System

Abstract

A system is provided.SOLUTION: A system comprising: an input device for a user to input a daily activity content and a current way of thinking; a transmission device for transmitting the input data to a server; a storage device for storing the data received by the server for each user; an analyzing device for generating a future prediction result using a AI model based on the stored data; and an output device for providing the generated prediction result to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In conventional life prediction systems, users have limited means to obtain specific predictions about their future, making it difficult to collect and analyze consistent data. Furthermore, there is a lack of a way for users to easily understand the prediction results and provide specific information to guide them in their next steps. This leaves users with vague anxieties about the future and makes it difficult for them to formulate specific action plans. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including an input means for a user to input their daily activities and current thoughts, a transmission means for transmitting the input data to a server, a storage means for storing the data received by the server for each user, an analysis means for generating future prediction results using an AI model based on the stored data, and an output means for providing the generated prediction results to the user. This allows users to easily input their daily information and receive specific future predictions based on that data. Furthermore, visual display of the prediction results makes it easier for users to plan their next actions.

[0006] "Input means" refers to a device or interface that allows a user to input details of daily activities and current thoughts.

[0007] "Transmission means" refers to a device or method for transmitting data entered by a user to a server.

[0008] "Storage means" refers to a database or storage system that classifies received data by user and records it safely.

[0009] "Analytical means" means algorithms and computing devices that use AI models to generate future predicted results based on stored data.

[0010] The "output means" is a device or interface for providing the generated prediction results to the user and visually displaying them.

[0011] A "user" is a person who accesses the system and inputs details of their daily activities and thoughts.

[0012] A "server" is a computer system capable of receiving, storing, and analyzing transmitted data.

[0013] A "database" is a structured collection of information for systematically storing and managing data received from users.

[0014] An "AI model" is a machine learning algorithm that learns patterns from past data and makes future predictions.

[0015] "Prediction Results" are forecasts and predictions about the future generated based on stored data and AI models. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

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

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0031] 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.

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

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The present invention relates to a system in which a user inputs details of their daily activities and current thoughts, sends the data to a server where it is stored, and generates and provides future prediction results using an AI model. A specific embodiment of this system will be described below.

[0038] User operation

[0039] Users input their daily activities and thoughts through the interface, which is designed as a simple multiple-choice form and includes items such as "work progress," "health status," "relationships," and "study content."

[0040] Examples:

[0041] Users enter their daily information by selecting options such as:

[0042] "Work progress: Good"

[0043] Health condition: A little tired

[0044] "Interpersonal relationships: Good"

[0045] "What I'm learning: I'm learning new technology."

[0046] Data transmission (operation on the terminal side)

[0047] The terminal collects the data entered by the user, converts it into the appropriate format, and sends it to the server, using a secure protocol to ensure the integrity of the data.

[0048] Receiving and saving data (server-side operation)

[0049] The server receives the data sent from the devices, classifies it by user, and stores it in a database. The stored data will be used for later analysis, so the database design ensures efficient data acquisition and storage.

[0050] Data analysis and prediction (server-side operation)

[0051] The AI ​​model makes future predictions based on data stored on the server. The AI ​​model learns from past data and generates future prediction results based on user input data. The prediction results include, for example, the following elements:

[0052] Annual income forecast

[0053] Family structure prediction

[0054] Predicting career progression

[0055] Examples:

[0056] Based on the user's input data, the server generates specific predictions such as "Expected annual income in five years: 6 million yen," "Family composition: married with one child," and "Career progress: section manager position."

[0057] Display of results (user and terminal actions)

[0058] The server sends the generated prediction results to the device, which then displays them to the user in a visually understandable format, such as graphs or charts.

[0059] Examples:

[0060] The user will see the following results on their screen:

[0061] "Expected annual income in 5 years: 6 million yen"

[0062] Family status: Married, one child

[0063] "Career Progression: Section Manager Position"

[0064] Users can create specific action plans based on these prediction results.

[0065] Continuous data collection and improvement

[0066] The system continuously collects data from users and uses that data to train the AI ​​model to improve prediction accuracy, while also accepting user feedback to improve the model.

[0067] In this way, the system of the present invention performs AI analysis based on user input data and provides specific future predictions. Users can plan their next actions based on the prediction results, and in the process, they continuously provide data to help the system make more accurate predictions.

[0068] The processing flow will be explained below.

[0069] Step 1:

[0070] The user inputs details of their daily activities and current thoughts. Specifically, the user enters the following information into a multiple-choice form displayed on the device: "Work progress: Good," "Health condition: A little tired," "Interpersonal relationships: Good," "Study content: Learning new skills."

[0071] Step 2:

[0072] The device receives the input, collects the data entered by the user, and converts it into a suitable format, which is then sent to a server for storage and analysis.

[0073] Step 3:

[0074] The device sends the collected data to the server. The device uses a secure protocol to send user data to the server via a POST request. The data sent is generally in JSON format.

[0075] Step 4:

[0076] The server receives the data sent from the terminal, analyzes the received data, identifies which user the data came from, and checks the integrity of the data.

[0077] Step 5:

[0078] The server classifies the received data by user and stores it in a database. The stored data is managed together with the user's past data. The database design has a structure that allows for efficient data retrieval and storage.

[0079] Step 6:

[0080] The server retrieves user data from a database and inputs it into an AI model, which uses machine learning algorithms to learn patterns from the user's past data.

[0081] Step 7:

[0082] The server uses AI models to analyze the data and generate future predictions, such as predicted annual income in five years, family structure, and career progression.

[0083] Step 8:

[0084] The server organizes the generated predictions and sends them to the device, possibly formatting the results in graphs or charts.

[0085] Step 9:

[0086] The device displays the prediction results received from the server to the user in a visually easy-to-understand format so that the user can easily understand them.

[0087] Step 10:

[0088] Users can create their own action plans based on the displayed prediction results. Users can think of specific actions and carry out activities based on those actions.

[0089] Step 11:

[0090] The server collects new data and feedback from users, which is then fed back into the AI ​​model to help improve prediction accuracy.

[0091] In this way, the system is composed of a series of steps, starting with user input, followed by data transmission, storage, analysis, and display of results. By inputting their daily activities, users can obtain specific predictions for the future, enabling them to create action plans based on those predictions.

[0092] Example 1

[0093] 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."

[0094] In today's busy lifestyles, it is not easy for individuals to continually review and improve their daily activities while keeping future prospects and goals in mind. In particular, there is a lack of methods for objectively analyzing a wide range of factors, such as one's health, work progress, relationships, and learning content, to obtain future predictions. As a result, it is difficult for individuals to have a long-term perspective and act in a planned manner. Therefore, there is a need for a system that performs AI analysis based on user input data and provides specific future predictions.

[0095] 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.

[0096] In this invention, the server includes an interface means for users to input their daily activities and current thoughts, a communication means for transmitting the input data to the server, a database means for classifying and storing the data received by the server for each user, an analysis means for generating future prediction results using a generative AI model based on the stored data, and a display means for visually presenting the generated prediction results to the user. This allows users to continuously input their own activity data and obtain specific future predictions based on that data.

[0097] The "interface means" is an operation screen or input device that allows the user to input details of daily activities and current thoughts.

[0098] "Communication means" refers to the communication protocols and techniques used to transmit the data entered by the user to the server.

[0099] The "database means" refers to a storage device and its management system for classifying and storing data received by the server for each user.

[0100] A "generative AI model" is an artificial intelligence model and its implementation technology that generates future prediction results based on stored data.

[0101] "Analytical Tools" are the processes and techniques that analyze stored data and generate future predicted outcomes using generative AI models.

[0102] The "display means" refers to a display device and its management software for visually presenting the generated prediction results to the user.

[0103] The present invention relates to a system in which a user inputs details of their daily activities and current thoughts, sends the data to a server for storage, and generates and provides future prediction results using a generative AI model. A detailed description of specific embodiments of this system is provided below.

[0104] User data entry

[0105] Users input their daily activities and thoughts through the interface. The interface is designed as a simple multiple-choice form, and includes items such as "work progress," "health status," "relationships," and "study content." This allows users to easily enter data.

[0106] Examples:

[0107] Users enter their daily activities by selecting options such as:

[0108] Work progress: Good

[0109] Health condition: A little tired

[0110] Relationships: Good

[0111] Learning content: Learning new technology

[0112] Data transmission (operation on the terminal side)

[0113] The device collects the data entered by the user, converts it into the appropriate format, and sends it to the server, using secure protocols such as HTTPS to ensure data security.

[0114] Data reception and storage (server-side operation)

[0115] The server receives the data sent from the device, classifies it by user, and stores it in a database. The database system used is MySQL or PostgreSQL. By setting appropriate indexes, it is possible to retrieve and store data efficiently.

[0116] Data analysis and prediction (server-side operation)

[0117] The server uses a generative AI model based on the stored data to make future predictions. This generative AI model is built using frameworks such as TensorFlow and PyTorch, and predicts the user's future state based on past data. Prediction results include, for example, predictions of annual income, family composition, and career progress.

[0118] Examples:

[0119] The server generates a concrete prediction:

[0120] Estimated annual income in 5 years: 6 million yen

[0121] Family: Married, 1 child

[0122] Career progression: Manager position

[0123] Display of results (user and terminal actions)

[0124] The server sends the generated prediction results to the device, which then displays them to the user in a visually easy-to-understand format, such as graphs or charts, allowing the user to intuitively understand the future prediction results.

[0125] Examples:

[0126] The user will see the following result on their screen:

[0127] Estimated annual income in 5 years: 6 million yen

[0128] Family: Married, 1 child

[0129] Career progression: Manager position

[0130] Input prompt for generative AI model

[0131] An example of an input prompt for a generative AI model is as follows:

[0132] User daily activity data:

[0133] Work progress: Good

[0134] Health condition: A little tired

[0135] Relationships: Good

[0136] Learning content: Learning new technology

[0137] Based on this, please provide your predicted results for the next five years.

[0138] This allows the system of the present invention to perform AI analysis based on data entered by the user and provide specific future predictions.The user can plan their next actions based on the prediction results and continuously provide data in the process, thereby helping the system make more accurate predictions.

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

[0140] Step 1:

[0141] User data entry

[0142] Users enter their daily activities and thoughts through the interface. The data is categorized into categories such as "work progress," "health status," "relationships," and "study content," and the interface presents them as a simple multiple-choice form.

[0143] input:

[0144] The user selects the following data on the interface:

[0145] Work progress: Good

[0146] Health condition: A little tired

[0147] Relationships: Good

[0148] Learning content: Learning new technology

[0149] Specific behavior:

[0150] The user selects the appropriate option for each item.

[0151] Once the input is complete, the data is compiled into a single data structure (e.g., JSON).

[0152] output:

[0153] Well-formed data structures (e.g., JSON-formatted data)

[0154] Step 2:

[0155] Data transmission (operation on the terminal side)

[0156] The device collects the data entered by the user, converts it into the appropriate format, and sends it to the server, using secure protocols such as HTTPS to ensure data security.

[0157] input:

[0158] Data entered by the user on the interface (formatted data structure)

[0159] Specific behavior:

[0160] The terminal formats the input data in JSON format.

[0161] Send the formatted data to the server using the HTTPS protocol.

[0162] output:

[0163] Data sent to the server (encrypted data in JSON format)

[0164] Step 3:

[0165] Data reception and storage (server-side operation)

[0166] The server receives the data sent from the terminal, classifies it by user, and stores it in a database.

[0167] input:

[0168] Data sent from the device (JSON format data)

[0169] Specific behavior:

[0170] The server parses the received HTTP request and extracts the data.

[0171] The extracted data is classified by user ID.

[0172] Execute the appropriate SQL queries to insert data into the database.

[0173] output:

[0174] User data stored in a database

[0175] Step 4:

[0176] Data analysis and prediction (server-side operation)

[0177] The server uses a generative AI model based on the stored data to make future predictions.

[0178] input:

[0179] User data stored in a database

[0180] Specific behavior:

[0181] The server retrieves the user's data from the database.

[0182] Input data into a generative AI model (e.g., using TensorFlow or PyTorch) and run a predictive algorithm.

[0183] Generate prediction results and organize them by user.

[0184] output:

[0185] Generated prediction results (e.g., predicted annual income in 5 years, family structure, career progress)

[0186] Step 5:

[0187] Display of results (user and terminal actions)

[0188] The server transmits the generated prediction results to the terminal, which displays them to the user in a visually easy-to-understand format.

[0189] input:

[0190] Generated prediction results (e.g., data encoded in JSON format)

[0191] Specific behavior:

[0192] The server sends the generated prediction results to the terminal in JSON format.

[0193] The device analyzes the received data, converts it into graphs and charts, and displays them to the user.

[0194] output:

[0195] Prediction results displayed on the user's screen (in graph and chart format)

[0196] The above is the specific processing flow of this system's program. Based on this flow, users can input their daily data and obtain specific future predictions based on that data. This provides useful information for users to act in a planned manner, and the system itself can continuously collect data, thereby improving the accuracy of predictions.

[0197] (Application example 1)

[0198] 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."

[0199] In today's busy lifestyles, there is a need for systems that continuously monitor users' daily health status and lifestyle habits and predict future health conditions. However, existing systems have issues such as cumbersome data collection from users and inaccurate prediction results. Furthermore, there is a lack of visual feedback to users, making it difficult to provide specific health improvement measures.

[0200] 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.

[0201] In this invention, the server includes an input means for users to input their daily activities and current thoughts, a transmission means for transmitting the input data to the server, a storage means for storing the data received by the server for each user, an analysis means for generating future predictions and health predictions using an AI model based on the stored data, and an output means for providing the generated predictions to the user. This allows users to input their daily health data in an intuitively understandable manner and receive highly accurate future predictions using the AI ​​model. Furthermore, feedback in a visually understandable format makes it easier for users to create action plans for taking specific health improvement measures.

[0202] An "input means" is a device or interface that a user uses to input details of their daily activities and current thoughts.

[0203] "Transmitting means" refers to a communication device or protocol for transmitting data entered by a user to a server.

[0204] The "storage means" refers to a database or storage system that classifies and stores data received by the server for each user.

[0205] "Analytical means" means a computing device or software that uses AI models to generate future predictions and health predictions based on stored data.

[0206] The "output means" is a display device or an output interface for providing the generated prediction results to a user.

[0207] The "healthcare prediction means" is a system in which a user inputs data about their daily health condition and lifestyle habits, and predicts their future health condition based on the data sent to a server.

[0208] The "interface means" is a display device or user interface for visually presenting the generated health prediction results to the user.

[0209] The present invention is a system that uses an AI model to predict future health based on user input data on daily activities, health status, and lifestyle habits. First, the user inputs daily health data using a device such as a smartphone, tablet, or personal computer. The input method is a form or application designed for user ease of operation. The input form may include, for example, the number of steps taken, calorie intake, sleep time, stress level, and dietary quality.

[0210] Next, the data entered by the user is sent by the transmission means to a server via the Internet. A secure communication protocol is used for transmission, protecting the data from leaking to third parties. The received data is classified by user on the server and stored in a database. The stored data is managed so that it can be efficiently retrieved for later analysis and prediction.

[0211] The server uses the stored data to make future health predictions using an AI model. The AI ​​model is designed to learn from large amounts of past data and continuously improve its prediction accuracy. Specifically, the AI ​​model includes machine learning algorithms such as linear regression and deep learning.

[0212] The predicted results are provided to the user through an interface that displays the results in visually easy-to-understand graphs, charts, and text format, allowing the user to intuitively understand specific health advice and improvement measures.

[0213] For example, if a user enters the following health data:

[0214] Date: 2023-10-01

[0215] Steps: 8,000

[0216] Calorie intake: 2200kcal

[0217] Sleep time: 7 hours

[0218] Stress level: Moderate

[0219] Food quality: Average

[0220] This data is sent to a server and stored, after which the AI ​​model analyzes it to generate health predictions such as "Weight forecast in 3 months: Increase by 2kg from current weight" and "Future disease risk: High." The results are then provided to the user, who can then create a specific action plan.

[0221] The hardware used may include smartphones, tablets, and personal computers. The software used may include database management systems, communication protocols, and machine learning libraries (e.g., TensorFlow, scikit-learn). An example of a prompt from the user may be in the following format:

[0222] "Date: 2023-10-01, Steps: 8000, Calorie Intake: 2200kcal, Sleep: 7 hours, Stress Level: Medium, Diet Quality: Average"

[0223] The system of the present invention efficiently collects, stores, and analyzes this data, and provides useful health predictions to users, thereby assisting them in managing their health.

[0224] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0225] Step 1:

[0226] The user inputs daily health data.

[0227] Users use a smartphone, tablet, or personal computer to access a dedicated application or web form to enter data about their daily health and lifestyle habits, including the number of steps taken, calorie intake, sleep time, stress level, and diet quality. This input data is then used as the basis for further processing.

[0228] Step 2:

[0229] The terminal sends the input data to the server.

[0230] Input data is sent from the terminal to the server via a transmission means. A secure communication protocol such as HTTPS is used. The terminal properly formats the input data and performs error checking to prevent data loss during transmission. Once the data transmission is complete, the server receives the data.

[0231] Step 3:

[0232] The server stores the received data.

[0233] When the server receives the input data, it classifies it by user and stores it in a database. The data is stored in an organized format so that it can be efficiently searched and analyzed. For example, a database management system (DBMS) is used to store the data using the user ID as a key. At this data storage stage, the consistency and integrity of the data are verified.

[0234] Step 4:

[0235] The server uses an AI model to make predictions based on the stored data.

[0236] Based on the stored data, the server uses an AI model (for example, a model using TensorFlow or scikit-learn) to predict future health conditions. The model, which has learned from past data, receives each user's new health data as input and generates predictions such as weight changes and future disease risk. Specifically, the input data is preprocessed and fed into the AI ​​model to obtain predictions.

[0237] Step 5:

[0238] The server provides the generated prediction results to the user.

[0239] The generated prediction results are sent from the server to the terminal and provided to the user through an interface means. The prediction results are displayed in a visually easy-to-understand format, such as a graph, chart, or text, allowing the user to receive specific advice based on their own health condition.

[0240] Step 6:

[0241] The user creates an action plan based on the prediction results.

[0242] Based on the displayed prediction results, the user plans actions for managing their own health. For example, they consider specific lifestyle improvements such as reviewing their diet, increasing exercise, and adjusting their sleep schedule. In this step, it is desirable to add a feedback function to check whether the prediction results are reflected in the user's actions.

[0243] As described above, the system of the present invention efficiently collects, stores, and analyzes a user's health data and provides specific health predictions, thereby supporting the user's health management.

[0244] 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.

[0245] The present invention relates to a system in which a user inputs details of their daily activities and current thoughts, an emotion engine recognizes the user's emotions, the data is sent to a server for storage, and an AI model generates and provides future prediction results. A specific embodiment of this system will be described below.

[0246] User operation

[0247] Users input their daily activities and thoughts through the interface. The interface is designed as a simple multiple-choice form, and includes items such as "work progress," "health status," "relationships," and "study content." The emotion engine also recognizes the user's emotions.

[0248] Examples:

[0249] Users enter their daily information by selecting options such as:

[0250] "Work progress: Good"

[0251] Health condition: A little tired

[0252] "Interpersonal relationships: Good"

[0253] "What I'm learning: I'm learning new technology."

[0254] The emotion engine recognizes emotions such as "joy," "anger," "sadness," and "surprise" in real time.

[0255] Data transmission (operation on the terminal side)

[0256] The device collects data entered by the user and emotional data recognized by the emotion engine, converts it into an appropriate format, and transmits it to the server using a secure protocol to ensure data integrity.

[0257] Receiving and saving data (server-side operation)

[0258] The server receives the data sent from the device, classifies it by user, and stores it in a database. The stored data is used for later analysis. Emotion data is also recorded along with the user's past data.

[0259] Data analysis and prediction (server-side operation)

[0260] The server uses an AI model to make future predictions based on the stored data. The AI ​​model learns the user's past data and emotional data, and generates future prediction results based on the user's input data. The prediction results include, for example, the following elements:

[0261] Annual income forecast

[0262] Family structure prediction

[0263] Predicting career progression

[0264] By incorporating emotional data, more accurate predictions can be made that take into account the transitions in the user's emotional state and their impact.

[0265] Examples:

[0266] Based on the user's input data and emotional data, the server generates specific predictions such as "Expected annual income in five years: 6 million yen," "Family structure: married with one child," and "Career progress: manager position." The prediction results also include insights such as "Improving emotional state will have a positive impact on work progress."

[0267] Display of results (user and terminal actions)

[0268] The server sends the generated prediction results to the device, which then displays them to the user in a visually easy-to-understand format, such as graphs or charts.

[0269] Examples:

[0270] The user will see the following results on their screen:

[0271] "Expected annual income in 5 years: 6 million yen"

[0272] Family status: Married, one child

[0273] "Career Progression: Section Manager Position"

[0274] Additionally, insights incorporating emotional data are also displayed, providing specific advice such as, "It is important to maintain positive emotions as you progress in your career."

[0275] Continuous data collection and improvement

[0276] The system continuously collects user data and sentiment data, and uses that data to continuously train the AI ​​model to improve prediction accuracy. It also accepts user feedback and uses it to improve the model.

[0277] In this way, the system of the present invention combines user input data and emotional data to perform AI analysis and provide specific future predictions. Users can plan their next actions based on the prediction results, and in the process, they continuously provide data to help the system make more accurate predictions.

[0278] The processing flow will be explained below.

[0279] Step 1:

[0280] The user inputs details of their daily activities and current thoughts. Specifically, the user enters information such as the following into a multiple-choice form displayed on the device: "Work progress: Good," "Health condition: A little tired," "Interpersonal relationships: Good," "Study content: Learning new skills." The emotion engine also simultaneously recognizes the user's emotions. For example, emotions such as "joy," "anger," "sadness," and "surprise" can be automatically recognized from the user's facial expressions and text.

[0281] Step 2:

[0282] The device receives the input content and emotion data. The device collects the data entered by the user and the emotion data recognized by the emotion engine, and converts it into JSON format.

[0283] Step 3:

[0284] The device sends the collected data to the server. The device uses a secure protocol to send user data and emotion data to the server via a POST request.

[0285] Step 4:

[0286] The server receives the data sent from the terminal, identifies which user the data is from, and checks the integrity of the data.

[0287] Step 5:

[0288] The server classifies the received data by user and stores it in a database. The stored data includes the user's activity, thoughts, and emotions. This data is used for later analysis.

[0289] Step 6:

[0290] The server retrieves user data from the database and inputs it into the AI ​​model, which uses machine learning algorithms to learn from the user's past data and emotional data.

[0291] Step 7:

[0292] The server uses an AI model to analyze the data and generate future predictions. The AI ​​model generates predictions such as annual income, family composition, and career progress based on the user's activities, thoughts, and emotional data. By taking emotional data into account, predictions can be made that include the impact that emotions will have on the user's future.

[0293] Step 8:

[0294] The server organizes the generated forecasts and sends them to the device, often formatted as graphs or charts.

[0295] Step 9:

[0296] The device displays the prediction results received from the server to the user in a visually easy-to-understand format so that the user can easily understand them.

[0297] Step 10:

[0298] Users can create their own action plan based on the displayed prediction results. Users can consider specific actions and take action based on them. Insights including emotional data are also displayed, such as "Improving your emotional state will have a positive impact on work progress."

[0299] Step 11:

[0300] The server collects new data and feedback from users, which is then fed back into the AI ​​model to help improve its prediction accuracy.

[0301] In this way, the system combines user input data with emotional data for AI analysis to provide specific future predictions. Users can plan their next actions based on the prediction results, and in the process, they continuously provide data to help the system make more accurate predictions.

[0302] Example 2

[0303] 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."

[0304] Conventional systems have issues with the accuracy of analyzing data when inputting user activities and thoughts, and making predictions based on that data. Another issue is that it is difficult to provide predictions that fully reflect the user's emotional data.

[0305] 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 following means are included: interface means for the user to input daily activities and current thoughts, emotion engine means for analyzing the input data and recognizing emotions, communication means for transmitting the analyzed data to a server, storage means for saving the data on the server, analysis means for generating future prediction results using a generative AI model based on the saved data, and display means for visually presenting the generated prediction results to the user. This makes it possible to accurately analyze the user's activities and emotion data and make highly accurate future predictions.

[0306] "Interface means" refers to the means by which a user inputs details of their daily activities and current thoughts, and specifically refers to a multiple-choice form or input screen.

[0307] The "emotion engine means" is a means having the function of analyzing input data and recognizing the user's emotions, and refers to an engine that performs emotion analysis using natural language processing technology, etc.

[0308] "Communication means" refers to the means for sending analyzed data to the server, and refers to the function for transferring data using a secure communication protocol (e.g., HTTPS).

[0309] "Storage means" refers to a means for storing data received by the server, and refers to the function of storing data using a database or other storage medium.

[0310] A "generative AI model" is an AI technology that generates future predictions based on stored data, and refers to a model that uses machine learning and deep learning to learn and make predictions.

[0311] "Analysis means" refers to a means that has the function of analyzing stored data using a generative AI model and generating future prediction results.

[0312] "Display means" refers to a means for providing the generated prediction results in a format that allows the user to visually confirm them, and specifically refers to a screen or interface that displays graphs and charts.

[0313] MODE FOR CARRYING OUT THE INVENTION

[0314] This invention relates to a system in which a user inputs details of their daily activities and current thoughts, an emotion engine is used to recognize the user's emotions, the data is sent to a server for storage, and a generative AI model is used to generate and provide future prediction results. Specific embodiments of this system are described below.

[0315] User operation

[0316] Users access a dedicated application or web interface using a device such as a smartphone or PC. The interface is designed as a simple multiple-choice form that includes items such as "work progress," "health status," "relationships," and "study content."

[0317] Examples:

[0318] The user enters the details of their daily activities as follows:

[0319] "Work progress: Good"

[0320] Health condition: A little tired

[0321] "Interpersonal relationships: Good"

[0322] "What I'm learning: I'm learning new technology."

[0323] Data analysis using emotion engine

[0324] The device is equipped with an emotion engine that analyzes emotions in real time based on the user input data. This emotion engine uses natural language processing libraries (e.g., NLTK and SpaCy) to recognize emotions such as "joy," "anger," "sadness," and "surprise."

[0325] Data transmission and storage

[0326] The device combines the recognized emotion data and the activity data entered by the user and sends it to a server using a secure protocol such as HTTPS. The server analyzes the received data, classifies it by user, and stores it in a database using a relational database (e.g., MySQL or PostgreSQL).

[0327] Data analysis and future predictions

[0328] The server uses the stored data to generate future predictions using a generative AI model, which uses machine learning and deep learning (e.g., TensorFlow and PyTorch) to learn from the user's past data and emotional data and generate future predictions.

[0329] Examples:

[0330] Based on the user's input data and emotional data, the server generates specific predictions such as "Expected annual income in five years: 6 million yen," "Family structure: married with one child," and "Career progress: manager position." The prediction results also include insights such as "Improving emotional state will have a positive impact on work progress."

[0331] Displaying the results

[0332] The server sends the generated forecast results to the device, which then displays them in a visually easy-to-understand format, using graphs and charts, allowing the user to intuitively understand future forecast results.

[0333] Examples:

[0334] The user will see the following results on their screen:

[0335] "Expected annual income in 5 years: 6 million yen"

[0336] Family status: Married, one child

[0337] "Career Progression: Section Manager Position"

[0338] In addition, specific advice is provided, such as "It is important to maintain a positive attitude in order to advance your career in the future."

[0339] Continuous data collection and model improvement

[0340] The system continuously collects data from users and uses that data to train the AI ​​model to improve prediction accuracy, while also accepting user feedback to improve the model.

[0341] This invention combines user input data with emotional data for AI analysis to provide specific future predictions. Users can plan their next actions based on the prediction results, and in the process, they continuously provide data to help the system make more accurate predictions.

[0342] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0343] Step 1:

[0344] The user inputs the activity and thoughts

[0345] Users input their daily activities and thoughts through a smartphone or PC interface. The interface displays options such as "Work progress," "Health status," "Interpersonal relationships," and "Study content." The user completes the input by entering each item and clicking the "Submit" button. Input data may include, for example, "Work progress: Good" or "Health status: A little tired."

[0346] Input: Data entered by the user into the interface

[0347] Output: Data sent from the interface to the terminal

[0348] Specific behavior:

[0349] The user launches an application.

[0350] Click the "Enter today's activity" button.

[0351] The user selects the appropriate option for each item and clicks the "Submit" button.

[0352] Step 2:

[0353] The device uses an emotion engine to recognize emotions

[0354] The device analyzes the data entered by the user in real time and recognizes the user's emotions using natural language processing libraries (such as NLTK or SpaCy). The emotion engine performs text analysis on the input data and identifies emotions such as "joy," "anger," "sadness," and "surprise."

[0355] Input: Data entered by the user

[0356] Output: Emotion data recognized by the emotion engine

[0357] Specific behavior:

[0358] The terminal receives input data.

[0359] The emotion engine analyzes the input data.

[0360] Emotional data is extracted as the analysis result.

[0361] Step 3:

[0362] The device sends the data to the server

[0363] The device combines the user's input data and the emotion data recognized by the emotion engine into a single data packet and sends it to the server using a secure protocol such as HTTPS.

[0364] Input: User input data and recognized emotion data

[0365] Output: Data packets sent to the server

[0366] Specific behavior:

[0367] The device integrates input data and emotion data.

[0368] The integrated data is converted into data packets.

[0369] The data packet is sent to the server using the HTTPS protocol.

[0370] Step 4:

[0371] The server receives and stores the data

[0372] The server receives the data sent from the device, analyzes it, and stores it in a database. The data is classified by user and stored for later analysis. The database is a relational database (e.g., MySQL or PostgreSQL).

[0373] Input: Data packets sent from the device

[0374] Output: User data stored in the database

[0375] Specific behavior:

[0376] The server receives the data packet.

[0377] The received data is analyzed and classified by user.

[0378] Insert the classified data into the database.

[0379] Step 5:

[0380] The server analyzes the data using an AI model and makes predictions

[0381] The server uses the stored data to make future predictions using a generative AI model, which uses machine learning libraries (such as TensorFlow or PyTorch) to learn from the user's past data and emotional data to generate future predictions.

[0382] Input: User data stored in the database

[0383] Output: Future prediction results generated by the generative AI model

[0384] Specific behavior:

[0385] The server retrieves the user's past data from the database.

[0386] A generative AI model learns and analyzes data.

[0387] Future predictions are generated as a result of the analysis.

[0388] Step 6:

[0389] The server sends the prediction results to the device.

[0390] The server formats the generated prediction results into an appropriate format and sends them to the device using a secure protocol such as HTTPS.

[0391] Input: Prediction results generated by a generative AI model

[0392] Output: Prediction results are sent in a nicely formatted format

[0393] Specific behavior:

[0394] The server receives and formats the prediction results.

[0395] The formatted prediction results are converted into data packets.

[0396] The data packet is sent to the terminal using the HTTPS protocol.

[0397] Step 7:

[0398] The device displays the prediction results to the user.

[0399] The terminal displays the prediction results received from the server to the user in a visually easy-to-understand format such as graphs and charts.

[0400] Input: Prediction results sent from the server

[0401] Output: Visually displayed prediction results

[0402] Specific behavior:

[0403] The terminal analyzes the data received from the server.

[0404] Create UI components to generate graphs and charts to visually display information.

[0405] The generated UI components are displayed on the screen.

[0406] Step 8:

[0407] The system continuously collects data and improves the model

[0408] The system continuously collects data from users and uses that data to train the generative AI model to improve prediction accuracy, while also incorporating user feedback to improve the model.

[0409] Input: New data and user feedback collected continuously

[0410] Output: A generative AI model with improved prediction accuracy

[0411] Specific behavior:

[0412] The server continuously collects new data.

[0413] Update the training of generative AI models based on new data.

[0414] Evaluate the accuracy of the model and make any necessary improvements.

[0415] (Application example 2)

[0416] 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."

[0417] Conventional systems were able to collect data on a user's daily activities and thoughts and make future predictions, but they were inadequate for predicting specific purchasing behavior or managing spending that reflected the user's emotional state. Furthermore, they lacked the ability to provide specific advice to users, which meant that users were unable to fully utilize the data. The purpose of this invention is to solve these problems.

[0418] The identification processing 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 an input means for the user to input daily activities and current thoughts, a transmission means for transmitting the input data to the server, a storage means for storing the data received by the server for each user, an analysis means for generating future prediction results using an AI model based on the stored data and emotional data, an output means for providing the generated prediction results to the user, an emotion recognition means for recognizing the emotional state of the user, an expenditure management means for predicting and managing purchasing behavior, and an insight provision means for providing actionable advice to the user. This enables more accurate prediction of purchasing behavior and expenditure management that takes emotional data into account, and makes it possible to provide specific and actionable advice to the user.

[0419] "Daily activities" is a record of the tasks and actions that a user performs on a daily basis.

[0420] "Current thinking" refers to the thoughts and opinions that a user has at that time.

[0421] "Input means" refers to an interface or device that allows a user to input their daily activities and current thoughts into the system.

[0422] "Transmission means" refers to the method or technology used to send the entered data to the server.

[0423] "Storage means" refers to the technology or device that the server uses to maintain and store the data it receives for each user.

[0424] "Emotion recognition means" refers to a method or technology that analyzes the user's emotional state in real time and recognizes it as data.

[0425] "Analysis Method" means a method or technique for generating future predictions using an AI model based on stored data and sentiment data.

[0426] "Output means" refers to a method or technology for providing the generated prediction results to a user.

[0427] A "spend manager" is a method or technique for predicting and managing a user's purchasing behavior.

[0428] An "insight providing means" is a method or technology for providing specific, actionable advice to a user.

[0429] An "AI model" is an artificial intelligence technology used to analyze data and make future predictions.

[0430] "Emotion data" refers to data that represents the user's emotional state.

[0431] "Purchasing behavior" refers to the behavioral patterns of users when purchasing products or services.

[0432] "Specific advice" refers to detailed, actionable instructions or advice on what actions or precautions the user should take.

[0433] This invention is a system that inputs a user's daily activities and current thoughts, predicts future purchasing behavior and expenditure management based on that data and emotion recognition data, and provides the user with specific advice. A specific embodiment of this system is described below.

[0434] First, users use devices such as smartphones or tablets to input details of their daily activities and current thoughts. An application using React Native is used as the input method. Users can easily enter details of their activities and thoughts using a text input form.

[0435] At the same time, the device's camera is used to recognize the user's emotional state in real time. The emotion recognition method uses the Azure Cognitive Services API, which acquires the user's emotional data.

[0436] These input data and emotion data are securely sent to the server via HTTPS. The server is built with Node.js and stores the received data in a MongoDB database. The stored data is organized by user, ensuring data integrity.

[0437] The server uses TensorFlow to perform analysis using an AI model based on the stored data and sentiment data. The analysis involves preprocessing the data using Python's pandas and NumPy, converting it into a format suitable for input into the AI ​​model. The AI ​​model learns from past data to predict future purchasing behavior and spending, and returns the resulting predictions.

[0438] The prediction results include information on the user's purchasing behavior patterns and spending management. Furthermore, the insight providing means generates specific actions and advice that the user should take, allowing the user to efficiently manage their spending in their daily lives.

[0439] Finally, the device presents the prediction results and advice sent from the server to the user in a visually easy-to-understand format. Graphs and charts can be used as visualization methods, allowing the user to easily understand the future predictions and the specific advice based on them.

[0440] Additionally, the system continuously collects data and learns to improve the accuracy of the AI ​​model, and user feedback can be incorporated and used to improve the model.

[0441] As a concrete example, the following prompt sentence is input to the generative AI model:

[0442] "EmotionPay has analyzed your emotional data and purchasing behavior over the past six months. Please show us the results of your analysis of your financial situation one year from now if you continue your current spending patterns, and the impact of your emotional data on your purchasing behavior."

[0443] Based on this, the AI ​​model returns the following results:

[0444] "Based on data from the past six months, our analysis shows that if people continue their current spending patterns, their savings will increase by 10% in one year. Furthermore, our sentiment data shows that positive emotions have a positive impact on purchasing decisions. Maintaining positive emotions will be a key factor in supporting financial stability."

[0445] In this way, the present invention realizes a system that allows users to predict purchasing behavior while utilizing emotion data and manage spending more effectively.

[0446] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0447] Step 1:

[0448] Users use a smartphone or tablet device to input their daily activities and current thoughts into a React Native application. The user enters specific details of their activities and thoughts into a text input form, and the data is sent to the application. Examples of input data include "Work progress: Good" and "Health condition: A little tired."

[0449] Step 2:

[0450] Using the device's camera, the system recognizes the user's emotions in real time through the Azure Cognitive Services API. Emotion analysis is performed based on images captured by the camera, and emotional data such as joy, anger, and sadness is generated. An example of emotional data is "Emotion: Happiness."

[0451] Step 3:

[0452] The device sends the activity details entered in step 1 and the emotion data recognized in step 2 to the server using the HTTPS protocol. The pair of input data and emotion data is sent to the server.

[0453] Step 4:

[0454] The server runs on Node.js and receives data sent from the device. The received data is stored in MongoDB and classified by user. The data is saved with a date and used for later analysis.

[0455] Step 5:

[0456] The server uses TensorFlow to preprocess the saved activity data and emotion data for input into the AI ​​model. Python's pandas and NumPy are used to clean the data and convert it into an input format for the AI ​​model. After preprocessing, the input data includes "Work progress: Good" and "Emotion: Happy."

[0457] Step 6:

[0458] The AI ​​model uses TensorFlow as an analysis tool to predict future purchasing behavior and spending. Predictions are generated based on the user's past data. The output predictions include "There is a high probability that spending will increase by 10% over the next six months."

[0459] Step 7:

[0460] The server analyzes the generated prediction results using insight provision methods and creates actionable advice for the user. It generates a prompt sentence and inputs specific advice from the prediction results into the generative AI model. An example of a prompt sentence in this case is, "After analyzing data from the past six months, we have determined that your expenses may increase by 10%. We recommend that you take the following actions to save money."

[0461] Step 8:

[0462] The server converts the forecast results and advice into HTML format and sends them to the device. A visualization tool is used to display them in easy-to-understand graphs and charts. The output data includes a "spending forecast" and "specific savings advice."

[0463] Step 9:

[0464] The terminal displays the prediction results and advice sent from the server on the user interface of the React Native application. The user can visually check the results and decide whether to take action. Specific examples of what is displayed in this step include "Expenses may increase by 10% over the next six months" and "Savings action: Eat out less."

[0465] Step 10:

[0466] The system continuously collects new data from users and updates the AI ​​model's learning to improve its prediction accuracy. User feedback is also incorporated and reflected in the model's improvements. Data from this step includes user feedback such as "Feedback: The advice was helpful."

[0467] This allows the system to utilize user emotional data to predict future purchasing behavior and provide more effective spending management.

[0468] 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.

[0469] 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.

[0470] 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.

[0471] [Second embodiment]

[0472] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0473] 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.

[0474] 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).

[0475] 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.

[0476] 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.

[0477] 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).

[0478] 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.

[0479] 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.

[0480] 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.

[0481] 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.

[0482] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0483] 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."

[0484] The present invention relates to a system in which a user inputs details of their daily activities and current thoughts, sends the data to a server where it is stored, and generates and provides future prediction results using an AI model. A specific embodiment of this system will be described below.

[0485] User operation

[0486] Users input their daily activities and thoughts through the interface, which is designed as a simple multiple-choice form and includes items such as "work progress," "health status," "relationships," and "study content."

[0487] Examples:

[0488] Users enter their daily information by selecting options such as:

[0489] "Work progress: Good"

[0490] Health condition: A little tired

[0491] "Interpersonal relationships: Good"

[0492] "What I'm learning: I'm learning new technology."

[0493] Data transmission (operation on the terminal side)

[0494] The terminal collects the data entered by the user, converts it into the appropriate format, and sends it to the server, using a secure protocol to ensure the integrity of the data.

[0495] Receiving and saving data (server-side operation)

[0496] The server receives the data sent from the devices, classifies it by user, and stores it in a database. The stored data will be used for later analysis, so the database design ensures efficient data acquisition and storage.

[0497] Data analysis and prediction (server-side operation)

[0498] The AI ​​model makes future predictions based on data stored on the server. The AI ​​model learns from past data and generates future prediction results based on user input data. The prediction results include, for example, the following elements:

[0499] Annual income forecast

[0500] Family structure prediction

[0501] Predicting career progression

[0502] Examples:

[0503] Based on the user's input data, the server generates specific predictions such as "Expected annual income in five years: 6 million yen," "Family composition: married with one child," and "Career progress: section manager position."

[0504] Display of results (user and terminal actions)

[0505] The server sends the generated prediction results to the device, which then displays them to the user in a visually understandable format, such as graphs or charts.

[0506] Examples:

[0507] The user will see the following results on their screen:

[0508] "Expected annual income in 5 years: 6 million yen"

[0509] Family status: Married, one child

[0510] "Career Progression: Section Manager Position"

[0511] Users can create specific action plans based on these prediction results.

[0512] Continuous data collection and improvement

[0513] The system continuously collects data from users and uses that data to train the AI ​​model to improve prediction accuracy, while also accepting user feedback to improve the model.

[0514] In this way, the system of the present invention performs AI analysis based on user input data and provides specific future predictions. Users can plan their next actions based on the prediction results, and in the process, they continuously provide data to help the system make more accurate predictions.

[0515] The processing flow will be explained below.

[0516] Step 1:

[0517] The user inputs details of their daily activities and current thoughts. Specifically, the user enters the following information into a multiple-choice form displayed on the device: "Work progress: Good," "Health condition: A little tired," "Interpersonal relationships: Good," "Study content: Learning new skills."

[0518] Step 2:

[0519] The device receives the input, collects the data entered by the user, and converts it into a suitable format, which is then sent to a server for storage and analysis.

[0520] Step 3:

[0521] The device sends the collected data to the server. The device uses a secure protocol to send user data to the server via a POST request. The data sent is generally in JSON format.

[0522] Step 4:

[0523] The server receives the data sent from the terminal, analyzes the received data, identifies which user the data came from, and checks the integrity of the data.

[0524] Step 5:

[0525] The server classifies the received data by user and stores it in a database. The stored data is managed together with the user's past data. The database design has a structure that allows for efficient data retrieval and storage.

[0526] Step 6:

[0527] The server retrieves user data from a database and inputs it into an AI model, which uses machine learning algorithms to learn patterns from the user's past data.

[0528] Step 7:

[0529] The server uses AI models to analyze the data and generate future predictions, such as predicted annual income in five years, family structure, and career progression.

[0530] Step 8:

[0531] The server organizes the generated predictions and sends them to the device, possibly formatting the results in graphs or charts.

[0532] Step 9:

[0533] The device displays the prediction results received from the server to the user in a visually easy-to-understand format so that the user can easily understand them.

[0534] Step 10:

[0535] Users can create their own action plans based on the displayed prediction results. Users can think of specific actions and carry out activities based on those actions.

[0536] Step 11:

[0537] The server collects new data and feedback from users, which is then fed back into the AI ​​model to help improve prediction accuracy.

[0538] In this way, the system is composed of a series of steps, starting with user input, followed by data transmission, storage, analysis, and display of results. By inputting their daily activities, users can obtain specific predictions for the future, enabling them to create action plans based on those predictions.

[0539] Example 1

[0540] 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."

[0541] In today's busy lifestyles, it is not easy for individuals to continually review and improve their daily activities while keeping future prospects and goals in mind. In particular, there is a lack of methods for objectively analyzing a wide range of factors, such as one's health, work progress, relationships, and learning content, to obtain future predictions. As a result, it is difficult for individuals to have a long-term perspective and act in a planned manner. Therefore, there is a need for a system that performs AI analysis based on user input data and provides specific future predictions.

[0542] 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.

[0543] In this invention, the server includes an interface means for users to input their daily activities and current thoughts, a communication means for transmitting the input data to the server, a database means for classifying and storing the data received by the server for each user, an analysis means for generating future prediction results using a generative AI model based on the stored data, and a display means for visually presenting the generated prediction results to the user. This allows users to continuously input their own activity data and obtain specific future predictions based on that data.

[0544] The "interface means" is an operation screen or input device that allows the user to input details of daily activities and current thoughts.

[0545] "Communication means" refers to the communication protocols and techniques used to transmit the data entered by the user to the server.

[0546] The "database means" refers to a storage device and its management system for classifying and storing data received by the server for each user.

[0547] A "generative AI model" is an artificial intelligence model and its implementation technology that generates future prediction results based on stored data.

[0548] "Analytical Tools" are the processes and techniques that analyze stored data and generate future predicted outcomes using generative AI models.

[0549] The "display means" refers to a display device and its management software for visually presenting the generated prediction results to the user.

[0550] The present invention relates to a system in which a user inputs details of their daily activities and current thoughts, sends the data to a server for storage, and generates and provides future prediction results using a generative AI model. A detailed description of specific embodiments of this system is provided below.

[0551] User data entry

[0552] Users input their daily activities and thoughts through the interface. The interface is designed as a simple multiple-choice form, and includes items such as "work progress," "health status," "relationships," and "study content." This allows users to easily enter data.

[0553] Examples:

[0554] Users enter their daily activities by selecting options such as:

[0555] Work progress: Good

[0556] Health condition: A little tired

[0557] Relationships: Good

[0558] Learning content: Learning new technology

[0559] Data transmission (operation on the terminal side)

[0560] The device collects the data entered by the user, converts it into the appropriate format, and sends it to the server, using secure protocols such as HTTPS to ensure data security.

[0561] Data reception and storage (server-side operation)

[0562] The server receives the data sent from the device, classifies it by user, and stores it in a database. The database system used is MySQL or PostgreSQL. By setting appropriate indexes, it is possible to retrieve and store data efficiently.

[0563] Data analysis and prediction (server-side operation)

[0564] The server uses a generative AI model based on the stored data to make future predictions. This generative AI model is built using frameworks such as TensorFlow and PyTorch, and predicts the user's future state based on past data. Prediction results include, for example, predictions of annual income, family composition, and career progress.

[0565] Examples:

[0566] The server generates a concrete prediction:

[0567] Estimated annual income in 5 years: 6 million yen

[0568] Family: Married, 1 child

[0569] Career progression: Manager position

[0570] Display of results (user and terminal actions)

[0571] The server sends the generated prediction results to the device, which then displays them to the user in a visually easy-to-understand format, such as graphs or charts, allowing the user to intuitively understand the future prediction results.

[0572] Examples:

[0573] The user will see the following result on their screen:

[0574] Estimated annual income in 5 years: 6 million yen

[0575] Family: Married, 1 child

[0576] Career progression: Manager position

[0577] Input prompt for generative AI model

[0578] An example of an input prompt for a generative AI model is as follows:

[0579] User daily activity data:

[0580] Work progress: Good

[0581] Health condition: A little tired

[0582] Relationships: Good

[0583] Learning content: Learning new technology

[0584] Based on this, please provide your predicted results for the next five years.

[0585] This allows the system of the present invention to perform AI analysis based on data entered by the user and provide specific future predictions.The user can plan their next actions based on the prediction results and continuously provide data in the process, thereby helping the system make more accurate predictions.

[0586] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0587] Step 1:

[0588] User data entry

[0589] Users enter their daily activities and thoughts through the interface. The data is categorized into categories such as "work progress," "health status," "relationships," and "study content," and the interface presents them as a simple multiple-choice form.

[0590] input:

[0591] The user selects the following data on the interface:

[0592] Work progress: Good

[0593] Health condition: A little tired

[0594] Relationships: Good

[0595] Learning content: Learning new technology

[0596] Specific behavior:

[0597] The user selects the appropriate option for each item.

[0598] Once the input is complete, the data is compiled into a single data structure (e.g., JSON).

[0599] output:

[0600] Well-formed data structures (e.g., JSON-formatted data)

[0601] Step 2:

[0602] Data transmission (operation on the terminal side)

[0603] The device collects the data entered by the user, converts it into the appropriate format, and sends it to the server, using secure protocols such as HTTPS to ensure data security.

[0604] input:

[0605] Data entered by the user on the interface (formatted data structure)

[0606] Specific behavior:

[0607] The terminal formats the input data in JSON format.

[0608] Send the formatted data to the server using the HTTPS protocol.

[0609] output:

[0610] Data sent to the server (encrypted data in JSON format)

[0611] Step 3:

[0612] Data reception and storage (server-side operation)

[0613] The server receives the data sent from the terminal, classifies it by user, and stores it in a database.

[0614] input:

[0615] Data sent from the device (JSON format data)

[0616] Specific behavior:

[0617] The server parses the received HTTP request and extracts the data.

[0618] The extracted data is classified by user ID.

[0619] Execute the appropriate SQL queries to insert data into the database.

[0620] output:

[0621] User data stored in a database

[0622] Step 4:

[0623] Data analysis and prediction (server-side operation)

[0624] The server uses a generative AI model based on the stored data to make future predictions.

[0625] input:

[0626] User data stored in a database

[0627] Specific behavior:

[0628] The server retrieves the user's data from the database.

[0629] Input data into a generative AI model (e.g., using TensorFlow or PyTorch) and run a predictive algorithm.

[0630] Generate prediction results and organize them by user.

[0631] output:

[0632] Generated prediction results (e.g., predicted annual income in 5 years, family structure, career progress)

[0633] Step 5:

[0634] Display of results (user and terminal actions)

[0635] The server transmits the generated prediction results to the terminal, which displays them to the user in a visually easy-to-understand format.

[0636] input:

[0637] Generated prediction results (e.g., data encoded in JSON format)

[0638] Specific behavior:

[0639] The server sends the generated prediction results to the terminal in JSON format.

[0640] The device analyzes the received data, converts it into graphs and charts, and displays them to the user.

[0641] output:

[0642] Prediction results displayed on the user's screen (in graph and chart format)

[0643] The above is the specific processing flow of this system's program. Based on this flow, users can input their daily data and obtain specific future predictions based on that data. This provides useful information for users to act in a planned manner, and the system itself can continuously collect data, thereby improving the accuracy of predictions.

[0644] (Application example 1)

[0645] 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."

[0646] In today's busy lifestyles, there is a need for systems that continuously monitor users' daily health status and lifestyle habits and predict future health conditions. However, existing systems have issues such as cumbersome data collection from users and inaccurate prediction results. Furthermore, there is a lack of visual feedback to users, making it difficult to provide specific health improvement measures.

[0647] 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.

[0648] In this invention, the server includes an input means for users to input their daily activities and current thoughts, a transmission means for transmitting the input data to the server, a storage means for storing the data received by the server for each user, an analysis means for generating future predictions and health predictions using an AI model based on the stored data, and an output means for providing the generated predictions to the user. This allows users to input their daily health data in an intuitively understandable manner and receive highly accurate future predictions using the AI ​​model. Furthermore, feedback in a visually understandable format makes it easier for users to create action plans for taking specific health improvement measures.

[0649] An "input means" is a device or interface that a user uses to input details of their daily activities and current thoughts.

[0650] "Transmitting means" refers to a communication device or protocol for transmitting data entered by a user to a server.

[0651] The "storage means" refers to a database or storage system that classifies and stores data received by the server for each user.

[0652] "Analytical means" means a computing device or software that uses AI models to generate future predictions and health predictions based on stored data.

[0653] The "output means" is a display device or an output interface for providing the generated prediction results to a user.

[0654] The "healthcare prediction means" is a system in which a user inputs data about their daily health condition and lifestyle habits, and predicts their future health condition based on the data sent to a server.

[0655] The "interface means" is a display device or user interface for visually presenting the generated health prediction results to the user.

[0656] The present invention is a system that uses an AI model to predict future health based on user input data on daily activities, health status, and lifestyle habits. First, the user inputs daily health data using a device such as a smartphone, tablet, or personal computer. The input method is a form or application designed for user ease of operation. The input form may include, for example, the number of steps taken, calorie intake, sleep time, stress level, and dietary quality.

[0657] Next, the data entered by the user is sent by the transmission means to a server via the Internet. A secure communication protocol is used for transmission, protecting the data from leaking to third parties. The received data is classified by user on the server and stored in a database. The stored data is managed so that it can be efficiently retrieved for later analysis and prediction.

[0658] The server uses the stored data to make future health predictions using an AI model. The AI ​​model is designed to learn from large amounts of past data and continuously improve its prediction accuracy. Specifically, the AI ​​model includes machine learning algorithms such as linear regression and deep learning.

[0659] The predicted results are provided to the user through an interface that displays the results in visually easy-to-understand graphs, charts, and text format, allowing the user to intuitively understand specific health advice and improvement measures.

[0660] For example, if a user enters the following health data:

[0661] Date: 2023-10-01

[0662] Steps: 8,000

[0663] Calorie intake: 2200kcal

[0664] Sleep time: 7 hours

[0665] Stress level: Moderate

[0666] Food quality: Average

[0667] This data is sent to a server and stored, after which the AI ​​model analyzes it to generate health predictions such as "Weight forecast in 3 months: Increase by 2kg from current weight" and "Future disease risk: High." The results are then provided to the user, who can then create a specific action plan.

[0668] The hardware used may include smartphones, tablets, and personal computers. The software used may include database management systems, communication protocols, and machine learning libraries (e.g., TensorFlow, scikit-learn). An example of a prompt from the user may be in the following format:

[0669] "Date: 2023-10-01, Steps: 8000, Calorie Intake: 2200kcal, Sleep: 7 hours, Stress Level: Medium, Diet Quality: Average"

[0670] The system of the present invention efficiently collects, stores, and analyzes this data, and provides useful health predictions to users, thereby assisting them in managing their health.

[0671] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0672] Step 1:

[0673] The user inputs daily health data.

[0674] Users use a smartphone, tablet, or personal computer to access a dedicated application or web form to enter data about their daily health and lifestyle habits, including the number of steps taken, calorie intake, sleep time, stress level, and diet quality. This input data is then used as the basis for further processing.

[0675] Step 2:

[0676] The terminal sends the input data to the server.

[0677] Input data is sent from the terminal to the server via a transmission means. A secure communication protocol such as HTTPS is used. The terminal properly formats the input data and performs error checking to prevent data loss during transmission. Once the data transmission is complete, the server receives the data.

[0678] Step 3:

[0679] The server stores the received data.

[0680] When the server receives the input data, it classifies it by user and stores it in a database. The data is stored in an organized format so that it can be efficiently searched and analyzed. For example, a database management system (DBMS) is used to store the data using the user ID as a key. At this data storage stage, the consistency and integrity of the data are verified.

[0681] Step 4:

[0682] The server uses an AI model to make predictions based on the stored data.

[0683] Based on the stored data, the server uses an AI model (for example, a model using TensorFlow or scikit-learn) to predict future health conditions. The model, which has learned from past data, receives each user's new health data as input and generates predictions such as weight changes and future disease risk. Specifically, the input data is preprocessed and fed into the AI ​​model to obtain predictions.

[0684] Step 5:

[0685] The server provides the generated prediction results to the user.

[0686] The generated prediction results are sent from the server to the terminal and provided to the user through an interface means. The prediction results are displayed in a visually easy-to-understand format, such as a graph, chart, or text, allowing the user to receive specific advice based on their own health condition.

[0687] Step 6:

[0688] The user creates an action plan based on the prediction results.

[0689] Based on the displayed prediction results, the user plans actions for managing their own health. For example, they consider specific lifestyle improvements such as reviewing their diet, increasing exercise, and adjusting their sleep schedule. In this step, it is desirable to add a feedback function to check whether the prediction results are reflected in the user's actions.

[0690] As described above, the system of the present invention efficiently collects, stores, and analyzes a user's health data and provides specific health predictions, thereby supporting the user's health management.

[0691] 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.

[0692] The present invention relates to a system in which a user inputs details of their daily activities and current thoughts, an emotion engine recognizes the user's emotions, the data is sent to a server for storage, and an AI model generates and provides future prediction results. A specific embodiment of this system will be described below.

[0693] User operation

[0694] Users input their daily activities and thoughts through the interface. The interface is designed as a simple multiple-choice form, and includes items such as "work progress," "health status," "relationships," and "study content." The emotion engine also recognizes the user's emotions.

[0695] Examples:

[0696] Users enter their daily information by selecting options such as:

[0697] "Work progress: Good"

[0698] Health condition: A little tired

[0699] "Interpersonal relationships: Good"

[0700] "What I'm learning: I'm learning new technology."

[0701] The emotion engine recognizes emotions such as "joy," "anger," "sadness," and "surprise" in real time.

[0702] Data transmission (operation on the terminal side)

[0703] The device collects data entered by the user and emotional data recognized by the emotion engine, converts it into an appropriate format, and transmits it to the server using a secure protocol to ensure data integrity.

[0704] Receiving and saving data (server-side operation)

[0705] The server receives the data sent from the device, classifies it by user, and stores it in a database. The stored data is used for later analysis. Emotion data is also recorded along with the user's past data.

[0706] Data analysis and prediction (server-side operation)

[0707] The server uses an AI model to make future predictions based on the stored data. The AI ​​model learns the user's past data and emotional data, and generates future prediction results based on the user's input data. The prediction results include, for example, the following elements:

[0708] Annual income forecast

[0709] Family structure prediction

[0710] Predicting career progression

[0711] By incorporating emotional data, more accurate predictions can be made that take into account the transitions in the user's emotional state and their impact.

[0712] Examples:

[0713] Based on the user's input data and emotional data, the server generates specific predictions such as "Expected annual income in five years: 6 million yen," "Family structure: married with one child," and "Career progress: manager position." The prediction results also include insights such as "Improving emotional state will have a positive impact on work progress."

[0714] Display of results (user and terminal actions)

[0715] The server sends the generated prediction results to the device, which then displays them to the user in a visually easy-to-understand format, such as graphs or charts.

[0716] Examples:

[0717] The user will see the following results on their screen:

[0718] "Expected annual income in 5 years: 6 million yen"

[0719] Family status: Married, one child

[0720] "Career Progression: Section Manager Position"

[0721] Additionally, insights incorporating emotional data are also displayed, providing specific advice such as, "It is important to maintain positive emotions as you progress in your career."

[0722] Continuous data collection and improvement

[0723] The system continuously collects user data and sentiment data, and uses that data to continuously train the AI ​​model to improve prediction accuracy. It also accepts user feedback and uses it to improve the model.

[0724] In this way, the system of the present invention combines user input data and emotional data to perform AI analysis and provide specific future predictions. Users can plan their next actions based on the prediction results, and in the process, they continuously provide data to help the system make more accurate predictions.

[0725] The processing flow will be explained below.

[0726] Step 1:

[0727] The user inputs details of their daily activities and current thoughts. Specifically, the user enters information such as the following into a multiple-choice form displayed on the device: "Work progress: Good," "Health condition: A little tired," "Interpersonal relationships: Good," "Study content: Learning new skills." The emotion engine also simultaneously recognizes the user's emotions. For example, emotions such as "joy," "anger," "sadness," and "surprise" can be automatically recognized from the user's facial expressions and text.

[0728] Step 2:

[0729] The device receives the input content and emotion data. The device collects the data entered by the user and the emotion data recognized by the emotion engine, and converts it into JSON format.

[0730] Step 3:

[0731] The device sends the collected data to the server. The device uses a secure protocol to send user data and emotion data to the server via a POST request.

[0732] Step 4:

[0733] The server receives the data sent from the terminal, identifies which user the data is from, and checks the integrity of the data.

[0734] Step 5:

[0735] The server classifies the received data by user and stores it in a database. The stored data includes the user's activity, thoughts, and emotions. This data is used for later analysis.

[0736] Step 6:

[0737] The server retrieves user data from the database and inputs it into the AI ​​model, which uses machine learning algorithms to learn from the user's past data and emotional data.

[0738] Step 7:

[0739] The server uses an AI model to analyze the data and generate future predictions. The AI ​​model generates predictions such as annual income, family composition, and career progress based on the user's activities, thoughts, and emotional data. By taking emotional data into account, predictions can be made that include the impact that emotions will have on the user's future.

[0740] Step 8:

[0741] The server organizes the generated forecasts and sends them to the device, often formatted as graphs or charts.

[0742] Step 9:

[0743] The device displays the prediction results received from the server to the user in a visually easy-to-understand format so that the user can easily understand them.

[0744] Step 10:

[0745] Users can create their own action plan based on the displayed prediction results. Users can consider specific actions and take action based on them. Insights including emotional data are also displayed, such as "Improving your emotional state will have a positive impact on work progress."

[0746] Step 11:

[0747] The server collects new data and feedback from users, which is then fed back into the AI ​​model to help improve its prediction accuracy.

[0748] In this way, the system combines user input data with emotional data for AI analysis to provide specific future predictions. Users can plan their next actions based on the prediction results, and in the process, they continuously provide data to help the system make more accurate predictions.

[0749] Example 2

[0750] 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."

[0751] Conventional systems have issues with the accuracy of analyzing data when inputting user activities and thoughts, and making predictions based on that data. Another issue is that it is difficult to provide predictions that fully reflect the user's emotional data.

[0752] 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 following means are included: interface means for the user to input daily activities and current thoughts, emotion engine means for analyzing the input data and recognizing emotions, communication means for transmitting the analyzed data to a server, storage means for saving the data on the server, analysis means for generating future prediction results using a generative AI model based on the saved data, and display means for visually presenting the generated prediction results to the user. This makes it possible to accurately analyze the user's activities and emotion data and make highly accurate future predictions.

[0753] "Interface means" refers to the means by which a user inputs details of their daily activities and current thoughts, and specifically refers to a multiple-choice form or input screen.

[0754] The "emotion engine means" is a means having the function of analyzing input data and recognizing the user's emotions, and refers to an engine that performs emotion analysis using natural language processing technology, etc.

[0755] "Communication means" refers to the means for sending analyzed data to the server, and refers to the function for transferring data using a secure communication protocol (e.g., HTTPS).

[0756] "Storage means" refers to a means for storing data received by the server, and refers to the function of storing data using a database or other storage medium.

[0757] A "generative AI model" is an AI technology that generates future predictions based on stored data, and refers to a model that uses machine learning and deep learning to learn and make predictions.

[0758] "Analysis means" refers to a means that has the function of analyzing stored data using a generative AI model and generating future prediction results.

[0759] "Display means" refers to a means for providing the generated prediction results in a format that allows the user to visually confirm them, and specifically refers to a screen or interface that displays graphs and charts.

[0760] MODE FOR CARRYING OUT THE INVENTION

[0761] This invention relates to a system in which a user inputs details of their daily activities and current thoughts, an emotion engine is used to recognize the user's emotions, the data is sent to a server for storage, and a generative AI model is used to generate and provide future prediction results. Specific embodiments of this system are described below.

[0762] User operation

[0763] Users access a dedicated application or web interface using a device such as a smartphone or PC. The interface is designed as a simple multiple-choice form that includes items such as "work progress," "health status," "relationships," and "study content."

[0764] Examples:

[0765] The user enters the details of their daily activities as follows:

[0766] "Work progress: Good"

[0767] Health condition: A little tired

[0768] "Interpersonal relationships: Good"

[0769] "What I'm learning: I'm learning new technology."

[0770] Data analysis using emotion engine

[0771] The device is equipped with an emotion engine that analyzes emotions in real time based on the user input data. This emotion engine uses natural language processing libraries (e.g., NLTK and SpaCy) to recognize emotions such as "joy," "anger," "sadness," and "surprise."

[0772] Data transmission and storage

[0773] The device combines the recognized emotion data and the activity data entered by the user and sends it to a server using a secure protocol such as HTTPS. The server analyzes the received data, classifies it by user, and stores it in a database using a relational database (e.g., MySQL or PostgreSQL).

[0774] Data analysis and future predictions

[0775] The server uses the stored data to generate future predictions using a generative AI model, which uses machine learning and deep learning (e.g., TensorFlow and PyTorch) to learn from the user's past data and emotional data and generate future predictions.

[0776] Examples:

[0777] Based on the user's input data and emotional data, the server generates specific predictions such as "Expected annual income in five years: 6 million yen," "Family structure: married with one child," and "Career progress: manager position." The prediction results also include insights such as "Improving emotional state will have a positive impact on work progress."

[0778] Displaying the results

[0779] The server sends the generated forecast results to the device, which then displays them in a visually easy-to-understand format, using graphs and charts, allowing the user to intuitively understand future forecast results.

[0780] Examples:

[0781] The user will see the following results on their screen:

[0782] "Expected annual income in 5 years: 6 million yen"

[0783] Family status: Married, one child

[0784] "Career Progression: Section Manager Position"

[0785] In addition, specific advice is provided, such as "It is important to maintain a positive attitude in order to advance your career in the future."

[0786] Continuous data collection and model improvement

[0787] The system continuously collects data from users and uses that data to train the AI ​​model to improve prediction accuracy, while also accepting user feedback to improve the model.

[0788] This invention combines user input data with emotional data for AI analysis to provide specific future predictions. Users can plan their next actions based on the prediction results, and in the process, they continuously provide data to help the system make more accurate predictions.

[0789] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0790] Step 1:

[0791] The user inputs the activity and thoughts

[0792] Users input their daily activities and thoughts through a smartphone or PC interface. The interface displays options such as "Work progress," "Health status," "Interpersonal relationships," and "Study content." The user completes the input by entering each item and clicking the "Submit" button. Input data may include, for example, "Work progress: Good" or "Health status: A little tired."

[0793] Input: Data entered by the user into the interface

[0794] Output: Data sent from the interface to the terminal

[0795] Specific behavior:

[0796] The user launches an application.

[0797] Click the "Enter today's activity" button.

[0798] The user selects the appropriate option for each item and clicks the "Submit" button.

[0799] Step 2:

[0800] The device uses an emotion engine to recognize emotions

[0801] The device analyzes the data entered by the user in real time and recognizes the user's emotions using natural language processing libraries (such as NLTK or SpaCy). The emotion engine performs text analysis on the input data and identifies emotions such as "joy," "anger," "sadness," and "surprise."

[0802] Input: Data entered by the user

[0803] Output: Emotion data recognized by the emotion engine

[0804] Specific behavior:

[0805] The terminal receives input data.

[0806] The emotion engine analyzes the input data.

[0807] Emotional data is extracted as the analysis result.

[0808] Step 3:

[0809] The device sends the data to the server

[0810] The device combines the user's input data and the emotion data recognized by the emotion engine into a single data packet and sends it to the server using a secure protocol such as HTTPS.

[0811] Input: User input data and recognized emotion data

[0812] Output: Data packets sent to the server

[0813] Specific behavior:

[0814] The device integrates input data and emotion data.

[0815] The integrated data is converted into data packets.

[0816] The data packet is sent to the server using the HTTPS protocol.

[0817] Step 4:

[0818] The server receives and stores the data

[0819] The server receives the data sent from the device, analyzes it, and stores it in a database. The data is classified by user and stored for later analysis. The database is a relational database (e.g., MySQL or PostgreSQL).

[0820] Input: Data packets sent from the device

[0821] Output: User data stored in the database

[0822] Specific behavior:

[0823] The server receives the data packet.

[0824] The received data is analyzed and classified by user.

[0825] Insert the classified data into the database.

[0826] Step 5:

[0827] The server analyzes the data using an AI model and makes predictions

[0828] The server uses the stored data to make future predictions using a generative AI model, which uses machine learning libraries (such as TensorFlow or PyTorch) to learn from the user's past data and emotional data to generate future predictions.

[0829] Input: User data stored in the database

[0830] Output: Future prediction results generated by the generative AI model

[0831] Specific behavior:

[0832] The server retrieves the user's past data from the database.

[0833] A generative AI model learns and analyzes data.

[0834] Future predictions are generated as a result of the analysis.

[0835] Step 6:

[0836] The server sends the prediction results to the device.

[0837] The server formats the generated prediction results into an appropriate format and sends them to the device using a secure protocol such as HTTPS.

[0838] Input: Prediction results generated by a generative AI model

[0839] Output: Prediction results are sent in a nicely formatted format

[0840] Specific behavior:

[0841] The server receives and formats the prediction results.

[0842] The formatted prediction results are converted into data packets.

[0843] The data packet is sent to the terminal using the HTTPS protocol.

[0844] Step 7:

[0845] The device displays the prediction results to the user.

[0846] The terminal displays the prediction results received from the server to the user in a visually easy-to-understand format such as graphs and charts.

[0847] Input: Prediction results sent from the server

[0848] Output: Visually displayed prediction results

[0849] Specific behavior:

[0850] The terminal analyzes the data received from the server.

[0851] Create UI components to generate graphs and charts to visually display information.

[0852] The generated UI components are displayed on the screen.

[0853] Step 8:

[0854] The system continuously collects data and improves the model

[0855] The system continuously collects data from users and uses that data to train the generative AI model to improve prediction accuracy, while also incorporating user feedback to improve the model.

[0856] Input: New data and user feedback collected continuously

[0857] Output: A generative AI model with improved prediction accuracy

[0858] Specific behavior:

[0859] The server continuously collects new data.

[0860] Update the training of generative AI models based on new data.

[0861] Evaluate the accuracy of the model and make any necessary improvements.

[0862] (Application example 2)

[0863] 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."

[0864] Conventional systems were able to collect data on a user's daily activities and thoughts and make future predictions, but they were inadequate for predicting specific purchasing behavior or managing spending that reflected the user's emotional state. Furthermore, they lacked the ability to provide specific advice to users, which meant that users were unable to fully utilize the data. The purpose of this invention is to solve these problems.

[0865] The identification processing 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 an input means for the user to input daily activities and current thoughts, a transmission means for transmitting the input data to the server, a storage means for storing the data received by the server for each user, an analysis means for generating future prediction results using an AI model based on the stored data and emotional data, an output means for providing the generated prediction results to the user, an emotion recognition means for recognizing the emotional state of the user, an expenditure management means for predicting and managing purchasing behavior, and an insight provision means for providing actionable advice to the user. This enables more accurate prediction of purchasing behavior and expenditure management that takes emotional data into account, and makes it possible to provide specific and actionable advice to the user.

[0866] "Daily activities" is a record of the tasks and actions that a user performs on a daily basis.

[0867] "Current thinking" refers to the thoughts and opinions that a user has at that time.

[0868] "Input means" refers to an interface or device that allows a user to input their daily activities and current thoughts into the system.

[0869] "Transmission means" refers to the method or technology used to send the entered data to the server.

[0870] "Storage means" refers to the technology or device that the server uses to maintain and store the data it receives for each user.

[0871] "Emotion recognition means" refers to a method or technology that analyzes the user's emotional state in real time and recognizes it as data.

[0872] "Analysis Method" means a method or technique for generating future predictions using an AI model based on stored data and sentiment data.

[0873] "Output means" refers to a method or technology for providing the generated prediction results to a user.

[0874] A "spend manager" is a method or technique for predicting and managing a user's purchasing behavior.

[0875] An "insight providing means" is a method or technology for providing specific, actionable advice to a user.

[0876] An "AI model" is an artificial intelligence technology used to analyze data and make future predictions.

[0877] "Emotion data" refers to data that represents the user's emotional state.

[0878] "Purchasing behavior" refers to the behavioral patterns of users when purchasing products or services.

[0879] "Specific advice" refers to detailed, actionable instructions or advice on what actions or precautions the user should take.

[0880] This invention is a system that inputs a user's daily activities and current thoughts, predicts future purchasing behavior and expenditure management based on that data and emotion recognition data, and provides the user with specific advice. A specific embodiment of this system is described below.

[0881] First, users use devices such as smartphones or tablets to input details of their daily activities and current thoughts. An application using React Native is used as the input method. Users can easily enter details of their activities and thoughts using a text input form.

[0882] At the same time, the device's camera is used to recognize the user's emotional state in real time. The emotion recognition method uses the Azure Cognitive Services API, which acquires the user's emotional data.

[0883] These input data and emotion data are securely sent to the server via HTTPS. The server is built with Node.js and stores the received data in a MongoDB database. The stored data is organized by user, ensuring data integrity.

[0884] The server uses TensorFlow to perform analysis using an AI model based on the stored data and sentiment data. The analysis involves preprocessing the data using Python's pandas and NumPy, converting it into a format suitable for input into the AI ​​model. The AI ​​model learns from past data to predict future purchasing behavior and spending, and returns the resulting predictions.

[0885] The prediction results include information on the user's purchasing behavior patterns and spending management. Furthermore, the insight providing means generates specific actions and advice that the user should take, allowing the user to efficiently manage their spending in their daily lives.

[0886] Finally, the device presents the prediction results and advice sent from the server to the user in a visually easy-to-understand format. Graphs and charts can be used as visualization methods, allowing the user to easily understand the future predictions and the specific advice based on them.

[0887] Additionally, the system continuously collects data and learns to improve the accuracy of the AI ​​model, and user feedback can be incorporated and used to improve the model.

[0888] As a concrete example, the following prompt sentence is input to the generative AI model:

[0889] "EmotionPay has analyzed your emotional data and purchasing behavior over the past six months. Please show us the results of your analysis of your financial situation one year from now if you continue your current spending patterns, and the impact of your emotional data on your purchasing behavior."

[0890] Based on this, the AI ​​model returns the following results:

[0891] "Based on data from the past six months, our analysis shows that if people continue their current spending patterns, their savings will increase by 10% in one year. Furthermore, our sentiment data shows that positive emotions have a positive impact on purchasing decisions. Maintaining positive emotions will be a key factor in supporting financial stability."

[0892] In this way, the present invention realizes a system that allows users to predict purchasing behavior while utilizing emotion data and manage spending more effectively.

[0893] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0894] Step 1:

[0895] Users use a smartphone or tablet device to input their daily activities and current thoughts into a React Native application. The user enters specific details of their activities and thoughts into a text input form, and the data is sent to the application. Examples of input data include "Work progress: Good" and "Health condition: A little tired."

[0896] Step 2:

[0897] Using the device's camera, the system recognizes the user's emotions in real time through the Azure Cognitive Services API. Emotion analysis is performed based on images captured by the camera, and emotional data such as joy, anger, and sadness is generated. An example of emotional data is "Emotion: Happiness."

[0898] Step 3:

[0899] The device sends the activity details entered in step 1 and the emotion data recognized in step 2 to the server using the HTTPS protocol. The pair of input data and emotion data is sent to the server.

[0900] Step 4:

[0901] The server runs on Node.js and receives data sent from the device. The received data is stored in MongoDB and classified by user. The data is saved with a date and used for later analysis.

[0902] Step 5:

[0903] The server uses TensorFlow to preprocess the saved activity data and emotion data for input into the AI ​​model. Python's pandas and NumPy are used to clean the data and convert it into an input format for the AI ​​model. After preprocessing, the input data includes "Work progress: Good" and "Emotion: Happy."

[0904] Step 6:

[0905] The AI ​​model uses TensorFlow as an analysis tool to predict future purchasing behavior and spending. Predictions are generated based on the user's past data. The output predictions include "There is a high probability that spending will increase by 10% over the next six months."

[0906] Step 7:

[0907] The server analyzes the generated prediction results using insight provision methods and creates actionable advice for the user. It generates a prompt sentence and inputs specific advice from the prediction results into the generative AI model. An example of a prompt sentence in this case is, "After analyzing data from the past six months, we have determined that your expenses may increase by 10%. We recommend that you take the following actions to save money."

[0908] Step 8:

[0909] The server converts the forecast results and advice into HTML format and sends them to the device. A visualization tool is used to display them in easy-to-understand graphs and charts. The output data includes a "spending forecast" and "specific savings advice."

[0910] Step 9:

[0911] The terminal displays the prediction results and advice sent from the server on the user interface of the React Native application. The user can visually check the results and decide whether to take action. Specific examples of what is displayed in this step include "Expenses may increase by 10% over the next six months" and "Savings action: Eat out less."

[0912] Step 10:

[0913] The system continuously collects new data from users and updates the AI ​​model's learning to improve its prediction accuracy. User feedback is also incorporated and reflected in the model's improvements. Data from this step includes user feedback such as "Feedback: The advice was helpful."

[0914] This allows the system to utilize user emotional data to predict future purchasing behavior and provide more effective spending management.

[0915] 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.

[0916] 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.

[0917] 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.

[0918] [Third embodiment]

[0919] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0920] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0921] 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).

[0922] 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.

[0923] 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.

[0924] 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).

[0925] 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.

[0926] 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.

[0927] 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.

[0928] 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.

[0929] 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.

[0930] 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."

[0931] The present invention relates to a system in which a user inputs details of their daily activities and current thoughts, sends the data to a server where it is stored, and generates and provides future prediction results using an AI model. A specific embodiment of this system will be described below.

[0932] User operation

[0933] Users input their daily activities and thoughts through the interface, which is designed as a simple multiple-choice form and includes items such as "work progress," "health status," "relationships," and "study content."

[0934] Examples:

[0935] Users enter their daily information by selecting options such as:

[0936] "Work progress: Good"

[0937] Health condition: A little tired

[0938] "Interpersonal relationships: Good"

[0939] "What I'm learning: I'm learning new technology."

[0940] Data transmission (operation on the terminal side)

[0941] The terminal collects the data entered by the user, converts it into the appropriate format, and sends it to the server, using a secure protocol to ensure the integrity of the data.

[0942] Receiving and saving data (server-side operation)

[0943] The server receives the data sent from the devices, classifies it by user, and stores it in a database. The stored data will be used for later analysis, so the database design ensures efficient data acquisition and storage.

[0944] Data analysis and prediction (server-side operation)

[0945] The AI ​​model makes future predictions based on data stored on the server. The AI ​​model learns from past data and generates future prediction results based on user input data. The prediction results include, for example, the following elements:

[0946] Annual income forecast

[0947] Family structure prediction

[0948] Predicting career progression

[0949] Examples:

[0950] Based on the user's input data, the server generates specific predictions such as "Expected annual income in five years: 6 million yen," "Family composition: married with one child," and "Career progress: section manager position."

[0951] Display of results (user and terminal actions)

[0952] The server sends the generated prediction results to the device, which then displays them to the user in a visually understandable format, such as graphs or charts.

[0953] Examples:

[0954] The user will see the following results on their screen:

[0955] "Expected annual income in 5 years: 6 million yen"

[0956] Family status: Married, one child

[0957] "Career Progression: Section Manager Position"

[0958] Users can create specific action plans based on these prediction results.

[0959] Continuous data collection and improvement

[0960] The system continuously collects data from users and uses that data to train the AI ​​model to improve prediction accuracy, while also accepting user feedback to improve the model.

[0961] In this way, the system of the present invention performs AI analysis based on user input data and provides specific future predictions. Users can plan their next actions based on the prediction results, and in the process, they continuously provide data to help the system make more accurate predictions.

[0962] The processing flow will be explained below.

[0963] Step 1:

[0964] The user inputs details of their daily activities and current thoughts. Specifically, the user enters the following information into a multiple-choice form displayed on the device: "Work progress: Good," "Health condition: A little tired," "Interpersonal relationships: Good," "Study content: Learning new skills."

[0965] Step 2:

[0966] The device receives the input, collects the data entered by the user, and converts it into a suitable format, which is then sent to a server for storage and analysis.

[0967] Step 3:

[0968] The device sends the collected data to the server. The device uses a secure protocol to send user data to the server via a POST request. The data sent is generally in JSON format.

[0969] Step 4:

[0970] The server receives the data sent from the terminal, analyzes the received data, identifies which user the data came from, and checks the integrity of the data.

[0971] Step 5:

[0972] The server classifies the received data by user and stores it in a database. The stored data is managed together with the user's past data. The database design has a structure that allows for efficient data retrieval and storage.

[0973] Step 6:

[0974] The server retrieves user data from a database and inputs it into an AI model, which uses machine learning algorithms to learn patterns from the user's past data.

[0975] Step 7:

[0976] The server uses AI models to analyze the data and generate future predictions, such as predicted annual income in five years, family structure, and career progression.

[0977] Step 8:

[0978] The server organizes the generated predictions and sends them to the device, possibly formatting the results in graphs or charts.

[0979] Step 9:

[0980] The device displays the prediction results received from the server to the user in a visually easy-to-understand format so that the user can easily understand them.

[0981] Step 10:

[0982] Users can create their own action plans based on the displayed prediction results. Users can think of specific actions and carry out activities based on those actions.

[0983] Step 11:

[0984] The server collects new data and feedback from users, which is then fed back into the AI ​​model to help improve prediction accuracy.

[0985] In this way, the system is composed of a series of steps, starting with user input, followed by data transmission, storage, analysis, and display of results. By inputting their daily activities, users can obtain specific predictions for the future, enabling them to create action plans based on those predictions.

[0986] Example 1

[0987] 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."

[0988] In today's busy lifestyles, it is not easy for individuals to continually review and improve their daily activities while keeping future prospects and goals in mind. In particular, there is a lack of methods for objectively analyzing a wide range of factors, such as one's health, work progress, relationships, and learning content, to obtain future predictions. As a result, it is difficult for individuals to have a long-term perspective and act in a planned manner. Therefore, there is a need for a system that performs AI analysis based on user input data and provides specific future predictions.

[0989] 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.

[0990] In this invention, the server includes an interface means for users to input their daily activities and current thoughts, a communication means for transmitting the input data to the server, a database means for classifying and storing the data received by the server for each user, an analysis means for generating future prediction results using a generative AI model based on the stored data, and a display means for visually presenting the generated prediction results to the user. This allows users to continuously input their own activity data and obtain specific future predictions based on that data.

[0991] The "interface means" is an operation screen or input device that allows the user to input details of daily activities and current thoughts.

[0992] "Communication means" refers to the communication protocols and techniques used to transmit the data entered by the user to the server.

[0993] The "database means" refers to a storage device and its management system for classifying and storing data received by the server for each user.

[0994] A "generative AI model" is an artificial intelligence model and its implementation technology that generates future prediction results based on stored data.

[0995] "Analytical Tools" are the processes and techniques that analyze stored data and generate future predicted outcomes using generative AI models.

[0996] The "display means" refers to a display device and its management software for visually presenting the generated prediction results to the user.

[0997] The present invention relates to a system in which a user inputs details of their daily activities and current thoughts, sends the data to a server for storage, and generates and provides future prediction results using a generative AI model. A detailed description of specific embodiments of this system is provided below.

[0998] User data entry

[0999] Users input their daily activities and thoughts through the interface. The interface is designed as a simple multiple-choice form, and includes items such as "work progress," "health status," "relationships," and "study content." This allows users to easily enter data.

[1000] Examples:

[1001] Users enter their daily activities by selecting options such as:

[1002] Work progress: Good

[1003] Health condition: A little tired

[1004] Relationships: Good

[1005] Learning content: Learning new technology

[1006] Data transmission (operation on the terminal side)

[1007] The device collects the data entered by the user, converts it into the appropriate format, and sends it to the server, using secure protocols such as HTTPS to ensure data security.

[1008] Data reception and storage (server-side operation)

[1009] The server receives the data sent from the device, classifies it by user, and stores it in a database. The database system used is MySQL or PostgreSQL. By setting appropriate indexes, it is possible to retrieve and store data efficiently.

[1010] Data analysis and prediction (server-side operation)

[1011] The server uses a generative AI model based on the stored data to make future predictions. This generative AI model is built using frameworks such as TensorFlow and PyTorch, and predicts the user's future state based on past data. Prediction results include, for example, predictions of annual income, family composition, and career progress.

[1012] Examples:

[1013] The server generates a concrete prediction:

[1014] Estimated annual income in 5 years: 6 million yen

[1015] Family: Married, 1 child

[1016] Career progression: Manager position

[1017] Display of results (user and terminal actions)

[1018] The server sends the generated prediction results to the device, which then displays them to the user in a visually easy-to-understand format, such as graphs or charts, allowing the user to intuitively understand the future prediction results.

[1019] Examples:

[1020] The user will see the following result on their screen:

[1021] Estimated annual income in 5 years: 6 million yen

[1022] Family: Married, 1 child

[1023] Career progression: Manager position

[1024] Input prompt for generative AI model

[1025] An example of an input prompt for a generative AI model is as follows:

[1026] User daily activity data:

[1027] Work progress: Good

[1028] Health condition: A little tired

[1029] Relationships: Good

[1030] Learning content: Learning new technology

[1031] Based on this, please provide your predicted results for the next five years.

[1032] This allows the system of the present invention to perform AI analysis based on data entered by the user and provide specific future predictions.The user can plan their next actions based on the prediction results and continuously provide data in the process, thereby helping the system make more accurate predictions.

[1033] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1034] Step 1:

[1035] User data entry

[1036] Users enter their daily activities and thoughts through the interface. The data is categorized into categories such as "work progress," "health status," "relationships," and "study content," and the interface presents them as a simple multiple-choice form.

[1037] input:

[1038] The user selects the following data on the interface:

[1039] Work progress: Good

[1040] Health condition: A little tired

[1041] Relationships: Good

[1042] Learning content: Learning new technology

[1043] Specific behavior:

[1044] The user selects the appropriate option for each item.

[1045] Once the input is complete, the data is compiled into a single data structure (e.g., JSON).

[1046] output:

[1047] Well-formed data structures (e.g., JSON-formatted data)

[1048] Step 2:

[1049] Data transmission (operation on the terminal side)

[1050] The device collects the data entered by the user, converts it into the appropriate format, and sends it to the server, using secure protocols such as HTTPS to ensure data security.

[1051] input:

[1052] Data entered by the user on the interface (formatted data structure)

[1053] Specific behavior:

[1054] The terminal formats the input data in JSON format.

[1055] Send the formatted data to the server using the HTTPS protocol.

[1056] output:

[1057] Data sent to the server (encrypted data in JSON format)

[1058] Step 3:

[1059] Data reception and storage (server-side operation)

[1060] The server receives the data sent from the terminal, classifies it by user, and stores it in a database.

[1061] input:

[1062] Data sent from the device (JSON format data)

[1063] Specific behavior:

[1064] The server parses the received HTTP request and extracts the data.

[1065] The extracted data is classified by user ID.

[1066] Execute the appropriate SQL queries to insert data into the database.

[1067] output:

[1068] User data stored in a database

[1069] Step 4:

[1070] Data analysis and prediction (server-side operation)

[1071] The server uses a generative AI model based on the stored data to make future predictions.

[1072] input:

[1073] User data stored in a database

[1074] Specific behavior:

[1075] The server retrieves the user's data from the database.

[1076] Input data into a generative AI model (e.g., using TensorFlow or PyTorch) and run a predictive algorithm.

[1077] Generate prediction results and organize them by user.

[1078] output:

[1079] Generated prediction results (e.g., predicted annual income in 5 years, family structure, career progress)

[1080] Step 5:

[1081] Display of results (user and terminal actions)

[1082] The server transmits the generated prediction results to the terminal, which displays them to the user in a visually easy-to-understand format.

[1083] input:

[1084] Generated prediction results (e.g., data encoded in JSON format)

[1085] Specific behavior:

[1086] The server sends the generated prediction results to the terminal in JSON format.

[1087] The device analyzes the received data, converts it into graphs and charts, and displays them to the user.

[1088] output:

[1089] Prediction results displayed on the user's screen (in graph and chart format)

[1090] The above is the specific processing flow of this system's program. Based on this flow, users can input their daily data and obtain specific future predictions based on that data. This provides useful information for users to act in a planned manner, and the system itself can continuously collect data, thereby improving the accuracy of predictions.

[1091] (Application example 1)

[1092] 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."

[1093] In today's busy lifestyles, there is a need for systems that continuously monitor users' daily health status and lifestyle habits and predict future health conditions. However, existing systems have issues such as cumbersome data collection from users and inaccurate prediction results. Furthermore, there is a lack of visual feedback to users, making it difficult to provide specific health improvement measures.

[1094] 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.

[1095] In this invention, the server includes an input means for users to input their daily activities and current thoughts, a transmission means for transmitting the input data to the server, a storage means for storing the data received by the server for each user, an analysis means for generating future predictions and health predictions using an AI model based on the stored data, and an output means for providing the generated predictions to the user. This allows users to input their daily health data in an intuitively understandable manner and receive highly accurate future predictions using the AI ​​model. Furthermore, feedback in a visually understandable format makes it easier for users to create action plans for taking specific health improvement measures.

[1096] An "input means" is a device or interface that a user uses to input details of their daily activities and current thoughts.

[1097] "Transmitting means" refers to a communication device or protocol for transmitting data entered by a user to a server.

[1098] The "storage means" refers to a database or storage system that classifies and stores data received by the server for each user.

[1099] "Analytical means" means a computing device or software that uses AI models to generate future predictions and health predictions based on stored data.

[1100] The "output means" is a display device or an output interface for providing the generated prediction results to a user.

[1101] The "healthcare prediction means" is a system in which a user inputs data about their daily health condition and lifestyle habits, and predicts their future health condition based on the data sent to a server.

[1102] The "interface means" is a display device or user interface for visually presenting the generated health prediction results to the user.

[1103] The present invention is a system that uses an AI model to predict future health based on user input data on daily activities, health status, and lifestyle habits. First, the user inputs daily health data using a device such as a smartphone, tablet, or personal computer. The input method is a form or application designed for user ease of operation. The input form may include, for example, the number of steps taken, calorie intake, sleep time, stress level, and dietary quality.

[1104] Next, the data entered by the user is sent by the transmission means to a server via the Internet. A secure communication protocol is used for transmission, protecting the data from leaking to third parties. The received data is classified by user on the server and stored in a database. The stored data is managed so that it can be efficiently retrieved for later analysis and prediction.

[1105] The server uses the stored data to make future health predictions using an AI model. The AI ​​model is designed to learn from large amounts of past data and continuously improve its prediction accuracy. Specifically, the AI ​​model includes machine learning algorithms such as linear regression and deep learning.

[1106] The predicted results are provided to the user through an interface that displays the results in visually easy-to-understand graphs, charts, and text format, allowing the user to intuitively understand specific health advice and improvement measures.

[1107] For example, if a user enters the following health data:

[1108] Date: 2023-10-01

[1109] Steps: 8,000

[1110] Calorie intake: 2200kcal

[1111] Sleep time: 7 hours

[1112] Stress level: Moderate

[1113] Food quality: Average

[1114] This data is sent to a server and stored, after which the AI ​​model analyzes it to generate health predictions such as "Weight forecast in 3 months: Increase by 2kg from current weight" and "Future disease risk: High." The results are then provided to the user, who can then create a specific action plan.

[1115] The hardware used may include smartphones, tablets, and personal computers. The software used may include database management systems, communication protocols, and machine learning libraries (e.g., TensorFlow, scikit-learn). An example of a prompt from the user may be in the following format:

[1116] "Date: 2023-10-01, Steps: 8000, Calorie Intake: 2200kcal, Sleep: 7 hours, Stress Level: Medium, Diet Quality: Average"

[1117] The system of the present invention efficiently collects, stores, and analyzes this data, and provides useful health predictions to users, thereby assisting them in managing their health.

[1118] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1119] Step 1:

[1120] The user inputs daily health data.

[1121] Users use a smartphone, tablet, or personal computer to access a dedicated application or web form to enter data about their daily health and lifestyle habits, including the number of steps taken, calorie intake, sleep time, stress level, and diet quality. This input data is then used as the basis for further processing.

[1122] Step 2:

[1123] The terminal sends the input data to the server.

[1124] Input data is sent from the terminal to the server via a transmission means. A secure communication protocol such as HTTPS is used. The terminal properly formats the input data and performs error checking to prevent data loss during transmission. Once the data transmission is complete, the server receives the data.

[1125] Step 3:

[1126] The server stores the received data.

[1127] When the server receives the input data, it classifies it by user and stores it in a database. The data is stored in an organized format so that it can be efficiently searched and analyzed. For example, a database management system (DBMS) is used to store the data using the user ID as a key. At this data storage stage, the consistency and integrity of the data are verified.

[1128] Step 4:

[1129] The server uses an AI model to make predictions based on the stored data.

[1130] Based on the stored data, the server uses an AI model (for example, a model using TensorFlow or scikit-learn) to predict future health conditions. The model, which has learned from past data, receives each user's new health data as input and generates predictions such as weight changes and future disease risk. Specifically, the input data is preprocessed and fed into the AI ​​model to obtain predictions.

[1131] Step 5:

[1132] The server provides the generated prediction results to the user.

[1133] The generated prediction results are sent from the server to the terminal and provided to the user through an interface means. The prediction results are displayed in a visually easy-to-understand format, such as a graph, chart, or text, allowing the user to receive specific advice based on their own health condition.

[1134] Step 6:

[1135] The user creates an action plan based on the prediction results.

[1136] Based on the displayed prediction results, the user plans actions for managing their own health. For example, they consider specific lifestyle improvements such as reviewing their diet, increasing exercise, and adjusting their sleep schedule. In this step, it is desirable to add a feedback function to check whether the prediction results are reflected in the user's actions.

[1137] As described above, the system of the present invention efficiently collects, stores, and analyzes a user's health data and provides specific health predictions, thereby supporting the user's health management.

[1138] 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.

[1139] The present invention relates to a system in which a user inputs details of their daily activities and current thoughts, an emotion engine recognizes the user's emotions, the data is sent to a server for storage, and an AI model generates and provides future prediction results. A specific embodiment of this system will be described below.

[1140] User operation

[1141] Users input their daily activities and thoughts through the interface. The interface is designed as a simple multiple-choice form, and includes items such as "work progress," "health status," "relationships," and "study content." The emotion engine also recognizes the user's emotions.

[1142] Examples:

[1143] Users enter their daily information by selecting options such as:

[1144] "Work progress: Good"

[1145] Health condition: A little tired

[1146] "Interpersonal relationships: Good"

[1147] "What I'm learning: I'm learning new technology."

[1148] The emotion engine recognizes emotions such as "joy," "anger," "sadness," and "surprise" in real time.

[1149] Data transmission (operation on the terminal side)

[1150] The device collects data entered by the user and emotional data recognized by the emotion engine, converts it into an appropriate format, and transmits it to the server using a secure protocol to ensure data integrity.

[1151] Receiving and saving data (server-side operation)

[1152] The server receives the data sent from the device, classifies it by user, and stores it in a database. The stored data is used for later analysis. Emotion data is also recorded along with the user's past data.

[1153] Data analysis and prediction (server-side operation)

[1154] The server uses an AI model to make future predictions based on the stored data. The AI ​​model learns the user's past data and emotional data, and generates future prediction results based on the user's input data. The prediction results include, for example, the following elements:

[1155] Annual income forecast

[1156] Family structure prediction

[1157] Predicting career progression

[1158] By incorporating emotional data, more accurate predictions can be made that take into account the transitions in the user's emotional state and their impact.

[1159] Examples:

[1160] Based on the user's input data and emotional data, the server generates specific predictions such as "Expected annual income in five years: 6 million yen," "Family structure: married with one child," and "Career progress: manager position." The prediction results also include insights such as "Improving emotional state will have a positive impact on work progress."

[1161] Display of results (user and terminal actions)

[1162] The server sends the generated prediction results to the device, which then displays them to the user in a visually easy-to-understand format, such as graphs or charts.

[1163] Examples:

[1164] The user will see the following results on their screen:

[1165] "Expected annual income in 5 years: 6 million yen"

[1166] Family status: Married, one child

[1167] "Career Progression: Section Manager Position"

[1168] Additionally, insights incorporating emotional data are also displayed, providing specific advice such as, "It is important to maintain positive emotions as you progress in your career."

[1169] Continuous data collection and improvement

[1170] The system continuously collects user data and sentiment data, and uses that data to continuously train the AI ​​model to improve prediction accuracy. It also accepts user feedback and uses it to improve the model.

[1171] In this way, the system of the present invention combines user input data and emotional data to perform AI analysis and provide specific future predictions. Users can plan their next actions based on the prediction results, and in the process, they continuously provide data to help the system make more accurate predictions.

[1172] The processing flow will be explained below.

[1173] Step 1:

[1174] The user inputs details of their daily activities and current thoughts. Specifically, the user enters information such as the following into a multiple-choice form displayed on the device: "Work progress: Good," "Health condition: A little tired," "Interpersonal relationships: Good," "Study content: Learning new skills." The emotion engine also simultaneously recognizes the user's emotions. For example, emotions such as "joy," "anger," "sadness," and "surprise" can be automatically recognized from the user's facial expressions and text.

[1175] Step 2:

[1176] The device receives the input content and emotion data. The device collects the data entered by the user and the emotion data recognized by the emotion engine, and converts it into JSON format.

[1177] Step 3:

[1178] The device sends the collected data to the server. The device uses a secure protocol to send user data and emotion data to the server via a POST request.

[1179] Step 4:

[1180] The server receives the data sent from the terminal, identifies which user the data is from, and checks the integrity of the data.

[1181] Step 5:

[1182] The server classifies the received data by user and stores it in a database. The stored data includes the user's activity, thoughts, and emotions. This data is used for later analysis.

[1183] Step 6:

[1184] The server retrieves user data from the database and inputs it into the AI ​​model, which uses machine learning algorithms to learn from the user's past data and emotional data.

[1185] Step 7:

[1186] The server uses an AI model to analyze the data and generate future predictions. The AI ​​model generates predictions such as annual income, family composition, and career progress based on the user's activities, thoughts, and emotional data. By taking emotional data into account, predictions can be made that include the impact that emotions will have on the user's future.

[1187] Step 8:

[1188] The server organizes the generated forecasts and sends them to the device, often formatted as graphs or charts.

[1189] Step 9:

[1190] The device displays the prediction results received from the server to the user in a visually easy-to-understand format so that the user can easily understand them.

[1191] Step 10:

[1192] Users can create their own action plan based on the displayed prediction results. Users can consider specific actions and take action based on them. Insights including emotional data are also displayed, such as "Improving your emotional state will have a positive impact on work progress."

[1193] Step 11:

[1194] The server collects new data and feedback from users, which is then fed back into the AI ​​model to help improve its prediction accuracy.

[1195] In this way, the system combines user input data with emotional data for AI analysis to provide specific future predictions. Users can plan their next actions based on the prediction results, and in the process, they continuously provide data to help the system make more accurate predictions.

[1196] Example 2

[1197] 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."

[1198] Conventional systems have issues with the accuracy of analyzing data when inputting user activities and thoughts, and making predictions based on that data. Another issue is that it is difficult to provide predictions that fully reflect the user's emotional data.

[1199] 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 following means are included: interface means for the user to input daily activities and current thoughts, emotion engine means for analyzing the input data and recognizing emotions, communication means for transmitting the analyzed data to a server, storage means for saving the data on the server, analysis means for generating future prediction results using a generative AI model based on the saved data, and display means for visually presenting the generated prediction results to the user. This makes it possible to accurately analyze the user's activities and emotion data and make highly accurate future predictions.

[1200] "Interface means" refers to the means by which a user inputs details of their daily activities and current thoughts, and specifically refers to a multiple-choice form or input screen.

[1201] The "emotion engine means" is a means having the function of analyzing input data and recognizing the user's emotions, and refers to an engine that performs emotion analysis using natural language processing technology, etc.

[1202] "Communication means" refers to the means for sending analyzed data to the server, and refers to the function for transferring data using a secure communication protocol (e.g., HTTPS).

[1203] "Storage means" refers to a means for storing data received by the server, and refers to the function of storing data using a database or other storage medium.

[1204] A "generative AI model" is an AI technology that generates future predictions based on stored data, and refers to a model that uses machine learning and deep learning to learn and make predictions.

[1205] "Analysis means" refers to a means that has the function of analyzing stored data using a generative AI model and generating future prediction results.

[1206] "Display means" refers to a means for providing the generated prediction results in a format that allows the user to visually confirm them, and specifically refers to a screen or interface that displays graphs and charts.

[1207] MODE FOR CARRYING OUT THE INVENTION

[1208] This invention relates to a system in which a user inputs details of their daily activities and current thoughts, an emotion engine is used to recognize the user's emotions, the data is sent to a server for storage, and a generative AI model is used to generate and provide future prediction results. Specific embodiments of this system are described below.

[1209] User operation

[1210] Users access a dedicated application or web interface using a device such as a smartphone or PC. The interface is designed as a simple multiple-choice form that includes items such as "work progress," "health status," "relationships," and "study content."

[1211] Examples:

[1212] The user enters the details of their daily activities as follows:

[1213] "Work progress: Good"

[1214] Health condition: A little tired

[1215] "Interpersonal relationships: Good"

[1216] "What I'm learning: I'm learning new technology."

[1217] Data analysis using emotion engine

[1218] The device is equipped with an emotion engine that analyzes emotions in real time based on the user input data. This emotion engine uses natural language processing libraries (e.g., NLTK and SpaCy) to recognize emotions such as "joy," "anger," "sadness," and "surprise."

[1219] Data transmission and storage

[1220] The device combines the recognized emotion data and the activity data entered by the user and sends it to a server using a secure protocol such as HTTPS. The server analyzes the received data, classifies it by user, and stores it in a database using a relational database (e.g., MySQL or PostgreSQL).

[1221] Data analysis and future predictions

[1222] The server uses the stored data to generate future predictions using a generative AI model, which uses machine learning and deep learning (e.g., TensorFlow and PyTorch) to learn from the user's past data and emotional data and generate future predictions.

[1223] Examples:

[1224] Based on the user's input data and emotional data, the server generates specific predictions such as "Expected annual income in five years: 6 million yen," "Family structure: married with one child," and "Career progress: manager position." The prediction results also include insights such as "Improving emotional state will have a positive impact on work progress."

[1225] Displaying the results

[1226] The server sends the generated forecast results to the device, which then displays them in a visually easy-to-understand format, using graphs and charts, allowing the user to intuitively understand future forecast results.

[1227] Examples:

[1228] The user will see the following results on their screen:

[1229] "Expected annual income in 5 years: 6 million yen"

[1230] Family status: Married, one child

[1231] "Career Progression: Section Manager Position"

[1232] In addition, specific advice is provided, such as "It is important to maintain a positive attitude in order to advance your career in the future."

[1233] Continuous data collection and model improvement

[1234] The system continuously collects data from users and uses that data to train the AI ​​model to improve prediction accuracy, while also accepting user feedback to improve the model.

[1235] This invention combines user input data with emotional data for AI analysis to provide specific future predictions. Users can plan their next actions based on the prediction results, and in the process, they continuously provide data to help the system make more accurate predictions.

[1236] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1237] Step 1:

[1238] The user inputs the activity and thoughts

[1239] Users input their daily activities and thoughts through a smartphone or PC interface. The interface displays options such as "Work progress," "Health status," "Interpersonal relationships," and "Study content." The user completes the input by entering each item and clicking the "Submit" button. Input data may include, for example, "Work progress: Good" or "Health status: A little tired."

[1240] Input: Data entered by the user into the interface

[1241] Output: Data sent from the interface to the terminal

[1242] Specific behavior:

[1243] The user launches an application.

[1244] Click the "Enter today's activity" button.

[1245] The user selects the appropriate option for each item and clicks the "Submit" button.

[1246] Step 2:

[1247] The device uses an emotion engine to recognize emotions

[1248] The device analyzes the data entered by the user in real time and recognizes the user's emotions using natural language processing libraries (such as NLTK or SpaCy). The emotion engine performs text analysis on the input data and identifies emotions such as "joy," "anger," "sadness," and "surprise."

[1249] Input: Data entered by the user

[1250] Output: Emotion data recognized by the emotion engine

[1251] Specific behavior:

[1252] The terminal receives input data.

[1253] The emotion engine analyzes the input data.

[1254] Emotional data is extracted as the analysis result.

[1255] Step 3:

[1256] The device sends the data to the server

[1257] The device combines the user's input data and the emotion data recognized by the emotion engine into a single data packet and sends it to the server using a secure protocol such as HTTPS.

[1258] Input: User input data and recognized emotion data

[1259] Output: Data packets sent to the server

[1260] Specific behavior:

[1261] The device integrates input data and emotion data.

[1262] The integrated data is converted into data packets.

[1263] The data packet is sent to the server using the HTTPS protocol.

[1264] Step 4:

[1265] The server receives and stores the data

[1266] The server receives the data sent from the device, analyzes it, and stores it in a database. The data is classified by user and stored for later analysis. The database is a relational database (e.g., MySQL or PostgreSQL).

[1267] Input: Data packets sent from the device

[1268] Output: User data stored in the database

[1269] Specific behavior:

[1270] The server receives the data packet.

[1271] The received data is analyzed and classified by user.

[1272] Insert the classified data into the database.

[1273] Step 5:

[1274] The server analyzes the data using an AI model and makes predictions

[1275] The server uses the stored data to make future predictions using a generative AI model, which uses machine learning libraries (such as TensorFlow or PyTorch) to learn from the user's past data and emotional data to generate future predictions.

[1276] Input: User data stored in the database

[1277] Output: Future prediction results generated by the generative AI model

[1278] Specific behavior:

[1279] The server retrieves the user's past data from the database.

[1280] A generative AI model learns and analyzes data.

[1281] Future predictions are generated as a result of the analysis.

[1282] Step 6:

[1283] The server sends the prediction results to the device.

[1284] The server formats the generated prediction results into an appropriate format and sends them to the device using a secure protocol such as HTTPS.

[1285] Input: Prediction results generated by a generative AI model

[1286] Output: Prediction results are sent in a nicely formatted format

[1287] Specific behavior:

[1288] The server receives and formats the prediction results.

[1289] The formatted prediction results are converted into data packets.

[1290] The data packet is sent to the terminal using the HTTPS protocol.

[1291] Step 7:

[1292] The device displays the prediction results to the user.

[1293] The terminal displays the prediction results received from the server to the user in a visually easy-to-understand format such as graphs and charts.

[1294] Input: Prediction results sent from the server

[1295] Output: Visually displayed prediction results

[1296] Specific behavior:

[1297] The terminal analyzes the data received from the server.

[1298] Create UI components to generate graphs and charts to visually display information.

[1299] The generated UI components are displayed on the screen.

[1300] Step 8:

[1301] The system continuously collects data and improves the model

[1302] The system continuously collects data from users and uses that data to train the generative AI model to improve prediction accuracy, while also incorporating user feedback to improve the model.

[1303] Input: New data and user feedback collected continuously

[1304] Output: A generative AI model with improved prediction accuracy

[1305] Specific behavior:

[1306] The server continuously collects new data.

[1307] Update the training of generative AI models based on new data.

[1308] Evaluate the accuracy of the model and make any necessary improvements.

[1309] (Application example 2)

[1310] 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."

[1311] Conventional systems were able to collect data on a user's daily activities and thoughts and make future predictions, but they were inadequate for predicting specific purchasing behavior or managing spending that reflected the user's emotional state. Furthermore, they lacked the ability to provide specific advice to users, which meant that users were unable to fully utilize the data. The purpose of this invention is to solve these problems.

[1312] The identification processing 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 an input means for the user to input daily activities and current thoughts, a transmission means for transmitting the input data to the server, a storage means for storing the data received by the server for each user, an analysis means for generating future prediction results using an AI model based on the stored data and emotional data, an output means for providing the generated prediction results to the user, an emotion recognition means for recognizing the emotional state of the user, an expenditure management means for predicting and managing purchasing behavior, and an insight provision means for providing actionable advice to the user. This enables more accurate prediction of purchasing behavior and expenditure management that takes emotional data into account, and makes it possible to provide specific and actionable advice to the user.

[1313] "Daily activities" is a record of the tasks and actions that a user performs on a daily basis.

[1314] "Current thinking" refers to the thoughts and opinions that a user has at that time.

[1315] "Input means" refers to an interface or device that allows a user to input their daily activities and current thoughts into the system.

[1316] "Transmission means" refers to the method or technology used to send the entered data to the server.

[1317] "Storage means" refers to the technology or device that the server uses to maintain and store the data it receives for each user.

[1318] "Emotion recognition means" refers to a method or technology that analyzes the user's emotional state in real time and recognizes it as data.

[1319] "Analysis Method" means a method or technique for generating future predictions using an AI model based on stored data and sentiment data.

[1320] "Output means" refers to a method or technology for providing the generated prediction results to a user.

[1321] A "spend manager" is a method or technique for predicting and managing a user's purchasing behavior.

[1322] An "insight providing means" is a method or technology for providing specific, actionable advice to a user.

[1323] An "AI model" is an artificial intelligence technology used to analyze data and make future predictions.

[1324] "Emotion data" refers to data that represents the user's emotional state.

[1325] "Purchasing behavior" refers to the behavioral patterns of users when purchasing products or services.

[1326] "Specific advice" refers to detailed, actionable instructions or advice on what actions or precautions the user should take.

[1327] This invention is a system that inputs a user's daily activities and current thoughts, predicts future purchasing behavior and expenditure management based on that data and emotion recognition data, and provides the user with specific advice. A specific embodiment of this system is described below.

[1328] First, users use devices such as smartphones or tablets to input details of their daily activities and current thoughts. An application using React Native is used as the input method. Users can easily enter details of their activities and thoughts using a text input form.

[1329] At the same time, the device's camera is used to recognize the user's emotional state in real time. The emotion recognition method uses the Azure Cognitive Services API, which acquires the user's emotional data.

[1330] These input data and emotion data are securely sent to the server via HTTPS. The server is built with Node.js and stores the received data in a MongoDB database. The stored data is organized by user, ensuring data integrity.

[1331] The server uses TensorFlow to perform analysis using an AI model based on the stored data and sentiment data. The analysis involves preprocessing the data using Python's pandas and NumPy, converting it into a format suitable for input into the AI ​​model. The AI ​​model learns from past data to predict future purchasing behavior and spending, and returns the resulting predictions.

[1332] The prediction results include information on the user's purchasing behavior patterns and spending management. Furthermore, the insight providing means generates specific actions and advice that the user should take, allowing the user to efficiently manage their spending in their daily lives.

[1333] Finally, the device presents the prediction results and advice sent from the server to the user in a visually easy-to-understand format. Graphs and charts can be used as visualization methods, allowing the user to easily understand the future predictions and the specific advice based on them.

[1334] Additionally, the system continuously collects data and learns to improve the accuracy of the AI ​​model, and user feedback can be incorporated and used to improve the model.

[1335] As a concrete example, the following prompt sentence is input to the generative AI model:

[1336] "EmotionPay has analyzed your emotional data and purchasing behavior over the past six months. Please show us the results of your analysis of your financial situation one year from now if you continue your current spending patterns, and the impact of your emotional data on your purchasing behavior."

[1337] Based on this, the AI ​​model returns the following results:

[1338] "Based on data from the past six months, our analysis shows that if people continue their current spending patterns, their savings will increase by 10% in one year. Furthermore, our sentiment data shows that positive emotions have a positive impact on purchasing decisions. Maintaining positive emotions will be a key factor in supporting financial stability."

[1339] In this way, the present invention realizes a system that allows users to predict purchasing behavior while utilizing emotion data and manage spending more effectively.

[1340] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1341] Step 1:

[1342] Users use a smartphone or tablet device to input their daily activities and current thoughts into a React Native application. The user enters specific details of their activities and thoughts into a text input form, and the data is sent to the application. Examples of input data include "Work progress: Good" and "Health condition: A little tired."

[1343] Step 2:

[1344] Using the device's camera, the system recognizes the user's emotions in real time through the Azure Cognitive Services API. Emotion analysis is performed based on images captured by the camera, and emotional data such as joy, anger, and sadness is generated. An example of emotional data is "Emotion: Happiness."

[1345] Step 3:

[1346] The device sends the activity details entered in step 1 and the emotion data recognized in step 2 to the server using the HTTPS protocol. The pair of input data and emotion data is sent to the server.

[1347] Step 4:

[1348] The server runs on Node.js and receives data sent from the device. The received data is stored in MongoDB and classified by user. The data is saved with a date and used for later analysis.

[1349] Step 5:

[1350] The server uses TensorFlow to preprocess the saved activity data and emotion data for input into the AI ​​model. Python's pandas and NumPy are used to clean the data and convert it into an input format for the AI ​​model. After preprocessing, the input data includes "Work progress: Good" and "Emotion: Happy."

[1351] Step 6:

[1352] The AI ​​model uses TensorFlow as an analysis tool to predict future purchasing behavior and spending. Predictions are generated based on the user's past data. The output predictions include "There is a high probability that spending will increase by 10% over the next six months."

[1353] Step 7:

[1354] The server analyzes the generated prediction results using insight provision methods and creates actionable advice for the user. It generates a prompt sentence and inputs specific advice from the prediction results into the generative AI model. An example of a prompt sentence in this case is, "After analyzing data from the past six months, we have determined that your expenses may increase by 10%. We recommend that you take the following actions to save money."

[1355] Step 8:

[1356] The server converts the forecast results and advice into HTML format and sends them to the device. A visualization tool is used to display them in easy-to-understand graphs and charts. The output data includes a "spending forecast" and "specific savings advice."

[1357] Step 9:

[1358] The terminal displays the prediction results and advice sent from the server on the user interface of the React Native application. The user can visually check the results and decide whether to take action. Specific examples of what is displayed in this step include "Expenses may increase by 10% over the next six months" and "Savings action: Eat out less."

[1359] Step 10:

[1360] The system continuously collects new data from users and updates the AI ​​model's learning to improve its prediction accuracy. User feedback is also incorporated and reflected in the model's improvements. Data from this step includes user feedback such as "Feedback: The advice was helpful."

[1361] This allows the system to utilize user emotional data to predict future purchasing behavior and provide more effective spending management.

[1362] 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.

[1363] 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.

[1364] 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.

[1365] [Fourth embodiment]

[1366] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1367] 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.

[1368] 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).

[1369] 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.

[1370] 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.

[1371] 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).

[1372] 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.

[1373] 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.

[1374] 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.

[1375] 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.

[1376] 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.

[1377] 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.

[1378] 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."

[1379] The present invention relates to a system in which a user inputs details of their daily activities and current thoughts, sends the data to a server where it is stored, and generates and provides future prediction results using an AI model. A specific embodiment of this system will be described below.

[1380] User operation

[1381] Users input their daily activities and thoughts through the interface, which is designed as a simple multiple-choice form and includes items such as "work progress," "health status," "relationships," and "study content."

[1382] Examples:

[1383] Users enter their daily information by selecting options such as:

[1384] "Work progress: Good"

[1385] Health condition: A little tired

[1386] "Interpersonal relationships: Good"

[1387] "What I'm learning: I'm learning new technology."

[1388] Data transmission (operation on the terminal side)

[1389] The terminal collects the data entered by the user, converts it into the appropriate format, and sends it to the server, using a secure protocol to ensure the integrity of the data.

[1390] Receiving and saving data (server-side operation)

[1391] The server receives the data sent from the devices, classifies it by user, and stores it in a database. The stored data will be used for later analysis, so the database design ensures efficient data acquisition and storage.

[1392] Data analysis and prediction (server-side operation)

[1393] The AI ​​model makes future predictions based on data stored on the server. The AI ​​model learns from past data and generates future prediction results based on user input data. The prediction results include, for example, the following elements:

[1394] Annual income forecast

[1395] Family structure prediction

[1396] Predicting career progression

[1397] Examples:

[1398] Based on the user's input data, the server generates specific predictions such as "Expected annual income in five years: 6 million yen," "Family composition: married with one child," and "Career progress: section manager position."

[1399] Display of results (user and terminal actions)

[1400] The server sends the generated prediction results to the device, which then displays them to the user in a visually understandable format, such as graphs or charts.

[1401] Examples:

[1402] The user will see the following results on their screen:

[1403] "Expected annual income in 5 years: 6 million yen"

[1404] Family status: Married, one child

[1405] "Career Progression: Section Manager Position"

[1406] Users can create specific action plans based on these prediction results.

[1407] Continuous data collection and improvement

[1408] The system continuously collects data from users and uses that data to train the AI ​​model to improve prediction accuracy, while also accepting user feedback to improve the model.

[1409] In this way, the system of the present invention performs AI analysis based on user input data and provides specific future predictions. Users can plan their next actions based on the prediction results, and in the process, they continuously provide data to help the system make more accurate predictions.

[1410] The processing flow will be explained below.

[1411] Step 1:

[1412] The user inputs details of their daily activities and current thoughts. Specifically, the user enters the following information into a multiple-choice form displayed on the device: "Work progress: Good," "Health condition: A little tired," "Interpersonal relationships: Good," "Study content: Learning new skills."

[1413] Step 2:

[1414] The device receives the input, collects the data entered by the user, and converts it into a suitable format, which is then sent to a server for storage and analysis.

[1415] Step 3:

[1416] The device sends the collected data to the server. The device uses a secure protocol to send user data to the server via a POST request. The data sent is generally in JSON format.

[1417] Step 4:

[1418] The server receives the data sent from the terminal, analyzes the received data, identifies which user the data came from, and checks the integrity of the data.

[1419] Step 5:

[1420] The server classifies the received data by user and stores it in a database. The stored data is managed together with the user's past data. The database design has a structure that allows for efficient data retrieval and storage.

[1421] Step 6:

[1422] The server retrieves user data from a database and inputs it into an AI model, which uses machine learning algorithms to learn patterns from the user's past data.

[1423] Step 7:

[1424] The server uses AI models to analyze the data and generate future predictions, such as predicted annual income in five years, family structure, and career progression.

[1425] Step 8:

[1426] The server organizes the generated predictions and sends them to the device, possibly formatting the results in graphs or charts.

[1427] Step 9:

[1428] The device displays the prediction results received from the server to the user in a visually easy-to-understand format so that the user can easily understand them.

[1429] Step 10:

[1430] Users can create their own action plans based on the displayed prediction results. Users can think of specific actions and carry out activities based on those actions.

[1431] Step 11:

[1432] The server collects new data and feedback from users, which is then fed back into the AI ​​model to help improve prediction accuracy.

[1433] In this way, the system is composed of a series of steps, starting with user input, followed by data transmission, storage, analysis, and display of results. By inputting their daily activities, users can obtain specific predictions for the future, enabling them to create action plans based on those predictions.

[1434] Example 1

[1435] 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."

[1436] In today's busy lifestyles, it is not easy for individuals to continually review and improve their daily activities while keeping future prospects and goals in mind. In particular, there is a lack of methods for objectively analyzing a wide range of factors, such as one's health, work progress, relationships, and learning content, to obtain future predictions. As a result, it is difficult for individuals to have a long-term perspective and act in a planned manner. Therefore, there is a need for a system that performs AI analysis based on user input data and provides specific future predictions.

[1437] 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.

[1438] In this invention, the server includes an interface means for users to input their daily activities and current thoughts, a communication means for transmitting the input data to the server, a database means for classifying and storing the data received by the server for each user, an analysis means for generating future prediction results using a generative AI model based on the stored data, and a display means for visually presenting the generated prediction results to the user. This allows users to continuously input their own activity data and obtain specific future predictions based on that data.

[1439] The "interface means" is an operation screen or input device that allows the user to input details of daily activities and current thoughts.

[1440] "Communication means" refers to the communication protocols and techniques used to transmit the data entered by the user to the server.

[1441] The "database means" refers to a storage device and its management system for classifying and storing data received by the server for each user.

[1442] A "generative AI model" is an artificial intelligence model and its implementation technology that generates future prediction results based on stored data.

[1443] "Analytical Tools" are the processes and techniques that analyze stored data and generate future predicted outcomes using generative AI models.

[1444] The "display means" refers to a display device and its management software for visually presenting the generated prediction results to the user.

[1445] The present invention relates to a system in which a user inputs details of their daily activities and current thoughts, sends the data to a server for storage, and generates and provides future prediction results using a generative AI model. A detailed description of specific embodiments of this system is provided below.

[1446] User data entry

[1447] Users input their daily activities and thoughts through the interface. The interface is designed as a simple multiple-choice form, and includes items such as "work progress," "health status," "relationships," and "study content." This allows users to easily enter data.

[1448] Examples:

[1449] Users enter their daily activities by selecting options such as:

[1450] Work progress: Good

[1451] Health condition: A little tired

[1452] Relationships: Good

[1453] Learning content: Learning new technology

[1454] Data transmission (operation on the terminal side)

[1455] The device collects the data entered by the user, converts it into the appropriate format, and sends it to the server, using secure protocols such as HTTPS to ensure data security.

[1456] Data reception and storage (server-side operation)

[1457] The server receives the data sent from the device, classifies it by user, and stores it in a database. The database system used is MySQL or PostgreSQL. By setting appropriate indexes, it is possible to retrieve and store data efficiently.

[1458] Data analysis and prediction (server-side operation)

[1459] The server uses a generative AI model based on the stored data to make future predictions. This generative AI model is built using frameworks such as TensorFlow and PyTorch, and predicts the user's future state based on past data. Prediction results include, for example, predictions of annual income, family composition, and career progress.

[1460] Examples:

[1461] The server generates a concrete prediction:

[1462] Estimated annual income in 5 years: 6 million yen

[1463] Family: Married, 1 child

[1464] Career progression: Manager position

[1465] Display of results (user and terminal actions)

[1466] The server sends the generated prediction results to the device, which then displays them to the user in a visually easy-to-understand format, such as graphs or charts, allowing the user to intuitively understand the future prediction results.

[1467] Examples:

[1468] The user will see the following result on their screen:

[1469] Estimated annual income in 5 years: 6 million yen

[1470] Family: Married, 1 child

[1471] Career progression: Manager position

[1472] Input prompt for generative AI model

[1473] An example of an input prompt for a generative AI model is as follows:

[1474] User daily activity data:

[1475] Work progress: Good

[1476] Health condition: A little tired

[1477] Relationships: Good

[1478] Learning content: Learning new technology

[1479] Based on this, please provide your predicted results for the next five years.

[1480] This allows the system of the present invention to perform AI analysis based on data entered by the user and provide specific future predictions.The user can plan their next actions based on the prediction results and continuously provide data in the process, thereby helping the system make more accurate predictions.

[1481] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1482] Step 1:

[1483] User data entry

[1484] Users enter their daily activities and thoughts through the interface. The data is categorized into categories such as "work progress," "health status," "relationships," and "study content," and the interface presents them as a simple multiple-choice form.

[1485] input:

[1486] The user selects the following data on the interface:

[1487] Work progress: Good

[1488] Health condition: A little tired

[1489] Relationships: Good

[1490] Learning content: Learning new technology

[1491] Specific behavior:

[1492] The user selects the appropriate option for each item.

[1493] Once the input is complete, the data is compiled into a single data structure (e.g., JSON).

[1494] output:

[1495] Well-formed data structures (e.g., JSON-formatted data)

[1496] Step 2:

[1497] Data transmission (operation on the terminal side)

[1498] The device collects the data entered by the user, converts it into the appropriate format, and sends it to the server, using secure protocols such as HTTPS to ensure data security.

[1499] input:

[1500] Data entered by the user on the interface (formatted data structure)

[1501] Specific behavior:

[1502] The terminal formats the input data in JSON format.

[1503] Send the formatted data to the server using the HTTPS protocol.

[1504] output:

[1505] Data sent to the server (encrypted data in JSON format)

[1506] Step 3:

[1507] Data reception and storage (server-side operation)

[1508] The server receives the data sent from the terminal, classifies it by user, and stores it in a database.

[1509] input:

[1510] Data sent from the device (JSON format data)

[1511] Specific behavior:

[1512] The server parses the received HTTP request and extracts the data.

[1513] The extracted data is classified by user ID.

[1514] Execute the appropriate SQL queries to insert data into the database.

[1515] output:

[1516] User data stored in a database

[1517] Step 4:

[1518] Data analysis and prediction (server-side operation)

[1519] The server uses a generative AI model based on the stored data to make future predictions.

[1520] input:

[1521] User data stored in a database

[1522] Specific behavior:

[1523] The server retrieves the user's data from the database.

[1524] Input data into a generative AI model (e.g., using TensorFlow or PyTorch) and run a predictive algorithm.

[1525] Generate prediction results and organize them by user.

[1526] output:

[1527] Generated prediction results (e.g., predicted annual income in 5 years, family structure, career progress)

[1528] Step 5:

[1529] Display of results (user and terminal actions)

[1530] The server transmits the generated prediction results to the terminal, which displays them to the user in a visually easy-to-understand format.

[1531] input:

[1532] Generated prediction results (e.g., data encoded in JSON format)

[1533] Specific behavior:

[1534] The server sends the generated prediction results to the terminal in JSON format.

[1535] The device analyzes the received data, converts it into graphs and charts, and displays them to the user.

[1536] output:

[1537] Prediction results displayed on the user's screen (in graph and chart format)

[1538] The above is the specific processing flow of this system's program. Based on this flow, users can input their daily data and obtain specific future predictions based on that data. This provides useful information for users to act in a planned manner, and the system itself can continuously collect data, thereby improving the accuracy of predictions.

[1539] (Application example 1)

[1540] 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."

[1541] In today's busy lifestyles, there is a need for systems that continuously monitor users' daily health status and lifestyle habits and predict future health conditions. However, existing systems have issues such as cumbersome data collection from users and inaccurate prediction results. Furthermore, there is a lack of visual feedback to users, making it difficult to provide specific health improvement measures.

[1542] 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.

[1543] In this invention, the server includes an input means for users to input their daily activities and current thoughts, a transmission means for transmitting the input data to the server, a storage means for storing the data received by the server for each user, an analysis means for generating future predictions and health predictions using an AI model based on the stored data, and an output means for providing the generated predictions to the user. This allows users to input their daily health data in an intuitively understandable manner and receive highly accurate future predictions using the AI ​​model. Furthermore, feedback in a visually understandable format makes it easier for users to create action plans for taking specific health improvement measures.

[1544] An "input means" is a device or interface that a user uses to input details of their daily activities and current thoughts.

[1545] "Transmitting means" refers to a communication device or protocol for transmitting data entered by a user to a server.

[1546] The "storage means" refers to a database or storage system that classifies and stores data received by the server for each user.

[1547] "Analytical means" means a computing device or software that uses AI models to generate future predictions and health predictions based on stored data.

[1548] The "output means" is a display device or an output interface for providing the generated prediction results to a user.

[1549] The "healthcare prediction means" is a system in which a user inputs data about their daily health condition and lifestyle habits, and predicts their future health condition based on the data sent to a server.

[1550] The "interface means" is a display device or user interface for visually presenting the generated health prediction results to the user.

[1551] The present invention is a system that uses an AI model to predict future health based on user input data on daily activities, health status, and lifestyle habits. First, the user inputs daily health data using a device such as a smartphone, tablet, or personal computer. The input method is a form or application designed for user ease of operation. The input form may include, for example, the number of steps taken, calorie intake, sleep time, stress level, and dietary quality.

[1552] Next, the data entered by the user is sent by the transmission means to a server via the Internet. A secure communication protocol is used for transmission, protecting the data from leaking to third parties. The received data is classified by user on the server and stored in a database. The stored data is managed so that it can be efficiently retrieved for later analysis and prediction.

[1553] The server uses the stored data to make future health predictions using an AI model. The AI ​​model is designed to learn from large amounts of past data and continuously improve its prediction accuracy. Specifically, the AI ​​model includes machine learning algorithms such as linear regression and deep learning.

[1554] The predicted results are provided to the user through an interface that displays the results in visually easy-to-understand graphs, charts, and text format, allowing the user to intuitively understand specific health advice and improvement measures.

[1555] For example, if a user enters the following health data:

[1556] Date: 2023-10-01

[1557] Steps: 8,000

[1558] Calorie intake: 2200kcal

[1559] Sleep time: 7 hours

[1560] Stress level: Moderate

[1561] Food quality: Average

[1562] This data is sent to a server and stored, after which the AI ​​model analyzes it to generate health predictions such as "Weight forecast in 3 months: Increase by 2kg from current weight" and "Future disease risk: High." The results are then provided to the user, who can then create a specific action plan.

[1563] The hardware used may include smartphones, tablets, and personal computers. The software used may include database management systems, communication protocols, and machine learning libraries (e.g., TensorFlow, scikit-learn). An example of a prompt from the user may be in the following format:

[1564] "Date: 2023-10-01, Steps: 8000, Calorie Intake: 2200kcal, Sleep: 7 hours, Stress Level: Medium, Diet Quality: Average"

[1565] The system of the present invention efficiently collects, stores, and analyzes this data, and provides useful health predictions to users, thereby assisting them in managing their health.

[1566] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1567] Step 1:

[1568] The user inputs daily health data.

[1569] Users use a smartphone, tablet, or personal computer to access a dedicated application or web form to enter data about their daily health and lifestyle habits, including the number of steps taken, calorie intake, sleep time, stress level, and diet quality. This input data is then used as the basis for further processing.

[1570] Step 2:

[1571] The terminal sends the input data to the server.

[1572] Input data is sent from the terminal to the server via a transmission means. A secure communication protocol such as HTTPS is used. The terminal properly formats the input data and performs error checking to prevent data loss during transmission. Once the data transmission is complete, the server receives the data.

[1573] Step 3:

[1574] The server stores the received data.

[1575] When the server receives the input data, it classifies it by user and stores it in a database. The data is stored in an organized format so that it can be efficiently searched and analyzed. For example, a database management system (DBMS) is used to store the data using the user ID as a key. At this data storage stage, the consistency and integrity of the data are verified.

[1576] Step 4:

[1577] The server uses an AI model to make predictions based on the stored data.

[1578] Based on the stored data, the server uses an AI model (for example, a model using TensorFlow or scikit-learn) to predict future health conditions. The model, which has learned from past data, receives each user's new health data as input and generates predictions such as weight changes and future disease risk. Specifically, the input data is preprocessed and fed into the AI ​​model to obtain predictions.

[1579] Step 5:

[1580] The server provides the generated prediction results to the user.

[1581] The generated prediction results are sent from the server to the terminal and provided to the user through an interface means. The prediction results are displayed in a visually easy-to-understand format, such as a graph, chart, or text, allowing the user to receive specific advice based on their own health condition.

[1582] Step 6:

[1583] The user creates an action plan based on the prediction results.

[1584] Based on the displayed prediction results, the user plans actions for managing their own health. For example, they consider specific lifestyle improvements such as reviewing their diet, increasing exercise, and adjusting their sleep schedule. In this step, it is desirable to add a feedback function to check whether the prediction results are reflected in the user's actions.

[1585] As described above, the system of the present invention efficiently collects, stores, and analyzes a user's health data and provides specific health predictions, thereby supporting the user's health management.

[1586] 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.

[1587] The present invention relates to a system in which a user inputs details of their daily activities and current thoughts, an emotion engine recognizes the user's emotions, the data is sent to a server for storage, and an AI model generates and provides future prediction results. A specific embodiment of this system will be described below.

[1588] User operation

[1589] Users input their daily activities and thoughts through the interface. The interface is designed as a simple multiple-choice form, and includes items such as "work progress," "health status," "relationships," and "study content." The emotion engine also recognizes the user's emotions.

[1590] Examples:

[1591] Users enter their daily information by selecting options such as:

[1592] "Work progress: Good"

[1593] Health condition: A little tired

[1594] "Interpersonal relationships: Good"

[1595] "What I'm learning: I'm learning new technology."

[1596] The emotion engine recognizes emotions such as "joy," "anger," "sadness," and "surprise" in real time.

[1597] Data transmission (operation on the terminal side)

[1598] The device collects data entered by the user and emotional data recognized by the emotion engine, converts it into an appropriate format, and transmits it to the server using a secure protocol to ensure data integrity.

[1599] Receiving and saving data (server-side operation)

[1600] The server receives the data sent from the device, classifies it by user, and stores it in a database. The stored data is used for later analysis. Emotion data is also recorded along with the user's past data.

[1601] Data analysis and prediction (server-side operation)

[1602] The server uses an AI model to make future predictions based on the stored data. The AI ​​model learns the user's past data and emotional data, and generates future prediction results based on the user's input data. The prediction results include, for example, the following elements:

[1603] Annual income forecast

[1604] Family structure prediction

[1605] Predicting career progression

[1606] By incorporating emotional data, more accurate predictions can be made that take into account the transitions in the user's emotional state and their impact.

[1607] Examples:

[1608] Based on the user's input data and emotional data, the server generates specific predictions such as "Expected annual income in five years: 6 million yen," "Family structure: married with one child," and "Career progress: manager position." The prediction results also include insights such as "Improving emotional state will have a positive impact on work progress."

[1609] Display of results (user and terminal actions)

[1610] The server sends the generated prediction results to the device, which then displays them to the user in a visually easy-to-understand format, such as graphs or charts.

[1611] Examples:

[1612] The user will see the following results on their screen:

[1613] "Expected annual income in 5 years: 6 million yen"

[1614] Family status: Married, one child

[1615] "Career Progression: Section Manager Position"

[1616] Additionally, insights incorporating emotional data are also displayed, providing specific advice such as, "It is important to maintain positive emotions as you progress in your career."

[1617] Continuous data collection and improvement

[1618] The system continuously collects user data and sentiment data, and uses that data to continuously train the AI ​​model to improve prediction accuracy. It also accepts user feedback and uses it to improve the model.

[1619] In this way, the system of the present invention combines user input data and emotional data to perform AI analysis and provide specific future predictions. Users can plan their next actions based on the prediction results, and in the process, they continuously provide data to help the system make more accurate predictions.

[1620] The processing flow will be explained below.

[1621] Step 1:

[1622] The user inputs details of their daily activities and current thoughts. Specifically, the user enters information such as the following into a multiple-choice form displayed on the device: "Work progress: Good," "Health condition: A little tired," "Interpersonal relationships: Good," "Study content: Learning new skills." The emotion engine also simultaneously recognizes the user's emotions. For example, emotions such as "joy," "anger," "sadness," and "surprise" can be automatically recognized from the user's facial expressions and text.

[1623] Step 2:

[1624] The device receives the input content and emotion data. The device collects the data entered by the user and the emotion data recognized by the emotion engine, and converts it into JSON format.

[1625] Step 3:

[1626] The device sends the collected data to the server. The device uses a secure protocol to send user data and emotion data to the server via a POST request.

[1627] Step 4:

[1628] The server receives the data sent from the terminal, identifies which user the data is from, and checks the integrity of the data.

[1629] Step 5:

[1630] The server classifies the received data by user and stores it in a database. The stored data includes the user's activity, thoughts, and emotions. This data is used for later analysis.

[1631] Step 6:

[1632] The server retrieves user data from the database and inputs it into the AI ​​model, which uses machine learning algorithms to learn from the user's past data and emotional data.

[1633] Step 7:

[1634] The server uses an AI model to analyze the data and generate future predictions. The AI ​​model generates predictions such as annual income, family composition, and career progress based on the user's activities, thoughts, and emotional data. By taking emotional data into account, predictions can be made that include the impact that emotions will have on the user's future.

[1635] Step 8:

[1636] The server organizes the generated forecasts and sends them to the device, often formatted as graphs or charts.

[1637] Step 9:

[1638] The device displays the prediction results received from the server to the user in a visually easy-to-understand format so that the user can easily understand them.

[1639] Step 10:

[1640] Users can create their own action plan based on the displayed prediction results. Users can consider specific actions and take action based on them. Insights including emotional data are also displayed, such as "Improving your emotional state will have a positive impact on work progress."

[1641] Step 11:

[1642] The server collects new data and feedback from users, which is then fed back into the AI ​​model to help improve its prediction accuracy.

[1643] In this way, the system combines user input data with emotional data for AI analysis to provide specific future predictions. Users can plan their next actions based on the prediction results, and in the process, they continuously provide data to help the system make more accurate predictions.

[1644] Example 2

[1645] 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."

[1646] Conventional systems have issues with the accuracy of analyzing data when inputting user activities and thoughts, and making predictions based on that data. Another issue is that it is difficult to provide predictions that fully reflect the user's emotional data.

[1647] 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 following means are included: interface means for the user to input daily activities and current thoughts, emotion engine means for analyzing the input data and recognizing emotions, communication means for transmitting the analyzed data to a server, storage means for saving the data on the server, analysis means for generating future prediction results using a generative AI model based on the saved data, and display means for visually presenting the generated prediction results to the user. This makes it possible to accurately analyze the user's activities and emotion data and make highly accurate future predictions.

[1648] "Interface means" refers to the means by which a user inputs details of their daily activities and current thoughts, and specifically refers to a multiple-choice form or input screen.

[1649] The "emotion engine means" is a means having the function of analyzing input data and recognizing the user's emotions, and refers to an engine that performs emotion analysis using natural language processing technology, etc.

[1650] "Communication means" refers to the means for sending analyzed data to the server, and refers to the function for transferring data using a secure communication protocol (e.g., HTTPS).

[1651] "Storage means" refers to a means for storing data received by the server, and refers to the function of storing data using a database or other storage medium.

[1652] A "generative AI model" is an AI technology that generates future predictions based on stored data, and refers to a model that uses machine learning and deep learning to learn and make predictions.

[1653] "Analysis means" refers to a means that has the function of analyzing stored data using a generative AI model and generating future prediction results.

[1654] "Display means" refers to a means for providing the generated prediction results in a format that allows the user to visually confirm them, and specifically refers to a screen or interface that displays graphs and charts.

[1655] MODE FOR CARRYING OUT THE INVENTION

[1656] This invention relates to a system in which a user inputs details of their daily activities and current thoughts, an emotion engine is used to recognize the user's emotions, the data is sent to a server for storage, and a generative AI model is used to generate and provide future prediction results. Specific embodiments of this system are described below.

[1657] User operation

[1658] Users access a dedicated application or web interface using a device such as a smartphone or PC. The interface is designed as a simple multiple-choice form that includes items such as "work progress," "health status," "relationships," and "study content."

[1659] Examples:

[1660] The user enters the details of their daily activities as follows:

[1661] "Work progress: Good"

[1662] Health condition: A little tired

[1663] "Interpersonal relationships: Good"

[1664] "What I'm learning: I'm learning new technology."

[1665] Data analysis using emotion engine

[1666] The device is equipped with an emotion engine that analyzes emotions in real time based on the user input data. This emotion engine uses natural language processing libraries (e.g., NLTK and SpaCy) to recognize emotions such as "joy," "anger," "sadness," and "surprise."

[1667] Data transmission and storage

[1668] The device combines the recognized emotion data and the activity data entered by the user and sends it to a server using a secure protocol such as HTTPS. The server analyzes the received data, classifies it by user, and stores it in a database using a relational database (e.g., MySQL or PostgreSQL).

[1669] Data analysis and future predictions

[1670] The server uses the stored data to generate future predictions using a generative AI model, which uses machine learning and deep learning (e.g., TensorFlow and PyTorch) to learn from the user's past data and emotional data and generate future predictions.

[1671] Examples:

[1672] Based on the user's input data and emotional data, the server generates specific predictions such as "Expected annual income in five years: 6 million yen," "Family structure: married with one child," and "Career progress: manager position." The prediction results also include insights such as "Improving emotional state will have a positive impact on work progress."

[1673] Displaying the results

[1674] The server sends the generated forecast results to the device, which then displays them in a visually easy-to-understand format, using graphs and charts, allowing the user to intuitively understand future forecast results.

[1675] Examples:

[1676] The user will see the following results on their screen:

[1677] "Expected annual income in 5 years: 6 million yen"

[1678] Family status: Married, one child

[1679] "Career Progression: Section Manager Position"

[1680] In addition, specific advice is provided, such as "It is important to maintain a positive attitude in order to advance your career in the future."

[1681] Continuous data collection and model improvement

[1682] The system continuously collects data from users and uses that data to train the AI ​​model to improve prediction accuracy, while also accepting user feedback to improve the model.

[1683] This invention combines user input data with emotional data for AI analysis to provide specific future predictions. Users can plan their next actions based on the prediction results, and in the process, they continuously provide data to help the system make more accurate predictions.

[1684] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1685] Step 1:

[1686] The user inputs the activity and thoughts

[1687] Users input their daily activities and thoughts through a smartphone or PC interface. The interface displays options such as "Work progress," "Health status," "Interpersonal relationships," and "Study content." The user completes the input by entering each item and clicking the "Submit" button. Input data may include, for example, "Work progress: Good" or "Health status: A little tired."

[1688] Input: Data entered by the user into the interface

[1689] Output: Data sent from the interface to the terminal

[1690] Specific behavior:

[1691] The user launches an application.

[1692] Click the "Enter today's activity" button.

[1693] The user selects the appropriate option for each item and clicks the "Submit" button.

[1694] Step 2:

[1695] The device uses an emotion engine to recognize emotions

[1696] The device analyzes the data entered by the user in real time and recognizes the user's emotions using natural language processing libraries (such as NLTK or SpaCy). The emotion engine performs text analysis on the input data and identifies emotions such as "joy," "anger," "sadness," and "surprise."

[1697] Input: Data entered by the user

[1698] Output: Emotion data recognized by the emotion engine

[1699] Specific behavior:

[1700] The terminal receives input data.

[1701] The emotion engine analyzes the input data.

[1702] Emotional data is extracted as the analysis result.

[1703] Step 3:

[1704] The device sends the data to the server

[1705] The device combines the user's input data and the emotion data recognized by the emotion engine into a single data packet and sends it to the server using a secure protocol such as HTTPS.

[1706] Input: User input data and recognized emotion data

[1707] Output: Data packets sent to the server

[1708] Specific behavior:

[1709] The device integrates input data and emotion data.

[1710] The integrated data is converted into data packets.

[1711] The data packet is sent to the server using the HTTPS protocol.

[1712] Step 4:

[1713] The server receives and stores the data

[1714] The server receives the data sent from the device, analyzes it, and stores it in a database. The data is classified by user and stored for later analysis. The database is a relational database (e.g., MySQL or PostgreSQL).

[1715] Input: Data packets sent from the device

[1716] Output: User data stored in the database

[1717] Specific behavior:

[1718] The server receives the data packet.

[1719] The received data is analyzed and classified by user.

[1720] Insert the classified data into the database.

[1721] Step 5:

[1722] The server analyzes the data using an AI model and makes predictions

[1723] The server uses the stored data to make future predictions using a generative AI model, which uses machine learning libraries (such as TensorFlow or PyTorch) to learn from the user's past data and emotional data to generate future predictions.

[1724] Input: User data stored in the database

[1725] Output: Future prediction results generated by the generative AI model

[1726] Specific behavior:

[1727] The server retrieves the user's past data from the database.

[1728] A generative AI model learns and analyzes data.

[1729] Future predictions are generated as a result of the analysis.

[1730] Step 6:

[1731] The server sends the prediction results to the device.

[1732] The server formats the generated prediction results into an appropriate format and sends them to the device using a secure protocol such as HTTPS.

[1733] Input: Prediction results generated by a generative AI model

[1734] Output: Prediction results are sent in a nicely formatted format

[1735] Specific behavior:

[1736] The server receives and formats the prediction results.

[1737] The formatted prediction results are converted into data packets.

[1738] The data packet is sent to the terminal using the HTTPS protocol.

[1739] Step 7:

[1740] The device displays the prediction results to the user.

[1741] The terminal displays the prediction results received from the server to the user in a visually easy-to-understand format such as graphs and charts.

[1742] Input: Prediction results sent from the server

[1743] Output: Visually displayed prediction results

[1744] Specific behavior:

[1745] The terminal analyzes the data received from the server.

[1746] Create UI components to generate graphs and charts to visually display information.

[1747] The generated UI components are displayed on the screen.

[1748] Step 8:

[1749] The system continuously collects data and improves the model

[1750] The system continuously collects data from users and uses that data to train the generative AI model to improve prediction accuracy, while also incorporating user feedback to improve the model.

[1751] Input: New data and user feedback collected continuously

[1752] Output: A generative AI model with improved prediction accuracy

[1753] Specific behavior:

[1754] The server continuously collects new data.

[1755] Update the training of generative AI models based on new data.

[1756] Evaluate the accuracy of the model and make any necessary improvements.

[1757] (Application example 2)

[1758] 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."

[1759] Conventional systems were able to collect data on a user's daily activities and thoughts and make future predictions, but they were inadequate for predicting specific purchasing behavior or managing spending that reflected the user's emotional state. Furthermore, they lacked the ability to provide specific advice to users, which meant that users were unable to fully utilize the data. The purpose of this invention is to solve these problems.

[1760] The identification processing 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 an input means for the user to input daily activities and current thoughts, a transmission means for transmitting the input data to the server, a storage means for storing the data received by the server for each user, an analysis means for generating future prediction results using an AI model based on the stored data and emotional data, an output means for providing the generated prediction results to the user, an emotion recognition means for recognizing the emotional state of the user, an expenditure management means for predicting and managing purchasing behavior, and an insight provision means for providing actionable advice to the user. This enables more accurate prediction of purchasing behavior and expenditure management that takes emotional data into account, and makes it possible to provide specific and actionable advice to the user.

[1761] "Daily activities" is a record of the tasks and actions that a user performs on a daily basis.

[1762] "Current thinking" refers to the thoughts and opinions that a user has at that time.

[1763] "Input means" refers to an interface or device that allows a user to input their daily activities and current thoughts into the system.

[1764] "Transmission means" refers to the method or technology used to send the entered data to the server.

[1765] "Storage means" refers to the technology or device that the server uses to maintain and store the data it receives for each user.

[1766] "Emotion recognition means" refers to a method or technology that analyzes the user's emotional state in real time and recognizes it as data.

[1767] "Analysis Method" means a method or technique for generating future predictions using an AI model based on stored data and sentiment data.

[1768] "Output means" refers to a method or technology for providing the generated prediction results to a user.

[1769] A "spend manager" is a method or technique for predicting and managing a user's purchasing behavior.

[1770] An "insight providing means" is a method or technology for providing specific, actionable advice to a user.

[1771] An "AI model" is an artificial intelligence technology used to analyze data and make future predictions.

[1772] "Emotion data" refers to data that represents the user's emotional state.

[1773] "Purchasing behavior" refers to the behavioral patterns of users when purchasing products or services.

[1774] "Specific advice" refers to detailed, actionable instructions or advice on what actions or precautions the user should take.

[1775] This invention is a system that inputs a user's daily activities and current thoughts, predicts future purchasing behavior and expenditure management based on that data and emotion recognition data, and provides the user with specific advice. A specific embodiment of this system is described below.

[1776] First, users use devices such as smartphones or tablets to input details of their daily activities and current thoughts. An application using React Native is used as the input method. Users can easily enter details of their activities and thoughts using a text input form.

[1777] At the same time, the device's camera is used to recognize the user's emotional state in real time. The emotion recognition method uses the Azure Cognitive Services API, which acquires the user's emotional data.

[1778] These input data and emotion data are securely sent to the server via HTTPS. The server is built with Node.js and stores the received data in a MongoDB database. The stored data is organized by user, ensuring data integrity.

[1779] The server uses TensorFlow to perform analysis using an AI model based on the stored data and sentiment data. The analysis involves preprocessing the data using Python's pandas and NumPy, converting it into a format suitable for input into the AI ​​model. The AI ​​model learns from past data to predict future purchasing behavior and spending, and returns the resulting predictions.

[1780] The prediction results include information on the user's purchasing behavior patterns and spending management. Furthermore, the insight providing means generates specific actions and advice that the user should take, allowing the user to efficiently manage their spending in their daily lives.

[1781] Finally, the device presents the prediction results and advice sent from the server to the user in a visually easy-to-understand format. Graphs and charts can be used as visualization methods, allowing the user to easily understand the future predictions and the specific advice based on them.

[1782] Additionally, the system continuously collects data and learns to improve the accuracy of the AI ​​model, and user feedback can be incorporated and used to improve the model.

[1783] As a concrete example, the following prompt sentence is input to the generative AI model:

[1784] "EmotionPay has analyzed your emotional data and purchasing behavior over the past six months. Please show us the results of your analysis of your financial situation one year from now if you continue your current spending patterns, and the impact of your emotional data on your purchasing behavior."

[1785] Based on this, the AI ​​model returns the following results:

[1786] "Based on data from the past six months, our analysis shows that if people continue their current spending patterns, their savings will increase by 10% in one year. Furthermore, our sentiment data shows that positive emotions have a positive impact on purchasing decisions. Maintaining positive emotions will be a key factor in supporting financial stability."

[1787] In this way, the present invention realizes a system that allows users to predict purchasing behavior while utilizing emotion data and manage spending more effectively.

[1788] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1789] Step 1:

[1790] Users use a smartphone or tablet device to input their daily activities and current thoughts into a React Native application. The user enters specific details of their activities and thoughts into a text input form, and the data is sent to the application. Examples of input data include "Work progress: Good" and "Health condition: A little tired."

[1791] Step 2:

[1792] Using the device's camera, the system recognizes the user's emotions in real time through the Azure Cognitive Services API. Emotion analysis is performed based on images captured by the camera, and emotional data such as joy, anger, and sadness is generated. An example of emotional data is "Emotion: Happiness."

[1793] Step 3:

[1794] The device sends the activity details entered in step 1 and the emotion data recognized in step 2 to the server using the HTTPS protocol. The pair of input data and emotion data is sent to the server.

[1795] Step 4:

[1796] The server runs on Node.js and receives data sent from the device. The received data is stored in MongoDB and classified by user. The data is saved with a date and used for later analysis.

[1797] Step 5:

[1798] The server uses TensorFlow to preprocess the saved activity data and emotion data for input into the AI ​​model. Python's pandas and NumPy are used to clean the data and convert it into an input format for the AI ​​model. After preprocessing, the input data includes "Work progress: Good" and "Emotion: Happy."

[1799] Step 6:

[1800] The AI ​​model uses TensorFlow as an analysis tool to predict future purchasing behavior and spending. Predictions are generated based on the user's past data. The output predictions include "There is a high probability that spending will increase by 10% over the next six months."

[1801] Step 7:

[1802] The server analyzes the generated prediction results using insight provision methods and creates actionable advice for the user. It generates a prompt sentence and inputs specific advice from the prediction results into the generative AI model. An example of a prompt sentence in this case is, "After analyzing data from the past six months, we have determined that your expenses may increase by 10%. We recommend that you take the following actions to save money."

[1803] Step 8:

[1804] The server converts the forecast results and advice into HTML format and sends them to the device. A visualization tool is used to display them in easy-to-understand graphs and charts. The output data includes a "spending forecast" and "specific savings advice."

[1805] Step 9:

[1806] The terminal displays the prediction results and advice sent from the server on the user interface of the React Native application. The user can visually check the results and decide whether to take action. Specific examples of what is displayed in this step include "Expenses may increase by 10% over the next six months" and "Savings action: Eat out less."

[1807] Step 10:

[1808] The system continuously collects new data from users and updates the AI ​​model's learning to improve its prediction accuracy. User feedback is also incorporated and reflected in the model's improvements. Data from this step includes user feedback such as "Feedback: The advice was helpful."

[1809] This allows the system to utilize user emotional data to predict future purchasing behavior and provide more effective spending management.

[1810] 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.

[1811] 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.

[1812] 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.

[1813] 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.

[1814] 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.

[1815] 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.

[1816] 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).

[1817] 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.

[1818] 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."

[1819] 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.

[1820] 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).

[1821] 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.

[1822] 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.

[1823] 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.

[1824] 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.

[1825] 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.

[1826] 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.

[1827] 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.

[1828] 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.

[1829] 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.

[1830] 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.

[1831] The following is further disclosed regarding the above embodiment.

[1832] (Claim 1)

[1833] an input means for a user to input daily activities and current thoughts;

[1834] a transmitting means for transmitting the input data to a server;

[1835] a storage means for storing the data received by the server for each user;

[1836] An analytical method that uses AI models to generate future predictions based on the stored data;

[1837] An output means for providing the generated prediction results to the user;

[1838] A system including:

[1839] (Claim 2)

[1840] 2. The system according to claim 1, wherein the data transmitted by the transmitting means is received and stored in a database.

[1841] (Claim 3)

[1842] 2. The system according to claim 1, wherein the prediction results generated by the analysis means are displayed in a format that can be visually confirmed by the user.

[1843] "Example 1"

[1844] Below are the claims rewritten to reflect the new invention:

[1845] (Claim 1)

[1846] an interface means for a user to input daily activities and current thoughts;

[1847] a communication means for transmitting the input data to a server;

[1848] a database means for classifying and storing data received by the server for each user;

[1849] An analytical method for generating future prediction results using a generative AI model based on the stored data;

[1850] a display means for visually displaying the generated prediction result to a user;

[1851] A system including:

[1852] (Claim 2)

[1853] 2. The system according to claim 1, wherein the data transmitted by the transmitting means is received and stored in a database.

[1854] (Claim 3)

[1855] 2. The system according to claim 1, wherein the prediction results generated by the analysis means are displayed in a format that can be visually confirmed by the user.

[1856] "Application Example 1"

[1857] (Claim 1)

[1858] an input means for a user to input daily activities and current thoughts;

[1859] a transmitting means for transmitting the input data to a server;

[1860] a storage means for storing the data received by the server for each user;

[1861] An analytical method that uses AI models to generate future predictions based on the stored data;

[1862] an output means for providing the generated prediction result to a user;

[1863] a healthcare prediction means for predicting future health conditions based on data input by a user regarding daily health conditions and lifestyle habits and data transmitted to a server;

[1864] an interface means for visually presenting the generated health prediction results to a user;

[1865] A system including:

[1866] (Claim 2)

[1867] 2. The system according to claim 1, wherein the data transmitted by the transmitting means is received and stored in a database.

[1868] (Claim 3)

[1869] 2. The system according to claim 1, wherein the prediction results and health prediction results generated by the analysis means are displayed in a format that can be visually confirmed by the user.

[1870] "Example 2: Combining Emotion Engines"

[1871] (Claim 1)

[1872] an interface means for a user to input daily activities and current thoughts;

[1873] emotion engine means for analyzing input data and recognizing emotions;

[1874] a communication means for transmitting the analyzed data to a server;

[1875] a storage means for storing the data on a server;

[1876] An analytical method for generating future prediction results using a generative AI model based on the stored data;

[1877] A display means for visually presenting the generated prediction results to the user;

[1878] A system including:

[1879] (Claim 2)

[1880] 2. The system according to claim 1, wherein the system receives data transmitted by the communication means and stores the data in a database.

[1881] (Claim 3)

[1882] 2. The system according to claim 1, wherein the prediction results generated by the analysis means are displayed in a format that can be visually confirmed by the user.

[1883] "Application example 2 when combining emotion engines"

[1884] (Claim 1)

[1885] an input means for a user to input daily activities and current thoughts;

[1886] a transmitting means for transmitting the input data to a server;

[1887] a storage means for storing the data received by the server for each user;

[1888] An analytical method that uses AI models to generate future predictions based on stored data and sentiment data;

[1889] an output means for providing the generated prediction result to a user;

[1890] emotion recognition means for recognizing an emotional state of a user;

[1891] spending control measures to predict and manage purchasing behavior;

[1892] an insight providing means for providing actionable advice to a user;

[1893] A system including:

[1894] (Claim 2)

[1895] 2. The system according to claim 1, wherein the data transmitted by the transmitting means and the emotion data recognized by the emotion recognizing means are received and stored in a database.

[1896] (Claim 3)

[1897] 2. The system according to claim 1, wherein the prediction results generated by the analysis means and the advice provided by the insight providing means are displayed in a format that can be visually confirmed by the user. [Explanation of symbols]

[1898] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. an input means for a user to input daily activities and current thoughts; a transmitting means for transmitting the input data to a server; a storage means for storing the data received by the server for each user; An analytical method that uses AI models to generate future predictions based on the stored data; An output means for providing the generated prediction results to the user; A system including:

2. 2. The system according to claim 1, further comprising: a database for receiving the data transmitted by the transmitting means;

3. 2. The system according to claim 1, wherein the prediction results generated by the analysis means are displayed in a format that can be visually confirmed by the user.

Images