 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.

[0416] 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."

[0417] The present invention relates to a system that provides advice based on input household finance information. Specific embodiments of the present invention will be described below.

[0418] System Overview

[0419] Users input household information into an application on their device (PC or smartphone). Specifically, they input items such as monthly income, rent, food expenses, and transportation expenses. This information is sent to the server via the device.

[0420] The server normalizes the received household information. For example, if there are abnormal values, it detects them and provides feedback. It also imputes missing values.

[0421] The server then analyzes the normalized data, calculating the income and expenditure items to arrive at a balance, and assessing the percentage of each expenditure category.

[0422] The server generates specific advice for the user's household finances based on the analysis results. For example, if food expenses are high, it will suggest "cooking more at home." If the balance is positive, it will provide a specific plan for achieving future savings goals.

[0423] Finally, the server sends the generated advice to the terminal and displays it to the user, who can then take specific actions to improve their household finances.

[0424] Specific examples

[0425] Suppose a user launches the application and enters the following household information:

[0426] Monthly salary: 500,000 yen

[0427] Rent: 100,000 yen

[0428] Food expenses: 50,000 yen

[0429] Transportation fee: 30,000 yen

[0430] Other expenses: 50,000 yen

[0431] The device sends this information to a server, which then receives the data and first normalizes it, taking into account, for example, unusually high food values ​​or unusually low values ​​for other expenditure items.

[0432] Next, the server analyzes the normalized data. Calculating the balance, the server finds that the monthly income is 500,000 yen and the expenditure is 230,000 yen, resulting in a positive balance of 270,000 yen. It also calculates the percentage of each expenditure item and finds that food expenses account for 10%.

[0433] The server generates advice based on the results of this analysis. For example, it could say, "Your food expenses are high. Cook more meals at home to save money," or "You can save 270,000 yen per month. Keep saving and get closer to your future goal."

[0434] Finally, the server sends the generated advice to the terminal, which displays it to the user, who can then take specific actions to improve their household finances.

[0435] This embodiment allows users to efficiently manage their household finances, reduce wasteful spending, and receive support in achieving their savings goals.

[0436] The processing flow will be explained below.

[0437] Step 1:

[0438] The user operates the device and launches the application. The user enters household information such as monthly income, rent, food expenses, and transportation expenses. After confirming that the input data is correct, the user clicks the send button.

[0439] Step 2:

[0440] The terminal sends the household information entered by the user to the server. The sent data includes detailed information on income and various expenses.

[0441] Step 3:

[0442] The server first validates the household information received from the device, checking that all data is entered in the correct format (e.g., numeric format), and returns feedback to the user if any data is invalid.

[0443] Step 4:

[0444] The server normalizes the received data. If the data contains abnormal values ​​(e.g., monthly income is extremely high or low), it detects this and asks the user to re-enter the data. It also imputes missing values.

[0445] Step 5:

[0446] The server analyzes the normalized data, calculating the balance by subtracting all expenses from income, and calculating the percentage of each expense item relative to monthly income.

[0447] Step 6:

[0448] The server generates specific advice based on the analysis results. For example, if the proportion of food expenses is high, it will suggest "cooking more meals at home to save money," and if there is a positive balance, it will display the amount of savings.

[0449] Step 7:

[0450] The server transmits the generated advice to the terminal, which includes a suggestion of what specific action the user should take.

[0451] Step 8:

[0452] The device receives the advice sent from the server and visually displays it to the user, who can then review the advice and take action to improve their household finances.

[0453] Example 1

[0454] 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."

[0455] Conventional household management systems often require users to manually input data, without providing sufficient analysis or advice. This makes it difficult for users to accurately grasp their own household situation and find appropriate improvement measures. Furthermore, the lack of accurate correction for data containing outliers or missing values ​​also creates a problem of low reliability in the analysis results.

[0456] 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.

[0457] In this invention, the server includes input means for inputting household information, normalization means for normalizing the household information received from the input means, analysis means for analyzing the data normalized by the normalization means, advice generation means for generating advice regarding household finances based on the analysis means, and display means for displaying the advice generated by the advice generation means. This allows a user to receive an accurate and reliable household analysis and easily obtain advice on specific improvement measures.

[0458] "Household information" is data relating to the user's income and expenses, specifically information consisting of income, rent, food expenses, transportation expenses, and other expense items.

[0459] "Input means" refers to the interface and device through which users input household information, including applications on smartphones and PCs.

[0460] "Normalization means" refers to functions for normalizing household information received from input means through the detection of outliers and completion of missing values, and includes data processing libraries such as Python's Pandas and NumPy.

[0461] "Analysis tools" refers to functions for calculating income and expenditure balances and evaluating the proportions of each expenditure category based on data normalized by the normalization tools, and includes the Python Scikit-learn library.

[0462] "Advice generation means" refers to a function for generating specific advice for improving household finances based on data obtained from the analysis means, and uses a generative AI model (e.g., GPT-3).

[0463] The "display means" refers to a function for displaying the advice generated by the advice generating means to the user, and includes an application interface on a smartphone or PC.

[0464] "Generative AI model" refers to an artificial intelligence model that generates advice in natural language based on an input prompt, and includes OpenAI's GPT series.

[0465] A "prompt" refers to a specific instruction to be input into the generative AI model, and is text used to generate advice based on the user's household financial information.

[0466] This invention relates to a system that provides advice based on input household information. This system allows users to input household information using a terminal (PC or smartphone), and the information is processed and analyzed by a server, which then generates and provides advice to the user. Specifically, this system is implemented using the following hardware and software.

[0467] Hardware used

[0468] 1. Terminal: A device such as a PC or smartphone

[0469] 2. Server: A remote server for data processing and analysis.

[0470] Software used

[0471] 1. Application: Software that runs on a device and provides an interface for users to enter household information.

[0472] 2. Data processing library: Use Python's Pandas or NumPy to normalize the data

[0473] 3. Data Analysis Library: Analyze data using Python's Scikit-learn

[0474] 4. Generative AI model: Uses OpenAI's GPT series to generate advice from analysis results.

[0475] Overview of program processing

[0476] The user launches the application on their device and enters their monthly income and expenses (rent, food, transportation, and other expenses). This household information is sent from the device to the server in JSON format. The server then normalizes the received household information using Python's Pandas and NumPy. Specifically, it detects outliers and completes missing values.

[0477] The server then analyzes the normalized data using Python's Scikit-learn. This analysis includes calculating the balance of income and expenditures and assessing the percentage of each expenditure category. For example, if income is ¥500,000 and expenditures are ¥230,000, the balance will be ¥270,000, with food spending accounting for 10%.

[0478] Based on the analysis results, the advice generator uses a generative AI model (GPT-3) to generate specific advice. An example of a prompt sentence to be input to the generative AI model is as follows:

[0479] The user's monthly income is 500,000 yen, rent is 100,000 yen, food is 50,000 yen, transportation is 30,000 yen, and other expenses are 50,000 yen. Please provide specific advice for their current financial situation.

[0480] The generated advice is sent from the server to the device and displayed on the device's application interface. Based on this advice, the user can take specific actions to improve their household finances. For example, advice could be, "Cook more meals at home to save money on food," or "You can save 270,000 yen each month. Keep saving and get closer to your future goal."

[0481] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0482] Step 1:

[0483] The user enters household information into an application on the terminal.

[0484] The user launches the application on their device and enters household information such as income, rent, food, transportation, and other expenses. The entered information is properly formatted and verified by the application. The input data format is numeric data for income and each expense item.

[0485] Step 2:

[0486] The terminal transmits the input information to the server.

[0487] The terminal converts the household information entered by the user into JSON format and sends it to the server using the HTTPS protocol. For example, the following data is sent:

[0488] json

[0489] {

[0490] "income": 500000,

[0491] "rent": 100000,

[0492] "food": 50000,

[0493] "transport": 30000,

[0494] "other": 50000

[0495] }

[0496] This data is input to and received by the server.

[0497] Step 3:

[0498] The server normalizes the data it receives.

[0499] The server converts the received JSON data into a data frame using Python's Pandas library and normalizes the data. Specifically, it detects outliers and imputes missing values. For example, if the food expenses figure is abnormally high, it will be determined to be an outlier and generate a notification to the user. Additionally, if there are missing values, they will be imputed using the average or median of past data. The input data is household information, and the output is normalized data.

[0500] Step 4:

[0501] The server analyzes the normalized data.

[0502] The server calculates the income and expenditure balance based on the normalized data. Specifically, it uses Python's Scikit-learn library to calculate the sum of the user's income and expenses and calculate the net balance. It also evaluates the percentage of each expenditure category. For example, if a monthly income is 500,000 yen and expenses are 230,000 yen, the balance will be positive 270,000 yen. The input data is normalized household information, and the output is the income and expenditure balance and the percentage of each expenditure category.

[0503] Step 5:

[0504] The server generates advice based on the analysis results.

[0505] The server generates advice using a generative AI model (e.g., GPT-3) based on the data on income and expenditure balance and expenditure ratio. A prompt sentence is constructed and input into the generative AI model. An example of a prompt sentence is as follows:

[0506] The user's monthly income is 500,000 yen, rent is 100,000 yen, food is 50,000 yen, transportation is 30,000 yen, and other expenses are 50,000 yen. Please provide specific advice for their current financial situation.

[0507] The generative AI model uses this prompt to generate specific advice for improving household finances. The input data is the numerical data from the analysis results and the prompt, and the output is the generated advice.

[0508] Step 6:

[0509] The server transmits the generated advice to the terminal.

[0510] The server converts the generated advice into JSON format and sends it to the device using the HTTPS protocol. For example, the following advice is sent:

[0511] json

[0512] {

[0513] "advice": "Food costs are high. Cook more meals at home and save money. You can save 270,000 yen per month. Keep saving and get closer to your future goal."

[0514] }

[0515] This data is entered into the terminal.

[0516] Step 7:

[0517] The terminal displays the advice to the user.

[0518] The device displays the advice received from the server on the application interface. The user can check the advice and take specific actions based on it. For example, they might cook more meals at home or create a savings plan. The input data is the advice received from the server, and the output is what is displayed to the user.

[0519] (Application example 1)

[0520] 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."

[0521] Conventional household management systems require users to manually input household information, which is time-consuming and can lead to input errors or missing information. Furthermore, the lack of automatic acquisition of expenditure information using electronic payment services makes comprehensive household management difficult.

[0522] 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.

[0523] In this invention, the server includes input means for inputting household information, normalization means for normalizing the household information received from the input means, analysis means for analyzing the data normalized by the normalization means, expenditure data acquisition means for automatically acquiring expenditure information from electronic payment services, advice generation means for generating advice regarding household finances based on the analysis means, and display means for displaying the advice generated by the advice generation means. This makes it possible to automatically acquire, normalize, and analyze expenditure information from electronic payment services that a user uses on a daily basis, and to provide highly accurate advice regarding household finances.

[0524] "Household information" is data regarding a user's income, fixed expenses, variable expenses, and other expenditure items.

[0525] "Input means" refers to an interface that allows a user to input household information into the system, and includes devices such as a keyboard, a touch screen, and voice input.

[0526] "Normalization means" refers to processes and functions for detecting and correcting outliers in the input household information and arranging it into an accurate format.

[0527] "Analysis tools" is a function that calculates and evaluates the ratio of income to each expenditure category and the overall balance of income and expenditure based on normalized data.

[0528] The "advice generation means" is a function for creating specific advice for improving household finances based on the analysis results of the analysis means.

[0529] The "expenditure data acquisition means" is a function for automatically acquiring user expenditure information from the electronic payment service.

[0530] The "display means" is an interface for displaying generated advice and analysis results to the user, and includes a smartphone screen, a computer display, a notification function, etc.

[0531] A system for implementing this invention includes an input means for inputting household information, a normalization means for normalizing the household information received from the input means, an analysis means for performing analysis based on the normalized data, an expenditure data acquisition means for automatically acquiring expenditure information from an electronic payment service, an advice generation means for generating specific advice based on the analysis results, and a display means for displaying the generated advice.

[0532] First, the user inputs household information using a device such as a smartphone or PC. This includes data on income, fixed expenses (e.g., rent), and variable expenses (e.g., food and transportation costs). The device then sends this information to the server.

[0533] The server detects outliers and fills in missing values ​​in the received household information to normalize it. The normalized data is then analyzed by analytical tools to calculate income, expenses, and the percentage of each expense category. For example, if monthly income is 500,000 yen, rent is 100,000 yen, food expenses are 50,000 yen, and transportation expenses are 30,000 yen, total expenses are calculated as 180,000 yen, and the income and expenditure balance is calculated.

[0534] At the same time, the server automatically obtains expenditure information from the API of electronic payment services (e.g., PayPal and Stripe) through expenditure data acquisition means. This eliminates the need for users to manually enter the information, enabling accurate data collection. More detailed expenditure information can also be collected using the smartphone's GPS and camera.

[0535] Once the analysis is complete, the server generates specific advice using an advice generation means. For example, based on the data analysis, the server may generate a suggestion such as "Your food expenses are high. Cook more meals at home to save money," or goal-setting advice such as "You can save 270,000 yen per month. Keep saving and get closer to your future goal."

[0536] The generated advice is sent to the user's terminal via the display means and displayed within the application, allowing the user to check the advice and use it to improve their household finance management.

[0537] Furthermore, the system can leverage generative AI models to provide more specific and personalized advice to users, who can input prompts to receive more detailed suggestions.

[0538] As a concrete example, the following prompt sentences can be input into a generative AI model to elicit optimal advice for the user:

[0539] Based on this month's household financial information, please give some specific advice on how to improve your lifestyle.

[0540] Monthly salary: 500,000 yen

[0541] Rent: 100,000 yen

[0542] Food expenses: 70,000 yen

[0543] Transportation fee: 30,000 yen

[0544] Other expenses: 50,000 yen

[0545] Other income and expenditure data: ...

[0546] Also consider the data you can get from electronic payment service APIs.

[0547] This allows users to get a complete picture of their household finances, cut down on wasteful spending, and create concrete action plans to achieve their savings goals.

[0548] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0549] Step 1:

[0550] Users enter household information using a smartphone or PC. Input items include income, rent, food, transportation, and other expenses. This information is structured in JSON format or similar and sent from the device to the server. The input at this stage is recorded as household information.

[0551] Input: Household information entered by the user (income, rent, food, transportation, and other expenses)

[0552] Output: The entered household information is sent to the server.

[0553] Step 2:

[0554] The server normalizes the received household information. This process involves detecting outliers and filling in missing values. For example, if the food expense value is abnormally high, a notification is sent to the user requesting reconfirmation. If no outliers are detected, missing values ​​are filled in with predicted values ​​or average values.

[0555] Input: Household information received from the device

[0556] Output: Normalized household data

[0557] Step 3:

[0558] The server then analyzes the normalized household data. Using analytical tools, it calculates the balance between income and expenditure, and calculates the percentage of each expenditure category. Based on the analysis results, the expenditure percentage and income / expense balance can be determined.

[0559] Input: Normalized household data

[0560] Output: Income and percentage of each expenditure category, balance

[0561] Step 4:

[0562] The server uses the expenditure data acquisition means to automatically acquire the user's expenditure information from the API of the electronic payment service. The API is called, and the acquired data is aggregated on the server. This information is added to the household information.

[0563] Input: Spending information obtained from the API of the electronic payment service

[0564] Output: Added expenditure information

[0565] Step 5:

[0566] The server then integrates the added spending information with the household data based on analytical methods to form a final data set, which accurately calculates the overall spending amount and the percentage of spending by category.

[0567] Input: Household data, expenditure information from electronic payment services

[0568] Output: Final merged dataset

[0569] Step 6:

[0570] The server uses the advice generation means to generate specific advice from the analysis results based on the final dataset. For example, the advice generated might be, "Your food expenses are high at 70,000 yen, so consider cooking more at home to save money."

[0571] Input: Final merged dataset

[0572] Output: Specific advice

[0573] Step 7:

[0574] Finally, the generated advice is transmitted from the server to the terminal and notified to the user using a display means, so that the user can check the generated advice within the application.

[0575] Input: Generated specific advice

[0576] Output: Advice displayed on the user's terminal

[0577] Through the above process, the user can efficiently manage daily household finance information and improve their household finances based on specific advice.

[0578] 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.

[0579] The present invention combines a system that provides advice based on input household finance information with an emotion engine that recognizes the user's emotions. An embodiment of the present invention will now be described in detail.

[0580] System Overview

[0581] Users input household information into an application on their device (PC or smartphone). Specifically, they input items such as monthly income, rent, food expenses, and transportation expenses. This information is sent to the server via the device.

[0582] The server normalizes the received household information. For example, if there are abnormal values, it detects them and provides feedback. It also imputes missing values.

[0583] The server then analyzes the normalized data, calculating the income and expenditure items to arrive at a balance, and assessing the percentage of each expenditure category.

[0584] The server generates specific advice for the user's household finances based on the analysis results. For example, if food expenses are high, it will suggest "cooking more at home." If the balance is positive, it will also display the amount of savings.

[0585] Furthermore, the present invention recognizes the user's emotions using an emotion engine, which identifies the user's emotions (joy, sadness, anger, stress, etc.) through, for example, the user's facial expressions, tone of voice, and content analysis of input content.

[0586] The server adjusts the content and presentation of advice based on the emotional information provided by the emotion engine. For example, if the user is feeling stressed, the server generates advice that contains more encouraging content.

[0587] Finally, the server sends the generated advice to the terminal and displays it to the user, who can then take specific actions to improve their household finances.

[0588] Specific examples

[0589] The user enters financial information using the application

[0590] Suppose a user launches the application and enters the following household information:

[0591] Monthly salary: 500,000 yen

[0592] Rent: 100,000 yen

[0593] Food expenses: 50,000 yen

[0594] Transportation fee: 30,000 yen

[0595] Other expenses: 50,000 yen

[0596] The device sends this information to a server, which then receives the data and first normalizes it, taking into account, for example, unusually high food values ​​or unusually low values ​​for other expenditure items.

[0597] Server analysis and advice generation

[0598] Next, the server analyzes the normalized data. Calculating the balance, the server finds that the monthly income is 500,000 yen and the expenditure is 230,000 yen, resulting in a positive balance of 270,000 yen. It also calculates the percentage of each expenditure item and finds that food expenses account for 10%.

[0599] The server generates advice based on the results of this analysis. For example, it could say, "Your food expenses are high. Cook more meals at home to save money," or "You can save 270,000 yen per month. Keep saving and get closer to your future goal."

[0600] Utilizing the Emotion Engine

[0601] If the emotion engine recognizes the user's emotions (e.g., the user is feeling stressed), the server adds encouraging advice such as, "This is a difficult situation, but let's work together to improve it little by little."

[0602] Displaying Advice

[0603] Finally, the server sends the generated advice to the terminal, which displays it to the user, who can then review the advice and take specific actions to improve their household finances.

[0604] This embodiment allows users to efficiently manage their household finances, reduce wasteful spending, and receive support in achieving their savings goals. Furthermore, by providing detailed advice based on the user's emotions, more effective household finance management is possible.

[0605] The processing flow will be explained below.

[0606] Step 1:

[0607] The user operates the device and launches the application. The user enters household information such as monthly income, rent, food expenses, and transportation expenses. After confirming that the input data is correct, the user clicks the send button.

[0608] Step 2:

[0609] The terminal sends the household information entered by the user to the server. The sent data includes detailed information on income and various expenses.

[0610] Step 3:

[0611] The server first validates the household information received from the device, checking that all data is entered in the correct format (e.g., numeric format), and returns feedback to the user if any data is invalid.

[0612] Step 4:

[0613] The server normalizes the received data. If the data contains abnormal values ​​(e.g., monthly income is extremely high or low), it detects this and asks the user to re-enter the data. It also imputes missing values.

[0614] Step 5:

[0615] The server analyzes the normalized data, calculating the balance by subtracting all expenses from income, and calculating the percentage of each expense item relative to monthly income.

[0616] Step 6:

[0617] The server generates specific advice based on the analysis results. For example, if the proportion of food expenses is high, it will suggest "cooking more meals at home to save money," and if there is a positive balance, it will display the amount of savings.

[0618] Step 7:

[0619] The user can input additional emotional information by operating the device. For example, the user can convey their emotional state (such as stress or satisfaction) to the emotion engine using text input or voice input.

[0620] Step 8:

[0621] The terminal transmits the user's emotional information to the server, which provides the emotional information together with the user's household financial information.

[0622] Step 9:

[0623] The emotion engine analyzes the user's emotion information and identifies the emotional state. For example, if the user inputs "I'm feeling stressed," the emotion engine will recognize that the user is feeling stressed.

[0624] Step 10:

[0625] The server adjusts the content and presentation of advice based on the emotional information provided by the emotion engine. For example, if the user is feeling stressed, the server will add encouraging advice such as, "This is a difficult situation, but let's work hard together to improve it little by little."

[0626] Step 11:

[0627] The server transmits the generated advice to the terminal, which includes a suggestion of what specific action the user should take.

[0628] Step 12:

[0629] The device receives the advice sent from the server and visually displays it to the user, who can then review the advice and take action to improve their household finances.

[0630] Example 2

[0631] 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."

[0632] Conventional household management systems are unable to consider the user's emotions when analyzing household information and providing advice. As a result, it is difficult to provide detailed advice based on the user's emotions, and appropriate support cannot be provided when the user is stressed or unmotivated.

[0633] 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.

[0634] In this invention, the server includes input means for inputting household information, normalization means for normalizing the information, analysis means for analyzing the information, advice generation means for generating advice, an emotion engine for adjustment, adjustment means for adjusting the content of the advice based on the emotion information, and display means for displaying the information, thereby making it possible to accurately analyze the user's household information and provide appropriate advice taking the user's emotions into consideration.

[0635] "Input means" refers to a device or mechanism that allows a user to input household information.

[0636] The "normalization means" is a device or mechanism that normalizes the household information received from the input means by complementing abnormal values ​​and missing values.

[0637] The "analysis means" is a device or mechanism that calculates the balance of income and expenditure and the proportion of each expenditure item based on the data normalized by the normalization means.

[0638] The "advice generating means" is a device or mechanism that generates specific advice regarding household finances based on the data obtained by the analysis means.

[0639] An "emotion engine" is a device or mechanism that analyzes facial expressions, voice tone, input content, etc. to recognize the user's emotional state.

[0640] The "adjustment means" is a device or mechanism that appropriately adjusts the content and expression of advice based on the emotion information obtained from the emotion engine.

[0641] The "display means" is a device or mechanism that displays the advice generated by the advice generating means and the adjustment means to the user.

[0642] System Overview

[0643] This system allows users to input household finance information and provides advice based on that information. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide advice that corresponds to the user's emotional state.

[0644] Users input household information into the application using devices such as PCs or smartphones. Examples of items include monthly income, rent, food expenses, and transportation expenses. This information is sent to the server via the device.

[0645] Data Receipt and Normalization

[0646] The server normalizes the household information received from the device. For example, if there are abnormal values, it detects and corrects them. It also completes any missing values. This ensures the consistency and reliability of the data.

[0647] Analyzing the data

[0648] The server then analyzes the normalized data, calculating income and each expense item to calculate the balance, and assessing the percentage of each expense category. This process is carried out using specialized analytical software installed on the server.

[0649] Generating Advice

[0650] The server generates specific advice for the user's household finances based on the analysis results. For example, if food expenses are high, it will suggest "cook more at home." If the balance is positive, it will also display the amount of savings. This process uses a generative AI model that is installed on the server.

[0651] Utilizing the Emotion Engine

[0652] Furthermore, the present invention uses an emotion engine to recognize the user's emotions. The emotion engine identifies the user's emotions through, for example, analyzing the user's facial expressions, tone of voice, and input content. The server adjusts the content and presentation of advice based on the emotion information provided by the emotion engine. For example, if the user is feeling stressed, the server generates advice that includes more encouraging content.

[0653] Displaying Advice

[0654] Finally, the server sends the generated advice to the terminal and displays it to the user, who can then take specific actions to improve their household finances.

[0655] Specific examples

[0656] Suppose a user launches the application and enters the following household information:

[0657] Monthly salary: 500,000 yen

[0658] Rent: 100,000 yen

[0659] Food expenses: 50,000 yen

[0660] Transportation fee: 30,000 yen

[0661] Other expenses: 50,000 yen

[0662] The device sends this information to a server, which then receives the data and first normalizes it, taking into account, for example, unusually high food values ​​or unusually low values ​​for other expenditure items.

[0663] Next, the server analyzes the normalized data. Calculating the balance, the server finds that the monthly income is 500,000 yen and the expenditure is 230,000 yen, resulting in a positive balance of 270,000 yen. It also calculates the percentage of each expenditure item and finds that food expenses account for 10%.

[0664] The server generates advice based on the results of this analysis. For example, it could say, "Your food expenses are high. Cook more meals at home to save money," or "You can save 270,000 yen per month. Keep saving and get closer to your future goal."

[0665] If the emotion engine recognizes the user's emotions (e.g., the user is feeling stressed), the server adds encouraging advice such as, "This is a difficult situation, but let's work together to improve it little by little."

[0666] Finally, the server sends the generated advice to the terminal, which displays it to the user, who can then review the advice and take specific actions to improve their household finances.

[0667] Example prompts for generative AI models

[0668] "This is an application that allows you to enter your monthly household finances. Based on the data you enter, it calculates your balance and provides you with the percentage of each expense item. It also recognizes your emotions and generates more personalized advice. Please enter your household finances below:

[0669] Monthly salary: 500,000 yen

[0670] Rent: 100,000 yen

[0671] Food expenses: 50,000 yen

[0672] Transportation fee: 30,000 yen

[0673] Other expenses: 50,000 yen

[0674] Emotional data: users are stressed

[0675] Please generate advice."

[0676]

[0677] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0678] Step 1: User enters household information

[0679] The user launches the application on their PC or smartphone and enters household information such as monthly income, rent, food expenses, and transportation costs. The user fills in this information in the input form and clicks the submit button.

[0680] Input: Household information such as monthly income, rent, food, transportation, and other expenses

[0681] Output: Input household information data

[0682] Step 2: The device sends the data to the server

[0683] The device parses the household information entered by the user into JSON format and sends it to the server via an HTTP POST request.

[0684] Input: Entered household information data

[0685] Output: Household information data sent to the server

[0686] Step 3: The server receives and normalizes the data

[0687] The server parses and normalizes the received household information data. Specifically, it detects outliers and missing values ​​and corrects or imputes them. For example, if monthly income is extremely high or food expenses are abnormally low, it generates a warning and imputes them with reasonable values.

[0688] Input: Household information data sent to the server

[0689] Output: Normalized household information data

[0690] Step 4: The server analyzes the data

[0691] The server analyzes the normalized data and calculates the balance and percentage of each expense item (for example, subtracting each expense from monthly income to get the remaining amount), as well as the percentage of total income each expense item contributes to.

[0692] Input: Normalized household information data

[0693] Output: Analysis result data (income and expenditure balance, expenditure ratio, etc.)

[0694] Step 5: Server generates advice

[0695] The server generates advice for improving household finances based on the analysis results data, using a generative AI model to create specific advice such as "Food costs are high, so cook more at home" or "Continue saving money to work toward your future goals."

[0696] Input: Analysis result data

[0697] Output: Generated advice

[0698] Step 6: The server uses the emotion engine

[0699] The server uses an emotion engine to recognize the user's emotions. It analyzes the text data, facial images, and voice data entered by the user to identify their emotional state. For example, if it determines that the user is feeling stressed, it adjusts the content of the advice.

[0700] Input: User's text data, facial images, voice data, and other emotional data

[0701] Output: User's emotional state data

[0702] Step 7: The server adjusts the advice

[0703] The server adjusts the content and presentation of the generated advice based on the user's emotional state data obtained from the emotion engine. For example, if the user is feeling stressed, the server adds encouraging words such as, "It's a tough situation, but let's try to improve it little by little."

[0704] Input: Generated advice, user emotional state data

[0705] Output: Adjusted advice

[0706] Step 8: The server sends the advice to the device

[0707] The server sends the finalized advice to the device, which converts the advice into JSON format and returns it to the device as an HTTP response.

[0708] Input: Tailored Advice

[0709] Output: Advice sent to terminal

[0710] Step 9: The device displays the advice to the user

[0711] The device parses the advice received from the server and displays it on the user's application screen. The user can then review the advice and take specific actions to improve their household finances.

[0712] Input: Advice sent to terminal

[0713] Output: Advice displayed to the user

[0714] (Application example 2)

[0715] 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."

[0716] In modern society, managing one's finances and receiving appropriate financial advice are becoming increasingly important. However, while many existing financial management systems allow users to input and analyze their financial information, they do not consider the user's emotional state. As a result, if the advice provided is not appropriate for the user's psychological state, it often does not lead to actual behavioral change. Furthermore, effective support is required, especially in emotionally stressful situations. Furthermore, the cumbersome interfaces of existing financial management systems often result in a lack of motivation for users to use them regularly.

[0717] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0718] In this invention, the server includes an input means for inputting household information, a normalization means for normalizing the household information received from the input means, an analysis means for analyzing the data normalized by the normalization means, an advice generation means for generating advice about household finances based on the analysis means, a recognition means for recognizing a user's emotions, and an adjustment means for adjusting the content and presentation of the advice based on the emotional information recognized by the recognition means. This makes it possible to provide advice based on the user's household information tailored to the user's emotional state at any given time. Furthermore, using an interface such as a robot enables natural dialogue with the user, thereby increasing motivation to use the household finance management system.

[0719] "Household information" refers to detailed data on the income and expenditure of individuals and households, such as monthly income, rent, food expenses, and transportation costs.

[0720] "Input means" refers to the device or interface that a user uses to input household information. Examples include smartphones and computer applications.

[0721] "Normalization measures" refer to processes or algorithms used to correct, amend, and transform input household information into a form suitable for analysis.

[0722] "Analytical tools" refers to processes and systems for analyzing normalized household information data and calculating income and expenditure balances and expenditure ratios.

[0723] The "advice generation means" refers to a system for forming specific advice and suggestions regarding the user's household finances based on the data obtained by the analysis means.

[0724] The term "display means" refers to a device or method for visually or audibly presenting the generated advice to the user. Specific examples include a display and a speaker.

[0725] "Recognition means" refers to technology for identifying a user's emotions. Specific examples include voice analysis and facial expression recognition.

[0726] "Adjustment means" refers to a process or algorithm that adjusts the content and expression of generated advice based on the recognized user's emotional information.

[0727] This invention combines a system that provides advice based on input household finance information with an emotion engine that recognizes the user's emotions. Specific embodiments for carrying out this invention will be described below.

[0728] System Overview

[0729] Users input household information into an application on their device (smartphone or computer), such as monthly income, rent, food expenses, and transportation expenses. This household information is then sent to a server via the device.

[0730] The server normalizes the household information it receives, a process that detects outliers and imputes missing values. Once normalization is complete, the server then analyzes the data, which includes calculating income and expenditure balances and assessing the percentages of each expenditure category.

[0731] The server generates specific advice for the user's household finances based on the analysis results. For example, it may suggest cooking more meals at home if food costs are high. If the balance is positive, the amount of savings will be displayed.

[0732] The system also recognizes the user's emotions. The emotion engine identifies emotions such as stress or joy through content analysis of the user's facial expressions, tone of voice, and input. The server adjusts the content and presentation of advice based on this emotional information. For example, if the user is feeling stressed, it generates advice that includes encouraging content.

[0733] Finally, the server sends the generated advice to the terminal and displays it to the user.

[0734] Hardware and software configuration

[0735] Hardware: smartphones, computers, robots (smart home assistants), microphones, cameras (for facial recognition)

[0736] Software: Python, Emotion Recognition API, Financial Management API

[0737] Data processing flow

[0738] 1. Enter user's household information:

[0739] The user enters household information and uses a prompt such as, "My monthly income is $500,000. My rent is $100,000 and my food expenses are $50,000. What is the balance?"

[0740] 2. Emotion recognition:

[0741] The emotion engine (Emotion Recognition API) analyzes the user's voice and facial expressions and generates messages based on their emotions, such as "Please do your best. We understand your situation."

[0742] 3. Data normalization and analysis:

[0743] The Financial Management API normalizes household information and analyzes income and expenditure balances and expenditure ratios.

[0744] 4. Advice Generation:

[0745] Based on the analysis results, specific advice tailored to the user's emotional state is generated.

[0746] 5. Display Advice:

[0747] The generated advice is provided to the user in an audio or visual manner.

[0748] This system allows users to efficiently manage their household finances and receive detailed support tailored to their emotions.

[0749] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0750] Step 1:

[0751] The user enters household information.

[0752] Input: Household information such as monthly income, rent, food expenses, and transportation costs. An example prompt is, "My monthly income is 500,000 yen. My rent is 100,000 yen, and my food expenses are 50,000 yen. Please tell me the balance of income and expenses."

[0753] Specific operation: The user uses a smartphone or computer to enter each item on the household information input screen. The device then sends the entered data to the server.

[0754] Step 2:

[0755] The server normalizes the household information.

[0756] Input: Household information data sent from the device.

[0757] Data processing: Detect outliers and correct or impute missing values ​​as necessary.

[0758] Output: Normalized household information data.

[0759] Specific operation: The server receives household information data and stores the normalized information in an internal database.

[0760] Step 3:

[0761] The server analyzes the normalized data.

[0762] Input: Normalized household information data.

[0763] Data calculation: Calculate income and expenditure balances and evaluate the percentage of each expenditure category.

[0764] Output: Analysis results (e.g. income / expense balance, percentage of each expenditure item).

[0765] Specific operation: The server aggregates the income and expenditure for each item, calculates the income and expenditure balance and expenditure ratio, and saves the results.

[0766] Step 4:

[0767] Recognize user emotions.

[0768] Input: User voice and facial expression data. An example prompt is "I've entered my financial information, what should I do next?"

[0769] Data processing: Using voice analysis and facial expression recognition technology to identify emotional states (e.g., joy, sadness, stress).

[0770] Output: User's emotion information.

[0771] Specific operation: The emotion engine analyzes the user's voice or facial expressions obtained from the camera, generates emotion data, and sends it to the server.

[0772] Step 5:

[0773] The server generates the advice.

[0774] Input: Analysis results and user sentiment information.

[0775] Data calculations: Generate tailored advice based on the user's financial situation and emotions. Example: "Cook more at home and save money on food."

[0776] Output: Specific advice on improving your finances.

[0777] Specific operation: The server uses a generative AI model to generate advice in text format based on analytical data and emotional data.

[0778] Step 6:

[0779] The server transmits the generated advice to the terminal.

[0780] Input: The generated advice.

[0781] Data processing: Converting advice content into a format that is easy for users to read.

[0782] Output: Advice displayed on the user's terminal.

[0783] Specific operation: The server sends the generated advice to the terminal, and the terminal displays it on the display screen.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] [Third embodiment]

[0788] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0789] 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.

[0790] 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).

[0791] 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.

[0792] 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.

[0793] 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).

[0794] 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. 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.

[0795] 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.

[0796] 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.

[0797] 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.

[0798] 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.

[0799] 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."

[0800] The present invention relates to a system that provides advice based on input household finance information. Specific embodiments of the present invention will be described below.

[0801] System Overview

[0802] Users input household information into an application on their device (PC or smartphone). Specifically, they input items such as monthly income, rent, food expenses, and transportation expenses. This information is sent to the server via the device.

[0803] The server normalizes the received household information. For example, if there are abnormal values, it detects them and provides feedback. It also imputes missing values.

[0804] The server then analyzes the normalized data, calculating the income and expenditure items to arrive at a balance, and assessing the percentage of each expenditure category.

[0805] The server generates specific advice for the user's household finances based on the analysis results. For example, if food expenses are high, it will suggest "cooking more at home." If the balance is positive, it will provide a specific plan for achieving future savings goals.

[0806] Finally, the server sends the generated advice to the terminal and displays it to the user, who can then take specific actions to improve their household finances.

[0807] Specific examples

[0808] Suppose a user launches the application and enters the following household information:

[0809] Monthly salary: 500,000 yen

[0810] Rent: 100,000 yen

[0811] Food expenses: 50,000 yen

[0812] Transportation fee: 30,000 yen

[0813] Other expenses: 50,000 yen

[0814] The device sends this information to a server, which then receives the data and first normalizes it, taking into account, for example, unusually high food values ​​or unusually low values ​​for other expenditure items.

[0815] Next, the server analyzes the normalized data. Calculating the balance, the server finds that the monthly income is 500,000 yen and the expenditure is 230,000 yen, resulting in a positive balance of 270,000 yen. It also calculates the percentage of each expenditure item and finds that food expenses account for 10%.

[0816] The server generates advice based on the results of this analysis. For example, it could say, "Your food expenses are high. Cook more meals at home to save money," or "You can save 270,000 yen per month. Keep saving and get closer to your future goal."

[0817] Finally, the server sends the generated advice to the terminal, which displays it to the user, who can then take specific actions to improve their household finances.

[0818] This embodiment allows users to efficiently manage their household finances, reduce wasteful spending, and receive support in achieving their savings goals.

[0819] The processing flow will be explained below.

[0820] Step 1:

[0821] The user operates the device and launches the application. The user enters household information such as monthly income, rent, food expenses, and transportation expenses. After confirming that the input data is correct, the user clicks the send button.

[0822] Step 2:

[0823] The terminal sends the household information entered by the user to the server. The sent data includes detailed information on income and various expenses.

[0824] Step 3:

[0825] The server first validates the household information received from the device, checking that all data is entered in the correct format (e.g., numeric format), and returns feedback to the user if any data is invalid.

[0826] Step 4:

[0827] The server normalizes the received data. If the data contains abnormal values ​​(e.g., monthly income is extremely high or low), it detects this and asks the user to re-enter the data. It also imputes missing values.

[0828] Step 5:

[0829] The server analyzes the normalized data, calculating the balance by subtracting all expenses from income, and calculating the percentage of each expense item relative to monthly income.

[0830] Step 6:

[0831] The server generates specific advice based on the analysis results. For example, if the proportion of food expenses is high, it will suggest "cooking more meals at home to save money," and if there is a positive balance, it will display the amount of savings.

[0832] Step 7:

[0833] The server transmits the generated advice to the terminal, which includes a suggestion of what specific action the user should take.

[0834] Step 8:

[0835] The device receives the advice sent from the server and visually displays it to the user, who can then review the advice and take action to improve their household finances.

[0836] Example 1

[0837] 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."

[0838] Conventional household management systems often require users to manually input data, without providing sufficient analysis or advice. This makes it difficult for users to accurately grasp their own household situation and find appropriate improvement measures. Furthermore, the lack of accurate correction for data containing outliers or missing values ​​also creates a problem of low reliability in the analysis results.

[0839] 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.

[0840] In this invention, the server includes input means for inputting household information, normalization means for normalizing the household information received from the input means, analysis means for analyzing the data normalized by the normalization means, advice generation means for generating advice regarding household finances based on the analysis means, and display means for displaying the advice generated by the advice generation means. This allows a user to receive an accurate and reliable household analysis and easily obtain advice on specific improvement measures.

[0841] "Household information" is data relating to the user's income and expenses, specifically information consisting of income, rent, food expenses, transportation expenses, and other expense items.

[0842] "Input means" refers to the interface and device through which users input household information, including applications on smartphones and PCs.

[0843] "Normalization means" refers to functions for normalizing household information received from input means through the detection of outliers and completion of missing values, and includes data processing libraries such as Python's Pandas and NumPy.

[0844] "Analysis tools" refers to functions for calculating income and expenditure balances and evaluating the proportions of each expenditure category based on data normalized by the normalization tools, and includes the Python Scikit-learn library.

[0845] "Advice generation means" refers to a function for generating specific advice for improving household finances based on data obtained from the analysis means, and uses a generative AI model (e.g., GPT-3).

[0846] The "display means" refers to a function for displaying the advice generated by the advice generating means to the user, and includes an application interface on a smartphone or PC.

[0847] "Generative AI model" refers to an artificial intelligence model that generates advice in natural language based on an input prompt, and includes OpenAI's GPT series.

[0848] A "prompt" refers to a specific instruction to be input into the generative AI model, and is text used to generate advice based on the user's household financial information.

[0849] This invention relates to a system that provides advice based on input household information. This system allows users to input household information using a terminal (PC or smartphone), and the information is processed and analyzed by a server, which then generates and provides advice to the user. Specifically, this system is implemented using the following hardware and software.

[0850] Hardware used

[0851] 1. Terminal: A device such as a PC or smartphone

[0852] 2. Server: A remote server for data processing and analysis.

[0853] Software used

[0854] 1. Application: Software that runs on a device and provides an interface for users to enter household information.

[0855] 2. Data processing library: Use Python's Pandas or NumPy to normalize the data

[0856] 3. Data Analysis Library: Analyze data using Python's Scikit-learn

[0857] 4. Generative AI model: Uses OpenAI's GPT series to generate advice from analysis results.

[0858] Overview of program processing

[0859] The user launches the application on their device and enters their monthly income and expenses (rent, food, transportation, and other expenses). This household information is sent from the device to the server in JSON format. The server then normalizes the received household information using Python's Pandas and NumPy. Specifically, it detects outliers and completes missing values.

[0860] The server then analyzes the normalized data using Python's Scikit-learn. This analysis includes calculating the balance of income and expenditures and assessing the percentage of each expenditure category. For example, if income is ¥500,000 and expenditures are ¥230,000, the balance will be ¥270,000, with food spending accounting for 10%.

[0861] Based on the analysis results, the advice generator uses a generative AI model (GPT-3) to generate specific advice. An example of a prompt sentence to be input to the generative AI model is as follows:

[0862] The user's monthly income is 500,000 yen, rent is 100,000 yen, food is 50,000 yen, transportation is 30,000 yen, and other expenses are 50,000 yen. Please provide specific advice for their current financial situation.

[0863] The generated advice is sent from the server to the device and displayed on the device's application interface. Based on this advice, the user can take specific actions to improve their household finances. For example, advice could be, "Cook more meals at home to save money on food," or "You can save 270,000 yen each month. Keep saving and get closer to your future goal."

[0864] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0865] Step 1:

[0866] The user enters household information into an application on the terminal.

[0867] The user launches the application on their device and enters household information such as income, rent, food, transportation, and other expenses. The entered information is properly formatted and verified by the application. The input data format is numeric data for income and each expense item.

[0868] Step 2:

[0869] The terminal transmits the input information to the server.

[0870] The terminal converts the household information entered by the user into JSON format and sends it to the server using the HTTPS protocol. For example, the following data is sent:

[0871] json

[0872] {

[0873] "income": 500000,

[0874] "rent": 100000,

[0875] "food": 50000,

[0876] "transport": 30000,

[0877] "other": 50000

[0878] }

[0879] This data is input to and received by the server.

[0880] Step 3:

[0881] The server normalizes the data it receives.

[0882] The server converts the received JSON data into a data frame using Python's Pandas library and normalizes the data. Specifically, it detects outliers and imputes missing values. For example, if the food expenses figure is abnormally high, it will be determined to be an outlier and generate a notification to the user. Additionally, if there are missing values, they will be imputed using the average or median of past data. The input data is household information, and the output is normalized data.

[0883] Step 4:

[0884] The server analyzes the normalized data.

[0885] The server calculates the income and expenditure balance based on the normalized data. Specifically, it uses Python's Scikit-learn library to calculate the sum of the user's income and expenses and calculate the net balance. It also evaluates the percentage of each expenditure category. For example, if a monthly income is 500,000 yen and expenses are 230,000 yen, the balance will be positive 270,000 yen. The input data is normalized household information, and the output is the income and expenditure balance and the percentage of each expenditure category.

[0886] Step 5:

[0887] The server generates advice based on the analysis results.

[0888] The server generates advice using a generative AI model (e.g., GPT-3) based on the data on income and expenditure balance and expenditure ratio. A prompt sentence is constructed and input into the generative AI model. An example of a prompt sentence is as follows:

[0889] The user's monthly income is 500,000 yen, rent is 100,000 yen, food is 50,000 yen, transportation is 30,000 yen, and other expenses are 50,000 yen. Please provide specific advice for their current financial situation.

[0890] The generative AI model uses this prompt to generate specific advice for improving household finances. The input data is the numerical data from the analysis results and the prompt, and the output is the generated advice.

[0891] Step 6:

[0892] The server transmits the generated advice to the terminal.

[0893] The server converts the generated advice into JSON format and sends it to the device using the HTTPS protocol. For example, the following advice is sent:

[0894] json

[0895] {

[0896] "advice": "Food costs are high. Cook more meals at home and save money. You can save 270,000 yen per month. Keep saving and get closer to your future goal."

[0897] }

[0898] This data is entered into the terminal.

[0899] Step 7:

[0900] The terminal displays the advice to the user.

[0901] The device displays the advice received from the server on the application interface. The user can check the advice and take specific actions based on it. For example, they might cook more meals at home or create a savings plan. The input data is the advice received from the server, and the output is what is displayed to the user.

[0902] (Application example 1)

[0903] 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."

[0904] Conventional household management systems require users to manually input household information, which is time-consuming and can lead to input errors or missing information. Furthermore, the lack of automatic acquisition of expenditure information using electronic payment services makes comprehensive household management difficult.

[0905] 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.

[0906] In this invention, the server includes input means for inputting household information, normalization means for normalizing the household information received from the input means, analysis means for analyzing the data normalized by the normalization means, expenditure data acquisition means for automatically acquiring expenditure information from electronic payment services, advice generation means for generating advice regarding household finances based on the analysis means, and display means for displaying the advice generated by the advice generation means. This makes it possible to automatically acquire, normalize, and analyze expenditure information from electronic payment services that a user uses on a daily basis, and to provide highly accurate advice regarding household finances.

[0907] "Household information" is data regarding a user's income, fixed expenses, variable expenses, and other expenditure items.

[0908] "Input means" refers to an interface that allows a user to input household information into the system, and includes devices such as a keyboard, a touch screen, and voice input.

[0909] "Normalization means" refers to processes and functions for detecting and correcting outliers in the input household information and arranging it into an accurate format.

[0910] "Analysis tools" is a function that calculates and evaluates the ratio of income to each expenditure category and the overall balance of income and expenditure based on normalized data.

[0911] The "advice generation means" is a function for creating specific advice for improving household finances based on the analysis results of the analysis means.

[0912] The "expenditure data acquisition means" is a function for automatically acquiring user expenditure information from the electronic payment service.

[0913] The "display means" is an interface for displaying generated advice and analysis results to the user, and includes a smartphone screen, a computer display, a notification function, etc.

[0914] A system for implementing this invention includes an input means for inputting household information, a normalization means for normalizing the household information received from the input means, an analysis means for performing analysis based on the normalized data, an expenditure data acquisition means for automatically acquiring expenditure information from an electronic payment service, an advice generation means for generating specific advice based on the analysis results, and a display means for displaying the generated advice.

[0915] First, the user inputs household information using a device such as a smartphone or PC. This includes data on income, fixed expenses (e.g., rent), and variable expenses (e.g., food and transportation costs). The device then sends this information to the server.

[0916] The server detects outliers and fills in missing values ​​in the received household information to normalize it. The normalized data is then analyzed by analytical tools to calculate income, expenses, and the percentage of each expense category. For example, if monthly income is 500,000 yen, rent is 100,000 yen, food expenses are 50,000 yen, and transportation expenses are 30,000 yen, total expenses are calculated as 180,000 yen, and the income and expenditure balance is calculated.

[0917] At the same time, the server automatically obtains expenditure information from the API of electronic payment services (e.g., PayPal and Stripe) through expenditure data acquisition means. This eliminates the need for users to manually enter the information, enabling accurate data collection. More detailed expenditure information can also be collected using the smartphone's GPS and camera.

[0918] Once the analysis is complete, the server generates specific advice using an advice generation means. For example, based on the data analysis, the server may generate a suggestion such as "Your food expenses are high. Cook more meals at home to save money," or goal-setting advice such as "You can save 270,000 yen per month. Keep saving and get closer to your future goal."

[0919] The generated advice is sent to the user's terminal via the display means and displayed within the application, allowing the user to check the advice and use it to improve their household finance management.

[0920] Furthermore, the system can leverage generative AI models to provide more specific and personalized advice to users, who can input prompts to receive more detailed suggestions.

[0921] As a concrete example, the following prompt sentences can be input into a generative AI model to elicit optimal advice for the user:

[0922] Based on this month's household financial information, please give some specific advice on how to improve your lifestyle.

[0923] Monthly salary: 500,000 yen

[0924] Rent: 100,000 yen

[0925] Food expenses: 70,000 yen

[0926] Transportation fee: 30,000 yen

[0927] Other expenses: 50,000 yen

[0928] Other income and expenditure data: ...

[0929] Also consider the data you can get from electronic payment service APIs.

[0930] This allows users to get a complete picture of their household finances, cut down on wasteful spending, and create concrete action plans to achieve their savings goals.

[0931] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0932] Step 1:

[0933] Users enter household information using a smartphone or PC. Input items include income, rent, food, transportation, and other expenses. This information is structured in JSON format or similar and sent from the device to the server. The input at this stage is recorded as household information.

[0934] Input: Household information entered by the user (income, rent, food, transportation, and other expenses)

[0935] Output: The entered household information is sent to the server.

[0936] Step 2:

[0937] The server normalizes the received household information. This process involves detecting outliers and filling in missing values. For example, if the food expense value is abnormally high, a notification is sent to the user requesting reconfirmation. If no outliers are detected, missing values ​​are filled in with predicted values ​​or average values.

[0938] Input: Household information received from the device

[0939] Output: Normalized household data

[0940] Step 3:

[0941] The server then analyzes the normalized household data. Using analytical tools, it calculates the balance between income and expenditure, and calculates the percentage of each expenditure category. Based on the analysis results, the expenditure percentage and income / expense balance can be determined.

[0942] Input: Normalized household data

[0943] Output: Income and percentage of each expenditure category, balance

[0944] Step 4:

[0945] The server uses the expenditure data acquisition means to automatically acquire the user's expenditure information from the API of the electronic payment service. The API is called, and the acquired data is aggregated on the server. This information is added to the household information.

[0946] Input: Spending information obtained from the API of the electronic payment service

[0947] Output: Added expenditure information

[0948] Step 5:

[0949] The server then integrates the added spending information with the household data based on analytical methods to form a final data set, which accurately calculates the overall spending amount and the percentage of spending by category.

[0950] Input: Household data, expenditure information from electronic payment services

[0951] Output: Final merged dataset

[0952] Step 6:

[0953] The server uses the advice generation means to generate specific advice from the analysis results based on the final dataset. For example, the advice generated might be, "Your food expenses are high at 70,000 yen, so consider cooking more at home to save money."

[0954] Input: Final merged dataset

[0955] Output: Specific advice

[0956] Step 7:

[0957] Finally, the generated advice is transmitted from the server to the terminal and notified to the user using a display means, so that the user can check the generated advice within the application.

[0958] Input: Generated specific advice

[0959] Output: Advice displayed on the user's terminal

[0960] Through the above process, the user can efficiently manage daily household finance information and improve their household finances based on specific advice.

[0961] 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.

[0962] The present invention combines a system that provides advice based on input household finance information with an emotion engine that recognizes the user's emotions. An embodiment of the present invention will now be described in detail.

[0963] System Overview

[0964] Users input household information into an application on their device (PC or smartphone). Specifically, they input items such as monthly income, rent, food expenses, and transportation expenses. This information is sent to the server via the device.

[0965] The server normalizes the received household information. For example, if there are abnormal values, it detects them and provides feedback. It also imputes missing values.

[0966] The server then analyzes the normalized data, calculating the income and expenditure items to arrive at a balance, and assessing the percentage of each expenditure category.

[0967] The server generates specific advice for the user's household finances based on the analysis results. For example, if food expenses are high, it will suggest "cooking more at home." If the balance is positive, it will also display the amount of savings.

[0968] Furthermore, the present invention recognizes the user's emotions using an emotion engine, which identifies the user's emotions (joy, sadness, anger, stress, etc.) through, for example, the user's facial expressions, tone of voice, and content analysis of input content.

[0969] The server adjusts the content and presentation of advice based on the emotional information provided by the emotion engine. For example, if the user is feeling stressed, the server generates advice that contains more encouraging content.

[0970] Finally, the server sends the generated advice to the terminal and displays it to the user, who can then take specific actions to improve their household finances.

[0971] Specific examples

[0972] The user enters financial information using the application

[0973] Suppose a user launches the application and enters the following household information:

[0974] Monthly salary: 500,000 yen

[0975] Rent: 100,000 yen

[0976] Food expenses: 50,000 yen

[0977] Transportation fee: 30,000 yen

[0978] Other expenses: 50,000 yen

[0979] The device sends this information to a server, which then receives the data and first normalizes it, taking into account, for example, unusually high food values ​​or unusually low values ​​for other expenditure items.

[0980] Server analysis and advice generation

[0981] Next, the server analyzes the normalized data. Calculating the balance, the server finds that the monthly income is 500,000 yen and the expenditure is 230,000 yen, resulting in a positive balance of 270,000 yen. It also calculates the percentage of each expenditure item and finds that food expenses account for 10%.

[0982] The server generates advice based on the results of this analysis. For example, it could say, "Your food expenses are high. Cook more meals at home to save money," or "You can save 270,000 yen per month. Keep saving and get closer to your future goal."

[0983] Utilizing the Emotion Engine

[0984] If the emotion engine recognizes the user's emotions (e.g., the user is feeling stressed), the server adds encouraging advice such as, "This is a difficult situation, but let's work together to improve it little by little."

[0985] Displaying Advice

[0986] Finally, the server sends the generated advice to the terminal, which displays it to the user, who can then review the advice and take specific actions to improve their household finances.

[0987] This embodiment allows users to efficiently manage their household finances, reduce wasteful spending, and receive support in achieving their savings goals. Furthermore, by providing detailed advice based on the user's emotions, more effective household finance management is possible.

[0988] The processing flow will be explained below.

[0989] Step 1:

[0990] The user operates the device and launches the application. The user enters household information such as monthly income, rent, food expenses, and transportation expenses. After confirming that the input data is correct, the user clicks the send button.

[0991] Step 2:

[0992] The terminal sends the household information entered by the user to the server. The sent data includes detailed information on income and various expenses.

[0993] Step 3:

[0994] The server first validates the household information received from the device, checking that all data is entered in the correct format (e.g., numeric format), and returns feedback to the user if any data is invalid.

[0995] Step 4:

[0996] The server normalizes the received data. If the data contains abnormal values ​​(e.g., monthly income is extremely high or low), it detects this and asks the user to re-enter the data. It also imputes missing values.

[0997] Step 5:

[0998] The server analyzes the normalized data, calculating the balance by subtracting all expenses from income, and calculating the percentage of each expense item relative to monthly income.

[0999] Step 6:

[1000] The server generates specific advice based on the analysis results. For example, if the proportion of food expenses is high, it will suggest "cooking more meals at home to save money," and if there is a positive balance, it will display the amount of savings.

[1001] Step 7:

[1002] The user can input additional emotional information by operating the device. For example, the user can convey their emotional state (such as stress or satisfaction) to the emotion engine using text input or voice input.

[1003] Step 8:

[1004] The terminal transmits the user's emotional information to the server, which provides the emotional information together with the user's household financial information.

[1005] Step 9:

[1006] The emotion engine analyzes the user's emotion information and identifies the emotional state. For example, if the user inputs "I'm feeling stressed," the emotion engine will recognize that the user is feeling stressed.

[1007] Step 10:

[1008] The server adjusts the content and presentation of advice based on the emotional information provided by the emotion engine. For example, if the user is feeling stressed, the server will add encouraging advice such as, "This is a difficult situation, but let's work hard together to improve it little by little."

[1009] Step 11:

[1010] The server transmits the generated advice to the terminal, which includes a suggestion of what specific action the user should take.

[1011] Step 12:

[1012] The device receives the advice sent from the server and visually displays it to the user, who can then review the advice and take action to improve their household finances.

[1013] Example 2

[1014] 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."

[1015] Conventional household management systems are unable to consider the user's emotions when analyzing household information and providing advice. As a result, it is difficult to provide detailed advice based on the user's emotions, and appropriate support cannot be provided when the user is stressed or unmotivated.

[1016] 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.

[1017] In this invention, the server includes input means for inputting household information, normalization means for normalizing the information, analysis means for analyzing the information, advice generation means for generating advice, an emotion engine for adjustment, adjustment means for adjusting the content of the advice based on the emotion information, and display means for displaying the information, thereby making it possible to accurately analyze the user's household information and provide appropriate advice taking the user's emotions into consideration.

[1018] "Input means" refers to a device or mechanism that allows a user to input household information.

[1019] The "normalization means" is a device or mechanism that normalizes the household information received from the input means by complementing abnormal values ​​and missing values.

[1020] The "analysis means" is a device or mechanism that calculates the balance of income and expenditure and the proportion of each expenditure item based on the data normalized by the normalization means.

[1021] The "advice generating means" is a device or mechanism that generates specific advice regarding household finances based on the data obtained by the analysis means.

[1022] An "emotion engine" is a device or mechanism that analyzes facial expressions, voice tone, input content, etc. to recognize the user's emotional state.

[1023] The "adjustment means" is a device or mechanism that appropriately adjusts the content and expression of advice based on the emotion information obtained from the emotion engine.

[1024] The "display means" is a device or mechanism that displays the advice generated by the advice generating means and the adjustment means to the user.

[1025] System Overview

[1026] This system allows users to input household finance information and provides advice based on that information. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide advice that corresponds to the user's emotional state.

[1027] Users input household information into the application using devices such as PCs or smartphones. Examples of items include monthly income, rent, food expenses, and transportation expenses. This information is sent to the server via the device.

[1028] Data Receipt and Normalization

[1029] The server normalizes the household information received from the device. For example, if there are abnormal values, it detects and corrects them. It also completes any missing values. This ensures the consistency and reliability of the data.

[1030] Analyzing the data

[1031] The server then analyzes the normalized data, calculating income and each expense item to calculate the balance, and assessing the percentage of each expense category. This process is carried out using specialized analytical software installed on the server.

[1032] Generating Advice

[1033] The server generates specific advice for the user's household finances based on the analysis results. For example, if food expenses are high, it will suggest "cook more at home." If the balance is positive, it will also display the amount of savings. This process uses a generative AI model that is installed on the server.

[1034] Utilizing the Emotion Engine

[1035] Furthermore, the present invention uses an emotion engine to recognize the user's emotions. The emotion engine identifies the user's emotions through, for example, analyzing the user's facial expressions, tone of voice, and input content. The server adjusts the content and presentation of advice based on the emotion information provided by the emotion engine. For example, if the user is feeling stressed, the server generates advice that includes more encouraging content.

[1036] Displaying Advice

[1037] Finally, the server sends the generated advice to the terminal and displays it to the user, who can then take specific actions to improve their household finances.

[1038] Specific examples

[1039] Suppose a user launches the application and enters the following household information:

[1040] Monthly salary: 500,000 yen

[1041] Rent: 100,000 yen

[1042] Food expenses: 50,000 yen

[1043] Transportation fee: 30,000 yen

[1044] Other expenses: 50,000 yen

[1045] The device sends this information to a server, which then receives the data and first normalizes it, taking into account, for example, unusually high food values ​​or unusually low values ​​for other expenditure items.

[1046] Next, the server analyzes the normalized data. Calculating the balance, the server finds that the monthly income is 500,000 yen and the expenditure is 230,000 yen, resulting in a positive balance of 270,000 yen. It also calculates the percentage of each expenditure item and finds that food expenses account for 10%.

[1047] The server generates advice based on the results of this analysis. For example, it could say, "Your food expenses are high. Cook more meals at home to save money," or "You can save 270,000 yen per month. Keep saving and get closer to your future goal."

[1048] If the emotion engine recognizes the user's emotions (e.g., the user is feeling stressed), the server adds encouraging advice such as, "This is a difficult situation, but let's work together to improve it little by little."

[1049] Finally, the server sends the generated advice to the terminal, which displays it to the user, who can then review the advice and take specific actions to improve their household finances.

[1050] Example prompts for generative AI models

[1051] "This is an application that allows you to enter your monthly household finances. Based on the data you enter, it calculates your balance and provides you with the percentage of each expense item. It also recognizes your emotions and generates more personalized advice. Please enter your household finances below:

[1052] Monthly salary: 500,000 yen

[1053] Rent: 100,000 yen

[1054] Food expenses: 50,000 yen

[1055] Transportation fee: 30,000 yen

[1056] Other expenses: 50,000 yen

[1057] Emotional data: users are stressed

[1058] Please generate advice."

[1059]

[1060] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1061] Step 1: User enters household information

[1062] The user launches the application on their PC or smartphone and enters household information such as monthly income, rent, food expenses, and transportation costs. The user fills in this information in the input form and clicks the submit button.

[1063] Input: Household information such as monthly income, rent, food, transportation, and other expenses

[1064] Output: Input household information data

[1065] Step 2: The device sends the data to the server

[1066] The device parses the household information entered by the user into JSON format and sends it to the server via an HTTP POST request.

[1067] Input: Entered household information data

[1068] Output: Household information data sent to the server

[1069] Step 3: The server receives and normalizes the data

[1070] The server parses and normalizes the received household information data. Specifically, it detects outliers and missing values ​​and corrects or imputes them. For example, if monthly income is extremely high or food expenses are abnormally low, it generates a warning and imputes them with reasonable values.

[1071] Input: Household information data sent to the server

[1072] Output: Normalized household information data

[1073] Step 4: The server analyzes the data

[1074] The server analyzes the normalized data and calculates the balance and percentage of each expense item (for example, subtracting each expense from monthly income to get the remaining amount), as well as the percentage of total income each expense item contributes to.

[1075] Input: Normalized household information data

[1076] Output: Analysis result data (income and expenditure balance, expenditure ratio, etc.)

[1077] Step 5: Server generates advice

[1078] The server generates advice for improving household finances based on the analysis results data, using a generative AI model to create specific advice such as "Food costs are high, so cook more at home" or "Continue saving money to work toward your future goals."

[1079] Input: Analysis result data

[1080] Output: Generated advice

[1081] Step 6: The server uses the emotion engine

[1082] The server uses an emotion engine to recognize the user's emotions. It analyzes the text data, facial images, and voice data entered by the user to identify their emotional state. For example, if it determines that the user is feeling stressed, it adjusts the content of the advice.

[1083] Input: User's text data, facial images, voice data, and other emotional data

[1084] Output: User's emotional state data

[1085] Step 7: The server adjusts the advice

[1086] The server adjusts the content and presentation of the generated advice based on the user's emotional state data obtained from the emotion engine. For example, if the user is feeling stressed, the server adds encouraging words such as, "It's a tough situation, but let's try to improve it little by little."

[1087] Input: Generated advice, user emotional state data

[1088] Output: Adjusted advice

[1089] Step 8: The server sends the advice to the device

[1090] The server sends the finalized advice to the device, which converts the advice into JSON format and returns it to the device as an HTTP response.

[1091] Input: Tailored Advice

[1092] Output: Advice sent to terminal

[1093] Step 9: The device displays the advice to the user

[1094] The device parses the advice received from the server and displays it on the user's application screen. The user can then review the advice and take specific actions to improve their household finances.

[1095] Input: Advice sent to terminal

[1096] Output: Advice displayed to the user

[1097] (Application example 2)

[1098] 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."

[1099] In modern society, managing one's finances and receiving appropriate financial advice are becoming increasingly important. However, while many existing financial management systems allow users to input and analyze their financial information, they do not consider the user's emotional state. As a result, if the advice provided is not appropriate for the user's psychological state, it often does not lead to actual behavioral change. Furthermore, effective support is required, especially in emotionally stressful situations. Furthermore, the cumbersome interfaces of existing financial management systems often result in a lack of motivation for users to use them regularly.

[1100] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1101] In this invention, the server includes an input means for inputting household information, a normalization means for normalizing the household information received from the input means, an analysis means for analyzing the data normalized by the normalization means, an advice generation means for generating advice about household finances based on the analysis means, a recognition means for recognizing a user's emotions, and an adjustment means for adjusting the content and presentation of the advice based on the emotional information recognized by the recognition means. This makes it possible to provide advice based on the user's household information tailored to the user's emotional state at any given time. Furthermore, using an interface such as a robot enables natural dialogue with the user, thereby increasing motivation to use the household finance management system.

[1102] "Household information" refers to detailed data on the income and expenditure of individuals and households, such as monthly income, rent, food expenses, and transportation costs.

[1103] "Input means" refers to the device or interface that a user uses to input household information. Examples include smartphones and computer applications.

[1104] "Normalization measures" refer to processes or algorithms used to correct, amend, and transform input household information into a form suitable for analysis.

[1105] "Analytical tools" refers to processes and systems for analyzing normalized household information data and calculating income and expenditure balances and expenditure ratios.

[1106] The "advice generation means" refers to a system for forming specific advice and suggestions regarding the user's household finances based on the data obtained by the analysis means.

[1107] The term "display means" refers to a device or method for visually or audibly presenting the generated advice to the user. Specific examples include a display and a speaker.

[1108] "Recognition means" refers to technology for identifying a user's emotions. Specific examples include voice analysis and facial expression recognition.

[1109] "Adjustment means" refers to a process or algorithm that adjusts the content and expression of generated advice based on the recognized user's emotional information.

[1110] This invention combines a system that provides advice based on input household finance information with an emotion engine that recognizes the user's emotions. Specific embodiments for carrying out this invention will be described below.

[1111] System Overview

[1112] Users input household information into an application on their device (smartphone or computer), such as monthly income, rent, food expenses, and transportation expenses. This household information is then sent to a server via the device.

[1113] The server normalizes the household information it receives, a process that detects outliers and imputes missing values. Once normalization is complete, the server then analyzes the data, which includes calculating income and expenditure balances and assessing the percentages of each expenditure category.

[1114] The server generates specific advice for the user's household finances based on the analysis results. For example, it may suggest cooking more meals at home if food costs are high. If the balance is positive, the amount of savings will be displayed.

[1115] The system also recognizes the user's emotions. The emotion engine identifies emotions such as stress or joy through content analysis of the user's facial expressions, tone of voice, and input. The server adjusts the content and presentation of advice based on this emotional information. For example, if the user is feeling stressed, it generates advice that includes encouraging content.

[1116] Finally, the server sends the generated advice to the terminal and displays it to the user.

[1117] Hardware and software configuration

[1118] Hardware: smartphones, computers, robots (smart home assistants), microphones, cameras (for facial recognition)

[1119] Software: Python, Emotion Recognition API, Financial Management API

[1120] Data processing flow

[1121] 1. Enter user's household information:

[1122] The user enters household information and uses a prompt such as, "My monthly income is $500,000. My rent is $100,000 and my food expenses are $50,000. What is the balance?"

[1123] 2. Emotion recognition:

[1124] The emotion engine (Emotion Recognition API) analyzes the user's voice and facial expressions and generates messages based on their emotions, such as "Please do your best. We understand your situation."

[1125] 3. Data normalization and analysis:

[1126] The Financial Management API normalizes household information and analyzes income and expenditure balances and expenditure ratios.

[1127] 4. Advice Generation:

[1128] Based on the analysis results, specific advice tailored to the user's emotional state is generated.

[1129] 5. Display Advice:

[1130] The generated advice is provided to the user in an audio or visual manner.

[1131] This system allows users to efficiently manage their household finances and receive detailed support tailored to their emotions.

[1132] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1133] Step 1:

[1134] The user enters household information.

[1135] Input: Household information such as monthly income, rent, food expenses, and transportation costs. An example prompt is, "My monthly income is 500,000 yen. My rent is 100,000 yen, and my food expenses are 50,000 yen. Please tell me the balance of income and expenses."

[1136] Specific operation: The user uses a smartphone or computer to enter each item on the household information input screen. The device then sends the entered data to the server.

[1137] Step 2:

[1138] The server normalizes the household information.

[1139] Input: Household information data sent from the device.

[1140] Data processing: Detect outliers and correct or impute missing values ​​as necessary.

[1141] Output: Normalized household information data.

[1142] Specific operation: The server receives household information data and stores the normalized information in an internal database.

[1143] Step 3:

[1144] The server analyzes the normalized data.

[1145] Input: Normalized household information data.

[1146] Data calculation: Calculate income and expenditure balances and evaluate the percentage of each expenditure category.

[1147] Output: Analysis results (e.g. income / expense balance, percentage of each expenditure item).

[1148] Specific operation: The server aggregates the income and expenditure for each item, calculates the income and expenditure balance and expenditure ratio, and saves the results.

[1149] Step 4:

[1150] Recognize user emotions.

[1151] Input: User voice and facial expression data. An example prompt is "I've entered my financial information, what should I do next?"

[1152] Data processing: Using voice analysis and facial expression recognition technology to identify emotional states (e.g., joy, sadness, stress).

[1153] Output: User's emotion information.

[1154] Specific operation: The emotion engine analyzes the user's voice or facial expressions obtained from the camera, generates emotion data, and sends it to the server.

[1155] Step 5:

[1156] The server generates the advice.

[1157] Input: Analysis results and user sentiment information.

[1158] Data calculations: Generate tailored advice based on the user's financial situation and emotions. Example: "Cook more at home and save money on food."

[1159] Output: Specific advice on improving your finances.

[1160] Specific operation: The server uses a generative AI model to generate advice in text format based on analytical data and emotional data.

[1161] Step 6:

[1162] The server transmits the generated advice to the terminal.

[1163] Input: The generated advice.

[1164] Data processing: Converting advice content into a format that is easy for users to read.

[1165] Output: Advice displayed on the user's terminal.

[1166] Specific operation: The server sends the generated advice to the terminal, and the terminal displays it on the display screen.

[1167] 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.

[1168] 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.

[1169] 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.

[1170] [Fourth embodiment]

[1171] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1172] 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.

[1173] 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).

[1174] 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.

[1175] 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.

[1176] 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).

[1177] 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. 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.

[1178] 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.

[1179] 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.

[1180] 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.

[1181] 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.

[1182] 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.

[1183] 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."

[1184] The present invention relates to a system that provides advice based on input household finance information. Specific embodiments of the present invention will be described below.

[1185] System Overview

[1186] Users input household information into an application on their device (PC or smartphone). Specifically, they input items such as monthly income, rent, food expenses, and transportation expenses. This information is sent to the server via the device.

[1187] The server normalizes the received household information. For example, if there are abnormal values, it detects them and provides feedback. It also imputes missing values.

[1188] The server then analyzes the normalized data, calculating the income and expenditure items to arrive at a balance, and assessing the percentage of each expenditure category.

[1189] The server generates specific advice for the user's household finances based on the analysis results. For example, if food expenses are high, it will suggest "cooking more at home." If the balance is positive, it will provide a specific plan for achieving future savings goals.

[1190] Finally, the server sends the generated advice to the terminal and displays it to the user, who can then take specific actions to improve their household finances.

[1191] Specific examples

[1192] Suppose a user launches the application and enters the following household information:

[1193] Monthly salary: 500,000 yen

[1194] Rent: 100,000 yen

[1195] Food expenses: 50,000 yen

[1196] Transportation fee: 30,000 yen

[1197] Other expenses: 50,000 yen

[1198] The device sends this information to a server, which then receives the data and first normalizes it, taking into account, for example, unusually high food values ​​or unusually low values ​​for other expenditure items.

[1199] Next, the server analyzes the normalized data. Calculating the balance, the server finds that the monthly income is 500,000 yen and the expenditure is 230,000 yen, resulting in a positive balance of 270,000 yen. It also calculates the percentage of each expenditure item and finds that food expenses account for 10%.

[1200] The server generates advice based on the results of this analysis. For example, it could say, "Your food expenses are high. Cook more meals at home to save money," or "You can save 270,000 yen each month. Keep saving and get closer to your future goal."

[1201] Finally, the server sends the generated advice to the terminal, which displays it to the user, who can then take specific actions to improve their household finances.

[1202] This embodiment allows users to efficiently manage their household finances, reduce wasteful spending, and receive support in achieving their savings goals.

[1203] The processing flow will be explained below.

[1204] Step 1:

[1205] The user operates the device and launches the application. The user enters household information such as monthly income, rent, food expenses, and transportation expenses. After confirming that the input data is correct, the user clicks the send button.

[1206] Step 2:

[1207] The terminal sends the household information entered by the user to the server. The sent data includes detailed information on income and various expenses.

[1208] Step 3:

[1209] The server first validates the household information received from the device, checking that all data is entered in the correct format (e.g., numeric format), and returns feedback to the user if any data is invalid.

[1210] Step 4:

[1211] The server normalizes the received data. If the data contains abnormal values ​​(e.g., monthly income is extremely high or low), it detects this and asks the user to re-enter the data. It also imputes missing values.

[1212] Step 5:

[1213] The server analyzes the normalized data, calculating the balance by subtracting all expenses from income, and calculating the percentage of each expense item relative to monthly income.

[1214] Step 6:

[1215] The server generates specific advice based on the analysis results. For example, if the proportion of food expenses is high, it will suggest "cooking more meals at home to save money," and if there is a positive balance, it will display the amount of savings.

[1216] Step 7:

[1217] The server transmits the generated advice to the terminal, which includes a suggestion of what specific action the user should take.

[1218] Step 8:

[1219] The device receives the advice sent from the server and visually displays it to the user, who can then review the advice and take action to improve their household finances.

[1220] Example 1

[1221] 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."

[1222] Conventional household management systems often require users to manually input data, without providing sufficient analysis or advice. This makes it difficult for users to accurately grasp their own household situation and find appropriate improvement measures. Furthermore, the lack of accurate correction for data containing outliers or missing values ​​also creates a problem of low reliability in the analysis results.

[1223] 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.

[1224] In this invention, the server includes input means for inputting household information, normalization means for normalizing the household information received from the input means, analysis means for analyzing the data normalized by the normalization means, advice generation means for generating advice regarding household finances based on the analysis means, and display means for displaying the advice generated by the advice generation means. This allows a user to receive an accurate and reliable household analysis and easily obtain advice on specific improvement measures.

[1225] "Household information" is data relating to the user's income and expenses, specifically information consisting of income, rent, food expenses, transportation expenses, and other expense items.

[1226] "Input means" refers to the interface and device through which users input household information, including applications on smartphones and PCs.

[1227] "Normalization means" refers to functions for normalizing household information received from input means through the detection of outliers and completion of missing values, and includes data processing libraries such as Python's Pandas and NumPy.

[1228] "Analysis tools" refers to functions for calculating income and expenditure balances and evaluating the proportions of each expenditure category based on data normalized by the normalization tools, and includes the Python Scikit-learn library.

[1229] "Advice generation means" refers to a function for generating specific advice for improving household finances based on data obtained from the analysis means, and uses a generative AI model (e.g., GPT-3).

[1230] The "display means" refers to a function for displaying the advice generated by the advice generating means to the user, and includes an application interface on a smartphone or PC.

[1231] "Generative AI models" refer to artificial intelligence models that generate advice in natural language based on input prompts, and include OpenAI's GPT series.

[1232] A "prompt" refers to a specific instruction to be input into the generative AI model, and is text used to generate advice based on the user's household financial information.

[1233] This invention relates to a system that provides advice based on input household information. This system allows users to input household information using a terminal (PC or smartphone), and the information is processed and analyzed by a server, which then generates and provides advice to the user. Specifically, this system is implemented using the following hardware and software.

[1234] Hardware used

[1235] 1. Terminal: A device such as a PC or smartphone

[1236] 2. Server: A remote server for data processing and analysis.

[1237] Software used

[1238] 1. Application: Software that runs on a device and provides an interface for users to enter household information.

[1239] 2. Data processing library: Use Python's Pandas or NumPy to normalize the data

[1240] 3. Data Analysis Library: Analyze data using Python's Scikit-learn

[1241] 4. Generative AI model: Uses OpenAI's GPT series to generate advice from analysis results.

[1242] Overview of program processing

[1243] The user launches the application on their device and enters their monthly income and expenses (rent, food, transportation, and other expenses). This household information is sent from the device to the server in JSON format. The server then normalizes the received household information using Python's Pandas and NumPy. Specifically, it detects outliers and completes missing values.

[1244] The server then analyzes the normalized data using Python's Scikit-learn. This analysis includes calculating the balance of income and expenditures and assessing the percentage of each expenditure category. For example, if income is ¥500,000 and expenditures are ¥230,000, the balance will be ¥270,000, with food spending accounting for 10%.

[1245] Based on the analysis results, the advice generator uses a generative AI model (GPT-3) to generate specific advice. An example of a prompt sentence to be input to the generative AI model is as follows:

[1246] The user's monthly income is 500,000 yen, rent is 100,000 yen, food is 50,000 yen, transportation is 30,000 yen, and other expenses are 50,000 yen. Please provide specific advice for their current financial situation.

[1247] The generated advice is sent from the server to the device and displayed on the device's application interface. Based on this advice, the user can take specific actions to improve their household finances. For example, advice could be, "Cook more meals at home to save money on food," or "You can save 270,000 yen each month. Keep saving and get closer to your future goal."

[1248] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1249] Step 1:

[1250] The user enters household information into an application on the terminal.

[1251] The user launches the application on their device and enters household information such as income, rent, food, transportation, and other expenses. The entered information is properly formatted and verified by the application. The input data is in the form of numeric data for income and each expense item.

[1252] Step 2:

[1253] The terminal transmits the input information to the server.

[1254] The terminal converts the household information entered by the user into JSON format and sends it to the server using the HTTPS protocol. For example, the following data is sent:

[1255] json

[1256] {

[1257] "income": 500000,

[1258] "rent": 100000,

[1259] "food": 50000,

[1260] "transport": 30000,

[1261] "other": 50000

[1262] }

[1263] This data is input to and received by the server.

[1264] Step 3:

[1265] The server normalizes the data it receives.

[1266] The server converts the received JSON data into a data frame using Python's Pandas library and normalizes the data. Specifically, it detects outliers and imputes missing values. For example, if the food expenses figure is abnormally high, it will be determined to be an outlier and generate a notification to the user. Additionally, if there are missing values, they will be imputed using the average or median of past data. The input data is household information, and the output is normalized data.

[1267] Step 4:

[1268] The server analyzes the normalized data.

[1269] The server calculates the income and expenditure balance based on the normalized data. Specifically, it uses Python's Scikit-learn library to calculate the sum of the user's income and expenses and calculate the net balance. It also evaluates the percentage of each expenditure category. For example, if a monthly income is 500,000 yen and expenses are 230,000 yen, the balance will be positive 270,000 yen. The input data is normalized household information, and the output is the income and expenditure balance and the percentage of each expenditure category.

[1270] Step 5:

[1271] The server generates advice based on the analysis results.

[1272] The server generates advice using a generative AI model (e.g., GPT-3) based on the data on income and expenditure balance and expenditure ratio. A prompt sentence is constructed and input into the generative AI model. An example of a prompt sentence is as follows:

[1273] The user's monthly income is 500,000 yen, rent is 100,000 yen, food is 50,000 yen, transportation is 30,000 yen, and other expenses are 50,000 yen. Please provide specific advice for their current financial situation.

[1274] The generative AI model uses this prompt to generate specific advice for improving household finances. The input data is the numerical data from the analysis results and the prompt, and the output is the generated advice.

[1275] Step 6:

[1276] The server transmits the generated advice to the terminal.

[1277] The server converts the generated advice into JSON format and sends it to the device using the HTTPS protocol. For example, the following advice is sent:

[1278] json

[1279] {

[1280] "advice": "Food costs are high. Cook more meals at home and save money. You can save 270,000 yen per month. Keep saving and get closer to your future goal."

[1281] }

[1282] This data is entered into the terminal.

[1283] Step 7:

[1284] The terminal displays the advice to the user.

[1285] The device displays the advice received from the server on the application interface. The user can check the advice and take specific actions based on it. For example, they might cook more meals at home or create a savings plan. The input data is the advice received from the server, and the output is what is displayed to the user.

[1286] (Application example 1)

[1287] 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."

[1288] Conventional household management systems require users to manually input household information, which is time-consuming and can lead to input errors or missing information. Furthermore, the lack of automatic acquisition of expenditure information using electronic payment services makes comprehensive household management difficult.

[1289] 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.

[1290] In this invention, the server includes input means for inputting household information, normalization means for normalizing the household information received from the input means, analysis means for analyzing the data normalized by the normalization means, expenditure data acquisition means for automatically acquiring expenditure information from electronic payment services, advice generation means for generating advice regarding household finances based on the analysis means, and display means for displaying the advice generated by the advice generation means. This makes it possible to automatically acquire, normalize, and analyze expenditure information from electronic payment services that a user uses on a daily basis, and to provide highly accurate advice regarding household finances.

[1291] "Household information" is data regarding a user's income, fixed expenses, variable expenses, and other expenditure items.

[1292] "Input means" refers to an interface that allows a user to input household information into the system, and includes devices such as a keyboard, a touch screen, and voice input.

[1293] "Normalization means" refers to the processes and functions for detecting and correcting outliers in the input household information and arranging it into an accurate format.

[1294] "Analysis tools" is a function that calculates and evaluates the ratio of income to each expenditure category and the overall balance of income and expenditure based on normalized data.

[1295] The "advice generation means" is a function for creating specific advice for improving household finances based on the analysis results of the analysis means.

[1296] The "expenditure data acquisition means" is a function for automatically acquiring user expenditure information from the electronic payment service.

[1297] The "display means" refers to an interface for displaying generated advice and analysis results to the user, and includes a smartphone screen, a computer display, a notification function, etc.

[1298] A system for implementing this invention includes an input means for inputting household information, a normalization means for normalizing the household information received from the input means, an analysis means for performing analysis based on the normalized data, an expenditure data acquisition means for automatically acquiring expenditure information from an electronic payment service, an advice generation means for generating specific advice based on the analysis results, and a display means for displaying the generated advice.

[1299] First, the user inputs household information using a device such as a smartphone or PC. This includes data on income, fixed expenses (e.g., rent), and variable expenses (e.g., food and transportation costs). The device then sends this information to the server.

[1300] The server detects outliers and fills in missing values ​​in the received household information to normalize it. The normalized data is then analyzed by analytical tools to calculate income, expenses, and the percentage of each expense category. For example, if monthly income is 500,000 yen, rent is 100,000 yen, food expenses are 50,000 yen, and transportation expenses are 30,000 yen, total expenses are calculated as 180,000 yen, and the income and expenditure balance is calculated.

[1301] At the same time, the server automatically obtains expenditure information from the API of electronic payment services (e.g., PayPal and Stripe) through expenditure data acquisition means. This eliminates the need for users to manually enter the information, enabling accurate data collection. More detailed expenditure information can also be collected using the smartphone's GPS and camera.

[1302] Once the analysis is complete, the server generates specific advice using an advice generation means. For example, based on the data analysis, the server may generate a suggestion such as "Your food expenses are high. Cook more meals at home to save money," or goal-setting advice such as "You can save 270,000 yen per month. Keep saving and get closer to your future goal."

[1303] The generated advice is sent to the user's terminal via the display means and displayed within the application, allowing the user to check the advice and use it to improve their household finance management.

[1304] Furthermore, the system can leverage generative AI models to provide more specific and personalized advice to users, who can input prompts to receive more detailed suggestions.

[1305] As a concrete example, the following prompt sentences can be input into a generative AI model to elicit optimal advice for the user:

[1306] Based on this month's household financial information, please give some specific advice on how to improve your lifestyle.

[1307] Monthly salary: 500,000 yen

[1308] Rent: 100,000 yen

[1309] Food expenses: 70,000 yen

[1310] Transportation fee: 30,000 yen

[1311] Other expenses: 50,000 yen

[1312] Other income and expenditure data: ...

[1313] Also consider the data you can get from electronic payment service APIs.

[1314] This allows users to get a complete picture of their household finances, cut down on wasteful spending, and create concrete action plans to achieve their savings goals.

[1315] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1316] Step 1:

[1317] Users enter household information using a smartphone or PC. Input items include income, rent, food, transportation, and other expenses. This information is structured in JSON format or similar and sent from the device to the server. The input at this stage is recorded as household information.

[1318] Input: Household information entered by the user (income, rent, food, transportation, and other expenses)

[1319] Output: The entered household information is sent to the server.

[1320] Step 2:

[1321] The server normalizes the received household information. This process involves detecting outliers and filling in missing values. For example, if the food expenses value is abnormally high, a notification is sent to the user requesting reconfirmation. If no outliers are detected, missing values ​​are filled in with predicted values ​​or average values.

[1322] Input: Household information received from the device

[1323] Output: Normalized household data

[1324] Step 3:

[1325] The server then analyzes the normalized household data. Using analytical tools, it calculates the balance between income and expenditure, and calculates the percentage of each expenditure category. Based on the analysis results, the expenditure percentage and income / expense balance can be determined.

[1326] Input: Normalized household data

[1327] Output: Income and percentage of each expenditure category, balance

[1328] Step 4:

[1329] The server uses the expenditure data acquisition means to automatically acquire the user's expenditure information from the API of the electronic payment service. The API is called, and the acquired data is aggregated on the server. This information is added to the household information.

[1330] Input: Spending information obtained from the API of the electronic payment service

[1331] Output: Added expenditure information

[1332] Step 5:

[1333] The server then uses analytical methods to integrate the added spending information with the household data to form a final data set, which accurately calculates the overall spending amount and the percentage of spending by category.

[1334] Input: Household data, expenditure information from electronic payment services

[1335] Output: Final merged dataset

[1336] Step 6:

[1337] The server uses the advice generation means to generate specific advice from the analysis results based on the final dataset. For example, the advice generated might be, "Your food expenses are high at 70,000 yen, so consider cooking more at home to save money."

[1338] Input: Final merged dataset

[1339] Output: Specific advice

[1340] Step 7:

[1341] Finally, the generated advice is transmitted from the server to the terminal and notified to the user using a display means, so that the user can check the generated advice within the application.

[1342] Input: Generated specific advice

[1343] Output: Advice displayed on the user's terminal

[1344] Through the above process, the user can efficiently manage daily household finance information and improve their household finances based on specific advice.

[1345] 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.

[1346] The present invention combines a system that provides advice based on input household finance information with an emotion engine that recognizes the user's emotions. An embodiment of the present invention will now be described in detail.

[1347] System Overview

[1348] Users input household information into an application on their device (PC or smartphone). Specifically, they input items such as monthly income, rent, food expenses, and transportation expenses. This information is sent to the server via the device.

[1349] The server normalizes the received household information. For example, if there are abnormal values, it detects them and provides feedback. It also imputes missing values.

[1350] The server then analyzes the normalized data, calculating the income and expenditure items to arrive at a balance, and assessing the percentage of each expenditure category.

[1351] The server generates specific advice for the user's household finances based on the analysis results. For example, if food expenses are high, it will suggest "cooking more at home." If the balance is positive, it will also display the amount of savings.

[1352] Furthermore, the present invention recognizes the user's emotions using an emotion engine, which identifies the user's emotions (joy, sadness, anger, stress, etc.) through content analysis of the user's facial expressions, tone of voice, and input content.

[1353] The server adjusts the content and presentation of advice based on the emotional information provided by the emotion engine. For example, if the user is feeling stressed, the server generates advice that contains more encouraging content.

[1354] Finally, the server sends the generated advice to the terminal and displays it to the user, who can then take specific actions to improve their household finances.

[1355] Specific examples

[1356] The user enters financial information using the application

[1357] Suppose a user launches the application and enters the following household information:

[1358] Monthly salary: 500,000 yen

[1359] Rent: 100,000 yen

[1360] Food expenses: 50,000 yen

[1361] Transportation fee: 30,000 yen

[1362] Other expenses: 50,000 yen

[1363] The device sends this information to a server, which then receives the data and first normalizes it, taking into account, for example, unusually high food values ​​or unusually low values ​​for other expenditure items.

[1364] Server analysis and advice generation

[1365] Next, the server analyzes the normalized data. Calculating the balance, the server finds that the monthly income is 500,000 yen and the expenditure is 230,000 yen, resulting in a positive balance of 270,000 yen. It also calculates the percentage of each expenditure item and finds that food expenses account for 10%.

[1366] The server generates advice based on the results of this analysis. For example, it could say, "Your food expenses are high. Cook more meals at home to save money," or "You can save 270,000 yen per month. Keep saving and get closer to your future goal."

[1367] Utilizing the Emotion Engine

[1368] If the emotion engine recognizes the user's emotions (e.g., the user is feeling stressed), the server adds encouraging advice such as, "This is a difficult situation, but let's work together to improve it little by little."

[1369] Displaying Advice

[1370] Finally, the server sends the generated advice to the terminal, which displays it to the user, who can then review the advice and take specific actions to improve their household finances.

[1371] This embodiment allows users to efficiently manage their household finances, reduce wasteful spending, and receive support in achieving their savings goals. Furthermore, by providing detailed advice based on the user's emotions, more effective household finance management is possible.

[1372] The processing flow will be explained below.

[1373] Step 1:

[1374] The user operates the device and launches the application. The user enters household information such as monthly income, rent, food expenses, and transportation expenses. After confirming that the input data is correct, the user clicks the send button.

[1375] Step 2:

[1376] The terminal sends the household information entered by the user to the server. The sent data includes detailed information on income and various expenses.

[1377] Step 3:

[1378] The server first validates the household information received from the device, checking that all data is entered in the correct format (e.g., numeric format), and returns feedback to the user if any data is invalid.

[1379] Step 4:

[1380] The server normalizes the received data. If the data contains abnormal values ​​(e.g., monthly income is extremely high or low), it detects this and asks the user to re-enter the data. It also imputes missing values.

[1381] Step 5:

[1382] The server analyzes the normalized data, calculating the balance by subtracting all expenses from income, and calculating the percentage of each expense item relative to monthly income.

[1383] Step 6:

[1384] The server generates specific advice based on the analysis results. For example, if the proportion of food expenses is high, it will suggest "cooking more meals at home to save money," and if there is a positive balance, it will display the amount of savings.

[1385] Step 7:

[1386] The user can input additional emotional information by operating the device. For example, the user can convey their emotional state (such as stress or satisfaction) to the emotion engine using text input or voice input.

[1387] Step 8:

[1388] The terminal transmits the user's emotional information to the server, which provides the emotional information together with the user's household financial information.

[1389] Step 9:

[1390] The emotion engine analyzes the user's emotion information and identifies the emotional state. For example, if the user inputs "I'm feeling stressed," the emotion engine will recognize that the user is feeling stressed.

[1391] Step 10:

[1392] The server adjusts the content and presentation of advice based on the emotional information provided by the emotion engine. For example, if the user is feeling stressed, the server will add encouraging advice such as, "This is a difficult situation, but let's work hard together to improve it little by little."

[1393] Step 11:

[1394] The server transmits the generated advice to the terminal, which includes a suggestion of what specific action the user should take.

[1395] Step 12:

[1396] The device receives the advice sent from the server and visually displays it to the user, who can then review the advice and take action to improve their household finances.

[1397] Example 2

[1398] 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."

[1399] Conventional household management systems are unable to consider the user's emotions when analyzing household information and providing advice. As a result, it is difficult to provide detailed advice based on the user's emotions, and appropriate support cannot be provided when the user is stressed or unmotivated.

[1400] 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.

[1401] In this invention, the server includes input means for inputting household information, normalization means for normalizing the information, analysis means for analyzing the information, advice generation means for generating advice, an emotion engine for adjustment, adjustment means for adjusting the content of the advice based on the emotion information, and display means for displaying the information, thereby making it possible to accurately analyze the user's household information and provide appropriate advice taking the user's emotions into consideration.

[1402] "Input means" refers to a device or mechanism that allows a user to input household information.

[1403] The "normalization means" is a device or mechanism that normalizes the household information received from the input means by complementing abnormal values ​​and missing values.

[1404] The "analysis means" is a device or mechanism that calculates the balance of income and expenditure and the proportion of each expenditure item based on the data normalized by the normalization means.

[1405] The "advice generating means" is a device or mechanism that generates specific advice regarding household finances based on the data obtained by the analysis means.

[1406] An "emotion engine" is a device or mechanism that analyzes facial expressions, voice tone, input content, etc. to recognize the user's emotional state.

[1407] The "adjustment means" is a device or mechanism that appropriately adjusts the content and expression of advice based on the emotion information obtained from the emotion engine.

[1408] The "display means" is a device or mechanism that displays the advice generated by the advice generating means and the adjustment means to the user.

[1409] System Overview

[1410] This system allows users to input household finance information and provides advice based on that information. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide advice that corresponds to the user's emotional state.

[1411] Users input household information into the application using devices such as PCs or smartphones. Examples of items include monthly income, rent, food expenses, and transportation expenses. This information is sent to the server via the device.

[1412] Data Receipt and Normalization

[1413] The server normalizes the household information received from the device. For example, if there are abnormal values, it detects and corrects them. It also completes any missing values. This ensures the consistency and reliability of the data.

[1414] Analyzing the data

[1415] The server then analyzes the normalized data, calculating income and each expense item to calculate the balance, and assessing the percentage of each expense category. This process is carried out using specialized analytical software installed on the server.

[1416] Generating Advice

[1417] The server generates specific advice for the user's household finances based on the analysis results. For example, if food expenses are high, it will suggest "cook more at home." If the balance is positive, it will also display the amount of savings. This process uses a generative AI model that is installed on the server.

[1418] Utilizing the Emotion Engine

[1419] Furthermore, the present invention uses an emotion engine to recognize the user's emotions. The emotion engine identifies the user's emotions through, for example, analyzing the user's facial expressions, tone of voice, and input content. The server adjusts the content and presentation of advice based on the emotion information provided by the emotion engine. For example, if the user is feeling stressed, the server generates advice that includes more encouraging content.

[1420] Displaying Advice

[1421] Finally, the server sends the generated advice to the terminal and displays it to the user, who can then take specific actions to improve their household finances.

[1422] Specific examples

[1423] Suppose a user launches the application and enters the following household information:

[1424] Monthly salary: 500,000 yen

[1425] Rent: 100,000 yen

[1426] Food expenses: 50,000 yen

[1427] Transportation fee: 30,000 yen

[1428] Other expenses: 50,000 yen

[1429] The device sends this information to a server, which then receives the data and first normalizes it, taking into account, for example, unusually high food values ​​or unusually low values ​​for other expenditure items.

[1430] Next, the server analyzes the normalized data. Calculating the balance, the server finds that the monthly income is 500,000 yen and the expenditure is 230,000 yen, resulting in a positive balance of 270,000 yen. It also calculates the percentage of each expenditure item and finds that food expenses account for 10%.

[1431] The server generates advice based on the results of this analysis. For example, it could say, "Your food expenses are high. Cook more meals at home to save money," or "You can save 270,000 yen per month. Keep saving and get closer to your future goal."

[1432] If the emotion engine recognizes the user's emotions (e.g., the user is feeling stressed), the server adds encouraging advice such as, "This is a difficult situation, but let's work together to improve it little by little."

[1433] Finally, the server sends the generated advice to the terminal, which displays it to the user, who can then review the advice and take specific actions to improve their household finances.

[1434] Example prompts for generative AI models

[1435] "This is an application that allows you to enter your monthly household finances. Based on the data you enter, it calculates your balance and provides you with the percentage of each expense item. It also recognizes your emotions and generates more personalized advice. Please enter your household finances below:

[1436] Monthly salary: 500,000 yen

[1437] Rent: 100,000 yen

[1438] Food expenses: 50,000 yen

[1439] Transportation fee: 30,000 yen

[1440] Other expenses: 50,000 yen

[1441] Emotional data: users are stressed

[1442] Please generate advice."

[1443]

[1444] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1445] Step 1: User enters household information

[1446] The user launches the application on their PC or smartphone and enters household information such as monthly income, rent, food expenses, and transportation costs. The user fills in this information in the input form and clicks the submit button.

[1447] Input: Household information such as monthly income, rent, food, transportation, and other expenses

[1448] Output: Input household information data

[1449] Step 2: The device sends the data to the server

[1450] The device parses the household information entered by the user into JSON format and sends it to the server via an HTTP POST request.

[1451] Input: Entered household information data

[1452] Output: Household information data sent to the server

[1453] Step 3: The server receives and normalizes the data

[1454] The server parses and normalizes the received household information data. Specifically, it detects outliers and missing values ​​and corrects or imputes them. For example, if monthly income is extremely high or food expenses are abnormally low, it generates a warning and imputes them with reasonable values.

[1455] Input: Household information data sent to the server

[1456] Output: Normalized household information data

[1457] Step 4: The server analyzes the data

[1458] The server analyzes the normalized data and calculates the balance and percentage of each expense item (for example, subtracting each expense from monthly income to get the remaining amount), as well as the percentage of total income each expense item contributes to.

[1459] Input: Normalized household information data

[1460] Output: Analysis result data (income and expenditure balance, expenditure ratio, etc.)

[1461] Step 5: Server generates advice

[1462] The server generates advice for improving household finances based on the analysis results data, using a generative AI model to create specific advice such as "Food costs are high, so cook more at home" or "Continue saving money to work toward your future goals."

[1463] Input: Analysis result data

[1464] Output: Generated advice

[1465] Step 6: The server uses the emotion engine

[1466] The server uses an emotion engine to recognize the user's emotions. It analyzes the text data, facial images, and voice data entered by the user to identify their emotional state. For example, if it determines that the user is feeling stressed, it adjusts the content of the advice.

[1467] Input: User's text data, facial images, voice data, and other emotional data

[1468] Output: User's emotional state data

[1469] Step 7: The server adjusts the advice

[1470] The server adjusts the content and presentation of the generated advice based on the user's emotional state data obtained from the emotion engine. For example, if the user is feeling stressed, the server adds encouraging words such as, "It's a tough situation, but let's try to improve it little by little."

[1471] Input: Generated advice, user emotional state data

[1472] Output: Adjusted advice

[1473] Step 8: The server sends the advice to the device

[1474] The server sends the finalized advice to the device, which converts the advice into JSON format and returns it to the device as an HTTP response.

[1475] Input: Tailored Advice

[1476] Output: Advice sent to terminal

[1477] Step 9: The device displays the advice to the user

[1478] The device parses the advice received from the server and displays it on the user's application screen. The user can then review the advice and take specific actions to improve their household finances.

[1479] Input: Advice sent to terminal

[1480] Output: Advice displayed to the user

[1481] (Application example 2)

[1482] 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."

[1483] In modern society, managing one's finances and receiving appropriate financial advice are becoming increasingly important. However, while many existing financial management systems allow users to input and analyze their financial information, they do not consider the user's emotional state. As a result, if the advice provided is not appropriate for the user's psychological state, it often does not lead to actual behavioral change. Furthermore, effective support is required, especially in emotionally stressful situations. Furthermore, the cumbersome interfaces of existing financial management systems often result in a lack of motivation for users to use them regularly.

[1484] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1485] In this invention, the server includes an input means for inputting household information, a normalization means for normalizing the household information received from the input means, an analysis means for analyzing the data normalized by the normalization means, an advice generation means for generating advice about household finances based on the analysis means, a recognition means for recognizing a user's emotions, and an adjustment means for adjusting the content and presentation of the advice based on the emotional information recognized by the recognition means. This makes it possible to provide advice based on the user's household information tailored to the user's emotional state at any given time. Furthermore, using an interface such as a robot enables natural dialogue with the user, thereby increasing motivation to use the household finance management system.

[1486] "Household information" refers to detailed data on the income and expenditure of individuals and households, such as monthly income, rent, food expenses, and transportation costs.

[1487] "Input means" refers to the device or interface that a user uses to input household information. Examples include smartphones and computer applications.

[1488] "Normalization measures" refer to processes or algorithms used to correct, amend, and transform input household information into a form suitable for analysis.

[1489] "Analytical tools" refers to processes and systems for analyzing normalized household information data and calculating income and expenditure balances and expenditure ratios.

[1490] The "advice generation means" refers to a system for forming specific advice and suggestions regarding the user's household finances based on the data obtained by the analysis means.

[1491] The term "display means" refers to a device or method for visually or audibly presenting the generated advice to the user. Specific examples include a display and a speaker.

[1492] "Recognition means" refers to technology for identifying a user's emotions. Specific examples include voice analysis and facial expression recognition.

[1493] "Adjustment means" refers to a process or algorithm that adjusts the content and expression of generated advice based on the recognized user's emotional information.

[1494] This invention combines a system that provides advice based on input household finance information with an emotion engine that recognizes the user's emotions. Specific embodiments for carrying out this invention will be described below.

[1495] System Overview

[1496] Users input household information into an application on their device (smartphone or computer), such as monthly income, rent, food expenses, and transportation expenses. This household information is then sent to a server via the device.

[1497] The server normalizes the household information it receives, a process that detects outliers and imputes missing values. Once normalization is complete, the server then analyzes the data, which includes calculating income and expenditure balances and assessing the percentages of each expenditure category.

[1498] The server generates specific advice for the user's household finances based on the analysis results. For example, it may suggest cooking more meals at home if food costs are high. If the balance is positive, the amount of savings will be displayed.

[1499] The system also recognizes the user's emotions. The emotion engine identifies emotions such as stress or joy through content analysis of the user's facial expressions, tone of voice, and input. The server adjusts the content and presentation of advice based on this emotional information. For example, if the user is feeling stressed, it generates advice that includes encouraging content.

[1500] Finally, the server sends the generated advice to the terminal and displays it to the user.

[1501] Hardware and software configuration

[1502] Hardware: smartphones, computers, robots (smart home assistants), microphones, cameras (for facial recognition)

[1503] Software: Python, Emotion Recognition API, Financial Management API

[1504] Data processing flow

[1505] 1. Enter user's household information:

[1506] The user enters household information and uses a prompt such as, "My monthly income is $500,000. My rent is $100,000 and my food expenses are $50,000. What is the balance?"

[1507] 2. Emotion recognition:

[1508] The emotion engine (Emotion Recognition API) analyzes the user's voice and facial expressions and generates messages based on their emotions, such as "Please do your best. We understand your situation."

[1509] 3. Data normalization and analysis:

[1510] The Financial Management API normalizes household information and analyzes income and expenditure balances and expenditure ratios.

[1511] 4. Advice Generation:

[1512] Based on the analysis results, specific advice tailored to the user's emotional state is generated.

[1513] 5. Display Advice:

[1514] The generated advice is provided to the user in an audio or visual manner.

[1515] This system allows users to efficiently manage their household finances and receive detailed support tailored to their emotions.

[1516] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1517] Step 1:

[1518] The user enters household information.

[1519] Input: Household information such as monthly income, rent, food expenses, and transportation costs. An example prompt is, "My monthly income is 500,000 yen. My rent is 100,000 yen, and my food expenses are 50,000 yen. Please tell me the balance of income and expenses."

[1520] Specific operation: The user uses a smartphone or computer to enter each item on the household information input screen. The device then sends the entered data to the server.

[1521] Step 2:

[1522] The server normalizes the household information.

[1523] Input: Household information data sent from the device.

[1524] Data processing: Detect outliers and correct or impute missing values ​​as necessary.

[1525] Output: Normalized household information data.

[1526] Specific operation: The server receives household information data and stores the normalized information in an internal database.

[1527] Step 3:

[1528] The server analyzes the normalized data.

[1529] Input: Normalized household information data.

[1530] Data calculation: Calculate income and expenditure balances and evaluate the percentage of each expenditure category.

[1531] Output: Analysis results (e.g. income / expense balance, percentage of each expenditure item).

[1532] Specific operation: The server aggregates the income and expenditure for each item, calculates the income and expenditure balance and expenditure ratio, and saves the results.

[1533] Step 4:

[1534] Recognize user emotions.

[1535] Input: User voice and facial expression data. An example prompt is "I've entered my financial information, what should I do next?"

[1536] Data processing: Using voice analysis and facial expression recognition technology to identify emotional states (e.g., joy, sadness, stress).

[1537] Output: User's emotion information.

[1538] Specific operation: The emotion engine analyzes the user's voice or facial expressions obtained from the camera, generates emotion data, and sends it to the server.

[1539] Step 5:

[1540] The server generates the advice.

[1541] Input: Analysis results and user sentiment information.

[1542] Data calculations: Generate tailored advice based on the user's financial situation and emotions. Example: "Cook more at home and save money on food."

[1543] Output: Specific advice on improving your finances.

[1544] Specific operation: The server uses a generative AI model to generate advice in text format based on analytical data and emotional data.

[1545] Step 6:

[1546] The server transmits the generated advice to the terminal.

[1547] Input: The generated advice.

[1548] Data processing: Converting advice content into a format that is easy for users to read.

[1549] Output: Advice displayed on the user's terminal.

[1550] Specific operation: The server sends the generated advice to the terminal, and the terminal displays it on the display screen.

[1551] 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.

[1552] 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.

[1553] 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.

[1554] 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.

[1555] FIG. 9 is a diagram illustrating 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 actions 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.

[1556] 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.

[1557] 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).

[1558] 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.

[1559] 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."

[1560] 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.

[1561] 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).

[1562] 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.

[1563] 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.

[1564] 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.

[1565] 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.

[1566] 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.

[1567] 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.

[1568] 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.

[1569] 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.

[1570] 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.

[1571] 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.

[1572] The following is further disclosed regarding the above embodiment.

[1573] (Claim 1)

[1574] an input means for inputting household information;

[1575] normalization means for normalizing the household information received from said input means;

[1576] analysis means for analyzing the data normalized by the normalization means;

[1577] advice generation means for generating advice regarding household finances based on the analysis means;

[1578] a display means for displaying the advice generated by the advice generating means;

[1579] A system including:

[1580] (Claim 2)

[1581] 10. The system of claim 1, wherein the input means includes input of the user's household information.

[1582] (Claim 3)

[1583] 2. The system of claim 1, wherein said analyzing means includes means for calculating a percentage of each category of expenditure.

[1584] "Example 1"

[1585] (Claim 1)

[1586] an input means for inputting household information;

[1587] normalization means for normalizing the household information received from the input means;

[1588] an analysis means for analyzing the data normalized by the normalization means;

[1589] advice generation means for generating advice regarding household finances based on the analysis means;

[1590] a display means for displaying the advice generated by the advice generating means;

[1591] A system including:

[1592] (Claim 2)

[1593] 2. The system of claim 1, wherein the input means includes input of the user's household financial information.

[1594] (Claim 3)

[1595] 2. The system of claim 1, wherein the normalization means includes outlier detection and missing value imputation.

[1596] (Claim 4)

[1597] 2. The system of claim 1, wherein the analysis means includes calculation of income and expenditure balance and percentage evaluation for each expenditure category.

[1598] (Claim 5)

[1599] 2. The system of claim 1, wherein the advice generation means includes means for generating specific advice for improving household finances using a generative AI model.

[1600] (Claim 6)

[1601] 2. The system of claim 1, wherein the advice generating means includes means for inputting a prompt sentence into a generative AI model.

[1602] "Application Example 1"

[1603] (Claim 1)

[1604] an input means for inputting household information;

[1605] normalization means for normalizing the household information received from said input means;

[1606] analysis means for analyzing the data normalized by the normalization means;

[1607] advice generation means for generating advice regarding household finances based on the analysis means;

[1608] an expenditure data acquisition means for automatically acquiring expenditure information from an electronic payment service;

[1609] a display means for displaying the advice generated by the advice generating means;

[1610] A system including:

[1611] (Claim 2)

[1612] 10. The system of claim 1, wherein the input means includes input of the user's household information.

[1613] (Claim 3)

[1614] 2. The system of claim 1, wherein said analyzing means includes means for calculating a percentage of each category of expenditure.

[1615] "Example 2: Combining Emotion Engines"

[1616] (Claim 1)

[1617] an input means for inputting household information;

[1618] normalization means for normalizing the household information received from said input means;

[1619] analysis means for analyzing the data normalized by the normalization means;

[1620] advice generation means for generating advice regarding household finances based on the analysis means;

[1621] an emotion engine that recognizes the user's emotions;

[1622] an adjustment means for adjusting the content of advice based on emotion information obtained from the emotion engine;

[1623] a display means for displaying the advice generated by the advice generating means;

[1624] A system including:

[1625] (Claim 2)

[1626] 2. The system of claim 1, wherein the input means includes input of the user's household financial information.

[1627] (Claim 3)

[1628] 2. The system of claim 1, wherein said analyzing means includes means for calculating a percentage of each category of expenditure.

[1629] "Application example 2 when combining emotion engines"

[1630] (Claim 1)

[1631] an input means for inputting household information;

[1632] normalization means for normalizing the household information received from said input means;

[1633] analysis means for analyzing the data normalized by the normalization means;

[1634] advice generation means for generating advice regarding household finances based on the analysis means;

[1635] a display means for displaying the advice generated by the advice generating means;

[1636] recognition means for recognizing an emotion of a user;

[1637] an adjustment means for adjusting the content and expression method of advice based on the emotion information recognized by the recognition means;

[1638] A system including:

[1639] (Claim 2)

[1640] 10. The system of claim 1, wherein the input means includes input of the user's household information.

[1641] (Claim 3)

[1642] 2. The system of claim 1, wherein said analyzing means includes means for calculating a percentage of each category of expenditure. [Explanation of symbols]

[1643] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. an input means for inputting household information; normalization means for normalizing the household information received from said input means; analysis means for analyzing the data normalized by the normalization means; advice generation means for generating advice regarding household finances based on the analysis means; a display means for displaying the advice generated by the advice generating means; A system including:

2. 2. The system of claim 1, wherein said input means includes input of the user's household information.

3. 2. The system of claim 1, wherein said analyzing means includes means for calculating a percentage of each category of expenditure.

Images