System

Abstract

A system is provided.SOLUTION: A system, comprising: means for collecting historical consumption data of a user; means for analyzing the collected historical consumption data to categorize each transaction; means for statistically analyzing the categorized consumption amounts; means for evaluating consumption patterns of the user in comparison with user data of similar attributes; and means for notifying the user of the analysis and comparison results.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] Conventional household management methods require the time-consuming manual recording and classification of consumption history, making accurate and efficient consumption management difficult. Furthermore, the lack of future consumption predictions and suggestions for cost-effective shopping methods left users prone to wasteful spending and inappropriate consumption behavior. Furthermore, the lack of a system for properly comparing individual user data with market information to provide advice meant that optimal consumption behavior could not be supported. [Means for solving the problem]

[0005] The personal AI financial assistant system of the present invention includes a means for automatically collecting and analyzing a user's consumption history data to categorize each transaction. It also provides a means for statistically analyzing the consumption amounts for each categorized item and comparing them with user data with similar attributes to evaluate consumption patterns. This allows for efficient consumption management for users. Additionally, by including a means for predicting future consumption based on past consumption data and a means for comparing the user's data with the latest market information to suggest cost-effective shopping methods, it is possible to optimize the user's consumption behavior and reduce wasteful spending.

[0006] "Consumption history data" refers to data that includes records of various consumption behaviors performed by a user over a specific period of time.

[0007] "Classifying by category" refers to the operation of dividing consumption history data into specific categories, such as food expenses, transportation expenses, and entertainment expenses.

[0008] "Statistical analysis" means analyzing collected data using numerical methods to reveal overall trends and relationships.

[0009] "Users with similar attributes" refers to a group of users who have similar attributes such as age, occupation, and family structure.

[0010] "Consumption patterns" indicate the tendencies and characteristics of a user's consumption behavior.

[0011] "Collection means" refers to a method or technology for automatically acquiring and transmitting consumption history data to a management system.

[0012] "Analysis means" refers to technology used to clarify consumer behavior based on collected data and analyze each transaction.

[0013] "Comparison methods" refer to technology for evaluating a user's consumption behavior by referencing user data, data on similar users, the latest market information, etc.

[0014] "Notification means" refers to a method or technology for notifying the user of the analysis results and suggested information.

[0015] "Prediction methods" refer to technologies for estimating future consumption using statistical models or machine learning models based on past consumption data.

[0016] "Proposal means" refers to a method or technology for presenting the most advantageous consumption method or plan to a user based on the latest market information and the user's consumption pattern. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] The present invention is a system that automatically collects and analyzes a user's consumption history data, performs statistical analysis by expenditure category, predicts future consumption, and suggests advantageous shopping methods, thereby optimizing the user's consumption behavior. Specific embodiments of the system are described below.

[0039] Data collection and classification

[0040] First, the server collects the user's consumption history data. This data includes consumption history using electronic services, credit card usage history, and online shopping records. The server obtains this data through an API and stores it in a database. Next, the server analyzes the stored data. Natural language processing (NLP) technology is used for the analysis, and each transaction is automatically classified into categories.

[0041] Statistical analysis and comparison

[0042] The server generates aggregate data to statistically analyze spending for each category. For example, it calculates the amount spent on food and transportation over the past month. The server then collects statistical data on similar users to compare with data from other users with similar attributes, and evaluates the user's spending patterns relatively. The results of the analysis and comparison are then sent to the device and provided to the user.

[0043] Future consumption forecast

[0044] To predict future spending using past consumption data, the server builds statistical and machine learning models. This allows the server to calculate the user's average monthly spending and predicted spending for a specific period. The device notifies the user of this information and encourages them to plan their spending accordingly.

[0045] Proposals for great shopping deals

[0046] The server collects the latest market information (e.g., smartphone plans, coupons, medical expense deduction information, etc.) and compares it with the user's consumption data. This identifies the best value option, which the device notifies the user. For example, it compares the user's current smartphone plan with the latest plan and suggests a plan with a lower monthly fee.

[0047] Specific examples

[0048] Categorizing and analyzing expenses

[0049] When a user spends 1,000 yen on daily shopping using electronic payment, the server collects this data and categorizes it as "food expenses." The server then analyzes the food expense data for the past three months and generates statistical data on the cumulative amount and monthly fluctuations.

[0050] Consumption forecast

[0051] The server builds a machine learning model based on consumption data from the past six months and calculates a predicted consumption amount of 50,000 yen for the next month. The device notifies the user that "Next month's predicted consumption amount is 50,000 yen," and the user confirms this and sets a budget.

[0052] Great Offers

[0053] The server collects the latest smartphone plans and compares them with the user's current plan. If a plan that is 1,000 yen cheaper per month is available, the device notifies the user. The user receives the proposal that "there is a new smartphone plan that will save you 1,000 yen per month," and considers changing their plan.

[0054] In this way, the personal AI financial assistant system of the present invention analyzes the user's consumption behavior in detail, predicts future expenditures, and proposes optimal consumption plans, thereby reducing the user's wasteful spending and realizing efficient consumption behavior.

[0055] The processing flow will be explained below.

[0056] Detailed processing steps

[0057] Data collection and classification

[0058] Step 1:

[0059] The server obtains consumption history data from the user's electronic services, credit cards, and online shopping via API.

[0060] Step 2:

[0061] The server saves the retrieved data in the database.

[0062] Step 3:

[0063] The server analyzes the stored spending data and extracts detailed information about each transaction (such as the recipient, amount, and date and time of the spending).

[0064] Step 4:

[0065] The server uses natural language processing (NLP) technology to automatically classify each transaction into a category (e.g., food, transportation, entertainment, etc.).

[0066] Statistical analysis and comparison

[0067] Step 5:

[0068] The server calculates the total amount spent for each category and generates statistical data.

[0069] Step 6:

[0070] The server collects statistical data of other users with similar attributes and compares it with the user's data.

[0071] Step 7:

[0072] The server evaluates the user's consumption patterns and identifies in which categories there is a surplus or deficit.

[0073] Step 8:

[0074] The terminal notifies the user of the analysis and comparison results.

[0075] Future consumption forecast

[0076] Step 9:

[0077] The server retrieves historical consumption data from the database.

[0078] Step 10:

[0079] The server builds statistical and machine learning models to learn past consumption patterns.

[0080] Step 11:

[0081] The server uses the model it has built to calculate the expected consumption amount for next month and this fiscal year.

[0082] Step 12:

[0083] The terminal notifies the user of the prediction result.

[0084] Proposals for great shopping deals

[0085] Step 13:

[0086] The server collects the latest market information (e.g., smartphone plans, coupons, medical expense deduction information, etc.) from the Internet.

[0087] Step 14:

[0088] The server retrieves the user's current contract information and consumption patterns from a database.

[0089] Step 15:

[0090] The server compares the collected market information with the user's data and generates optimal proposals.

[0091] Step 16:

[0092] The terminal notifies the user of the suggested information.

[0093] Step 17:

[0094] The user reviews the suggestions and takes action as needed.

[0095] Specific examples

[0096] Step 18:

[0097] When a user spends 1,000 yen at a convenience store using electronic payment, the server collects this data.

[0098] Step 19:

[0099] The server analyzes the collected data and classifies it as "food expenses."

[0100] Step 20:

[0101] The server statistically analyzes food expense data from the past three months and generates cumulative amounts and monthly fluctuations.

[0102] Step 21:

[0103] The server compares the food expenses with the average expenses of similar users and evaluates whether the amount is excessive or insufficient.

[0104] Step 22:

[0105] The device will notify the user that "Your food expenses are higher than average," and the user will confirm this.

[0106] Example 1

[0107] 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."

[0108] As consumer behavior in modern society becomes more complex, it is becoming increasingly difficult for individual users to understand and efficiently manage their own consumption history. Furthermore, the lack of future consumption predictions or suggestions for optimal shopping methods leads to the problem of increased wasteful spending. Therefore, there is a need for a system that can analyze users' consumption behavior in detail and provide effective advice.

[0109] 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.

[0110] In this invention, the server includes means for automatically collecting user consumption history data, means for saving the collected consumption history data in a database, means for analyzing the saved consumption history data using natural language processing technology and classifying each transaction by category, means for statistically analyzing the consumption amounts for each classified category and generating aggregate data, means for relatively evaluating the user's consumption patterns by comparing with data of other users with similar attributes, means for notifying the user of the analysis and comparison results to their terminal, means for building a statistical model or machine learning model based on past consumption data and predicting the user's future consumption amounts, and means for comparing the collected consumption history data with the latest market information and suggesting the most cost-effective shopping methods to the user. This enables users to understand their own consumption behavior in detail, plan future consumption, and shop efficiently.

[0111] "Means for automatically collecting user consumption history data" refers to a system that periodically obtains all transaction data made by a user using the APIs of credit card companies and online shopping sites.

[0112] "Means for storing collected consumption history data in a database" refers to a system that accumulates consumption history data in a database in a structured format, enabling efficient management and retrieval.

[0113] "Means of analyzing using natural language processing technology and classifying each transaction by category" refers to technology that analyzes the text information in consumption history data and automatically classifies it into categories such as food expenses, transportation expenses, and entertainment expenses.

[0114] "Means for statistically analyzing consumption amounts by category and generating aggregated data" refers to a system that calculates totals and average amounts for each category based on collected and classified data, and generates statistical analysis results.

[0115] "Means for relatively evaluating a user's consumption patterns by comparing them with data from other users with similar attributes" refers to a system that identifies similar users based on attributes such as age and occupation, and compares their consumption data with the user's consumption data to evaluate them.

[0116] "Means for notifying the user of the analysis and comparison results" refers to a system that displays and notifies the results of consumption analysis and comparison on devices such as smartphones and PCs.

[0117] "Means of building statistical models or machine learning models to predict future consumption amounts of users" refers to technology that applies predictive algorithms based on past consumption data to estimate future consumption amounts.

[0118] "A means of collecting the latest market information and proposing the most cost-effective shopping methods to users" is a system that obtains the latest pricing plans and discount information from resources on the Internet and proposes the most economical options to users.

[0119] This invention is a system for efficiently managing a user's consumption behavior and reducing wasteful spending. This system automatically collects the user's consumption history data, analyzes the data, performs statistical analysis, and evaluates the user's consumption patterns. Furthermore, it predicts future consumption amounts and suggests optimal shopping methods, thereby optimizing the user's consumption behavior.

[0120] Data collection and storage

[0121] The server automatically collects user spending history data using APIs from credit card companies and online shopping sites. This data includes details of each transaction (e.g., date and time, amount, store name, etc.). The collected data is stored in a structured database. An SQL database is typically used for the database.

[0122] Data analysis and classification

[0123] The server analyzes the stored consumption history data using natural language processing (NLP) techniques. Specifically, it uses Python natural language processing libraries such as spaCy and NLTK to classify each transaction into categories. This process automatically assigns categories such as food, transportation, and entertainment expenses.

[0124] Statistical analysis and comparison

[0125] The server uses Python libraries such as pandas and NumPy to statistically analyze the amount spent for each category. This generates aggregate data such as the total food expenses for the past month and monthly fluctuations. Additionally, methods such as cluster analysis are used to evaluate the user's spending patterns relative to other users with similar attributes (age, occupation, income, etc.). The results of these analyses are sent to devices such as smartphones.

[0126] For example, if a user spends 1,000 yen on everyday shopping, the server collects this data and categorizes it as "food expenses."Then, based on the food expenses data from the past three months, the cumulative amount and monthly fluctuations are statistically analyzed and a notification is sent to the smartphone.

[0127] Future consumption forecast

[0128] The server builds statistical and machine learning models based on past consumption data to predict future consumption amounts. Specifically, it uses machine learning libraries such as scikit-learn, TensorFlow, and PyTorch. This predicted data is sent to the device, encouraging users to plan their consumption behavior.

[0129] Example prompt:

[0130] "Calculate your predicted spending for next month based on your spending data from the past six months."

[0131] Proposals for great shopping deals

[0132] The server collects the latest market information from internet resources (news sites, corporate APIs, etc.). It uses web scraping technology to obtain the latest smartphone pricing plans and discount information and compares it with the user's consumption data. It identifies the most economical option and notifies the device. For example, it may notify the user with a suggestion such as, "We have a new smartphone plan that will save you 1,000 yen per month."

[0133] Example prompt:

[0134] "Check out the latest smartphone pricing plans and compare them to your current plan."

[0135] In this way, the system of the present invention realizes efficient consumption behavior by analyzing the user's consumption behavior in detail, predicting future expenditures, and encouraging optimal consumption.

[0136] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0137] Step 1: Data collection

[0138] The server collects user spending history data through the APIs of credit card companies and online shopping sites. User authentication information and API key are required as input. The server uses this information to send API requests and retrieve spending history data. The retrieved data is returned in JSON format, including details of each transaction (date and time, amount, store name, etc.).

[0139] Step 2: Save data

[0140] The server saves the collected consumption history data in a database. The input includes consumption history data in JSON format. The server parses it and inserts each transaction into an SQL database. For example, the user ID, date and time, amount, and store name are stored in the corresponding columns. The output is a successful insertion into the database.

[0141] Step 3: Data analysis and categorization

[0142] The server analyzes the stored consumption history data using natural language processing (NLP) techniques. The input includes detailed transaction data retrieved from an SQL database. The server uses a Python natural language processing library (e.g., spaCy) to analyze the description of each transaction and classify it into the appropriate category (e.g., food expenses, transportation expenses). The output is the transaction data with the categories assigned.

[0143] Step 4: Statistical analysis and aggregate data generation

[0144] The server statistically analyzes the expenditures for each classified category. The input includes transaction data with categories assigned. The server uses Python's pandas library to calculate the total and average amounts for each category. As a specific example, it calculates the total amount of food expenses for the past month and monthly fluctuations. The output is statistically analyzed aggregated data.

[0145] Step 5: Compare with similar users

[0146] The server evaluates a user's consumption patterns relative to other users with similar attributes. The input includes the user's attribute data (age, occupation, income, etc.) and consumption data. The server uses cluster analysis to identify similar users and compares their consumption amounts in each category. The output is the relative evaluation result.

[0147] Step 6: Notification of results

[0148] The device notifies the user of the analysis and comparison results sent from the server. The input includes the evaluation result data sent from the server. The device organizes this data and displays it to the user as alerts or notifications. For example, information such as "Your food expenses for the past month are 20% higher than average" is displayed on a smartphone screen. The output is the notification the user receives.

[0149] Step 7: Forecast future consumption

[0150] The server builds statistical and machine learning models based on past consumption data to predict future consumption. The input includes consumption data from the past few months. The server uses machine learning libraries such as scikit-learn and TensorFlow to build linear regression models and other prediction algorithms. The output is predicted data, such as "Next month's predicted consumption is 50,000 yen."

[0151] Step 8: Predictive Data Notification

[0152] The device notifies the user of the forecast data sent from the server. The input includes the forecast data sent from the server. The device organizes this data and displays it as a notification to the user. For example, information such as "Next month's forecast consumption amount is 50,000 yen" is sent to a smartphone as a push notification. The output is the forecast notification received by the user.

[0153] Step 9: Gather market intelligence

[0154] The server collects the latest market information from internet resources. The input includes user consumption data and the latest pricing plans and discount information obtained from web scraping technology and company APIs. The server organizes this information and stores it in a database. The output is the collected latest market information.

[0155] Step 10: Suggestions for great shopping deals

[0156] The server compares the collected market information with the user's consumption data to identify the best value option. The input includes the user's current consumption data and the latest market information. The server calculates the most economical option and sends the result to the device. The device notifies the user with information such as "There is a new smartphone plan that will save you 1,000 yen per month." The output is a notification of the offer that the user receives.

[0157] (Application example 1)

[0158] 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."

[0159] Conventional consumption data analysis systems have difficulty in properly analyzing and predicting users' consumption behavior, and are unable to suggest optimal purchasing methods in a timely manner. As a result, users are unable to efficiently manage their consumption behavior, which often results in wasteful spending. They are also unable to effectively utilize the latest market information, coupons, and discount information. As a result, many users suffer economic disadvantages.

[0160] 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.

[0161] In this invention, the server includes: means for collecting user consumption history data; means for analyzing the collected consumption history data and classifying each transaction by category; means for statistically analyzing the consumption amounts for each category; means for evaluating the user's consumption patterns by comparing them with user data of similar attributes; means for notifying the user of the analysis and comparison results; means for analyzing the user's consumption behavior in real time based on electronic payment information; means for predicting future consumption amounts based on past consumption data; and means for collecting the latest market information and comparing it with the user's consumption data to suggest optimal purchasing methods. This allows users to efficiently manage their consumption behavior and reduce wasteful spending. Users can also receive suggestions for advantageous purchasing methods using the latest market information, coupons, and discount information.

[0162] "User consumption history data" is information about the user's past consumption behavior, including items, amounts, dates and times, stores, and the like.

[0163] "Transaction" refers to each purchase or service use made by a User, including payment details.

[0164] A "category" is a broad group for classifying consumption behavior, and includes specific consumption items such as "food expenses" and "transportation expenses."

[0165] "Electronic payment information" refers to detailed data related to payments made using credit cards or electronic wallets, and serves as basic data for analyzing users' consumption behavior.

[0166] "Statistical analysis" means collecting and classifying data and using mathematical methods to calculate summaries, averages, distributions, etc., to reveal consumption patterns.

[0167] "User data with similar attributes" refers to consumption data of other users who share common characteristics such as age, gender, income range, etc.

[0168] "Consumption patterns" indicate the characteristics and tendencies of a user's consumption behavior, such as frequency, consumption trends by category, and seasonal fluctuations.

[0169] "Latest information" refers to information about new offers and sales in the market, such as coupons, discounts, and pricing plans.

[0170] "Predicting future spending" means predicting the amount of money a user will spend within a certain period of time in the future based on past data.

[0171] "Notifying" means providing the analysis results and suggestions to the user's device so that the user can easily obtain the information.

[0172] A "best value purchase method" refers to the most economical possible option when a user purchases a product or service.

[0173] "Analyzing in real time" means collecting data the moment a consumer behavior occurs and analyzing it immediately.

[0174] The present invention is a system for collecting and analyzing consumption history data of a user and optimizing the consumption behavior of the user based on the collected data. Specific embodiments are described below.

[0175] Data collection and classification

[0176] First, the server collects the user's spending history data. This data includes electronic payment information, online shopping records, and credit card usage history. The server obtains this data through an API and stores it in a database. Next, the server analyzes the stored data and automatically categorizes each transaction. For example, data containing "food" in the transaction description is classified as "food expenses."

[0177] Statistical analysis and comparison

[0178] The server then statistically analyzes the amount spent for each category. This reveals the user's spending patterns. For example, it can determine how much money was spent on food over the past month and how that amount changed. Furthermore, it uses data from other users with similar attributes to evaluate the user's spending patterns relative to their own. The results are then sent to the user via their device.

[0179] Future consumption forecast

[0180] The server builds a machine learning model based on past consumption data to predict future consumption amounts. This allows users to understand their average monthly consumption amount and predicted consumption amounts for a specific period. The prediction results are sent to the device, where users can check them and set their budget.

[0181] Proposals for advantageous purchasing methods

[0182] The server collects the latest market information (e.g., coupons, discounts, pricing plans, etc.) and compares it with the user's consumption data. For example, it compares the user's current smartphone plan with the latest plans and suggests a cheaper plan to the user if one is available. This suggestion is then notified to the user via the device.

[0183] Hardware and software used

[0184] The server uses high-performance server facilities for data collection and analysis, and software such as database management systems (e.g., MySQL), libraries for natural language processing (NLP) techniques (e.g., NLTK), and frameworks for building machine learning models (e.g., TensorFlow).

[0185] Specific examples

[0186] Everyday shopping

[0187] When a user spends 1,000 yen using electronic payment, the server collects this data and categorizes it as "food expenses." The server then analyzes the food expense data from the past three months and generates statistical data on the cumulative amount and monthly fluctuations.

[0188] Consumption forecast

[0189] The server builds a machine learning model based on consumption data from the past six months and calculates a predicted consumption amount of 50,000 yen for the next month. The device notifies the user that "Next month's predicted consumption amount is 50,000 yen," and the user confirms this and sets a budget.

[0190] Great Offers

[0191] The server collects the latest smartphone plans and compares them with the user's current plan. If a plan that is 1,000 yen cheaper per month is available, the device notifies the user. The user receives the proposal that "there is a new smartphone plan that will save you 1,000 yen per month," and considers changing their plan.

[0192] Example prompts to be input to the generative AI model

[0193] The generative AI model is given a prompt like this:

[0194] text

[0195] Design an application that suggests the most economical spending patterns based on a user's spending history. Consider the following data:

[0196] 1. Consumption history by date, amount, and category

[0197] 2. Statistical data from past consumption behavior

[0198] 3. Future spending forecast

[0199] 4. Market updates and coupons

[0200] This system analyzes users' consumption behavior in detail, predicts future expenditures, and proposes optimal consumption plans, thereby reducing wasteful spending and realizing efficient consumption behavior.

[0201] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0202] Step 1: Data collection

[0203] The server collects the user's consumption history data. Specifically, this data includes electronic payment information, online shopping records, credit card usage history, etc., and is retrieved via API and stored in a database. The input is the user's transaction history, and the output is the categorized and stored information in the database.

[0204] Step 2: Data Classification

[0205] The server analyzes the stored data and automatically classifies each transaction into a category. Data classification is performed using natural language processing (NLP) technology. For example, data containing "food" is classified as "food expenses." The input is unclassified transaction data, and the output is data classified by category.

[0206] Step 3: Statistical analysis

[0207] The server statistically analyzes the spending amount for each category, which reveals the user's spending patterns. Specifically, it calculates the spending amount and its fluctuations over the past month. The input is spending data by category, and the output is the statistical analysis results.

[0208] Step 4: Comparative evaluation

[0209] The server uses data from other users with similar attributes to evaluate a user's consumption patterns relatively. By comparing with users with similar attributes, the quality of the user's consumption is evaluated. The input is the user's statistical data and the statistical data of similar users, and the output is the result of the relative evaluation.

[0210] Step 5: Notification

[0211] The terminal notifies the user of the results of the analysis and comparison. Specifically, consumption patterns and comparison results are displayed on the user's smartphone or PC. The input is the analysis and comparison results, and the output is the notification content to the user.

[0212] Step 6: Consumption forecast

[0213] The server builds a machine learning model based on past consumption data and predicts future consumption. For example, the server analyzes consumption data from the past six months and calculates the predicted consumption amount for next month. The input is past consumption data and the output is the predicted consumption amount.

[0214] Step 7: Gather up-to-date information

[0215] The server collects the latest market information (e.g. coupons, discounts, pricing plans, etc.) using web scraping technology or APIs. The input is a market data collection request, and the output is the latest market information.

[0216] Step 8: Propose a good deal

[0217] The server compares the latest collected data with the user's consumption data to suggest the optimal purchasing method. For example, it compares the current smartphone plan with the latest plans and suggests the cheapest plan to the user. The input is the user's consumption data and the latest market information, and the output is the optimal purchasing suggestion.

[0218] Step 9: Proposal Notification

[0219] The device notifies the user of a suggestion for a more advantageous purchasing method. Specifically, the suggestion is displayed on the user's smartphone. The input is the suggestion, and the output is the notification to the user.

[0220] By going through these steps, users can effectively manage their consumption habits and reduce wasteful spending. They can also receive suggestions for great deals by using the latest market information, coupons, and discount information.

[0221] 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.

[0222] The present invention is a system that automatically collects and analyzes a user's consumption history data, classifies it by consumption category, and provides statistical analysis and comparison results with similar users. Furthermore, by combining this system with an emotion engine that recognizes the user's emotions, it is possible to provide advice, predictions, and suggestions based on the user's emotional state. Specific embodiments of this system are described below.

[0223] Data collection and classification

[0224] First, the server retrieves the user's consumption history data from electronic services, credit cards, and online shopping via API. This data is then stored in a database and analyzed by the server. Natural language processing (NLP) technology is used for the analysis, automatically classifying each transaction into categories.

[0225] Statistical analysis and comparison

[0226] The server calculates the total amount spent for each category and generates statistical data. Furthermore, it evaluates the user's spending patterns by collecting and comparing data from other users with similar attributes. The results of this evaluation are then sent to the user via their device.

[0227] Future consumption forecast

[0228] Based on past consumption data, the server builds statistical and machine learning models to predict the user's future consumption amounts. The prediction results are notified to the user via the device, encouraging them to plan their consumption.

[0229] Proposals for great shopping deals

[0230] The server collects the latest market information (e.g., smartphone pricing plans, coupons, tax deduction information, etc.) and compares it with the user's consumption patterns, generating optimal proposals and notifying the user via their device.

[0231] Combining Emotion Engines

[0232] This system also recognizes the user's emotional state by combining it with an emotion engine. The specific processing flow is explained below.

[0233] emotion recognition

[0234] The server analyzes the user's input data (e.g., text, voice, facial expressions) and recognizes the user's emotions. This analysis is performed using emotion recognition algorithms and machine learning models.

[0235] Emotional advice

[0236] If the user is feeling stressed, the server will provide advice on consumer behavior based on the emotional data, such as suggesting the purchase of relaxation products.

[0237] Emotion-based predictions

[0238] The server incorporates the user's emotional data into the consumption prediction model, providing more accurate consumption predictions.

[0239] Emotional suggestions

[0240] The server uses the emotional data to adjust shopping methods and notify the user via the device. For example, if the user is feeling financially anxious, suggestions for cost reduction will be made.

[0241] Specific examples

[0242] Emotion Recognition and Advice

[0243] The server analyzes the text entered by the user, "I've been feeling stressed lately," and recognizes it as a "stressed state."

[0244] The server will advise you on the availability of relaxation-related products and services (e.g., massage, spa).

[0245] Emotion-based predictions

[0246] The server calculates next month's predicted consumption amount as 40,000 yen based on past consumption data and emotional data entered by the user, such as "My income has decreased this month."

[0247] The device notifies the user that "Next month's estimated consumption is 40,000 yen," and the user confirms this and sets a budget.

[0248] Emotional suggestions

[0249] The server collects the latest smartphone plans and, based on emotional data entered by the user, such as "I'm concerned about my recent spending," suggests plans with even lower monthly fees.

[0250] The device will notify the user of a proposal that says, "There is a new smartphone plan that will save you 1,500 yen per month," and the user will review it and consider making the change.

[0251] In this way, by combining consumption history data and emotion recognition, the system of the present invention can analyze the user's consumption behavior in detail and provide optimal advice and suggestions, enabling the user to realize more efficient and planned consumption behavior.

[0252] The processing flow will be explained below.

[0253] Data collection and classification

[0254] Step 1:

[0255] The server obtains the user's electronic payment service, credit card transaction, and online shopping consumption history data via the API.

[0256] Step 2:

[0257] The server stores the acquired consumption history data in a database.

[0258] Step 3:

[0259] The server extracts the details of each stored transaction (recipient, amount, date and time).

[0260] Step 4:

[0261] The server uses natural language processing (NLP) technology to automatically classify each transaction into a category (e.g., food, transportation, entertainment).

[0262] Statistical analysis and comparison

[0263] Step 5:

[0264] The server calculates the total amount spent for each classified category and generates statistical data.

[0265] Step 6:

[0266] The server collects data of other users with similar attributes and compares it with the user's data.

[0267] Step 7:

[0268] The server evaluates the user's consumption patterns and identifies excesses or shortages in certain categories.

[0269] Step 8:

[0270] The terminal notifies the user of the analysis results and the results of comparison with similar users.

[0271] Future consumption forecast

[0272] Step 9:

[0273] The server retrieves historical consumption data from the database.

[0274] Step 10:

[0275] The server builds statistical and machine learning models based on past consumption patterns.

[0276] Step 11:

[0277] The server uses the model it has built to calculate the expected consumption amount for the next month or the current fiscal year.

[0278] Step 12:

[0279] The terminal notifies the user of the prediction result.

[0280] Proposals for great shopping deals

[0281] Step 13:

[0282] The server collects the latest market information (e.g. smartphone plans, coupons, medical expense deduction information, etc.).

[0283] Step 14:

[0284] The server retrieves the user's current contract information and consumption patterns from a database.

[0285] Step 15:

[0286] The server compares the collected market information with the user's data and generates optimal proposals.

[0287] Step 16:

[0288] The terminal notifies the user of the suggested information.

[0289] Step 17:

[0290] The user reviews the suggestions and takes action as needed.

[0291] Combining Emotion Engines

[0292] Step 18:

[0293] The server analyzes the user's input data (e.g., text, voice, facial expressions) using an emotion engine to recognize the user's emotions.

[0294] Step 19:

[0295] The server stores the user's emotion data in a database.

[0296] Step 20:

[0297] The server generates consumption advice based on the emotional data. For example, if the user is feeling stressed, the server will recommend products and services related to relaxation.

[0298] Step 21:

[0299] The server incorporates the emotion data into the consumption prediction model to improve the accuracy of the prediction.

[0300] Step 22:

[0301] The terminal notifies the user of the prediction result.

[0302] Step 23:

[0303] The server then uses the emotional data to tailor its shopping recommendations, for example, suggesting ways to cut costs if the user is feeling financially anxious.

[0304] Step 24:

[0305] The terminal notifies the user of the adjusted proposal.

[0306] Specific examples

[0307] Step 25:

[0308] When a user enters text such as "I've been feeling stressed lately," the server analyzes it using an emotion engine and recognizes it as a "stressed state."

[0309] Step 26:

[0310] The server generates advice suggesting relaxation services (e.g., massage, spa) to reduce stress.

[0311] Step 27:

[0312] The terminal notifies the user of the advice.

[0313] Step 28:

[0314] The server calculates next month's predicted consumption amount as 40,000 yen based on past consumption data and emotional data entered by the user, such as "My income has decreased this month."

[0315] Step 29:

[0316] The device notifies the user that "Next month's estimated consumption is 40,000 yen," and the user confirms this and sets a budget.

[0317] Step 30:

[0318] The server collects the latest smartphone plans and, based on emotional data entered by the user, such as "I'm concerned about my recent spending," suggests plans with even lower monthly fees.

[0319] Step 31:

[0320] The device will notify the user of the proposal, saying, "We have a new smartphone plan that will save you 1,500 yen per month," and the user can review it and consider making the change.

[0321] In this way, by combining consumption history data and emotion recognition, the system of the present invention can analyze the user's consumption behavior in detail and provide optimal advice and suggestions, enabling the user to realize more efficient and planned consumption behavior.

[0322] Example 2

[0323] 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."

[0324] Existing consumption history analysis systems have limitations in analyzing users' consumption data and providing effective feedback. Furthermore, they rarely provide advice or predictions that take into account the user's emotional state, making it difficult to provide optimized recommendations for individual users. Therefore, a system that can analyze users' consumption behavior in detail and with high accuracy and provide advice and recommendations tailored to their emotional state is needed.

[0325] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting user consumption history data, means for analyzing the collected consumption history data and classifying each transaction by category, means for statistically analyzing the consumption amounts for each classified category, means for evaluating the user's consumption pattern by comparing with user data of similar attributes, means for analyzing emotion data and recognizing emotions, means for generating advice on consumption behavior based on the emotion data, and means for notifying the user of the evaluation result and emotion-based advice. This enables advanced analysis based on the user's consumption history data and emotional state, and individual advice and suggestions.

[0326] "Consumption history data" refers to a record of purchases and expenditures made by a user, and is obtained from electronic services, credit card usage history, online shopping, etc.

[0327] "Categorizing by category" means automatically sorting collected consumption history data into categories such as food, entertainment, and transportation based on specific criteria.

[0328] "Statistical analysis" means analyzing collected and classified data using statistical methods such as mean, median, and variance to clarify consumption patterns and overall trends.

[0329] "User data with similar attributes" is a collection of consumption data collected from multiple users with similar attributes such as age, income, and lifestyle.

[0330] "Evaluating consumption patterns" means comparing a user's consumption history data with data of users with similar attributes and analyzing consumption trends and characteristics.

[0331] "Emotion data" is data that indicates the user's emotional state obtained from text, voice, facial expressions, etc.

[0332] "Emotion recognition" refers to analyzing emotion data and determining the user's current emotional state (e.g., joy, sadness, stress, etc.).

[0333] "Consumer behavior advice" refers to action plans and purchasing recommendations provided to users based on collected and analyzed data.

[0334] "Notifying" refers to the means of communicating evaluation results and advice to users, including smartphone push notifications, emails, and in-app notifications.

[0335] The present invention is a system that automatically collects and analyzes a user's consumption history data, classifies it by consumption category, and provides statistical analysis and comparison results with similar users. Furthermore, the present invention uses an emotion engine that recognizes the user's emotions, and provides advice, predictions, and suggestions based on the user's emotional state. Specific embodiments of the system are described below.

[0336] Data collection and classification

[0337] The server obtains consumption history data from users' electronic services, credit cards, and online shopping via API. This data is saved in JSON format and stored in a database. Data collection is performed using API calls and web scraping techniques, using Python libraries (e.g., Beautiful Soup). Specifically, the server calls the Amazon API to obtain the user's purchase history data and stores it in a database.

[0338] Data analysis and classification

[0339] The server analyzes the stored consumption history data using Python's natural language processing (NLP) library (e.g., spaCy). Each transaction is classified into a category (e.g., food, entertainment, transportation) based on specific keywords. For example, data whose "item_name" contains the keyword "groceries" is classified into the "food" category.

[0340] Statistical analysis and comparison

[0341] The server calculates the total amount spent for each category and performs analysis using an SQL database or statistical analysis software (e.g., R, Pandas). The server then compares the data of other users with similar attributes to evaluate the user's consumption patterns. The results of this evaluation are notified to the user via their device. For example, the server calculates the total amount spent in the "food" category for each month and notifies the user that "your food consumption is 10% above average."

[0342] Future consumption forecast

[0343] The server builds a machine learning model (e.g., Scikit-learn, TensorFlow) based on past consumption data and predicts future consumption. The predicted results are notified to the user via the device. For example, the server may notify the user that "next month's consumption will be 45,000 yen."

[0344] Combining Emotion Engines

[0345] The server analyzes the user's input data (e.g., text, voice, facial expressions) and recognizes their emotional state using emotion recognition algorithms and machine learning models. This utilizes Microsoft Azure's emotion API, among others. If the user inputs, "I've been feeling stressed lately," the server recognizes this as a "negative emotion" and generates advice on consumer behavior based on the emotional data. For example, it may recommend "products that help with relaxation" and suggest, "Why not try a massage chair?"

[0346] Emotion-based predictions

[0347] The server builds a composite consumption prediction model that includes emotional data, providing more accurate consumption predictions. When a user inputs "My income has decreased," the server calculates the predicted consumption amount for the next month and predicts that "next month's consumption amount will be 35,000 yen." This result is notified by the device.

[0348] Emotional suggestions

[0349] The server adjusts the optimal shopping method based on emotional data. When a user inputs "I'm feeling stressed because my expenses are increasing," the server uses market data to suggest "a new smartphone plan that will help you save money." This suggestion is displayed on the device as "There is a plan that will save you 1,500 yen per month."

[0350] In this way, the system of the present invention combines consumption history data with emotion recognition to analyze the user's consumption behavior in detail and provide optimal advice and suggestions, allowing the user to achieve efficient and planned consumption behavior.

[0351] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0352] Step 1: Data collection

[0353] The server collects user consumption history data via APIs, such as from electronic services, credit cards, and online shopping, and stores the data in a database in JSON format using API calls and web scraping techniques.

[0354] Input: Historical consumption data based on API calls

[0355] Output: Saved consumption history data (JSON format)

[0356] Specific behavior:

[0357] The server calls the Amazon API to retrieve the user's purchase history data.

[0358] The acquired data is stored in a MySQL database in JSON format with fields such as "purchase_date", "item_name", and "amount".

[0359] Step 2: Data analysis and classification

[0360] The server analyzes the stored consumption history data using natural language processing (NLP) techniques and categorizes each transaction. A Python NLP library (e.g., spaCy) is used.

[0361] Input: Saved consumption history data (JSON format)

[0362] Output: Historical consumption data broken down by category

[0363] Specific behavior:

[0364] The server classifies data whose "item_name" contains the keyword "groceries" into the "food" category.

[0365] Uses NLP models to automatically assign categories to each purchased item.

[0366] Step 3: Statistical analysis and comparison

[0367] The server calculates the total amount spent for each category and performs statistical analysis. It compares the data with other users with similar attributes using an SQL database and statistical analysis software (e.g., R, Pandas).

[0368] Input: Historical consumption data broken down by category

[0369] Output: Statistical data and evaluation of user consumption patterns

[0370] Specific behavior:

[0371] The server calculates the total amount spent in the "food" category for each month.

[0372] It compares data with similar users and generates an assessment such as "Your food spending is 10% above average."

[0373] Step 4: Forecast future consumption

[0374] The server builds a machine learning model based on past consumption data and predicts future consumption amounts using Scikit-learn and TensorFlow.

[0375] Input: Historical consumption data

[0376] Output: Future consumption forecast data

[0377] Specific behavior:

[0378] The server trains a consumption prediction model using data from the past six months.

[0379] The model predicts that next month's consumption will be 45,000 yen.

[0380] Step 5: Emotion Recognition

[0381] The server collects user input data (text, voice, facial expressions) and analyzes emotions using emotion recognition algorithms and machine learning models (e.g., Microsoft Azure's Emotion API).

[0382] Input: User input data (text, voice, facial expressions)

[0383] Output: Recognized emotion data

[0384] Specific behavior:

[0385] The user types, "I've been feeling stressed lately."

[0386] The server analyzes this text and recognizes it as "negative sentiment."

[0387] Step 6: Emotional Advice

[0388] The server generates advice on consumer behavior based on the recognized emotion data, and the advice is sent to the user via the device.

[0389] Input: Recognized emotion data

[0390] Output: Advice on consumer behavior

[0391] Specific behavior:

[0392] The server will select "products that will help you relax" based on your "stress level."

[0393] The device will notify you, "Why not try a massage chair?"

[0394] Step 7: Emotional forecasting

[0395] The server builds a complex consumption prediction model that includes emotional data, providing more accurate consumption predictions.

[0396] Input: Recognized emotion data

[0397] Output: Updated consumption forecast data

[0398] Specific behavior:

[0399] The user types, "My income has decreased."

[0400] The server takes this data and calculates the predicted consumption amount for next month, predicting that ``next month's consumption amount will be 35,000 yen.''

[0401] The terminal notifies the user of this result.

[0402] Step 8: Emotional Suggestion

[0403] The server compares emotional data and user consumption data with the latest market information and suggests the optimal shopping method.

[0404] Input: Recognized emotion data and user consumption data

[0405] Output: Recommendations for the best shopping method

[0406] Specific behavior:

[0407] A user types, "I'm stressed out because my expenses are increasing."

[0408] The server will propose "new, cost-saving smartphone plans" based on market data.

[0409] The device will notify you that "We have a plan that will save you 1,500 yen per month."

[0410] (Application example 2)

[0411] 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."

[0412] Current consumption data analysis systems analyze users' consumption history and suggest financial planning and cost-effective shopping methods, but they do not provide advice on security risks. Furthermore, because the advice does not take into account the user's emotional state, users may overlook fraud risks. Therefore, there is a need for a system that combines users' consumption history data with their emotional state to provide more comprehensive security management and advice.

[0413] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user consumption history data, means for analyzing the collected consumption history data and classifying each transaction by category, means for statistically analyzing the consumption amounts for each classified category, means for evaluating the user's consumption pattern by comparing it with user data of similar attributes, means for notifying the user of the analysis and comparison results, means for recognizing the user's emotional state, and means for providing the user with security risk advice based on the recognized emotional state. This makes it possible to analyze the user's consumption behavior in detail and evaluate and advise on security risks taking the user's emotional state into consideration.

[0414] "User spending history data" is data that includes records of purchases and transactions that a user has made in the past.

[0415] A "transaction" includes information indicating the specific content, amount, date, etc. of an individual purchase or transaction.

[0416] "Classifying by category" means dividing the collected consumption history data into specific categories (e.g., food expenses, transportation expenses, entertainment expenses, etc.).

[0417] "Statistical analysis" means analyzing collected data using statistical methods (e.g., mean, median, variance, etc.).

[0418] "User data with similar attributes" refers to consumption history data of other users with similar attributes such as age, gender, and income.

[0419] "Evaluating consumption patterns" means evaluating and visualizing users' consumption trends and behavior using numbers and graphs.

[0420] "Notifying" means sending the analysis results and advice to the user's device (e.g., a smartphone) and displaying them.

[0421] "Recognizing emotional states" means analyzing emotions (e.g., happiness, anxiety, stress, etc.) from a user's text or voice input.

[0422] "Providing security risk advice" means suggesting specific measures to reduce the risk of fraudulent transactions based on the user's current spending patterns and emotional state.

[0423] To implement this invention, it is necessary to build a system in which a server, terminals, and users work together. The main components of this system include a consumption history data collection and analysis module, an emotion recognition module, a security risk assessment module, and a user notification module.

[0424] Data collection and analysis

[0425] The server collects consumption history data from users' electronic services, credit cards, and online shopping via API. This data is stored in the server's database. The consumption history data is analyzed using natural language processing (NLP) techniques to classify each transaction into categories. Software used for analysis includes Python and its libraries (e.g., NLTK).

[0426] emotion recognition

[0427] To recognize the user's emotional state, the server analyzes the user's text input. Emotion recognition algorithms use NLP techniques and sentiment analysis models. For example, NLTK's SentimentIntensityAnalyzer can be used to evaluate the user's emotional state as a numerical value.

[0428] Security Risk Assessment and Advice

[0429] The server evaluates the user's security risk based on the collected data and sentiment data. It uses clustering techniques (e.g., KMeans) to compare users with similar consumption patterns and calculates a risk score. Python's scikit-learn library is used here.

[0430] Based on the recognized emotional state and risk assessment, the server will provide the user with specific security advice. For example, if a user inputs "I've been worried about my spending lately," the emotion will be recognized as anxiety, and if the risk score is high, advice such as "Enable two-factor authentication" will be generated.

[0431] User Notifications

[0432] The generated advice and risk assessment results are notified to the user via a device (e.g., a smartphone), allowing the user to receive advice in real time.

[0433] Specific examples

[0434] For example, if a user types into the app, "I've been worrying about my spending history lately and it's making me more stressed," that text is sent to an emotion recognition engine, which recognizes the emotion as "anxiety." Meanwhile, spending history data is retrieved and spending patterns are analyzed using a clustering algorithm. If the user is assessed as high risk, the app will display advice such as, "Caution! Please enable two-factor authentication."

[0435] Prompt Sentence Examples

[0436] "I've been feeling stressed lately because I'm worried about my spending history. I'd like some advice on how to alleviate this stress. I'd also like to know what I can do to reduce the risk of fraudulent transactions."

[0437] In this way, the system can integrate consumption history data and emotional data to provide users with more personalized security advice, enabling them to better manage their spending and implement security measures.

[0438] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0439] Step 1:

[0440] The server collects consumption history data from users' electronic services, credit cards, and online shopping via API. It uses the user's identification information and API endpoint as input and stores consumption history data in a database as output. Specifically, it collects information such as the amount, date, and category of each transaction and stores it in JSON format.

[0441] Step 2:

[0442] The server analyzes the collected consumption history data and classifies each transaction by category. It uses the collected consumption history data as input and obtains data classified by category as output. Specifically, it uses natural language processing (NLP) technology to extract category information from each transaction data and stores it in a database by category.

[0443] Step 3:

[0444] The server statistically analyzes the consumption amounts for each categorized item. It uses the categorized consumption data as input and obtains the total and average consumption amounts for each category as output. Specifically, it calculates statistical information such as the total amount and average amount for each category and generates statistical graphs and charts.

[0445] Step 4:

[0446] The server evaluates the user's consumption patterns by comparing them with other user data with similar attributes. It uses the analyzed user consumption data and other user data with similar attributes as input, and obtains the evaluation results of the consumption patterns as output. Specifically, it uses clustering techniques (e.g., KMeans) to compare consumption patterns and evaluate the risk score and user positioning.

[0447] Step 5:

[0448] The server evaluates security risks and provides advice based on the user's consumption data and emotional data. It uses the user's emotional data (input text and voice) and consumption data as input and generates security advice as output. Specifically, it uses an emotion recognition algorithm to analyze the user's emotional state, combines it with the clustering results to perform risk assessment and generate advice.

[0449] Step 6:

[0450] The server sends the generated advice and risk assessment results to the device. The generated advice and assessment results are used as input, and notifications are sent to the user's smartphone or device as output. Specifically, advice is delivered in real time using an API or notification system, and notifications are set up so that the user can check them.

[0451] Step 7:

[0452] The user checks the advice and evaluation results notified on the device and takes necessary measures. The user receives the notified security advice as input and implements security measures as output. Specifically, this involves changing the smartphone settings or enabling new security measures (e.g., two-step authentication).

[0453] 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.

[0454] 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.

[0455] 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.

[0456] [Second embodiment]

[0457] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0458] 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.

[0459] 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).

[0460] 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.

[0461] 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.

[0462] 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).

[0463] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0464] 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.

[0465] 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.

[0466] 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.

[0467] In the smart glasses 214, 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.

[0468] 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."

[0469] The present invention is a system that automatically collects and analyzes a user's consumption history data, performs statistical analysis by expenditure category, predicts future consumption, and suggests advantageous shopping methods, thereby optimizing the user's consumption behavior. Specific embodiments of the system are described below.

[0470] Data collection and classification

[0471] First, the server collects the user's consumption history data. This data includes consumption history using electronic services, credit card usage history, and online shopping records. The server obtains this data through an API and stores it in a database. Next, the server analyzes the stored data. Natural language processing (NLP) technology is used for the analysis, and each transaction is automatically classified into categories.

[0472] Statistical analysis and comparison

[0473] The server generates aggregate data to statistically analyze spending for each category. For example, it calculates the amount spent on food and transportation over the past month. The server then collects statistical data on similar users to compare with data from other users with similar attributes, and evaluates the user's spending patterns relatively. The results of the analysis and comparison are then sent to the device and provided to the user.

[0474] Future consumption forecast

[0475] To predict future spending using past consumption data, the server builds statistical and machine learning models. This allows the server to calculate the user's average monthly spending and predicted spending for a specific period. The device notifies the user of this information and encourages them to plan their spending accordingly.

[0476] Proposals for great shopping deals

[0477] The server collects the latest market information (e.g., smartphone plans, coupons, medical expense deduction information, etc.) and compares it with the user's consumption data. This identifies the best value option, which the device notifies the user. For example, it compares the user's current smartphone plan with the latest plan and suggests a plan with a lower monthly fee.

[0478] Specific examples

[0479] Categorizing and analyzing expenses

[0480] When a user spends 1,000 yen on daily shopping using electronic payment, the server collects this data and categorizes it as "food expenses." The server then analyzes the food expense data for the past three months and generates statistical data on the cumulative amount and monthly fluctuations.

[0481] Consumption forecast

[0482] The server builds a machine learning model based on consumption data from the past six months and calculates a predicted consumption amount of 50,000 yen for the next month. The device notifies the user that "Next month's predicted consumption amount is 50,000 yen," and the user confirms this and sets a budget.

[0483] Great Offers

[0484] The server collects the latest smartphone plans and compares them with the user's current plan. If a plan that is 1,000 yen cheaper per month is available, the device notifies the user. The user receives the proposal that "there is a new smartphone plan that will save you 1,000 yen per month," and considers changing their plan.

[0485] In this way, the personal AI financial assistant system of the present invention analyzes the user's consumption behavior in detail, predicts future expenditures, and proposes optimal consumption plans, thereby reducing the user's wasteful spending and realizing efficient consumption behavior.

[0486] The processing flow will be explained below.

[0487] Detailed processing steps

[0488] Data collection and classification

[0489] Step 1:

[0490] The server obtains consumption history data from the user's electronic services, credit cards, and online shopping via API.

[0491] Step 2:

[0492] The server saves the retrieved data in the database.

[0493] Step 3:

[0494] The server analyzes the stored spending data and extracts detailed information about each transaction (such as the recipient, amount, and date and time of the spending).

[0495] Step 4:

[0496] The server uses natural language processing (NLP) technology to automatically classify each transaction into a category (e.g., food, transportation, entertainment, etc.).

[0497] Statistical analysis and comparison

[0498] Step 5:

[0499] The server calculates the total amount spent for each category and generates statistical data.

[0500] Step 6:

[0501] The server collects statistical data of other users with similar attributes and compares it with the user's data.

[0502] Step 7:

[0503] The server evaluates the user's consumption patterns and identifies in which categories there is a surplus or deficit.

[0504] Step 8:

[0505] The terminal notifies the user of the analysis and comparison results.

[0506] Future consumption forecast

[0507] Step 9:

[0508] The server retrieves historical consumption data from the database.

[0509] Step 10:

[0510] The server builds statistical and machine learning models to learn past consumption patterns.

[0511] Step 11:

[0512] The server uses the model it has built to calculate the expected consumption amount for next month and this fiscal year.

[0513] Step 12:

[0514] The terminal notifies the user of the prediction result.

[0515] Proposals for great shopping deals

[0516] Step 13:

[0517] The server collects the latest market information (e.g., smartphone plans, coupons, medical expense deduction information, etc.) from the Internet.

[0518] Step 14:

[0519] The server retrieves the user's current contract information and consumption patterns from a database.

[0520] Step 15:

[0521] The server compares the collected market information with the user's data and generates optimal proposals.

[0522] Step 16:

[0523] The terminal notifies the user of the suggested information.

[0524] Step 17:

[0525] The user reviews the suggestions and takes action as needed.

[0526] Specific examples

[0527] Step 18:

[0528] When a user spends 1,000 yen at a convenience store using electronic payment, the server collects this data.

[0529] Step 19:

[0530] The server analyzes the collected data and classifies it as "food expenses."

[0531] Step 20:

[0532] The server statistically analyzes food expense data from the past three months and generates cumulative amounts and monthly fluctuations.

[0533] Step 21:

[0534] The server compares the food expenses with the average expenses of similar users and evaluates whether the amount is excessive or insufficient.

[0535] Step 22:

[0536] The device will notify the user that "Your food expenses are higher than average," and the user will confirm this.

[0537] Example 1

[0538] 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."

[0539] As consumer behavior in modern society becomes more complex, it is becoming increasingly difficult for individual users to understand and efficiently manage their own consumption history. Furthermore, the lack of future consumption predictions or suggestions for optimal shopping methods leads to the problem of increased wasteful spending. Therefore, there is a need for a system that can analyze users' consumption behavior in detail and provide effective advice.

[0540] 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.

[0541] In this invention, the server includes means for automatically collecting user consumption history data, means for saving the collected consumption history data in a database, means for analyzing the saved consumption history data using natural language processing technology and classifying each transaction by category, means for statistically analyzing the consumption amounts for each classified category and generating aggregate data, means for relatively evaluating the user's consumption patterns by comparing with data of other users with similar attributes, means for notifying the user of the analysis and comparison results to their terminal, means for building a statistical model or machine learning model based on past consumption data and predicting the user's future consumption amounts, and means for comparing the collected consumption history data with the latest market information and suggesting the most cost-effective shopping methods to the user. This enables users to understand their own consumption behavior in detail, plan future consumption, and shop efficiently.

[0542] "Means for automatically collecting user consumption history data" refers to a system that periodically obtains all transaction data made by a user using the APIs of credit card companies and online shopping sites.

[0543] "Means for storing collected consumption history data in a database" refers to a system that accumulates consumption history data in a database in a structured format, enabling efficient management and retrieval.

[0544] "Means of analyzing using natural language processing technology and classifying each transaction by category" refers to technology that analyzes the text information in consumption history data and automatically classifies it into categories such as food expenses, transportation expenses, and entertainment expenses.

[0545] "Means for statistically analyzing consumption amounts by category and generating aggregated data" refers to a system that calculates totals and average amounts for each category based on collected and classified data, and generates statistical analysis results.

[0546] "Means for relatively evaluating a user's consumption patterns by comparing them with data from other users with similar attributes" refers to a system that identifies similar users based on attributes such as age and occupation, and compares their consumption data with the user's consumption data to evaluate them.

[0547] "Means for notifying the user of the analysis and comparison results" refers to a system that displays and notifies the results of consumption analysis and comparison on devices such as smartphones and PCs.

[0548] "Means of building statistical models or machine learning models to predict future consumption amounts of users" refers to technology that applies predictive algorithms based on past consumption data to estimate future consumption amounts.

[0549] "A means of collecting the latest market information and proposing the most cost-effective shopping methods to users" is a system that obtains the latest pricing plans and discount information from resources on the Internet and proposes the most economical options to users.

[0550] This invention is a system for efficiently managing a user's consumption behavior and reducing wasteful spending. This system automatically collects the user's consumption history data, analyzes the data, performs statistical analysis, and evaluates the user's consumption patterns. Furthermore, it predicts future consumption amounts and suggests optimal shopping methods, thereby optimizing the user's consumption behavior.

[0551] Data collection and storage

[0552] The server automatically collects user spending history data using APIs from credit card companies and online shopping sites. This data includes details of each transaction (e.g., date and time, amount, store name, etc.). The collected data is stored in a structured database. An SQL database is typically used for the database.

[0553] Data analysis and classification

[0554] The server analyzes the stored consumption history data using natural language processing (NLP) techniques. Specifically, it uses Python natural language processing libraries such as spaCy and NLTK to classify each transaction into categories. This process automatically assigns categories such as food, transportation, and entertainment expenses.

[0555] Statistical analysis and comparison

[0556] The server uses Python libraries such as pandas and NumPy to statistically analyze the amount spent for each category. This generates aggregate data such as the total food expenses for the past month and monthly fluctuations. Additionally, methods such as cluster analysis are used to evaluate the user's spending patterns relative to other users with similar attributes (age, occupation, income, etc.). The results of these analyses are sent to devices such as smartphones.

[0557] For example, if a user spends 1,000 yen on everyday shopping, the server collects this data and categorizes it as "food expenses."Then, based on the food expenses data from the past three months, the cumulative amount and monthly fluctuations are statistically analyzed and a notification is sent to the smartphone.

[0558] Future consumption forecast

[0559] The server builds statistical and machine learning models based on past consumption data to predict future consumption amounts. Specifically, it uses machine learning libraries such as scikit-learn, TensorFlow, and PyTorch. This predicted data is sent to the device, encouraging users to plan their consumption behavior.

[0560] Example prompt:

[0561] "Calculate your predicted spending for next month based on your spending data from the past six months."

[0562] Proposals for great shopping deals

[0563] The server collects the latest market information from internet resources (news sites, corporate APIs, etc.). It uses web scraping technology to obtain the latest smartphone pricing plans and discount information and compares it with the user's consumption data. It identifies the most economical option and notifies the device. For example, it may notify the user with a suggestion such as, "We have a new smartphone plan that will save you 1,000 yen per month."

[0564] Example prompt:

[0565] "Check out the latest smartphone pricing plans and compare them to your current plan."

[0566] In this way, the system of the present invention realizes efficient consumption behavior by analyzing the user's consumption behavior in detail, predicting future expenditures, and encouraging optimal consumption.

[0567] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0568] Step 1: Data collection

[0569] The server collects user spending history data through the APIs of credit card companies and online shopping sites. User authentication information and API key are required as input. The server uses this information to send API requests and retrieve spending history data. The retrieved data is returned in JSON format, including details of each transaction (date and time, amount, store name, etc.).

[0570] Step 2: Save data

[0571] The server saves the collected consumption history data in a database. The input includes consumption history data in JSON format. The server parses it and inserts each transaction into an SQL database. For example, the user ID, date and time, amount, and store name are stored in the corresponding columns. The output is a successful insertion into the database.

[0572] Step 3: Data analysis and categorization

[0573] The server analyzes the stored consumption history data using natural language processing (NLP) techniques. The input includes detailed transaction data retrieved from an SQL database. The server uses a Python natural language processing library (e.g., spaCy) to analyze the description of each transaction and classify it into the appropriate category (e.g., food expenses, transportation expenses). The output is the transaction data with the categories assigned.

[0574] Step 4: Statistical analysis and aggregate data generation

[0575] The server statistically analyzes the expenditures for each classified category. The input includes transaction data with categories assigned. The server uses Python's pandas library to calculate the total and average amounts for each category. As a specific example, it calculates the total amount of food expenses for the past month and monthly fluctuations. The output is statistically analyzed aggregated data.

[0576] Step 5: Compare with similar users

[0577] The server evaluates a user's consumption patterns relative to other users with similar attributes. The input includes the user's attribute data (age, occupation, income, etc.) and consumption data. The server uses cluster analysis to identify similar users and compares their consumption amounts in each category. The output is the relative evaluation result.

[0578] Step 6: Notification of results

[0579] The device notifies the user of the analysis and comparison results sent from the server. The input includes the evaluation result data sent from the server. The device organizes this data and displays it to the user as alerts or notifications. For example, information such as "Your food expenses for the past month are 20% higher than average" is displayed on a smartphone screen. The output is the notification the user receives.

[0580] Step 7: Forecast future consumption

[0581] The server builds statistical and machine learning models based on past consumption data to predict future consumption. The input includes consumption data from the past few months. The server uses machine learning libraries such as scikit-learn and TensorFlow to build linear regression models and other prediction algorithms. The output is predicted data, such as "Next month's predicted consumption is 50,000 yen."

[0582] Step 8: Predictive Data Notification

[0583] The device notifies the user of the forecast data sent from the server. The input includes the forecast data sent from the server. The device organizes this data and displays it as a notification to the user. For example, information such as "Next month's forecast consumption amount is 50,000 yen" is sent to a smartphone as a push notification. The output is the forecast notification received by the user.

[0584] Step 9: Gather market intelligence

[0585] The server collects the latest market information from internet resources. The input includes user consumption data and the latest pricing plans and discount information obtained from web scraping technology and company APIs. The server organizes this information and stores it in a database. The output is the collected latest market information.

[0586] Step 10: Suggestions for great shopping deals

[0587] The server compares the collected market information with the user's consumption data to identify the best value option. The input includes the user's current consumption data and the latest market information. The server calculates the most economical option and sends the result to the device. The device notifies the user with information such as "There is a new smartphone plan that will save you 1,000 yen per month." The output is a notification of the offer that the user receives.

[0588] (Application example 1)

[0589] 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."

[0590] Conventional consumption data analysis systems have difficulty in properly analyzing and predicting users' consumption behavior, and are unable to suggest optimal purchasing methods in a timely manner. As a result, users are unable to efficiently manage their consumption behavior, which often results in wasteful spending. They are also unable to effectively utilize the latest market information, coupons, and discount information. As a result, many users suffer economic disadvantages.

[0591] 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.

[0592] In this invention, the server includes: means for collecting user consumption history data; means for analyzing the collected consumption history data and classifying each transaction by category; means for statistically analyzing the consumption amounts for each category; means for evaluating the user's consumption patterns by comparing them with user data of similar attributes; means for notifying the user of the analysis and comparison results; means for analyzing the user's consumption behavior in real time based on electronic payment information; means for predicting future consumption amounts based on past consumption data; and means for collecting the latest market information and comparing it with the user's consumption data to suggest optimal purchasing methods. This allows users to efficiently manage their consumption behavior and reduce wasteful spending. Users can also receive suggestions for advantageous purchasing methods using the latest market information, coupons, and discount information.

[0593] "User consumption history data" is information about the user's past consumption behavior, including items, amounts, dates and times, stores, and the like.

[0594] "Transaction" refers to each purchase or service use made by a User, including payment details.

[0595] A "category" is a broad group for classifying consumption behavior, and includes specific consumption items such as "food expenses" and "transportation expenses."

[0596] "Electronic payment information" refers to detailed data related to payments made using credit cards or electronic wallets, and serves as basic data for analyzing users' consumption behavior.

[0597] "Statistical analysis" means collecting and classifying data and using mathematical methods to calculate summaries, averages, distributions, etc., to reveal consumption patterns.

[0598] "User data with similar attributes" refers to consumption data of other users who share common characteristics such as age, gender, income range, etc.

[0599] "Consumption patterns" indicate the characteristics and tendencies of a user's consumption behavior, such as frequency, consumption trends by category, and seasonal fluctuations.

[0600] "Latest information" refers to information about new offers and sales in the market, such as coupons, discounts, and pricing plans.

[0601] "Predicting future spending" means predicting the amount of money a user will spend within a certain period of time in the future based on past data.

[0602] "Notifying" means providing the analysis results and suggestions to the user's device so that the user can easily obtain the information.

[0603] A "best value purchase method" refers to the most economical possible option when a user purchases a product or service.

[0604] "Analyzing in real time" means collecting data the moment a consumer behavior occurs and analyzing it immediately.

[0605] The present invention is a system for collecting and analyzing consumption history data of a user and optimizing the consumption behavior of the user based on the collected data. Specific embodiments are described below.

[0606] Data collection and classification

[0607] First, the server collects the user's spending history data. This data includes electronic payment information, online shopping records, and credit card usage history. The server obtains this data through an API and stores it in a database. Next, the server analyzes the stored data and automatically categorizes each transaction. For example, data containing "food" in the transaction description is classified as "food expenses."

[0608] Statistical analysis and comparison

[0609] The server then statistically analyzes the amount spent for each category. This reveals the user's spending patterns. For example, it can determine how much money was spent on food over the past month and how that amount changed. Furthermore, it uses data from other users with similar attributes to evaluate the user's spending patterns relative to their own. The results are then sent to the user via their device.

[0610] Future consumption forecast

[0611] The server builds a machine learning model based on past consumption data to predict future consumption amounts. This allows users to understand their average monthly consumption amount and predicted consumption amounts for a specific period. The prediction results are sent to the device, where users can check them and set their budget.

[0612] Proposals for advantageous purchasing methods

[0613] The server collects the latest market information (e.g., coupons, discounts, pricing plans, etc.) and compares it with the user's consumption data. For example, it compares the user's current smartphone plan with the latest plans and suggests a cheaper plan to the user if one is available. This suggestion is then notified to the user via the device.

[0614] Hardware and software used

[0615] The server uses high-performance server facilities for data collection and analysis, and software such as database management systems (e.g., MySQL), libraries for natural language processing (NLP) techniques (e.g., NLTK), and frameworks for building machine learning models (e.g., TensorFlow).

[0616] Specific examples

[0617] Everyday shopping

[0618] When a user spends 1,000 yen using electronic payment, the server collects this data and categorizes it as "food expenses." The server then analyzes the food expense data from the past three months and generates statistical data on the cumulative amount and monthly fluctuations.

[0619] Consumption forecast

[0620] The server builds a machine learning model based on consumption data from the past six months and calculates a predicted consumption amount of 50,000 yen for the next month. The device notifies the user that "Next month's predicted consumption amount is 50,000 yen," and the user confirms this and sets a budget.

[0621] Great Offers

[0622] The server collects the latest smartphone plans and compares them with the user's current plan. If a plan that is 1,000 yen cheaper per month is available, the device notifies the user. The user receives the proposal that "there is a new smartphone plan that will save you 1,000 yen per month," and considers changing their plan.

[0623] Example prompts to be input to the generative AI model

[0624] The generative AI model is given a prompt like this:

[0625] text

[0626] Design an application that suggests the most economical spending patterns based on a user's spending history. Consider the following data:

[0627] 1. Consumption history by date, amount, and category

[0628] 2. Statistical data from past consumption behavior

[0629] 3. Future spending forecast

[0630] 4. Market updates and coupons

[0631] This system analyzes users' consumption behavior in detail, predicts future expenditures, and proposes optimal consumption plans, thereby reducing wasteful spending and realizing efficient consumption behavior.

[0632] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0633] Step 1: Data collection

[0634] The server collects the user's consumption history data. Specifically, this data includes electronic payment information, online shopping records, credit card usage history, etc., and is retrieved via API and stored in a database. The input is the user's transaction history, and the output is the categorized and stored information in the database.

[0635] Step 2: Data Classification

[0636] The server analyzes the stored data and automatically classifies each transaction into a category. Data classification is performed using natural language processing (NLP) technology. For example, data containing "food" is classified as "food expenses." The input is unclassified transaction data, and the output is data classified by category.

[0637] Step 3: Statistical analysis

[0638] The server statistically analyzes the spending amount for each category, which reveals the user's spending patterns. Specifically, it calculates the spending amount and its fluctuations over the past month. The input is spending data by category, and the output is the statistical analysis results.

[0639] Step 4: Comparative evaluation

[0640] The server uses data from other users with similar attributes to evaluate a user's consumption patterns relatively. By comparing with users with similar attributes, the quality of the user's consumption is evaluated. The input is the user's statistical data and the statistical data of similar users, and the output is the result of the relative evaluation.

[0641] Step 5: Notification

[0642] The terminal notifies the user of the results of the analysis and comparison. Specifically, consumption patterns and comparison results are displayed on the user's smartphone or PC. The input is the analysis and comparison results, and the output is the notification content to the user.

[0643] Step 6: Consumption forecast

[0644] The server builds a machine learning model based on past consumption data and predicts future consumption. For example, the server analyzes consumption data from the past six months and calculates the predicted consumption amount for next month. The input is past consumption data and the output is the predicted consumption amount.

[0645] Step 7: Gather up-to-date information

[0646] The server collects the latest market information (e.g. coupons, discounts, pricing plans, etc.) using web scraping technology or APIs. The input is a market data collection request, and the output is the latest market information.

[0647] Step 8: Propose a good deal

[0648] The server compares the latest collected data with the user's consumption data to suggest the optimal purchasing method. For example, it compares the current smartphone plan with the latest plans and suggests the cheapest plan to the user. The input is the user's consumption data and the latest market information, and the output is the optimal purchasing suggestion.

[0649] Step 9: Proposal Notification

[0650] The device notifies the user of a suggestion for a more advantageous purchasing method. Specifically, the suggestion is displayed on the user's smartphone. The input is the suggestion, and the output is the notification to the user.

[0651] By going through these steps, users can effectively manage their consumption habits and reduce wasteful spending. They can also receive suggestions for great deals by using the latest market information, coupons, and discount information.

[0652] 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.

[0653] The present invention is a system that automatically collects and analyzes a user's consumption history data, classifies it by consumption category, and provides statistical analysis and comparison results with similar users. Furthermore, by combining this system with an emotion engine that recognizes the user's emotions, it is possible to provide advice, predictions, and suggestions based on the user's emotional state. Specific embodiments of this system are described below.

[0654] Data collection and classification

[0655] First, the server retrieves the user's consumption history data from electronic services, credit cards, and online shopping via API. This data is then stored in a database and analyzed by the server. Natural language processing (NLP) technology is used for the analysis, automatically classifying each transaction into categories.

[0656] Statistical analysis and comparison

[0657] The server calculates the total amount spent for each category and generates statistical data. Furthermore, it evaluates the user's spending patterns by collecting and comparing data from other users with similar attributes. The results of this evaluation are then sent to the user via their device.

[0658] Future consumption forecast

[0659] Based on past consumption data, the server builds statistical and machine learning models to predict the user's future consumption amounts. The prediction results are notified to the user via the device, encouraging them to plan their consumption.

[0660] Proposals for great shopping deals

[0661] The server collects the latest market information (e.g., smartphone pricing plans, coupons, tax deduction information, etc.) and compares it with the user's consumption patterns, generating optimal proposals and notifying the user via their device.

[0662] Combining Emotion Engines

[0663] This system also recognizes the user's emotional state by combining it with an emotion engine. The specific processing flow is explained below.

[0664] emotion recognition

[0665] The server analyzes the user's input data (e.g., text, voice, facial expressions) and recognizes the user's emotions. This analysis is performed using emotion recognition algorithms and machine learning models.

[0666] Emotional advice

[0667] If the user is feeling stressed, the server will provide advice on consumer behavior based on the emotional data, such as suggesting the purchase of relaxation products.

[0668] Emotion-based predictions

[0669] The server incorporates the user's emotional data into the consumption prediction model, providing more accurate consumption predictions.

[0670] Emotional suggestions

[0671] The server uses the emotional data to adjust shopping methods and notify the user via the device. For example, if the user is feeling financially anxious, suggestions for cost reduction will be made.

[0672] Specific examples

[0673] Emotion Recognition and Advice

[0674] The server analyzes the text entered by the user, "I've been feeling stressed lately," and recognizes it as a "stressed state."

[0675] The server will advise you on the availability of relaxation-related products and services (e.g., massage, spa).

[0676] Emotion-based predictions

[0677] The server calculates next month's predicted consumption amount as 40,000 yen based on past consumption data and emotional data entered by the user, such as "My income has decreased this month."

[0678] The device notifies the user that "Next month's estimated consumption is 40,000 yen," and the user confirms this and sets a budget.

[0679] Emotional suggestions

[0680] The server collects the latest smartphone plans and, based on emotional data entered by the user, such as "I'm concerned about my recent spending," suggests plans with even lower monthly fees.

[0681] The device will notify the user of a proposal that says, "There is a new smartphone plan that will save you 1,500 yen per month," and the user will review it and consider making the change.

[0682] In this way, by combining consumption history data and emotion recognition, the system of the present invention can analyze the user's consumption behavior in detail and provide optimal advice and suggestions, enabling the user to realize more efficient and planned consumption behavior.

[0683] The processing flow will be explained below.

[0684] Data collection and classification

[0685] Step 1:

[0686] The server obtains the user's electronic payment service, credit card transaction, and online shopping consumption history data via the API.

[0687] Step 2:

[0688] The server stores the acquired consumption history data in a database.

[0689] Step 3:

[0690] The server extracts the details of each stored transaction (recipient, amount, date and time).

[0691] Step 4:

[0692] The server uses natural language processing (NLP) technology to automatically classify each transaction into a category (e.g., food, transportation, entertainment).

[0693] Statistical analysis and comparison

[0694] Step 5:

[0695] The server calculates the total amount spent for each classified category and generates statistical data.

[0696] Step 6:

[0697] The server collects data of other users with similar attributes and compares it with the user's data.

[0698] Step 7:

[0699] The server evaluates the user's consumption patterns and identifies excesses or shortages in certain categories.

[0700] Step 8:

[0701] The terminal notifies the user of the analysis results and the results of comparison with similar users.

[0702] Future consumption forecast

[0703] Step 9:

[0704] The server retrieves historical consumption data from the database.

[0705] Step 10:

[0706] The server builds statistical and machine learning models based on past consumption patterns.

[0707] Step 11:

[0708] The server uses the model it has built to calculate the expected consumption amount for the next month or the current fiscal year.

[0709] Step 12:

[0710] The terminal notifies the user of the prediction result.

[0711] Proposals for great shopping deals

[0712] Step 13:

[0713] The server collects the latest market information (e.g. smartphone plans, coupons, medical expense deduction information, etc.).

[0714] Step 14:

[0715] The server retrieves the user's current contract information and consumption patterns from a database.

[0716] Step 15:

[0717] The server compares the collected market information with the user's data and generates optimal proposals.

[0718] Step 16:

[0719] The terminal notifies the user of the suggested information.

[0720] Step 17:

[0721] The user reviews the suggestions and takes action as needed.

[0722] Combining Emotion Engines

[0723] Step 18:

[0724] The server analyzes the user's input data (e.g., text, voice, facial expressions) using an emotion engine to recognize the user's emotions.

[0725] Step 19:

[0726] The server stores the user's emotion data in a database.

[0727] Step 20:

[0728] The server generates consumption advice based on the emotional data. For example, if the user is feeling stressed, the server will recommend products and services related to relaxation.

[0729] Step 21:

[0730] The server incorporates the emotion data into the consumption prediction model to improve the accuracy of the prediction.

[0731] Step 22:

[0732] The terminal notifies the user of the prediction result.

[0733] Step 23:

[0734] The server then uses the emotional data to tailor its shopping recommendations, for example, suggesting ways to cut costs if the user is feeling financially anxious.

[0735] Step 24:

[0736] The terminal notifies the user of the adjusted proposal.

[0737] Specific examples

[0738] Step 25:

[0739] When a user enters text such as "I've been feeling stressed lately," the server analyzes it using an emotion engine and recognizes it as a "stressed state."

[0740] Step 26:

[0741] The server generates advice suggesting relaxation services (e.g., massage, spa) to reduce stress.

[0742] Step 27:

[0743] The terminal notifies the user of the advice.

[0744] Step 28:

[0745] The server calculates next month's predicted consumption amount as 40,000 yen based on past consumption data and emotional data entered by the user, such as "My income has decreased this month."

[0746] Step 29:

[0747] The device notifies the user that "Next month's estimated consumption is 40,000 yen," and the user confirms this and sets a budget.

[0748] Step 30:

[0749] The server collects the latest smartphone plans and, based on emotional data entered by the user, such as "I'm concerned about my recent spending," suggests plans with even lower monthly fees.

[0750] Step 31:

[0751] The device will notify the user of the proposal, saying, "We have a new smartphone plan that will save you 1,500 yen per month," and the user can review it and consider making the change.

[0752] In this way, by combining consumption history data and emotion recognition, the system of the present invention can analyze the user's consumption behavior in detail and provide optimal advice and suggestions, enabling the user to realize more efficient and planned consumption behavior.

[0753] Example 2

[0754] 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."

[0755] Existing consumption history analysis systems have limitations in analyzing users' consumption data and providing effective feedback. Furthermore, they rarely provide advice or predictions that take into account the user's emotional state, making it difficult to provide optimized recommendations for individual users. Therefore, a system that can analyze users' consumption behavior in detail and with high accuracy and provide advice and recommendations tailored to their emotional state is needed.

[0756] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting user consumption history data, means for analyzing the collected consumption history data and classifying each transaction by category, means for statistically analyzing the consumption amounts for each classified category, means for evaluating the user's consumption pattern by comparing with user data of similar attributes, means for analyzing emotion data and recognizing emotions, means for generating advice on consumption behavior based on the emotion data, and means for notifying the user of the evaluation result and emotion-based advice. This enables advanced analysis based on the user's consumption history data and emotional state, and individual advice and suggestions.

[0757] "Consumption history data" refers to a record of purchases and expenditures made by a user, and is obtained from electronic services, credit card usage history, online shopping, etc.

[0758] "Categorizing by category" means automatically sorting collected consumption history data into categories such as food, entertainment, and transportation based on specific criteria.

[0759] "Statistical analysis" means analyzing collected and classified data using statistical methods such as mean, median, and variance to clarify consumption patterns and overall trends.

[0760] "User data with similar attributes" is a collection of consumption data collected from multiple users with similar attributes such as age, income, and lifestyle.

[0761] "Evaluating consumption patterns" means comparing a user's consumption history data with data of users with similar attributes and analyzing consumption trends and characteristics.

[0762] "Emotion data" is data that indicates the user's emotional state obtained from text, voice, facial expressions, etc.

[0763] "Emotion recognition" refers to analyzing emotion data and determining the user's current emotional state (e.g., joy, sadness, stress, etc.).

[0764] "Consumer behavior advice" refers to action plans and purchasing recommendations provided to users based on collected and analyzed data.

[0765] "Notifying" refers to the means of communicating evaluation results and advice to users, including smartphone push notifications, emails, and in-app notifications.

[0766] The present invention is a system that automatically collects and analyzes a user's consumption history data, classifies it by consumption category, and provides statistical analysis and comparison results with similar users. Furthermore, the present invention uses an emotion engine that recognizes the user's emotions, and provides advice, predictions, and suggestions based on the user's emotional state. Specific embodiments of the system are described below.

[0767] Data collection and classification

[0768] The server obtains consumption history data from users' electronic services, credit cards, and online shopping via API. This data is saved in JSON format and stored in a database. Data collection is performed using API calls and web scraping techniques, using Python libraries (e.g., Beautiful Soup). Specifically, the server calls the Amazon API to obtain the user's purchase history data and stores it in a database.

[0769] Data analysis and classification

[0770] The server analyzes the stored consumption history data using Python's natural language processing (NLP) library (e.g., spaCy). Each transaction is classified into a category (e.g., food, entertainment, transportation) based on specific keywords. For example, data whose "item_name" contains the keyword "groceries" is classified into the "food" category.

[0771] Statistical analysis and comparison

[0772] The server calculates the total amount spent for each category and performs analysis using an SQL database or statistical analysis software (e.g., R, Pandas). The server then compares the data of other users with similar attributes to evaluate the user's consumption patterns. The results of this evaluation are notified to the user via their device. For example, the server calculates the total amount spent in the "food" category for each month and notifies the user that "your food consumption is 10% above average."

[0773] Future consumption forecast

[0774] The server builds a machine learning model (e.g., Scikit-learn, TensorFlow) based on past consumption data and predicts future consumption. The predicted results are notified to the user via the device. For example, the server may notify the user that "next month's consumption will be 45,000 yen."

[0775] Combining Emotion Engines

[0776] The server analyzes the user's input data (e.g., text, voice, facial expressions) and recognizes their emotional state using emotion recognition algorithms and machine learning models. This utilizes Microsoft Azure's emotion API, among others. If the user inputs, "I've been feeling stressed lately," the server recognizes this as a "negative emotion" and generates advice on consumer behavior based on the emotional data. For example, it may recommend "products that help with relaxation" and suggest, "Why not try a massage chair?"

[0777] Emotion-based predictions

[0778] The server builds a composite consumption prediction model that includes emotional data, providing more accurate consumption predictions. When a user inputs "My income has decreased," the server calculates the predicted consumption amount for the next month and predicts that "next month's consumption amount will be 35,000 yen." This result is notified by the device.

[0779] Emotional suggestions

[0780] The server adjusts the optimal shopping method based on emotional data. When a user inputs "I'm feeling stressed because my expenses are increasing," the server uses market data to suggest "a new smartphone plan that will help you save money." This suggestion is displayed on the device as "There is a plan that will save you 1,500 yen per month."

[0781] In this way, the system of the present invention combines consumption history data with emotion recognition to analyze the user's consumption behavior in detail and provide optimal advice and suggestions, allowing the user to achieve efficient and planned consumption behavior.

[0782] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0783] Step 1: Data collection

[0784] The server collects user consumption history data via APIs, such as from electronic services, credit cards, and online shopping, and stores the data in a database in JSON format using API calls and web scraping techniques.

[0785] Input: Historical consumption data based on API calls

[0786] Output: Saved consumption history data (JSON format)

[0787] Specific behavior:

[0788] The server calls the Amazon API to retrieve the user's purchase history data.

[0789] The acquired data is stored in a MySQL database in JSON format with fields such as "purchase_date", "item_name", and "amount".

[0790] Step 2: Data analysis and classification

[0791] The server analyzes the stored consumption history data using natural language processing (NLP) techniques and categorizes each transaction. A Python NLP library (e.g., spaCy) is used.

[0792] Input: Saved consumption history data (JSON format)

[0793] Output: Historical consumption data broken down by category

[0794] Specific behavior:

[0795] The server classifies data whose "item_name" contains the keyword "groceries" into the "food" category.

[0796] Uses NLP models to automatically assign categories to each purchased item.

[0797] Step 3: Statistical analysis and comparison

[0798] The server calculates the total amount spent for each category and performs statistical analysis. It compares the data with other users with similar attributes using an SQL database and statistical analysis software (e.g., R, Pandas).

[0799] Input: Historical consumption data broken down by category

[0800] Output: Statistical data and evaluation of user consumption patterns

[0801] Specific behavior:

[0802] The server calculates the total amount spent in the "food" category for each month.

[0803] It compares data with similar users and generates an assessment such as "Your food spending is 10% above average."

[0804] Step 4: Forecast future consumption

[0805] The server builds a machine learning model based on past consumption data and predicts future consumption amounts using Scikit-learn and TensorFlow.

[0806] Input: Historical consumption data

[0807] Output: Future consumption forecast data

[0808] Specific behavior:

[0809] The server trains a consumption prediction model using data from the past six months.

[0810] The model predicts that next month's consumption will be 45,000 yen.

[0811] Step 5: Emotion Recognition

[0812] The server collects user input data (text, voice, facial expressions) and analyzes emotions using emotion recognition algorithms and machine learning models (e.g., Microsoft Azure's Emotion API).

[0813] Input: User input data (text, voice, facial expressions)

[0814] Output: Recognized emotion data

[0815] Specific behavior:

[0816] The user types, "I've been feeling stressed lately."

[0817] The server analyzes this text and recognizes it as "negative sentiment."

[0818] Step 6: Emotional Advice

[0819] The server generates advice on consumer behavior based on the recognized emotion data, and the advice is sent to the user via the device.

[0820] Input: Recognized emotion data

[0821] Output: Advice on consumer behavior

[0822] Specific behavior:

[0823] The server will select "products that will help you relax" based on your "stress level."

[0824] The device will notify you, "Why not try a massage chair?"

[0825] Step 7: Emotional forecasting

[0826] The server builds a complex consumption prediction model that includes emotional data, providing more accurate consumption predictions.

[0827] Input: Recognized emotion data

[0828] Output: Updated consumption forecast data

[0829] Specific behavior:

[0830] The user types, "My income has decreased."

[0831] The server takes this data and calculates the predicted consumption amount for next month, predicting that ``next month's consumption amount will be 35,000 yen.''

[0832] The terminal notifies the user of this result.

[0833] Step 8: Emotional Suggestion

[0834] The server compares emotional data and user consumption data with the latest market information and suggests the optimal shopping method.

[0835] Input: Recognized emotion data and user consumption data

[0836] Output: Recommendations for the best shopping method

[0837] Specific behavior:

[0838] A user types, "I'm stressed out because my expenses are increasing."

[0839] The server will propose "new, cost-saving smartphone plans" based on market data.

[0840] The device will notify you that "We have a plan that will save you 1,500 yen per month."

[0841] (Application example 2)

[0842] 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."

[0843] Current consumption data analysis systems analyze users' consumption history and suggest financial planning and cost-effective shopping methods, but they do not provide advice on security risks. Furthermore, because the advice does not take into account the user's emotional state, users may overlook fraud risks. Therefore, there is a need for a system that combines users' consumption history data with their emotional state to provide more comprehensive security management and advice.

[0844] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user consumption history data, means for analyzing the collected consumption history data and classifying each transaction by category, means for statistically analyzing the consumption amounts for each classified category, means for evaluating the user's consumption pattern by comparing it with user data of similar attributes, means for notifying the user of the analysis and comparison results, means for recognizing the user's emotional state, and means for providing the user with security risk advice based on the recognized emotional state. This makes it possible to analyze the user's consumption behavior in detail and evaluate and advise on security risks taking the user's emotional state into consideration.

[0845] "User spending history data" is data that includes records of purchases and transactions that a user has made in the past.

[0846] A "transaction" includes information indicating the specific content, amount, date, etc. of an individual purchase or transaction.

[0847] "Classifying by category" means dividing the collected consumption history data into specific categories (e.g., food expenses, transportation expenses, entertainment expenses, etc.).

[0848] "Statistical analysis" means analyzing collected data using statistical methods (e.g., mean, median, variance, etc.).

[0849] "User data with similar attributes" refers to consumption history data of other users with similar attributes such as age, gender, and income.

[0850] "Evaluating consumption patterns" means evaluating and visualizing users' consumption trends and behavior using numbers and graphs.

[0851] "Notifying" means sending the analysis results and advice to the user's device (e.g., a smartphone) and displaying them.

[0852] "Recognizing emotional states" means analyzing emotions (e.g., happiness, anxiety, stress, etc.) from a user's text or voice input.

[0853] "Providing security risk advice" means suggesting specific measures to reduce the risk of fraudulent transactions based on the user's current spending patterns and emotional state.

[0854] To implement this invention, it is necessary to build a system in which a server, terminals, and users work together. The main components of this system include a consumption history data collection and analysis module, an emotion recognition module, a security risk assessment module, and a user notification module.

[0855] Data collection and analysis

[0856] The server collects consumption history data from users' electronic services, credit cards, and online shopping via API. This data is stored in the server's database. The consumption history data is analyzed using natural language processing (NLP) techniques to classify each transaction into categories. Software used for analysis includes Python and its libraries (e.g., NLTK).

[0857] emotion recognition

[0858] To recognize the user's emotional state, the server analyzes the user's text input. Emotion recognition algorithms use NLP techniques and sentiment analysis models. For example, NLTK's SentimentIntensityAnalyzer can be used to evaluate the user's emotional state as a numerical value.

[0859] Security Risk Assessment and Advice

[0860] The server evaluates the user's security risk based on the collected data and sentiment data. It uses clustering techniques (e.g., KMeans) to compare users with similar consumption patterns and calculates a risk score. Python's scikit-learn library is used here.

[0861] Based on the recognized emotional state and risk assessment, the server will provide the user with specific security advice. For example, if a user inputs "I've been worried about my spending lately," the emotion will be recognized as anxiety, and if the risk score is high, advice such as "Enable two-factor authentication" will be generated.

[0862] User Notifications

[0863] The generated advice and risk assessment results are notified to the user via a device (e.g., a smartphone), allowing the user to receive advice in real time.

[0864] Specific examples

[0865] For example, if a user types into the app, "I've been worrying about my spending history lately and it's making me more stressed," that text is sent to an emotion recognition engine, which recognizes the emotion as "anxiety." Meanwhile, spending history data is retrieved and spending patterns are analyzed using a clustering algorithm. If the user is assessed as high risk, the app will display advice such as, "Caution! Please enable two-factor authentication."

[0866] Prompt Sentence Examples

[0867] "I've been feeling stressed lately because I'm worried about my spending history. I'd like some advice on how to alleviate this stress. I'd also like to know what I can do to reduce the risk of fraudulent transactions."

[0868] In this way, the system can integrate consumption history data and emotional data to provide users with more personalized security advice, enabling them to better manage their spending and implement security measures.

[0869] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0870] Step 1:

[0871] The server collects consumption history data from users' electronic services, credit cards, and online shopping via API. It uses the user's identification information and API endpoint as input and stores consumption history data in a database as output. Specifically, it collects information such as the amount, date, and category of each transaction and stores it in JSON format.

[0872] Step 2:

[0873] The server analyzes the collected consumption history data and classifies each transaction by category. It uses the collected consumption history data as input and obtains data classified by category as output. Specifically, it uses natural language processing (NLP) technology to extract category information from each transaction data and stores it in a database by category.

[0874] Step 3:

[0875] The server statistically analyzes the consumption amounts for each categorized item. It uses the categorized consumption data as input and obtains the total and average consumption amounts for each category as output. Specifically, it calculates statistical information such as the total amount and average amount for each category and generates statistical graphs and charts.

[0876] Step 4:

[0877] The server evaluates the user's consumption patterns by comparing them with other user data with similar attributes. It uses the analyzed user consumption data and other user data with similar attributes as input, and obtains the evaluation results of the consumption patterns as output. Specifically, it uses clustering techniques (e.g., KMeans) to compare consumption patterns and evaluate the risk score and user positioning.

[0878] Step 5:

[0879] The server evaluates security risks and provides advice based on the user's consumption data and emotional data. It uses the user's emotional data (input text and voice) and consumption data as input and generates security advice as output. Specifically, it uses an emotion recognition algorithm to analyze the user's emotional state, combines it with the clustering results to perform risk assessment and generate advice.

[0880] Step 6:

[0881] The server sends the generated advice and risk assessment results to the device. The generated advice and assessment results are used as input, and notifications are sent to the user's smartphone or device as output. Specifically, advice is delivered in real time using an API or notification system, and notifications are set up so that the user can check them.

[0882] Step 7:

[0883] The user checks the advice and evaluation results notified on the device and takes necessary measures. The user receives the notified security advice as input and implements security measures as output. Specifically, this involves changing the smartphone settings or enabling new security measures (e.g., two-step authentication).

[0884] 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.

[0885] 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.

[0886] 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.

[0887] [Third embodiment]

[0888] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0889] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0890] 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).

[0891] 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.

[0892] 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.

[0893] 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).

[0894] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] 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.

[0899] 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."

[0900] The present invention is a system that automatically collects and analyzes a user's consumption history data, performs statistical analysis by expenditure category, predicts future consumption, and suggests advantageous shopping methods, thereby optimizing the user's consumption behavior. Specific embodiments of the system are described below.

[0901] Data collection and classification

[0902] First, the server collects the user's consumption history data. This data includes consumption history using electronic services, credit card usage history, and online shopping records. The server obtains this data through an API and stores it in a database. Next, the server analyzes the stored data. Natural language processing (NLP) technology is used for the analysis, and each transaction is automatically classified into categories.

[0903] Statistical analysis and comparison

[0904] The server generates aggregate data to statistically analyze spending for each category. For example, it calculates the amount spent on food and transportation over the past month. The server then collects statistical data on similar users to compare with data from other users with similar attributes, and evaluates the user's spending patterns relatively. The results of the analysis and comparison are then sent to the device and provided to the user.

[0905] Future consumption forecast

[0906] To predict future spending using past consumption data, the server builds statistical and machine learning models. This allows the server to calculate the user's average monthly spending and predicted spending for a specific period. The device notifies the user of this information and encourages them to plan their spending accordingly.

[0907] Proposals for great shopping deals

[0908] The server collects the latest market information (e.g., smartphone plans, coupons, medical expense deduction information, etc.) and compares it with the user's consumption data. This identifies the best value option, which the device notifies the user. For example, it compares the user's current smartphone plan with the latest plan and suggests a plan with a lower monthly fee.

[0909] Specific examples

[0910] Categorizing and analyzing expenses

[0911] When a user spends 1,000 yen on daily shopping using electronic payment, the server collects this data and categorizes it as "food expenses." The server then analyzes the food expense data for the past three months and generates statistical data on the cumulative amount and monthly fluctuations.

[0912] Consumption forecast

[0913] The server builds a machine learning model based on consumption data from the past six months and calculates a predicted consumption amount of 50,000 yen for the next month. The device notifies the user that "Next month's predicted consumption amount is 50,000 yen," and the user confirms this and sets a budget.

[0914] Great Offers

[0915] The server collects the latest smartphone plans and compares them with the user's current plan. If a plan that is 1,000 yen cheaper per month is available, the device notifies the user. The user receives the proposal that "there is a new smartphone plan that will save you 1,000 yen per month," and considers changing their plan.

[0916] In this way, the personal AI financial assistant system of the present invention analyzes the user's consumption behavior in detail, predicts future expenditures, and proposes optimal consumption plans, thereby reducing the user's wasteful spending and realizing efficient consumption behavior.

[0917] The processing flow will be explained below.

[0918] Detailed processing steps

[0919] Data collection and classification

[0920] Step 1:

[0921] The server obtains consumption history data from the user's electronic services, credit cards, and online shopping via API.

[0922] Step 2:

[0923] The server saves the retrieved data in the database.

[0924] Step 3:

[0925] The server analyzes the stored spending data and extracts detailed information about each transaction (such as the recipient, amount, and date and time of the spending).

[0926] Step 4:

[0927] The server uses natural language processing (NLP) technology to automatically classify each transaction into a category (e.g., food, transportation, entertainment, etc.).

[0928] Statistical analysis and comparison

[0929] Step 5:

[0930] The server calculates the total amount spent for each category and generates statistical data.

[0931] Step 6:

[0932] The server collects statistical data of other users with similar attributes and compares it with the user's data.

[0933] Step 7:

[0934] The server evaluates the user's consumption patterns and identifies in which categories there is a surplus or deficit.

[0935] Step 8:

[0936] The terminal notifies the user of the analysis and comparison results.

[0937] Future consumption forecast

[0938] Step 9:

[0939] The server retrieves historical consumption data from the database.

[0940] Step 10:

[0941] The server builds statistical and machine learning models to learn past consumption patterns.

[0942] Step 11:

[0943] The server uses the model it has built to calculate the expected consumption amount for next month and this fiscal year.

[0944] Step 12:

[0945] The terminal notifies the user of the prediction result.

[0946] Proposals for great shopping deals

[0947] Step 13:

[0948] The server collects the latest market information (e.g., smartphone plans, coupons, medical expense deduction information, etc.) from the Internet.

[0949] Step 14:

[0950] The server retrieves the user's current contract information and consumption patterns from a database.

[0951] Step 15:

[0952] The server compares the collected market information with the user's data and generates optimal proposals.

[0953] Step 16:

[0954] The terminal notifies the user of the suggested information.

[0955] Step 17:

[0956] The user reviews the suggestions and takes action as needed.

[0957] Specific examples

[0958] Step 18:

[0959] When a user spends 1,000 yen at a convenience store using electronic payment, the server collects this data.

[0960] Step 19:

[0961] The server analyzes the collected data and classifies it as "food expenses."

[0962] Step 20:

[0963] The server statistically analyzes food expense data from the past three months and generates cumulative amounts and monthly fluctuations.

[0964] Step 21:

[0965] The server compares the food expenses with the average expenses of similar users and evaluates whether the amount is excessive or insufficient.

[0966] Step 22:

[0967] The device will notify the user that "Your food expenses are higher than average," and the user will confirm this.

[0968] Example 1

[0969] 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."

[0970] As consumer behavior in modern society becomes more complex, it is becoming increasingly difficult for individual users to understand and efficiently manage their own consumption history. Furthermore, the lack of future consumption predictions or suggestions for optimal shopping methods leads to the problem of increased wasteful spending. Therefore, there is a need for a system that can analyze users' consumption behavior in detail and provide effective advice.

[0971] 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.

[0972] In this invention, the server includes means for automatically collecting user consumption history data, means for saving the collected consumption history data in a database, means for analyzing the saved consumption history data using natural language processing technology and classifying each transaction by category, means for statistically analyzing the consumption amounts for each classified category and generating aggregate data, means for relatively evaluating the user's consumption patterns by comparing with data of other users with similar attributes, means for notifying the user of the analysis and comparison results to their terminal, means for building a statistical model or machine learning model based on past consumption data and predicting the user's future consumption amounts, and means for comparing the collected consumption history data with the latest market information and suggesting the most cost-effective shopping methods to the user. This enables users to understand their own consumption behavior in detail, plan future consumption, and shop efficiently.

[0973] "Means for automatically collecting user consumption history data" refers to a system that periodically obtains all transaction data made by a user using the APIs of credit card companies and online shopping sites.

[0974] "Means for storing collected consumption history data in a database" refers to a system that accumulates consumption history data in a database in a structured format, enabling efficient management and retrieval.

[0975] "Means of analyzing using natural language processing technology and classifying each transaction by category" refers to technology that analyzes the text information in consumption history data and automatically classifies it into categories such as food expenses, transportation expenses, and entertainment expenses.

[0976] "Means for statistically analyzing consumption amounts by category and generating aggregated data" refers to a system that calculates totals and average amounts for each category based on collected and classified data, and generates statistical analysis results.

[0977] "Means for relatively evaluating a user's consumption patterns by comparing them with data from other users with similar attributes" refers to a system that identifies similar users based on attributes such as age and occupation, and compares their consumption data with the user's consumption data to evaluate them.

[0978] "Means for notifying the user of the analysis and comparison results" refers to a system that displays and notifies the results of consumption analysis and comparison on devices such as smartphones and PCs.

[0979] "Means of building statistical models or machine learning models to predict future consumption amounts of users" refers to technology that applies predictive algorithms based on past consumption data to estimate future consumption amounts.

[0980] "A means of collecting the latest market information and proposing the most cost-effective shopping methods to users" is a system that obtains the latest pricing plans and discount information from resources on the Internet and proposes the most economical options to users.

[0981] This invention is a system for efficiently managing a user's consumption behavior and reducing wasteful spending. This system automatically collects the user's consumption history data, analyzes the data, performs statistical analysis, and evaluates the user's consumption patterns. Furthermore, it predicts future consumption amounts and suggests optimal shopping methods, thereby optimizing the user's consumption behavior.

[0982] Data collection and storage

[0983] The server automatically collects user spending history data using APIs from credit card companies and online shopping sites. This data includes details of each transaction (e.g., date and time, amount, store name, etc.). The collected data is stored in a structured database. An SQL database is typically used for the database.

[0984] Data analysis and classification

[0985] The server analyzes the stored consumption history data using natural language processing (NLP) techniques. Specifically, it uses Python natural language processing libraries such as spaCy and NLTK to classify each transaction into categories. This process automatically assigns categories such as food, transportation, and entertainment expenses.

[0986] Statistical analysis and comparison

[0987] The server uses Python libraries such as pandas and NumPy to statistically analyze the amount spent for each category. This generates aggregate data such as the total food expenses for the past month and monthly fluctuations. Additionally, methods such as cluster analysis are used to evaluate the user's spending patterns relative to other users with similar attributes (age, occupation, income, etc.). The results of these analyses are sent to devices such as smartphones.

[0988] For example, if a user spends 1,000 yen on everyday shopping, the server collects this data and categorizes it as "food expenses."Then, based on the food expenses data from the past three months, the cumulative amount and monthly fluctuations are statistically analyzed and a notification is sent to the smartphone.

[0989] Future consumption forecast

[0990] The server builds statistical and machine learning models based on past consumption data to predict future consumption amounts. Specifically, it uses machine learning libraries such as scikit-learn, TensorFlow, and PyTorch. This predicted data is sent to the device, encouraging users to plan their consumption behavior.

[0991] Example prompt:

[0992] "Calculate your predicted spending for next month based on your spending data from the past six months."

[0993] Proposals for great shopping deals

[0994] The server collects the latest market information from internet resources (news sites, corporate APIs, etc.). It uses web scraping technology to obtain the latest smartphone pricing plans and discount information and compares it with the user's consumption data. It identifies the most economical option and notifies the device. For example, it may notify the user with a suggestion such as, "We have a new smartphone plan that will save you 1,000 yen per month."

[0995] Example prompt:

[0996] "Check out the latest smartphone pricing plans and compare them to your current plan."

[0997] In this way, the system of the present invention realizes efficient consumption behavior by analyzing the user's consumption behavior in detail, predicting future expenditures, and encouraging optimal consumption.

[0998] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0999] Step 1: Data collection

[1000] The server collects user spending history data through the APIs of credit card companies and online shopping sites. User authentication information and API key are required as input. The server uses this information to send API requests and retrieve spending history data. The retrieved data is returned in JSON format, including details of each transaction (date and time, amount, store name, etc.).

[1001] Step 2: Save data

[1002] The server saves the collected consumption history data in a database. The input includes consumption history data in JSON format. The server parses it and inserts each transaction into an SQL database. For example, the user ID, date and time, amount, and store name are stored in the corresponding columns. The output is a successful insertion into the database.

[1003] Step 3: Data analysis and categorization

[1004] The server analyzes the stored consumption history data using natural language processing (NLP) techniques. The input includes detailed transaction data retrieved from an SQL database. The server uses a Python natural language processing library (e.g., spaCy) to analyze the description of each transaction and classify it into the appropriate category (e.g., food expenses, transportation expenses). The output is the transaction data with the categories assigned.

[1005] Step 4: Statistical analysis and aggregate data generation

[1006] The server statistically analyzes the expenditures for each classified category. The input includes transaction data with categories assigned. The server uses Python's pandas library to calculate the total and average amounts for each category. As a specific example, it calculates the total amount of food expenses for the past month and monthly fluctuations. The output is statistically analyzed aggregated data.

[1007] Step 5: Compare with similar users

[1008] The server evaluates a user's consumption patterns relative to other users with similar attributes. The input includes the user's attribute data (age, occupation, income, etc.) and consumption data. The server uses cluster analysis to identify similar users and compares their consumption amounts in each category. The output is the relative evaluation result.

[1009] Step 6: Notification of results

[1010] The device notifies the user of the analysis and comparison results sent from the server. The input includes the evaluation result data sent from the server. The device organizes this data and displays it to the user as alerts or notifications. For example, information such as "Your food expenses for the past month are 20% higher than average" is displayed on a smartphone screen. The output is the notification the user receives.

[1011] Step 7: Forecast future consumption

[1012] The server builds statistical and machine learning models based on past consumption data to predict future consumption. The input includes consumption data from the past few months. The server uses machine learning libraries such as scikit-learn and TensorFlow to build linear regression models and other prediction algorithms. The output is predicted data, such as "Next month's predicted consumption is 50,000 yen."

[1013] Step 8: Predictive Data Notification

[1014] The device notifies the user of the forecast data sent from the server. The input includes the forecast data sent from the server. The device organizes this data and displays it as a notification to the user. For example, information such as "Next month's forecast consumption amount is 50,000 yen" is sent to a smartphone as a push notification. The output is the forecast notification received by the user.

[1015] Step 9: Gather market intelligence

[1016] The server collects the latest market information from internet resources. The input includes user consumption data and the latest pricing plans and discount information obtained from web scraping technology and company APIs. The server organizes this information and stores it in a database. The output is the collected latest market information.

[1017] Step 10: Suggestions for great shopping deals

[1018] The server compares the collected market information with the user's consumption data to identify the best value option. The input includes the user's current consumption data and the latest market information. The server calculates the most economical option and sends the result to the device. The device notifies the user with information such as "There is a new smartphone plan that will save you 1,000 yen per month." The output is a notification of the offer that the user receives.

[1019] (Application example 1)

[1020] 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."

[1021] Conventional consumption data analysis systems have difficulty in properly analyzing and predicting users' consumption behavior, and are unable to suggest optimal purchasing methods in a timely manner. As a result, users are unable to efficiently manage their consumption behavior, which often results in wasteful spending. They are also unable to effectively utilize the latest market information, coupons, and discount information. As a result, many users suffer economic disadvantages.

[1022] 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.

[1023] In this invention, the server includes: means for collecting user consumption history data; means for analyzing the collected consumption history data and classifying each transaction by category; means for statistically analyzing the consumption amounts for each category; means for evaluating the user's consumption patterns by comparing them with user data of similar attributes; means for notifying the user of the analysis and comparison results; means for analyzing the user's consumption behavior in real time based on electronic payment information; means for predicting future consumption amounts based on past consumption data; and means for collecting the latest market information and comparing it with the user's consumption data to suggest optimal purchasing methods. This allows users to efficiently manage their consumption behavior and reduce wasteful spending. Users can also receive suggestions for advantageous purchasing methods using the latest market information, coupons, and discount information.

[1024] "User consumption history data" is information about the user's past consumption behavior, including items, amounts, dates and times, stores, and the like.

[1025] "Transaction" refers to each purchase or service use made by a User, including payment details.

[1026] A "category" is a broad group for classifying consumption behavior, and includes specific consumption items such as "food expenses" and "transportation expenses."

[1027] "Electronic payment information" refers to detailed data related to payments made using credit cards or electronic wallets, and serves as basic data for analyzing users' consumption behavior.

[1028] "Statistical analysis" means collecting and classifying data and using mathematical methods to calculate summaries, averages, distributions, etc., to reveal consumption patterns.

[1029] "User data with similar attributes" refers to consumption data of other users who share common characteristics such as age, gender, income range, etc.

[1030] "Consumption patterns" indicate the characteristics and tendencies of a user's consumption behavior, such as frequency, consumption trends by category, and seasonal fluctuations.

[1031] "Latest information" refers to information about new offers and sales in the market, such as coupons, discounts, and pricing plans.

[1032] "Predicting future spending" means predicting the amount of money a user will spend within a certain period of time in the future based on past data.

[1033] "Notifying" means providing the analysis results and suggestions to the user's device so that the user can easily obtain the information.

[1034] A "best value purchase method" refers to the most economical possible option when a user purchases a product or service.

[1035] "Analyzing in real time" means collecting data the moment a consumer behavior occurs and analyzing it immediately.

[1036] The present invention is a system for collecting and analyzing consumption history data of a user and optimizing the consumption behavior of the user based on the collected data. Specific embodiments are described below.

[1037] Data collection and classification

[1038] First, the server collects the user's spending history data. This data includes electronic payment information, online shopping records, and credit card usage history. The server obtains this data through an API and stores it in a database. Next, the server analyzes the stored data and automatically categorizes each transaction. For example, data containing "food" in the transaction description is classified as "food expenses."

[1039] Statistical analysis and comparison

[1040] The server then statistically analyzes the amount spent for each category. This reveals the user's spending patterns. For example, it can determine how much money was spent on food over the past month and how that amount changed. Furthermore, it uses data from other users with similar attributes to evaluate the user's spending patterns relative to their own. The results are then sent to the user via their device.

[1041] Future consumption forecast

[1042] The server builds a machine learning model based on past consumption data to predict future consumption amounts. This allows users to understand their average monthly consumption amount and predicted consumption amounts for a specific period. The prediction results are sent to the device, where users can check them and set their budget.

[1043] Proposals for advantageous purchasing methods

[1044] The server collects the latest market information (e.g., coupons, discounts, pricing plans, etc.) and compares it with the user's consumption data. For example, it compares the user's current smartphone plan with the latest plans and suggests a cheaper plan to the user if one is available. This suggestion is then notified to the user via the device.

[1045] Hardware and software used

[1046] The server uses high-performance server facilities for data collection and analysis, and software such as database management systems (e.g., MySQL), libraries for natural language processing (NLP) techniques (e.g., NLTK), and frameworks for building machine learning models (e.g., TensorFlow).

[1047] Specific examples

[1048] Everyday shopping

[1049] When a user spends 1,000 yen using electronic payment, the server collects this data and categorizes it as "food expenses." The server then analyzes the food expense data from the past three months and generates statistical data on the cumulative amount and monthly fluctuations.

[1050] Consumption forecast

[1051] The server builds a machine learning model based on consumption data from the past six months and calculates a predicted consumption amount of 50,000 yen for the next month. The device notifies the user that "Next month's predicted consumption amount is 50,000 yen," and the user confirms this and sets a budget.

[1052] Great Offers

[1053] The server collects the latest smartphone plans and compares them with the user's current plan. If a plan that is 1,000 yen cheaper per month is available, the device notifies the user. The user receives the proposal that "there is a new smartphone plan that will save you 1,000 yen per month," and considers changing their plan.

[1054] Example prompts to be input to the generative AI model

[1055] The generative AI model is given a prompt like this:

[1056] text

[1057] Design an application that suggests the most economical spending patterns based on a user's spending history. Consider the following data:

[1058] 1. Consumption history by date, amount, and category

[1059] 2. Statistical data from past consumption behavior

[1060] 3. Future spending forecast

[1061] 4. Market updates and coupons

[1062] This system analyzes users' consumption behavior in detail, predicts future expenditures, and proposes optimal consumption plans, thereby reducing wasteful spending and realizing efficient consumption behavior.

[1063] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1064] Step 1: Data collection

[1065] The server collects the user's consumption history data. Specifically, this data includes electronic payment information, online shopping records, credit card usage history, etc., and is retrieved via API and stored in a database. The input is the user's transaction history, and the output is the categorized and stored information in the database.

[1066] Step 2: Data Classification

[1067] The server analyzes the stored data and automatically classifies each transaction into a category. Data classification is performed using natural language processing (NLP) technology. For example, data containing "food" is classified as "food expenses." The input is unclassified transaction data, and the output is data classified by category.

[1068] Step 3: Statistical analysis

[1069] The server statistically analyzes the spending amount for each category, which reveals the user's spending patterns. Specifically, it calculates the spending amount and its fluctuations over the past month. The input is spending data by category, and the output is the statistical analysis results.

[1070] Step 4: Comparative evaluation

[1071] The server uses data from other users with similar attributes to evaluate a user's consumption patterns relatively. By comparing with users with similar attributes, the quality of the user's consumption is evaluated. The input is the user's statistical data and the statistical data of similar users, and the output is the result of the relative evaluation.

[1072] Step 5: Notification

[1073] The terminal notifies the user of the results of the analysis and comparison. Specifically, consumption patterns and comparison results are displayed on the user's smartphone or PC. The input is the analysis and comparison results, and the output is the notification content to the user.

[1074] Step 6: Consumption forecast

[1075] The server builds a machine learning model based on past consumption data and predicts future consumption. For example, the server analyzes consumption data from the past six months and calculates the predicted consumption amount for next month. The input is past consumption data and the output is the predicted consumption amount.

[1076] Step 7: Gather up-to-date information

[1077] The server collects the latest market information (e.g. coupons, discounts, pricing plans, etc.) using web scraping technology or APIs. The input is a market data collection request, and the output is the latest market information.

[1078] Step 8: Propose a good deal

[1079] The server compares the latest collected data with the user's consumption data to suggest the optimal purchasing method. For example, it compares the current smartphone plan with the latest plans and suggests the cheapest plan to the user. The input is the user's consumption data and the latest market information, and the output is the optimal purchasing suggestion.

[1080] Step 9: Proposal Notification

[1081] The device notifies the user of a suggestion for a more advantageous purchasing method. Specifically, the suggestion is displayed on the user's smartphone. The input is the suggestion, and the output is the notification to the user.

[1082] By going through these steps, users can effectively manage their consumption habits and reduce wasteful spending. They can also receive suggestions for great deals by using the latest market information, coupons, and discount information.

[1083] 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.

[1084] The present invention is a system that automatically collects and analyzes a user's consumption history data, classifies it by consumption category, and provides statistical analysis and comparison results with similar users. Furthermore, by combining this system with an emotion engine that recognizes the user's emotions, it is possible to provide advice, predictions, and suggestions based on the user's emotional state. Specific embodiments of this system are described below.

[1085] Data collection and classification

[1086] First, the server retrieves the user's consumption history data from electronic services, credit cards, and online shopping via API. This data is then stored in a database and analyzed by the server. Natural language processing (NLP) technology is used for the analysis, automatically classifying each transaction into categories.

[1087] Statistical analysis and comparison

[1088] The server calculates the total amount spent for each category and generates statistical data. Furthermore, it evaluates the user's spending patterns by collecting and comparing data from other users with similar attributes. The results of this evaluation are then sent to the user via their device.

[1089] Future consumption forecast

[1090] Based on past consumption data, the server builds statistical and machine learning models to predict the user's future consumption amounts. The prediction results are notified to the user via the device, encouraging them to plan their consumption.

[1091] Proposals for great shopping deals

[1092] The server collects the latest market information (e.g., smartphone pricing plans, coupons, tax deduction information, etc.) and compares it with the user's consumption patterns, generating optimal proposals and notifying the user via their device.

[1093] Combining Emotion Engines

[1094] This system also recognizes the user's emotional state by combining it with an emotion engine. The specific processing flow is explained below.

[1095] emotion recognition

[1096] The server analyzes the user's input data (e.g., text, voice, facial expressions) and recognizes the user's emotions. This analysis is performed using emotion recognition algorithms and machine learning models.

[1097] Emotional advice

[1098] If the user is feeling stressed, the server will provide advice on consumer behavior based on the emotional data, such as suggesting the purchase of relaxation products.

[1099] Emotion-based predictions

[1100] The server incorporates the user's emotional data into the consumption prediction model, providing more accurate consumption predictions.

[1101] Emotional suggestions

[1102] The server uses the emotional data to adjust shopping methods and notify the user via the device. For example, if the user is feeling financially anxious, suggestions for cost reduction will be made.

[1103] Specific examples

[1104] Emotion Recognition and Advice

[1105] The server analyzes the text entered by the user, "I've been feeling stressed lately," and recognizes it as a "stressed state."

[1106] The server will advise you on the availability of relaxation-related products and services (e.g., massage, spa).

[1107] Emotion-based predictions

[1108] The server calculates next month's predicted consumption amount as 40,000 yen based on past consumption data and emotional data entered by the user, such as "My income has decreased this month."

[1109] The device notifies the user that "Next month's estimated consumption is 40,000 yen," and the user confirms this and sets a budget.

[1110] Emotional suggestions

[1111] The server collects the latest smartphone plans and, based on emotional data entered by the user, such as "I'm concerned about my recent spending," suggests plans with even lower monthly fees.

[1112] The device will notify the user of a proposal that says, "There is a new smartphone plan that will save you 1,500 yen per month," and the user will review it and consider making the change.

[1113] In this way, by combining consumption history data and emotion recognition, the system of the present invention can analyze the user's consumption behavior in detail and provide optimal advice and suggestions, enabling the user to realize more efficient and planned consumption behavior.

[1114] The processing flow will be explained below.

[1115] Data collection and classification

[1116] Step 1:

[1117] The server obtains the user's electronic payment service, credit card transaction, and online shopping consumption history data via the API.

[1118] Step 2:

[1119] The server stores the acquired consumption history data in a database.

[1120] Step 3:

[1121] The server extracts the details of each stored transaction (recipient, amount, date and time).

[1122] Step 4:

[1123] The server uses natural language processing (NLP) technology to automatically classify each transaction into a category (e.g., food, transportation, entertainment).

[1124] Statistical analysis and comparison

[1125] Step 5:

[1126] The server calculates the total amount spent for each classified category and generates statistical data.

[1127] Step 6:

[1128] The server collects data of other users with similar attributes and compares it with the user's data.

[1129] Step 7:

[1130] The server evaluates the user's consumption patterns and identifies excesses or shortages in certain categories.

[1131] Step 8:

[1132] The terminal notifies the user of the analysis results and the results of comparison with similar users.

[1133] Future consumption forecast

[1134] Step 9:

[1135] The server retrieves historical consumption data from the database.

[1136] Step 10:

[1137] The server builds statistical and machine learning models based on past consumption patterns.

[1138] Step 11:

[1139] The server uses the model it has built to calculate the expected consumption amount for the next month or the current fiscal year.

[1140] Step 12:

[1141] The terminal notifies the user of the prediction result.

[1142] Proposals for great shopping deals

[1143] Step 13:

[1144] The server collects the latest market information (e.g. smartphone plans, coupons, medical expense deduction information, etc.).

[1145] Step 14:

[1146] The server retrieves the user's current contract information and consumption patterns from a database.

[1147] Step 15:

[1148] The server compares the collected market information with the user's data and generates optimal proposals.

[1149] Step 16:

[1150] The terminal notifies the user of the suggested information.

[1151] Step 17:

[1152] The user reviews the suggestions and takes action as needed.

[1153] Combining Emotion Engines

[1154] Step 18:

[1155] The server analyzes the user's input data (e.g., text, voice, facial expressions) using an emotion engine to recognize the user's emotions.

[1156] Step 19:

[1157] The server stores the user's emotion data in a database.

[1158] Step 20:

[1159] The server generates consumption advice based on the emotional data. For example, if the user is feeling stressed, the server will recommend products and services related to relaxation.

[1160] Step 21:

[1161] The server incorporates the emotion data into the consumption prediction model to improve the accuracy of the prediction.

[1162] Step 22:

[1163] The terminal notifies the user of the prediction result.

[1164] Step 23:

[1165] The server then uses the emotional data to tailor its shopping recommendations, for example, suggesting ways to cut costs if the user is feeling financially anxious.

[1166] Step 24:

[1167] The terminal notifies the user of the adjusted proposal.

[1168] Specific examples

[1169] Step 25:

[1170] When a user enters text such as "I've been feeling stressed lately," the server analyzes it using an emotion engine and recognizes it as a "stressed state."

[1171] Step 26:

[1172] The server generates advice suggesting relaxation services (e.g., massage, spa) to reduce stress.

[1173] Step 27:

[1174] The terminal notifies the user of the advice.

[1175] Step 28:

[1176] The server calculates next month's predicted consumption amount as 40,000 yen based on past consumption data and emotional data entered by the user, such as "My income has decreased this month."

[1177] Step 29:

[1178] The device notifies the user that "Next month's estimated consumption is 40,000 yen," and the user confirms this and sets a budget.

[1179] Step 30:

[1180] The server collects the latest smartphone plans and, based on emotional data entered by the user, such as "I'm concerned about my recent spending," suggests plans with even lower monthly fees.

[1181] Step 31:

[1182] The device will notify the user of the proposal, saying, "We have a new smartphone plan that will save you 1,500 yen per month," and the user can review it and consider making the change.

[1183] In this way, by combining consumption history data and emotion recognition, the system of the present invention can analyze the user's consumption behavior in detail and provide optimal advice and suggestions, enabling the user to realize more efficient and planned consumption behavior.

[1184] Example 2

[1185] 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."

[1186] Existing consumption history analysis systems have limitations in analyzing users' consumption data and providing effective feedback. Furthermore, they rarely provide advice or predictions that take into account the user's emotional state, making it difficult to provide optimized recommendations for individual users. Therefore, a system that can analyze users' consumption behavior in detail and with high accuracy and provide advice and recommendations tailored to their emotional state is needed.

[1187] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting user consumption history data, means for analyzing the collected consumption history data and classifying each transaction by category, means for statistically analyzing the consumption amounts for each classified category, means for evaluating the user's consumption pattern by comparing with user data of similar attributes, means for analyzing emotion data and recognizing emotions, means for generating advice on consumption behavior based on the emotion data, and means for notifying the user of the evaluation result and emotion-based advice. This enables advanced analysis based on the user's consumption history data and emotional state, and individual advice and suggestions.

[1188] "Consumption history data" refers to a record of purchases and expenditures made by a user, and is obtained from electronic services, credit card usage history, online shopping, etc.

[1189] "Categorizing by category" means automatically sorting collected consumption history data into categories such as food, entertainment, and transportation based on specific criteria.

[1190] "Statistical analysis" means analyzing collected and classified data using statistical methods such as mean, median, and variance to clarify consumption patterns and overall trends.

[1191] "User data with similar attributes" is a collection of consumption data collected from multiple users with similar attributes such as age, income, and lifestyle.

[1192] "Evaluating consumption patterns" means comparing a user's consumption history data with data of users with similar attributes and analyzing consumption trends and characteristics.

[1193] "Emotion data" is data that indicates the user's emotional state obtained from text, voice, facial expressions, etc.

[1194] "Emotion recognition" refers to analyzing emotion data and determining the user's current emotional state (e.g., joy, sadness, stress, etc.).

[1195] "Consumer behavior advice" refers to action plans and purchasing recommendations provided to users based on collected and analyzed data.

[1196] "Notifying" refers to the means of communicating evaluation results and advice to users, including smartphone push notifications, emails, and in-app notifications.

[1197] The present invention is a system that automatically collects and analyzes a user's consumption history data, classifies it by consumption category, and provides statistical analysis and comparison results with similar users. Furthermore, the present invention uses an emotion engine that recognizes the user's emotions, and provides advice, predictions, and suggestions based on the user's emotional state. Specific embodiments of the system are described below.

[1198] Data collection and classification

[1199] The server obtains consumption history data from users' electronic services, credit cards, and online shopping via API. This data is saved in JSON format and stored in a database. Data collection is performed using API calls and web scraping techniques, using Python libraries (e.g., Beautiful Soup). Specifically, the server calls the Amazon API to obtain the user's purchase history data and stores it in a database.

[1200] Data analysis and classification

[1201] The server analyzes the stored consumption history data using Python's natural language processing (NLP) library (e.g., spaCy). Each transaction is classified into a category (e.g., food, entertainment, transportation) based on specific keywords. For example, data whose "item_name" contains the keyword "groceries" is classified into the "food" category.

[1202] Statistical analysis and comparison

[1203] The server calculates the total amount spent for each category and performs analysis using an SQL database or statistical analysis software (e.g., R, Pandas). The server then compares the data of other users with similar attributes to evaluate the user's consumption patterns. The results of this evaluation are notified to the user via their device. For example, the server calculates the total amount spent in the "food" category for each month and notifies the user that "your food consumption is 10% above average."

[1204] Future consumption forecast

[1205] The server builds a machine learning model (e.g., Scikit-learn, TensorFlow) based on past consumption data and predicts future consumption. The predicted results are notified to the user via the device. For example, the server may notify the user that "next month's consumption will be 45,000 yen."

[1206] Combining Emotion Engines

[1207] The server analyzes the user's input data (e.g., text, voice, facial expressions) and recognizes their emotional state using emotion recognition algorithms and machine learning models. This utilizes Microsoft Azure's emotion API, among others. If the user inputs, "I've been feeling stressed lately," the server recognizes this as a "negative emotion" and generates advice on consumer behavior based on the emotional data. For example, it may recommend "products that help with relaxation" and suggest, "Why not try a massage chair?"

[1208] Emotion-based predictions

[1209] The server builds a composite consumption prediction model that includes emotional data, providing more accurate consumption predictions. When a user inputs "My income has decreased," the server calculates the predicted consumption amount for the next month and predicts that "next month's consumption amount will be 35,000 yen." This result is notified by the device.

[1210] Emotional suggestions

[1211] The server adjusts the optimal shopping method based on emotional data. When a user inputs "I'm feeling stressed because my expenses are increasing," the server uses market data to suggest "a new smartphone plan that will help you save money." This suggestion is displayed on the device as "There is a plan that will save you 1,500 yen per month."

[1212] In this way, the system of the present invention combines consumption history data with emotion recognition to analyze the user's consumption behavior in detail and provide optimal advice and suggestions, allowing the user to achieve efficient and planned consumption behavior.

[1213] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1214] Step 1: Data collection

[1215] The server collects user consumption history data via APIs, such as from electronic services, credit cards, and online shopping, and stores the data in a database in JSON format using API calls and web scraping techniques.

[1216] Input: Historical consumption data based on API calls

[1217] Output: Saved consumption history data (JSON format)

[1218] Specific behavior:

[1219] The server calls the Amazon API to retrieve the user's purchase history data.

[1220] The acquired data is stored in a MySQL database in JSON format with fields such as "purchase_date", "item_name", and "amount".

[1221] Step 2: Data analysis and classification

[1222] The server analyzes the stored consumption history data using natural language processing (NLP) techniques and categorizes each transaction. A Python NLP library (e.g., spaCy) is used.

[1223] Input: Saved consumption history data (JSON format)

[1224] Output: Historical consumption data broken down by category

[1225] Specific behavior:

[1226] The server classifies data whose "item_name" contains the keyword "groceries" into the "food" category.

[1227] Uses NLP models to automatically assign categories to each purchased item.

[1228] Step 3: Statistical analysis and comparison

[1229] The server calculates the total amount spent for each category and performs statistical analysis. It compares the data with other users with similar attributes using an SQL database and statistical analysis software (e.g., R, Pandas).

[1230] Input: Historical consumption data broken down by category

[1231] Output: Statistical data and evaluation of user consumption patterns

[1232] Specific behavior:

[1233] The server calculates the total amount spent in the "food" category for each month.

[1234] It compares data with similar users and generates an assessment such as "Your food spending is 10% above average."

[1235] Step 4: Forecast future consumption

[1236] The server builds a machine learning model based on past consumption data and predicts future consumption amounts using Scikit-learn and TensorFlow.

[1237] Input: Historical consumption data

[1238] Output: Future consumption forecast data

[1239] Specific behavior:

[1240] The server trains a consumption prediction model using data from the past six months.

[1241] The model predicts that next month's consumption will be 45,000 yen.

[1242] Step 5: Emotion Recognition

[1243] The server collects user input data (text, voice, facial expressions) and analyzes emotions using emotion recognition algorithms and machine learning models (e.g., Microsoft Azure's Emotion API).

[1244] Input: User input data (text, voice, facial expressions)

[1245] Output: Recognized emotion data

[1246] Specific behavior:

[1247] The user types, "I've been feeling stressed lately."

[1248] The server analyzes this text and recognizes it as "negative sentiment."

[1249] Step 6: Emotional Advice

[1250] The server generates advice on consumer behavior based on the recognized emotion data, and the advice is sent to the user via the device.

[1251] Input: Recognized emotion data

[1252] Output: Advice on consumer behavior

[1253] Specific behavior:

[1254] The server will select "products that will help you relax" based on your "stress level."

[1255] The device will notify you, "Why not try a massage chair?"

[1256] Step 7: Emotional forecasting

[1257] The server builds a complex consumption prediction model that includes emotional data, providing more accurate consumption predictions.

[1258] Input: Recognized emotion data

[1259] Output: Updated consumption forecast data

[1260] Specific behavior:

[1261] The user types, "My income has decreased."

[1262] The server takes this data and calculates the predicted consumption amount for next month, predicting that ``next month's consumption amount will be 35,000 yen.''

[1263] The terminal notifies the user of this result.

[1264] Step 8: Emotional Suggestion

[1265] The server compares emotional data and user consumption data with the latest market information and suggests the optimal shopping method.

[1266] Input: Recognized emotion data and user consumption data

[1267] Output: Recommendations for the best shopping method

[1268] Specific behavior:

[1269] A user types, "I'm stressed out because my expenses are increasing."

[1270] The server will propose "new, cost-saving smartphone plans" based on market data.

[1271] The device will notify you that "We have a plan that will save you 1,500 yen per month."

[1272] (Application example 2)

[1273] 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."

[1274] Current consumption data analysis systems analyze users' consumption history and suggest financial planning and cost-effective shopping methods, but they do not provide advice on security risks. Furthermore, because the advice does not take into account the user's emotional state, users may overlook fraud risks. Therefore, there is a need for a system that combines users' consumption history data with their emotional state to provide more comprehensive security management and advice.

[1275] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user consumption history data, means for analyzing the collected consumption history data and classifying each transaction by category, means for statistically analyzing the consumption amounts for each classified category, means for evaluating the user's consumption pattern by comparing it with user data of similar attributes, means for notifying the user of the analysis and comparison results, means for recognizing the user's emotional state, and means for providing the user with security risk advice based on the recognized emotional state. This makes it possible to analyze the user's consumption behavior in detail and evaluate and advise on security risks taking the user's emotional state into consideration.

[1276] "User spending history data" is data that includes records of purchases and transactions that a user has made in the past.

[1277] A "transaction" includes information indicating the specific content, amount, date, etc. of an individual purchase or transaction.

[1278] "Classifying by category" means dividing the collected consumption history data into specific categories (e.g., food expenses, transportation expenses, entertainment expenses, etc.).

[1279] "Statistical analysis" means analyzing collected data using statistical methods (e.g., mean, median, variance, etc.).

[1280] "User data with similar attributes" refers to consumption history data of other users with similar attributes such as age, gender, and income.

[1281] "Evaluating consumption patterns" means evaluating and visualizing users' consumption trends and behavior using numbers and graphs.

[1282] "Notifying" means sending the analysis results and advice to the user's device (e.g., a smartphone) and displaying them.

[1283] "Recognizing emotional states" means analyzing emotions (e.g., happiness, anxiety, stress, etc.) from a user's text or voice input.

[1284] "Providing security risk advice" means suggesting specific measures to reduce the risk of fraudulent transactions based on the user's current spending patterns and emotional state.

[1285] To implement this invention, it is necessary to build a system in which a server, terminals, and users work together. The main components of this system include a consumption history data collection and analysis module, an emotion recognition module, a security risk assessment module, and a user notification module.

[1286] Data collection and analysis

[1287] The server collects consumption history data from users' electronic services, credit cards, and online shopping via API. This data is stored in the server's database. The consumption history data is analyzed using natural language processing (NLP) techniques to classify each transaction into categories. Software used for analysis includes Python and its libraries (e.g., NLTK).

[1288] emotion recognition

[1289] To recognize the user's emotional state, the server analyzes the user's text input. Emotion recognition algorithms use NLP techniques and sentiment analysis models. For example, NLTK's SentimentIntensityAnalyzer can be used to evaluate the user's emotional state as a numerical value.

[1290] Security Risk Assessment and Advice

[1291] The server evaluates the user's security risk based on the collected data and sentiment data. It uses clustering techniques (e.g., KMeans) to compare users with similar consumption patterns and calculates a risk score. Python's scikit-learn library is used here.

[1292] Based on the recognized emotional state and risk assessment, the server will provide the user with specific security advice. For example, if a user inputs "I've been worried about my spending lately," the emotion will be recognized as anxiety, and if the risk score is high, advice such as "Enable two-factor authentication" will be generated.

[1293] User Notifications

[1294] The generated advice and risk assessment results are notified to the user via a device (e.g., a smartphone), allowing the user to receive advice in real time.

[1295] Specific examples

[1296] For example, if a user types into the app, "I've been worrying about my spending history lately and it's making me more stressed," that text is sent to an emotion recognition engine, which recognizes the emotion as "anxiety." Meanwhile, spending history data is retrieved and spending patterns are analyzed using a clustering algorithm. If the user is assessed as high risk, the app will display advice such as, "Caution! Please enable two-factor authentication."

[1297] Prompt Sentence Examples

[1298] "I've been feeling stressed lately because I'm worried about my spending history. I'd like some advice on how to alleviate this stress. I'd also like to know what I can do to reduce the risk of fraudulent transactions."

[1299] In this way, the system can integrate consumption history data and emotional data to provide users with more personalized security advice, enabling them to better manage their spending and implement security measures.

[1300] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1301] Step 1:

[1302] The server collects consumption history data from users' electronic services, credit cards, and online shopping via API. It uses the user's identification information and API endpoint as input and stores consumption history data in a database as output. Specifically, it collects information such as the amount, date, and category of each transaction and stores it in JSON format.

[1303] Step 2:

[1304] The server analyzes the collected consumption history data and classifies each transaction by category. It uses the collected consumption history data as input and obtains data classified by category as output. Specifically, it uses natural language processing (NLP) technology to extract category information from each transaction data and stores it in a database by category.

[1305] Step 3:

[1306] The server statistically analyzes the consumption amounts for each categorized item. It uses the categorized consumption data as input and obtains the total and average consumption amounts for each category as output. Specifically, it calculates statistical information such as the total amount and average amount for each category and generates statistical graphs and charts.

[1307] Step 4:

[1308] The server evaluates the user's consumption patterns by comparing them with other user data with similar attributes. It uses the analyzed user consumption data and other user data with similar attributes as input, and obtains the evaluation results of the consumption patterns as output. Specifically, it uses clustering techniques (e.g., KMeans) to compare consumption patterns and evaluate the risk score and user positioning.

[1309] Step 5:

[1310] The server evaluates security risks and provides advice based on the user's consumption data and emotional data. It uses the user's emotional data (input text and voice) and consumption data as input and generates security advice as output. Specifically, it uses an emotion recognition algorithm to analyze the user's emotional state, combines it with the clustering results to perform risk assessment and generate advice.

[1311] Step 6:

[1312] The server sends the generated advice and risk assessment results to the device. The generated advice and assessment results are used as input, and notifications are sent to the user's smartphone or device as output. Specifically, advice is delivered in real time using an API or notification system, and notifications are set up so that the user can check them.

[1313] Step 7:

[1314] The user checks the advice and evaluation results notified on the device and takes necessary measures. The user receives the notified security advice as input and implements security measures as output. Specifically, this involves changing the smartphone settings or enabling new security measures (e.g., two-step authentication).

[1315] 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.

[1316] 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.

[1317] 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.

[1318] [Fourth embodiment]

[1319] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1320] 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.

[1321] 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).

[1322] 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.

[1323] 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.

[1324] 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).

[1325] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1326] 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.

[1327] 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.

[1328] 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.

[1329] 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.

[1330] 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.

[1331] 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."

[1332] The present invention is a system that automatically collects and analyzes a user's consumption history data, performs statistical analysis by expenditure category, predicts future consumption, and suggests advantageous shopping methods, thereby optimizing the user's consumption behavior. Specific embodiments of the system are described below.

[1333] Data collection and classification

[1334] First, the server collects the user's consumption history data. This data includes consumption history using electronic services, credit card usage history, and online shopping records. The server obtains this data through an API and stores it in a database. Next, the server analyzes the stored data. Natural language processing (NLP) technology is used for the analysis, and each transaction is automatically classified into categories.

[1335] Statistical analysis and comparison

[1336] The server generates aggregate data to statistically analyze spending for each category. For example, it calculates the amount spent on food and transportation over the past month. The server then collects statistical data on similar users to compare with data from other users with similar attributes, and evaluates the user's spending patterns relatively. The results of the analysis and comparison are then sent to the device and provided to the user.

[1337] Future consumption forecast

[1338] To predict future spending using past consumption data, the server builds statistical and machine learning models. This allows the server to calculate the user's average monthly spending and predicted spending for a specific period. The device notifies the user of this information and encourages them to plan their spending accordingly.

[1339] Proposals for great shopping deals

[1340] The server collects the latest market information (e.g., smartphone plans, coupons, medical expense deduction information, etc.) and compares it with the user's consumption data. This identifies the best value option, which the device notifies the user. For example, it compares the user's current smartphone plan with the latest plan and suggests a plan with a lower monthly fee.

[1341] Specific examples

[1342] Categorizing and analyzing expenses

[1343] When a user spends 1,000 yen on daily shopping using electronic payment, the server collects this data and categorizes it as "food expenses." The server then analyzes the food expense data for the past three months and generates statistical data on the cumulative amount and monthly fluctuations.

[1344] Consumption forecast

[1345] The server builds a machine learning model based on consumption data from the past six months and calculates a predicted consumption amount of 50,000 yen for the next month. The device notifies the user that "Next month's predicted consumption amount is 50,000 yen," and the user confirms this and sets a budget.

[1346] Great Offers

[1347] The server collects the latest smartphone plans and compares them with the user's current plan. If a plan that is 1,000 yen cheaper per month is available, the device notifies the user. The user receives the proposal that "there is a new smartphone plan that will save you 1,000 yen per month," and considers changing their plan.

[1348] In this way, the personal AI financial assistant system of the present invention analyzes the user's consumption behavior in detail, predicts future expenditures, and proposes optimal consumption plans, thereby reducing the user's wasteful spending and realizing efficient consumption behavior.

[1349] The processing flow will be explained below.

[1350] Detailed processing steps

[1351] Data collection and classification

[1352] Step 1:

[1353] The server obtains consumption history data from the user's electronic services, credit cards, and online shopping via API.

[1354] Step 2:

[1355] The server saves the retrieved data in the database.

[1356] Step 3:

[1357] The server analyzes the stored spending data and extracts detailed information about each transaction (such as the recipient, amount, and date and time of the spending).

[1358] Step 4:

[1359] The server uses natural language processing (NLP) technology to automatically classify each transaction into a category (e.g., food, transportation, entertainment, etc.).

[1360] Statistical analysis and comparison

[1361] Step 5:

[1362] The server calculates the total amount spent for each category and generates statistical data.

[1363] Step 6:

[1364] The server collects statistical data of other users with similar attributes and compares it with the user's data.

[1365] Step 7:

[1366] The server evaluates the user's consumption patterns and identifies in which categories there is a surplus or deficit.

[1367] Step 8:

[1368] The terminal notifies the user of the analysis and comparison results.

[1369] Future consumption forecast

[1370] Step 9:

[1371] The server retrieves historical consumption data from the database.

[1372] Step 10:

[1373] The server builds statistical and machine learning models to learn past consumption patterns.

[1374] Step 11:

[1375] The server uses the model it has built to calculate the expected consumption amount for next month and this fiscal year.

[1376] Step 12:

[1377] The terminal notifies the user of the prediction result.

[1378] Proposals for great shopping deals

[1379] Step 13:

[1380] The server collects the latest market information (e.g., smartphone plans, coupons, medical expense deduction information, etc.) from the Internet.

[1381] Step 14:

[1382] The server retrieves the user's current contract information and consumption patterns from a database.

[1383] Step 15:

[1384] The server compares the collected market information with the user's data and generates optimal proposals.

[1385] Step 16:

[1386] The terminal notifies the user of the suggested information.

[1387] Step 17:

[1388] The user reviews the suggestions and takes action as needed.

[1389] Specific examples

[1390] Step 18:

[1391] When a user spends 1,000 yen at a convenience store using electronic payment, the server collects this data.

[1392] Step 19:

[1393] The server analyzes the collected data and classifies it as "food expenses."

[1394] Step 20:

[1395] The server statistically analyzes food expense data from the past three months and generates cumulative amounts and monthly fluctuations.

[1396] Step 21:

[1397] The server compares the food expenses with the average expenses of similar users and evaluates whether the amount is excessive or insufficient.

[1398] Step 22:

[1399] The device will notify the user that "Your food expenses are higher than average," and the user will confirm this.

[1400] Example 1

[1401] 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."

[1402] As consumer behavior in modern society becomes more complex, it is becoming increasingly difficult for individual users to understand and efficiently manage their own consumption history. Furthermore, the lack of future consumption predictions or suggestions for optimal shopping methods leads to the problem of increased wasteful spending. Therefore, there is a need for a system that can analyze users' consumption behavior in detail and provide effective advice.

[1403] 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.

[1404] In this invention, the server includes means for automatically collecting user consumption history data, means for saving the collected consumption history data in a database, means for analyzing the saved consumption history data using natural language processing technology and classifying each transaction by category, means for statistically analyzing the consumption amounts for each classified category and generating aggregate data, means for relatively evaluating the user's consumption patterns by comparing with data of other users with similar attributes, means for notifying the user of the analysis and comparison results to their terminal, means for building a statistical model or machine learning model based on past consumption data and predicting the user's future consumption amounts, and means for comparing the collected consumption history data with the latest market information and suggesting the most cost-effective shopping methods to the user. This enables users to understand their own consumption behavior in detail, plan future consumption, and shop efficiently.

[1405] "Means for automatically collecting user consumption history data" refers to a system that periodically obtains all transaction data made by a user using the APIs of credit card companies and online shopping sites.

[1406] "Means for storing collected consumption history data in a database" refers to a system that accumulates consumption history data in a database in a structured format, enabling efficient management and retrieval.

[1407] "Means of analyzing using natural language processing technology and classifying each transaction by category" refers to technology that analyzes the text information in consumption history data and automatically classifies it into categories such as food expenses, transportation expenses, and entertainment expenses.

[1408] "Means for statistically analyzing consumption amounts by category and generating aggregated data" refers to a system that calculates totals and average amounts for each category based on collected and classified data, and generates statistical analysis results.

[1409] "Means for relatively evaluating a user's consumption patterns by comparing them with data from other users with similar attributes" refers to a system that identifies similar users based on attributes such as age and occupation, and compares their consumption data with the user's consumption data to evaluate them.

[1410] "Means for notifying the user of the analysis and comparison results" refers to a system that displays and notifies the results of consumption analysis and comparison on devices such as smartphones and PCs.

[1411] "Means of building statistical models or machine learning models to predict future consumption amounts of users" refers to technology that applies predictive algorithms based on past consumption data to estimate future consumption amounts.

[1412] "A means of collecting the latest market information and proposing the most cost-effective shopping methods to users" is a system that obtains the latest pricing plans and discount information from resources on the Internet and proposes the most economical options to users.

[1413] This invention is a system for efficiently managing a user's consumption behavior and reducing wasteful spending. This system automatically collects the user's consumption history data, analyzes the data, performs statistical analysis, and evaluates the user's consumption patterns. Furthermore, it predicts future consumption amounts and suggests optimal shopping methods, thereby optimizing the user's consumption behavior.

[1414] Data collection and storage

[1415] The server automatically collects user spending history data using APIs from credit card companies and online shopping sites. This data includes details of each transaction (e.g., date and time, amount, store name, etc.). The collected data is stored in a structured database. An SQL database is typically used for the database.

[1416] Data analysis and classification

[1417] The server analyzes the stored consumption history data using natural language processing (NLP) techniques. Specifically, it uses Python natural language processing libraries such as spaCy and NLTK to classify each transaction into categories. This process automatically assigns categories such as food, transportation, and entertainment expenses.

[1418] Statistical analysis and comparison

[1419] The server uses Python libraries such as pandas and NumPy to statistically analyze the amount spent for each category. This generates aggregate data such as the total food expenses for the past month and monthly fluctuations. Additionally, methods such as cluster analysis are used to evaluate the user's spending patterns relative to other users with similar attributes (age, occupation, income, etc.). The results of these analyses are sent to devices such as smartphones.

[1420] For example, if a user spends 1,000 yen on everyday shopping, the server collects this data and categorizes it as "food expenses."Then, based on the food expenses data from the past three months, the cumulative amount and monthly fluctuations are statistically analyzed and a notification is sent to the smartphone.

[1421] Future consumption forecast

[1422] The server builds statistical and machine learning models based on past consumption data to predict future consumption amounts. Specifically, it uses machine learning libraries such as scikit-learn, TensorFlow, and PyTorch. This predicted data is sent to the device, encouraging users to plan their consumption behavior.

[1423] Example prompt:

[1424] "Calculate your predicted spending for next month based on your spending data from the past six months."

[1425] Proposals for great shopping deals

[1426] The server collects the latest market information from internet resources (news sites, corporate APIs, etc.). It uses web scraping technology to obtain the latest smartphone pricing plans and discount information and compares it with the user's consumption data. It identifies the most economical option and notifies the device. For example, it may notify the user with a suggestion such as, "We have a new smartphone plan that will save you 1,000 yen per month."

[1427] Example prompt:

[1428] "Check out the latest smartphone pricing plans and compare them to your current plan."

[1429] In this way, the system of the present invention realizes efficient consumption behavior by analyzing the user's consumption behavior in detail, predicting future expenditures, and encouraging optimal consumption.

[1430] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1431] Step 1: Data collection

[1432] The server collects user spending history data through the APIs of credit card companies and online shopping sites. User authentication information and API key are required as input. The server uses this information to send API requests and retrieve spending history data. The retrieved data is returned in JSON format, including details of each transaction (date and time, amount, store name, etc.).

[1433] Step 2: Save data

[1434] The server saves the collected consumption history data in a database. The input includes consumption history data in JSON format. The server parses it and inserts each transaction into an SQL database. For example, the user ID, date and time, amount, and store name are stored in the corresponding columns. The output is a successful insertion into the database.

[1435] Step 3: Data analysis and categorization

[1436] The server analyzes the stored consumption history data using natural language processing (NLP) techniques. The input includes detailed transaction data retrieved from an SQL database. The server uses a Python natural language processing library (e.g., spaCy) to analyze the description of each transaction and classify it into the appropriate category (e.g., food expenses, transportation expenses). The output is the transaction data with the categories assigned.

[1437] Step 4: Statistical analysis and aggregate data generation

[1438] The server statistically analyzes the expenditures for each classified category. The input includes transaction data with categories assigned. The server uses Python's pandas library to calculate the total and average amounts for each category. As a specific example, it calculates the total amount of food expenses for the past month and monthly fluctuations. The output is statistically analyzed aggregated data.

[1439] Step 5: Compare with similar users

[1440] The server evaluates a user's consumption patterns relative to other users with similar attributes. The input includes the user's attribute data (age, occupation, income, etc.) and consumption data. The server uses cluster analysis to identify similar users and compares their consumption amounts in each category. The output is the relative evaluation result.

[1441] Step 6: Notification of results

[1442] The device notifies the user of the analysis and comparison results sent from the server. The input includes the evaluation result data sent from the server. The device organizes this data and displays it to the user as alerts or notifications. For example, information such as "Your food expenses for the past month are 20% higher than average" is displayed on a smartphone screen. The output is the notification the user receives.

[1443] Step 7: Forecast future consumption

[1444] The server builds statistical and machine learning models based on past consumption data to predict future consumption. The input includes consumption data from the past few months. The server uses machine learning libraries such as scikit-learn and TensorFlow to build linear regression models and other prediction algorithms. The output is predicted data, such as "Next month's predicted consumption is 50,000 yen."

[1445] Step 8: Predictive Data Notification

[1446] The device notifies the user of the forecast data sent from the server. The input includes the forecast data sent from the server. The device organizes this data and displays it as a notification to the user. For example, information such as "Next month's forecast consumption amount is 50,000 yen" is sent to a smartphone as a push notification. The output is the forecast notification received by the user.

[1447] Step 9: Gather market intelligence

[1448] The server collects the latest market information from internet resources. The input includes user consumption data and the latest pricing plans and discount information obtained from web scraping technology and company APIs. The server organizes this information and stores it in a database. The output is the collected latest market information.

[1449] Step 10: Suggestions for great shopping deals

[1450] The server compares the collected market information with the user's consumption data to identify the best value option. The input includes the user's current consumption data and the latest market information. The server calculates the most economical option and sends the result to the device. The device notifies the user with information such as "There is a new smartphone plan that will save you 1,000 yen per month." The output is a notification of the offer that the user receives.

[1451] (Application example 1)

[1452] 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."

[1453] Conventional consumption data analysis systems have difficulty in properly analyzing and predicting users' consumption behavior, and are unable to suggest optimal purchasing methods in a timely manner. As a result, users are unable to efficiently manage their consumption behavior, which often results in wasteful spending. They are also unable to effectively utilize the latest market information, coupons, and discount information. As a result, many users suffer economic disadvantages.

[1454] 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.

[1455] In this invention, the server includes: means for collecting user consumption history data; means for analyzing the collected consumption history data and classifying each transaction by category; means for statistically analyzing the consumption amounts for each category; means for evaluating the user's consumption patterns by comparing them with user data of similar attributes; means for notifying the user of the analysis and comparison results; means for analyzing the user's consumption behavior in real time based on electronic payment information; means for predicting future consumption amounts based on past consumption data; and means for collecting the latest market information and comparing it with the user's consumption data to suggest optimal purchasing methods. This allows users to efficiently manage their consumption behavior and reduce wasteful spending. Users can also receive suggestions for advantageous purchasing methods using the latest market information, coupons, and discount information.

[1456] "User consumption history data" is information about the user's past consumption behavior, including items, amounts, dates and times, stores, and the like.

[1457] "Transaction" refers to each purchase or service use made by a User, including payment details.

[1458] A "category" is a broad group for classifying consumption behavior, and includes specific consumption items such as "food expenses" and "transportation expenses."

[1459] "Electronic payment information" refers to detailed data related to payments made using credit cards or electronic wallets, and serves as basic data for analyzing users' consumption behavior.

[1460] "Statistical analysis" means collecting and classifying data and using mathematical methods to calculate summaries, averages, distributions, etc., to reveal consumption patterns.

[1461] "User data with similar attributes" refers to consumption data of other users who share common characteristics such as age, gender, income range, etc.

[1462] "Consumption patterns" indicate the characteristics and tendencies of a user's consumption behavior, such as frequency, consumption trends by category, and seasonal fluctuations.

[1463] "Latest information" refers to information about new offers and sales in the market, such as coupons, discounts, and pricing plans.

[1464] "Predicting future spending" means predicting the amount of money a user will spend within a certain period of time in the future based on past data.

[1465] "Notifying" means providing the analysis results and suggestions to the user's device so that the user can easily obtain the information.

[1466] A "best value purchase method" refers to the most economical possible option when a user purchases a product or service.

[1467] "Analyzing in real time" means collecting data the moment a consumer behavior occurs and analyzing it immediately.

[1468] The present invention is a system for collecting and analyzing consumption history data of a user and optimizing the consumption behavior of the user based on the collected data. Specific embodiments are described below.

[1469] Data collection and classification

[1470] First, the server collects the user's spending history data. This data includes electronic payment information, online shopping records, and credit card usage history. The server obtains this data through an API and stores it in a database. Next, the server analyzes the stored data and automatically categorizes each transaction. For example, data containing "food" in the transaction description is classified as "food expenses."

[1471] Statistical analysis and comparison

[1472] The server then statistically analyzes the amount spent for each category. This reveals the user's spending patterns. For example, it can determine how much money was spent on food over the past month and how that amount changed. Furthermore, it uses data from other users with similar attributes to evaluate the user's spending patterns relative to their own. The results are then sent to the user via their device.

[1473] Future consumption forecast

[1474] The server builds a machine learning model based on past consumption data to predict future consumption amounts. This allows users to understand their average monthly consumption amount and predicted consumption amounts for a specific period. The prediction results are sent to the device, where users can check them and set their budget.

[1475] Proposals for advantageous purchasing methods

[1476] The server collects the latest market information (e.g., coupons, discounts, pricing plans, etc.) and compares it with the user's consumption data. For example, it compares the user's current smartphone plan with the latest plans and suggests a cheaper plan to the user if one is available. This suggestion is then notified to the user via the device.

[1477] Hardware and software used

[1478] The server uses high-performance server facilities for data collection and analysis, and software such as database management systems (e.g., MySQL), libraries for natural language processing (NLP) techniques (e.g., NLTK), and frameworks for building machine learning models (e.g., TensorFlow).

[1479] Specific examples

[1480] Everyday shopping

[1481] When a user spends 1,000 yen using electronic payment, the server collects this data and categorizes it as "food expenses." The server then analyzes the food expense data from the past three months and generates statistical data on the cumulative amount and monthly fluctuations.

[1482] Consumption forecast

[1483] The server builds a machine learning model based on consumption data from the past six months and calculates a predicted consumption amount of 50,000 yen for the next month. The device notifies the user that "Next month's predicted consumption amount is 50,000 yen," and the user confirms this and sets a budget.

[1484] Great Offers

[1485] The server collects the latest smartphone plans and compares them with the user's current plan. If a plan that is 1,000 yen cheaper per month is available, the device notifies the user. The user receives the proposal that "there is a new smartphone plan that will save you 1,000 yen per month," and considers changing their plan.

[1486] Example prompts to be input to the generative AI model

[1487] The generative AI model is given a prompt like this:

[1488] text

[1489] Design an application that suggests the most economical spending patterns based on a user's spending history. Consider the following data:

[1490] 1. Consumption history by date, amount, and category

[1491] 2. Statistical data from past consumption behavior

[1492] 3. Future spending forecast

[1493] 4. Market updates and coupons

[1494] This system analyzes users' consumption behavior in detail, predicts future expenditures, and proposes optimal consumption plans, thereby reducing wasteful spending and realizing efficient consumption behavior.

[1495] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1496] Step 1: Data collection

[1497] The server collects the user's consumption history data. Specifically, this data includes electronic payment information, online shopping records, credit card usage history, etc., and is retrieved via API and stored in a database. The input is the user's transaction history, and the output is the categorized and stored information in the database.

[1498] Step 2: Data Classification

[1499] The server analyzes the stored data and automatically classifies each transaction into a category. Data classification is performed using natural language processing (NLP) technology. For example, data containing "food" is classified as "food expenses." The input is unclassified transaction data, and the output is data classified by category.

[1500] Step 3: Statistical analysis

[1501] The server statistically analyzes the spending amount for each category, which reveals the user's spending patterns. Specifically, it calculates the spending amount and its fluctuations over the past month. The input is spending data by category, and the output is the statistical analysis results.

[1502] Step 4: Comparative evaluation

[1503] The server uses data from other users with similar attributes to evaluate a user's consumption patterns relatively. By comparing with users with similar attributes, the quality of the user's consumption is evaluated. The input is the user's statistical data and the statistical data of similar users, and the output is the result of the relative evaluation.

[1504] Step 5: Notification

[1505] The terminal notifies the user of the results of the analysis and comparison. Specifically, consumption patterns and comparison results are displayed on the user's smartphone or PC. The input is the analysis and comparison results, and the output is the notification content to the user.

[1506] Step 6: Consumption forecast

[1507] The server builds a machine learning model based on past consumption data and predicts future consumption. For example, the server analyzes consumption data from the past six months and calculates the predicted consumption amount for next month. The input is past consumption data and the output is the predicted consumption amount.

[1508] Step 7: Gather up-to-date information

[1509] The server collects the latest market information (e.g. coupons, discounts, pricing plans, etc.) using web scraping technology or APIs. The input is a market data collection request, and the output is the latest market information.

[1510] Step 8: Propose a good deal

[1511] The server compares the latest collected data with the user's consumption data to suggest the optimal purchasing method. For example, it compares the current smartphone plan with the latest plans and suggests the cheapest plan to the user. The input is the user's consumption data and the latest market information, and the output is the optimal purchasing suggestion.

[1512] Step 9: Proposal Notification

[1513] The device notifies the user of a suggestion for a more advantageous purchasing method. Specifically, the suggestion is displayed on the user's smartphone. The input is the suggestion, and the output is the notification to the user.

[1514] By going through these steps, users can effectively manage their consumption habits and reduce wasteful spending. They can also receive suggestions for great deals by using the latest market information, coupons, and discount information.

[1515] 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.

[1516] The present invention is a system that automatically collects and analyzes a user's consumption history data, classifies it by consumption category, and provides statistical analysis and comparison results with similar users. Furthermore, by combining this system with an emotion engine that recognizes the user's emotions, it is possible to provide advice, predictions, and suggestions based on the user's emotional state. Specific embodiments of this system are described below.

[1517] Data collection and classification

[1518] First, the server retrieves the user's consumption history data from electronic services, credit cards, and online shopping via API. This data is then stored in a database and analyzed by the server. Natural language processing (NLP) technology is used for the analysis, automatically classifying each transaction into categories.

[1519] Statistical analysis and comparison

[1520] The server calculates the total amount spent for each category and generates statistical data. Furthermore, it evaluates the user's spending patterns by collecting and comparing data from other users with similar attributes. The results of this evaluation are then sent to the user via their device.

[1521] Future consumption forecast

[1522] Based on past consumption data, the server builds statistical and machine learning models to predict the user's future consumption amounts. The prediction results are notified to the user via the device, encouraging them to plan their consumption.

[1523] Proposals for great shopping deals

[1524] The server collects the latest market information (e.g., smartphone pricing plans, coupons, tax deduction information, etc.) and compares it with the user's consumption patterns, generating optimal proposals and notifying the user via their device.

[1525] Combining Emotion Engines

[1526] This system also recognizes the user's emotional state by combining it with an emotion engine. The specific processing flow is explained below.

[1527] emotion recognition

[1528] The server analyzes the user's input data (e.g., text, voice, facial expressions) and recognizes the user's emotions. This analysis is performed using emotion recognition algorithms and machine learning models.

[1529] Emotional advice

[1530] If the user is feeling stressed, the server will provide advice on consumer behavior based on the emotional data, such as suggesting the purchase of relaxation products.

[1531] Emotion-based predictions

[1532] The server incorporates the user's emotional data into the consumption prediction model, providing more accurate consumption predictions.

[1533] Emotional suggestions

[1534] The server uses the emotional data to adjust shopping methods and notify the user via the device. For example, if the user is feeling financially anxious, suggestions for cost reduction will be made.

[1535] Specific examples

[1536] Emotion Recognition and Advice

[1537] The server analyzes the text entered by the user, "I've been feeling stressed lately," and recognizes it as a "stressed state."

[1538] The server will advise you on the availability of relaxation-related products and services (e.g., massage, spa).

[1539] Emotion-based predictions

[1540] The server calculates next month's predicted consumption amount as 40,000 yen based on past consumption data and emotional data entered by the user, such as "My income has decreased this month."

[1541] The device notifies the user that "Next month's estimated consumption is 40,000 yen," and the user confirms this and sets a budget.

[1542] Emotional suggestions

[1543] The server collects the latest smartphone plans and, based on emotional data entered by the user, such as "I'm concerned about my recent spending," suggests plans with even lower monthly fees.

[1544] The device will notify the user of a proposal that says, "There is a new smartphone plan that will save you 1,500 yen per month," and the user will review it and consider making the change.

[1545] In this way, by combining consumption history data and emotion recognition, the system of the present invention can analyze the user's consumption behavior in detail and provide optimal advice and suggestions, enabling the user to realize more efficient and planned consumption behavior.

[1546] The processing flow will be explained below.

[1547] Data collection and classification

[1548] Step 1:

[1549] The server obtains the user's electronic payment service, credit card transaction, and online shopping consumption history data via the API.

[1550] Step 2:

[1551] The server stores the acquired consumption history data in a database.

[1552] Step 3:

[1553] The server extracts the details of each stored transaction (recipient, amount, date and time).

[1554] Step 4:

[1555] The server uses natural language processing (NLP) technology to automatically classify each transaction into a category (e.g., food, transportation, entertainment).

[1556] Statistical analysis and comparison

[1557] Step 5:

[1558] The server calculates the total amount spent for each classified category and generates statistical data.

[1559] Step 6:

[1560] The server collects data of other users with similar attributes and compares it with the user's data.

[1561] Step 7:

[1562] The server evaluates the user's consumption patterns and identifies excesses or shortages in certain categories.

[1563] Step 8:

[1564] The terminal notifies the user of the analysis results and the results of comparison with similar users.

[1565] Future consumption forecast

[1566] Step 9:

[1567] The server retrieves historical consumption data from the database.

[1568] Step 10:

[1569] The server builds statistical and machine learning models based on past consumption patterns.

[1570] Step 11:

[1571] The server uses the model it has built to calculate the expected consumption amount for the next month or the current fiscal year.

[1572] Step 12:

[1573] The terminal notifies the user of the prediction result.

[1574] Proposals for great shopping deals

[1575] Step 13:

[1576] The server collects the latest market information (e.g. smartphone plans, coupons, medical expense deduction information, etc.).

[1577] Step 14:

[1578] The server retrieves the user's current contract information and consumption patterns from a database.

[1579] Step 15:

[1580] The server compares the collected market information with the user's data and generates optimal proposals.

[1581] Step 16:

[1582] The terminal notifies the user of the suggested information.

[1583] Step 17:

[1584] The user reviews the suggestions and takes action as needed.

[1585] Combining Emotion Engines

[1586] Step 18:

[1587] The server analyzes the user's input data (e.g., text, voice, facial expressions) using an emotion engine to recognize the user's emotions.

[1588] Step 19:

[1589] The server stores the user's emotion data in a database.

[1590] Step 20:

[1591] The server generates consumption advice based on the emotional data. For example, if the user is feeling stressed, the server will recommend products and services related to relaxation.

[1592] Step 21:

[1593] The server incorporates the emotion data into the consumption prediction model to improve the accuracy of the prediction.

[1594] Step 22:

[1595] The terminal notifies the user of the prediction result.

[1596] Step 23:

[1597] The server then uses the emotional data to tailor its shopping recommendations, for example, suggesting ways to cut costs if the user is feeling financially anxious.

[1598] Step 24:

[1599] The terminal notifies the user of the adjusted proposal.

[1600] Specific examples

[1601] Step 25:

[1602] When a user enters text such as "I've been feeling stressed lately," the server analyzes it using an emotion engine and recognizes it as a "stressed state."

[1603] Step 26:

[1604] The server generates advice suggesting relaxation services (e.g., massage, spa) to reduce stress.

[1605] Step 27:

[1606] The terminal notifies the user of the advice.

[1607] Step 28:

[1608] The server calculates next month's predicted consumption amount as 40,000 yen based on past consumption data and emotional data entered by the user, such as "My income has decreased this month."

[1609] Step 29:

[1610] The device notifies the user that "Next month's estimated consumption is 40,000 yen," and the user confirms this and sets a budget.

[1611] Step 30:

[1612] The server collects the latest smartphone plans and, based on emotional data entered by the user, such as "I'm concerned about my recent spending," suggests plans with even lower monthly fees.

[1613] Step 31:

[1614] The device will notify the user of the proposal, saying, "We have a new smartphone plan that will save you 1,500 yen per month," and the user can review it and consider making the change.

[1615] In this way, by combining consumption history data and emotion recognition, the system of the present invention can analyze the user's consumption behavior in detail and provide optimal advice and suggestions, enabling the user to realize more efficient and planned consumption behavior.

[1616] Example 2

[1617] 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."

[1618] Existing consumption history analysis systems have limitations in analyzing users' consumption data and providing effective feedback. Furthermore, they rarely provide advice or predictions that take into account the user's emotional state, making it difficult to provide optimized recommendations for individual users. Therefore, a system that can analyze users' consumption behavior in detail and with high accuracy and provide advice and recommendations tailored to their emotional state is needed.

[1619] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting user consumption history data, means for analyzing the collected consumption history data and classifying each transaction by category, means for statistically analyzing the consumption amounts for each classified category, means for evaluating the user's consumption pattern by comparing with user data of similar attributes, means for analyzing emotion data and recognizing emotions, means for generating advice on consumption behavior based on the emotion data, and means for notifying the user of the evaluation result and emotion-based advice. This enables advanced analysis based on the user's consumption history data and emotional state, and individual advice and suggestions.

[1620] "Consumption history data" refers to a record of purchases and expenditures made by a user, and is obtained from electronic services, credit card usage history, online shopping, etc.

[1621] "Categorizing by category" means automatically sorting collected consumption history data into categories such as food, entertainment, and transportation based on specific criteria.

[1622] "Statistical analysis" means analyzing collected and classified data using statistical methods such as mean, median, and variance to clarify consumption patterns and overall trends.

[1623] "User data with similar attributes" is a collection of consumption data collected from multiple users with similar attributes such as age, income, and lifestyle.

[1624] "Evaluating consumption patterns" means comparing a user's consumption history data with data of users with similar attributes and analyzing consumption trends and characteristics.

[1625] "Emotion data" is data that indicates the user's emotional state obtained from text, voice, facial expressions, etc.

[1626] "Emotion recognition" refers to analyzing emotion data and determining the user's current emotional state (e.g., joy, sadness, stress, etc.).

[1627] "Consumer behavior advice" refers to action plans and purchasing recommendations provided to users based on collected and analyzed data.

[1628] "Notifying" refers to the means of communicating evaluation results and advice to users, including smartphone push notifications, emails, and in-app notifications.

[1629] The present invention is a system that automatically collects and analyzes a user's consumption history data, classifies it by consumption category, and provides statistical analysis and comparison results with similar users. Furthermore, the present invention uses an emotion engine that recognizes the user's emotions, and provides advice, predictions, and suggestions based on the user's emotional state. Specific embodiments of the system are described below.

[1630] Data collection and classification

[1631] The server obtains consumption history data from users' electronic services, credit cards, and online shopping via API. This data is saved in JSON format and stored in a database. Data collection is performed using API calls and web scraping techniques, using Python libraries (e.g., Beautiful Soup). Specifically, the server calls the Amazon API to obtain the user's purchase history data and stores it in a database.

[1632] Data analysis and classification

[1633] The server analyzes the stored consumption history data using Python's natural language processing (NLP) library (e.g., spaCy). Each transaction is classified into a category (e.g., food, entertainment, transportation) based on specific keywords. For example, data whose "item_name" contains the keyword "groceries" is classified into the "food" category.

[1634] Statistical analysis and comparison

[1635] The server calculates the total amount spent for each category and performs analysis using an SQL database or statistical analysis software (e.g., R, Pandas). The server then compares the data of other users with similar attributes to evaluate the user's consumption patterns. The results of this evaluation are notified to the user via their device. For example, the server calculates the total amount spent in the "food" category for each month and notifies the user that "your food consumption is 10% above average."

[1636] Future consumption forecast

[1637] The server builds a machine learning model (e.g., Scikit-learn, TensorFlow) based on past consumption data and predicts future consumption. The predicted results are notified to the user via the device. For example, the server may notify the user that "next month's consumption will be 45,000 yen."

[1638] Combining Emotion Engines

[1639] The server analyzes the user's input data (e.g., text, voice, facial expressions) and recognizes their emotional state using emotion recognition algorithms and machine learning models. This utilizes Microsoft Azure's emotion API, among others. If the user inputs, "I've been feeling stressed lately," the server recognizes this as a "negative emotion" and generates advice on consumer behavior based on the emotional data. For example, it may recommend "products that help with relaxation" and suggest, "Why not try a massage chair?"

[1640] Emotion-based predictions

[1641] The server builds a composite consumption prediction model that includes emotional data, providing more accurate consumption predictions. When a user inputs "My income has decreased," the server calculates the predicted consumption amount for the next month and predicts that "next month's consumption amount will be 35,000 yen." This result is notified by the device.

[1642] Emotional suggestions

[1643] The server adjusts the optimal shopping method based on emotional data. When a user inputs "I'm feeling stressed because my expenses are increasing," the server uses market data to suggest "a new smartphone plan that will help you save money." This suggestion is displayed on the device as "There is a plan that will save you 1,500 yen per month."

[1644] In this way, the system of the present invention combines consumption history data with emotion recognition to analyze the user's consumption behavior in detail and provide optimal advice and suggestions, allowing the user to achieve efficient and planned consumption behavior.

[1645] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1646] Step 1: Data collection

[1647] The server collects user consumption history data via APIs, such as from electronic services, credit cards, and online shopping, and stores the data in a database in JSON format using API calls and web scraping techniques.

[1648] Input: Historical consumption data based on API calls

[1649] Output: Saved consumption history data (JSON format)

[1650] Specific behavior:

[1651] The server calls the Amazon API to retrieve the user's purchase history data.

[1652] The acquired data is stored in a MySQL database in JSON format with fields such as "purchase_date", "item_name", and "amount".

[1653] Step 2: Data analysis and classification

[1654] The server analyzes the stored consumption history data using natural language processing (NLP) techniques and categorizes each transaction. A Python NLP library (e.g., spaCy) is used.

[1655] Input: Saved consumption history data (JSON format)

[1656] Output: Historical consumption data broken down by category

[1657] Specific behavior:

[1658] The server classifies data whose "item_name" contains the keyword "groceries" into the "food" category.

[1659] Uses NLP models to automatically assign categories to each purchased item.

[1660] Step 3: Statistical analysis and comparison

[1661] The server calculates the total amount spent for each category and performs statistical analysis. It compares the data with other users with similar attributes using an SQL database and statistical analysis software (e.g., R, Pandas).

[1662] Input: Historical consumption data broken down by category

[1663] Output: Statistical data and evaluation of user consumption patterns

[1664] Specific behavior:

[1665] The server calculates the total amount spent in the "food" category for each month.

[1666] It compares data with similar users and generates an assessment such as "Your food spending is 10% above average."

[1667] Step 4: Forecast future consumption

[1668] The server builds a machine learning model based on past consumption data and predicts future consumption amounts using Scikit-learn and TensorFlow.

[1669] Input: Historical consumption data

[1670] Output: Future consumption forecast data

[1671] Specific behavior:

[1672] The server trains a consumption prediction model using data from the past six months.

[1673] The model predicts that next month's consumption will be 45,000 yen.

[1674] Step 5: Emotion Recognition

[1675] The server collects user input data (text, voice, facial expressions) and analyzes emotions using emotion recognition algorithms and machine learning models (e.g., Microsoft Azure's Emotion API).

[1676] Input: User input data (text, voice, facial expressions)

[1677] Output: Recognized emotion data

[1678] Specific behavior:

[1679] The user types, "I've been feeling stressed lately."

[1680] The server analyzes this text and recognizes it as "negative sentiment."

[1681] Step 6: Emotional Advice

[1682] The server generates advice on consumer behavior based on the recognized emotion data, and the advice is sent to the user via the device.

[1683] Input: Recognized emotion data

[1684] Output: Advice on consumer behavior

[1685] Specific behavior:

[1686] The server will select "products that will help you relax" based on your "stress level."

[1687] The device will notify you, "Why not try a massage chair?"

[1688] Step 7: Emotional forecasting

[1689] The server builds a complex consumption prediction model that includes emotional data, providing more accurate consumption predictions.

[1690] Input: Recognized emotion data

[1691] Output: Updated consumption forecast data

[1692] Specific behavior:

[1693] The user types, "My income has decreased."

[1694] The server takes this data and calculates the predicted consumption amount for next month, predicting that ``next month's consumption amount will be 35,000 yen.''

[1695] The terminal notifies the user of this result.

[1696] Step 8: Emotional Suggestion

[1697] The server compares emotional data and user consumption data with the latest market information and suggests the optimal shopping method.

[1698] Input: Recognized emotion data and user consumption data

[1699] Output: Recommendations for the best shopping method

[1700] Specific behavior:

[1701] A user types, "I'm stressed out because my expenses are increasing."

[1702] The server will propose "new, cost-saving smartphone plans" based on market data.

[1703] The device will notify you that "We have a plan that will save you 1,500 yen per month."

[1704] (Application example 2)

[1705] 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."

[1706] Current consumption data analysis systems analyze users' consumption history and suggest financial planning and cost-effective shopping methods, but they do not provide advice on security risks. Furthermore, because the advice does not take into account the user's emotional state, users may overlook fraud risks. Therefore, there is a need for a system that combines users' consumption history data with their emotional state to provide more comprehensive security management and advice.

[1707] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user consumption history data, means for analyzing the collected consumption history data and classifying each transaction by category, means for statistically analyzing the consumption amounts for each classified category, means for evaluating the user's consumption pattern by comparing it with user data of similar attributes, means for notifying the user of the analysis and comparison results, means for recognizing the user's emotional state, and means for providing the user with security risk advice based on the recognized emotional state. This makes it possible to analyze the user's consumption behavior in detail and evaluate and advise on security risks taking the user's emotional state into consideration.

[1708] "User spending history data" is data that includes records of purchases and transactions that a user has made in the past.

[1709] A "transaction" includes information indicating the specific content, amount, date, etc. of an individual purchase or transaction.

[1710] "Classifying by category" means dividing the collected consumption history data into specific categories (e.g., food expenses, transportation expenses, entertainment expenses, etc.).

[1711] "Statistical analysis" means analyzing collected data using statistical methods (e.g., mean, median, variance, etc.).

[1712] "User data with similar attributes" refers to consumption history data of other users with similar attributes such as age, gender, and income.

[1713] "Evaluating consumption patterns" means evaluating and visualizing users' consumption trends and behavior using numbers and graphs.

[1714] "Notifying" means sending the analysis results and advice to the user's device (e.g., a smartphone) and displaying them.

[1715] "Recognizing emotional states" means analyzing emotions (e.g., happiness, anxiety, stress, etc.) from a user's text or voice input.

[1716] "Providing security risk advice" means suggesting specific measures to reduce the risk of fraudulent transactions based on the user's current spending patterns and emotional state.

[1717] To implement this invention, it is necessary to build a system in which a server, terminals, and users work together. The main components of this system include a consumption history data collection and analysis module, an emotion recognition module, a security risk assessment module, and a user notification module.

[1718] Data collection and analysis

[1719] The server collects consumption history data from users' electronic services, credit cards, and online shopping via API. This data is stored in the server's database. The consumption history data is analyzed using natural language processing (NLP) techniques to classify each transaction into categories. Software used for analysis includes Python and its libraries (e.g., NLTK).

[1720] emotion recognition

[1721] To recognize the user's emotional state, the server analyzes the user's text input. Emotion recognition algorithms use NLP techniques and sentiment analysis models. For example, NLTK's SentimentIntensityAnalyzer can be used to evaluate the user's emotional state as a numerical value.

[1722] Security Risk Assessment and Advice

[1723] The server evaluates the user's security risk based on the collected data and sentiment data. It uses clustering techniques (e.g., KMeans) to compare users with similar consumption patterns and calculates a risk score. Python's scikit-learn library is used here.

[1724] Based on the recognized emotional state and risk assessment, the server will provide the user with specific security advice. For example, if a user inputs "I've been worried about my spending lately," the emotion will be recognized as anxiety, and if the risk score is high, advice such as "Enable two-factor authentication" will be generated.

[1725] User Notifications

[1726] The generated advice and risk assessment results are notified to the user via a device (e.g., a smartphone), allowing the user to receive advice in real time.

[1727] Specific examples

[1728] For example, if a user types into the app, "I've been worrying about my spending history lately and it's making me more stressed," that text is sent to an emotion recognition engine, which recognizes the emotion as "anxiety." Meanwhile, spending history data is retrieved and spending patterns are analyzed using a clustering algorithm. If the user is assessed as high risk, the app will display advice such as, "Caution! Please enable two-factor authentication."

[1729] Prompt Sentence Examples

[1730] "I've been feeling stressed lately because I'm worried about my spending history. I'd like some advice on how to alleviate this stress. I'd also like to know what I can do to reduce the risk of fraudulent transactions."

[1731] In this way, the system can integrate consumption history data and emotional data to provide users with more personalized security advice, enabling them to better manage their spending and implement security measures.

[1732] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1733] Step 1:

[1734] The server collects consumption history data from users' electronic services, credit cards, and online shopping via API. It uses the user's identification information and API endpoint as input and stores consumption history data in a database as output. Specifically, it collects information such as the amount, date, and category of each transaction and stores it in JSON format.

[1735] Step 2:

[1736] The server analyzes the collected consumption history data and classifies each transaction by category. It uses the collected consumption history data as input and obtains data classified by category as output. Specifically, it uses natural language processing (NLP) technology to extract category information from each transaction data and stores it in a database by category.

[1737] Step 3:

[1738] The server statistically analyzes the consumption amounts for each categorized item. It uses the categorized consumption data as input and obtains the total and average consumption amounts for each category as output. Specifically, it calculates statistical information such as the total amount and average amount for each category and generates statistical graphs and charts.

[1739] Step 4:

[1740] The server evaluates the user's consumption patterns by comparing them with other user data with similar attributes. It uses the analyzed user consumption data and other user data with similar attributes as input, and obtains the evaluation results of the consumption patterns as output. Specifically, it uses clustering techniques (e.g., KMeans) to compare consumption patterns and evaluate the risk score and user positioning.

[1741] Step 5:

[1742] The server evaluates security risks and provides advice based on the user's consumption data and emotional data. It uses the user's emotional data (input text and voice) and consumption data as input and generates security advice as output. Specifically, it uses an emotion recognition algorithm to analyze the user's emotional state, combines it with the clustering results to perform risk assessment and generate advice.

[1743] Step 6:

[1744] The server sends the generated advice and risk assessment results to the device. The generated advice and assessment results are used as input, and notifications are sent to the user's smartphone or device as output. Specifically, advice is delivered in real time using an API or notification system, and notifications are set up so that the user can check them.

[1745] Step 7:

[1746] The user checks the advice and evaluation results notified on the device and takes necessary measures. The user receives the notified security advice as input and implements security measures as output. Specifically, this involves changing the smartphone settings or enabling new security measures (e.g., two-step authentication).

[1747] 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.

[1748] 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.

[1749] 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.

[1750] 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.

[1751] 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.

[1752] 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.

[1753] 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).

[1754] 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.

[1755] 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."

[1756] 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.

[1757] 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).

[1758] 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.

[1759] 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.

[1760] 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.

[1761] 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.

[1762] 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.

[1763] 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.

[1764] 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.

[1765] 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.

[1766] 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.

[1767] 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.

[1768] The following is further disclosed regarding the above embodiment.

[1769] (Claim 1)

[1770] means for collecting user consumption history data;

[1771] A means of analyzing the collected consumption history data and classifying each transaction into categories;

[1772] A means for statistically analyzing the amount of expenditure by classified category;

[1773] means for evaluating a user's consumption patterns by comparing them with user data of similar attributes;

[1774] means for notifying the user of the analysis and comparison results;

[1775] A system including:

[1776] (Claim 2)

[1777] 2. The system according to claim 1, further comprising means for predicting future consumption of the user based on the collected consumption history data.

[1778] (Claim 3)

[1779] The system according to claim 1, further comprising means for comparing the collected consumption history data with the latest market information to suggest advantageous shopping methods.

[1780] "Example 1"

[1781] (Claim 1)

[1782] A means for automatically collecting user consumption history data;

[1783] A means for storing the collected consumption history data in a database;

[1784] A means for analyzing the stored consumption history data using natural language processing technology and categorizing each transaction;

[1785] a means for statistically analyzing the amounts of spending by classified category to generate aggregate data;

[1786] A means for relatively evaluating a user's consumption patterns by comparing them with other user data having similar attributes;

[1787] means for notifying a user of the analysis results and comparison results;

[1788] A system including:

[1789] (Claim 2)

[1790] The system according to claim 1, further comprising means for constructing a statistical model or a machine learning model based on past consumption data and predicting the user's future consumption amount.

[1791] (Claim 3)

[1792] 2. The system according to claim 1, further comprising means for comparing the collected consumption history data with the latest market information and suggesting the most cost-effective shopping method to the user.

[1793] "Application Example 1"

[1794] (Claim 1)

[1795] means for collecting user consumption history data;

[1796] A means of analyzing the collected consumption history data and classifying each transaction into categories;

[1797] A means for statistically analyzing the amount of expenditure by classified category;

[1798] means for evaluating a user's consumption patterns by comparing them with user data of similar attributes;

[1799] a means for notifying the user of the analysis and comparison results;

[1800] A means for analyzing user consumption behavior in real time based on electronic payment information;

[1801] A means of predicting future consumption amounts based on past consumption data;

[1802] A means of collecting the latest market information and comparing it with the user's consumption data to suggest optimal purchasing methods;

[1803] A system including:

[1804] (Claim 2)

[1805] 2. The system according to claim 1, further comprising means for predicting future consumption based on the user data.

[1806] (Claim 3)

[1807] The system according to claim 1, further comprising means for suggesting an optimal purchasing method based on user data in comparison with the latest market information.

[1808] (Claim 4)

[1809] 2. The system according to claim 1, further comprising means for collecting coupon and discount information, comparing the information with the user's consumption data, and suggesting advantageous purchasing methods.

[1810] "Example 2: Combining Emotion Engines"

[1811] (Claim 1)

[1812] means for collecting user consumption history data;

[1813] A means of analyzing the collected consumption history data and classifying each transaction into categories;

[1814] A means for statistically analyzing the amount of expenditure by classified category;

[1815] means for evaluating a user's consumption pa...

Claims

1. means for collecting user consumption history data; A means of analyzing the collected consumption history data and classifying each transaction into categories; A means for statistically analyzing the amount of expenditure by classified category; means for evaluating a user's consumption patterns by comparing them with user data of similar attributes; means for notifying the user of the analysis and comparison results; A system including:

2. The system according to claim 1 , further comprising means for predicting future consumption of the user based on the collected consumption history data.

3. The system according to claim 1, further comprising means for comparing the collected consumption history data with the latest market information to suggest advantageous shopping methods.

Images