System

Abstract

A system is provided.SOLUTION: A system including means for collecting data such as a communication fee of a user, an activation time, and an application use time, means for transmitting the collected data to a server, means for preprocessing the received data in the server, AI means for analyzing the preprocessed data, means for generating a specific proposal for a user based on a result of the analysis, and means for delivering the generated proposal to a terminal of 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 today's world, mobile devices have become an essential tool in daily life, but their use can have a significant impact on quality of life. Examples include excessive communication charges and lack of sleep due to prolonged use of the device. However, it is currently difficult for users to effectively solve these problems through self-management alone. The present invention aims to address these issues by providing a system that automatically makes suggestions for improving quality of life based on data acquired by the user. [Means for solving the problem]

[0005] The present invention relates to a system that includes a means for collecting data such as user communication charges, startup times, and application usage time; a means for transmitting the collected data to a server; a means for preprocessing the received data in the server; an AI means for analyzing the preprocessed data; a means for generating specific suggestions for the user based on the analysis results; and a means for delivering the generated suggestions to the user's device. This allows the user to understand their own behavioral patterns in detail and receive appropriate lifestyle improvement suggestions. Furthermore, by including a means for supplementing missing data from the collected data, the accuracy of the data can be improved, allowing for more accurate suggestions to be made. Furthermore, by including a means for identifying trends in usage frequency by time period, peak communication charge times, startup times, and usage times in order to analyze user behavioral patterns, it is possible to provide more detailed analysis results and suggest specific actions for lifestyle improvement.

[0006] "User" means any person or entity that uses a mobile device and generates data.

[0007] "Communication charges" are fees incurred when a mobile device uses communication services such as internet connection and voice calls.

[0008] The "startup time" is the time from when the power of the mobile terminal is turned on to when it is turned off, or the time from when a specific application is started to when it is terminated.

[0009] "App time" is the total amount of time a particular application is in use.

[0010] "Means for collecting data" refers to mechanisms or devices for automatically acquiring and recording various data such as communication charges, startup time, and application usage time.

[0011] A "server" is a computer system that receives collected data and processes it for analysis and recommendations.

[0012] "Data pre-processing measures" are processes or algorithms used to transform collected data into a form suitable for analysis.

[0013] "AI methods" are systems or algorithms that use artificial intelligence to analyze data and detect patterns and anomalies.

[0014] "Means of generating suggestions" refers to the process of creating specific actions and improvement proposals for users based on the results of AI analysis.

[0015] A "means for delivering a proposal" is a mechanism or method for notifying a user's device of a generated proposal.

[0016] "Data imputation methods" are algorithms or techniques that fill in missing values ​​and improve the completeness and accuracy of data.

[0017] "Behavioral pattern analysis measures" are processes or systems for identifying and analyzing trends in user usage and behavior. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] System Overview

[0040] The present invention is a system that collects data such as user communication charges, startup times, and application usage times, and analyzes the data using a server to provide specific suggestions for improving the user's quality of life. Specific embodiments of the system are described below.

[0041] Data collection implementation

[0042] The device records the user's data usage, startup time, and app usage time at regular intervals (e.g., every hour or every day). For example, it records the amount of time a user uses a particular app over a certain period of time and the amount of data usage during that time. This data is stored in a database or temporary file within the device.

[0043] Data transmission and storage practices

[0044] The collected data is sent from the device to the server at regular intervals (e.g., daily or weekly). The data sent here includes communication charges, startup time, and app usage time. The server converts the received data into an appropriate format (e.g., JSON, CSV) and saves it in a database for safekeeping.

[0045] Data Preprocessing Embodiments

[0046] The server reads the received data and performs pre-processing, which may include the following:

[0047] Imputing missing data: For example, if data is missing for a specific time period, impute that portion with the historical average or median.

[0048] Outlier detection and removal: For example, removing values ​​that deviate significantly from normal usage patterns.

[0049] Data normalization: Adjusting data values ​​to a uniform scale (e.g., converting them to the range 0 to 1).

[0050] Data Analysis Embodiments

[0051] Once preprocessed, the data is analyzed by AI installed on the server. The AI ​​analyzes user behavior patterns in detail and identifies specific issues. For example, it identifies the frequency of app use by time of day and peak times for data charges. It also analyzes trends in launch times and usage duration to uncover user usage trends.

[0052] Suggestion Generation Embodiments

[0053] The server's AI generates specific action suggestions for the user based on the analysis results. For example, the following suggestions may be generated:

[0054] "Recently, app use after midnight has been increasing. Reducing app use by one hour after midnight is expected to increase sleep time by approximately 30 hours per month."

[0055] "70% of data usage is used for certain streaming apps. By using them only when connected to Wi-Fi, you can significantly reduce your data usage."

[0056] Embodiments of Proposal Delivery

[0057] Finally, the server sends the generated proposal to the device and notifies the user. The device displays the proposal to the user via a push notification, allowing the user to review its contents. If necessary, the user can view the proposal details within the app.

[0058] Specific examples

[0059] Example 1: Suggestions for users with high late-night usage

[0060] 1. The device measures the user's app usage data every night after midnight and records usage data every hour.

[0061] 2. The device sends one week's worth of data to the server. For example, "2023-10-01 00:00: 120 minutes", "2023-10-02 00:00: 110 minutes", etc.

[0062] 3. The server receives the data, imputes missing values, and removes outliers if necessary.

[0063] 4. The server compiles usage time from midnight onwards for one week, and AI analyzes the user's usage patterns.

[0064] 5. The AI ​​identifies that "the average usage after midnight is 120 minutes per week" and automatically generates an improvement suggestion (reducing usage time by 60 minutes).

[0065] 6. The server generates a suggestion to the device, saying, "If you reduce your usage time after midnight by one hour, you will increase your sleep time by a total of 30 hours in one month." and sends it to the device.

[0066] 7. The device will then push a notification to the user with the suggestions, which the user can then review in the app.

[0067] Example 2: Suggestions for users with excessive data usage

[0068] 1. The device collects the user's data usage data for one month.

[0069] 2. The device sends the collected data to the server, which includes information on daily communication charges and apps used.

[0070] 3. The server receives the data and pre-processes it for analysis.

[0071] 4. AI will analyze and identify which specific streaming apps are taking up the majority of your data usage.

[0072] 5. The server generates a suggestion that suggests limiting the use of certain streaming apps to Wi-Fi or using data saving features to reduce data charges.

[0073] 6. The server sends the generated proposal to the device and notifies the user.

[0074] 7. Users can reduce data costs by checking notifications and reviewing how they use streaming apps.

[0075] The above is a specific description of the embodiment of the present invention. This system allows users to understand their own behavioral patterns and receive appropriate suggestions for improving their lifestyle.

[0076] The processing flow will be explained below.

[0077] Step 1:

[0078] The device collects the user's data usage, startup time, and app usage time. This data is recorded at regular intervals (e.g., hourly or daily). Specifically, the device's log function is used to record the start and end times of each app's use, the amount of data consumed, etc.

[0079] Step 2:

[0080] The data collected by the device is stored in a temporary file or an internal database. At this stage, the data is checked for duplication or format inconsistencies, and the data format is unified if necessary.

[0081] Step 3:

[0082] The device periodically (e.g. daily or weekly) transmits stored data to the server via the network. The transmitted data includes communication charges, startup time, and application usage time. HTTP or HTTPS is used as the communication protocol.

[0083] Step 4:

[0084] The server receives the received data and performs security checks (e.g., data encryption, integrity checks) to ensure that the data has not been tampered with.

[0085] Step 5:

[0086] The server saves the received data in the database. Common formats such as JSON and CSV are used for saving. When saving, the consistency of each data item is rechecked.

[0087] Step 6:

[0088] The server performs data preprocessing, such as imputing missing data (e.g., imputing with historical average values), detecting and removing outliers, and normalizing data (e.g., scaling to a range of 0 to 1).

[0089] Step 7:

[0090] The server inputs the preprocessed data into the AI ​​model for analysis, which analyzes the frequency of app use by time of day, peak times for data usage, and trends in startup and usage time.

[0091] Step 8:

[0092] The server's AI generates specific suggestions for users based on the analysis results. The suggestions are expressed in natural language and formatted in a way that is easy for users to understand. For example, "Recently, your app usage after midnight has increased. If you reduce your app usage by one hour after midnight, it is predicted that you will gain approximately 30 hours of sleep per month."

[0093] Step 9:

[0094] The server sends the generated proposal to the device. When sending, the data format is checked to ensure that the proposal content is transmitted correctly.

[0095] Step 10:

[0096] The device will notify the user of the suggestions, typically as a push notification or in-app message. The user can then view the details of the suggestions by checking the notification.

[0097] Step 11:

[0098] Users can check the notification and change their behavior based on the suggestions, for example, by refraining from using apps late at night to ensure they get enough sleep.

[0099] These are the specific processing steps of the program. Through this series of processes, users can gain a detailed understanding of their own behavioral patterns and receive specific suggestions for improving their quality of life.

[0100] Example 1

[0101] 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."

[0102] In systems that collect and analyze data on users' communication charges and app usage time, it can be difficult to generate effective lifestyle improvement proposals using existing methods. In particular, it is difficult to understand missing data, the presence of outliers, and user behavior patterns in detail to generate specific and effective proposals.

[0103] 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.

[0104] In this invention, the server includes means for collecting data such as user communication charges, startup times, and application usage times, means for transmitting the collected data to the server, and means for preprocessing the received data in the server, which enables detailed analysis of user behavior patterns, completion and removal of missing data and outliers, and normalization to a unified scale.

[0105] The server also includes an artificial intelligence unit that analyzes the preprocessed data, a unit that generates specific suggestions for the user based on the analysis results, and a unit that delivers the generated suggestions to the user's terminal, thereby providing the user with specific and effective suggestions for action.

[0106] "User's communication charges" means the total amount of data communication usage and charges incurred when a User uses the communication service.

[0107] "Boot time" is the time it takes for a particular application or device to start and become available for use, and the cumulative time that the application or device is running.

[0108] "App time" is the amount of time a particular application is actually used by a user.

[0109] "Means for collecting data" refers to a device or program that records information such as a user's communication charges, startup time, and application usage time at regular intervals.

[0110] "Means for transmitting data" refers to a device or program for transferring collected data to a database or server.

[0111] The "preprocessing means" is a device or program for imputing missing data, removing outliers, and normalizing the received data.

[0112] "Artificial intelligence means" refers to artificial intelligence technology that uses collected and pre-processed data to analyze user behavior patterns and generate specific suggestions based on the analysis results.

[0113] The "means for generating specific suggestions" is a device or program for generating action suggestions for users based on the analysis results using artificial intelligence technology.

[0114] "Means for distributing to terminal" means a device or program for transferring the proposal generated by the server to the user's terminal and notifying the user.

[0115] "Recording means" means a device or program that records the user's currently running apps and their running time at regular intervals.

[0116] A "means for completing missing data" is a device or program that, when there is a gap in the collected data, fills in the gaps with past data, estimated values, etc.

[0117] An "outlier removal means" is a device or program that detects data that deviates significantly from normal usage patterns and removes them from the analysis.

[0118] A "means for normalization" is a device or program that converts data values ​​to a uniform scale (e.g., a range of 0 to 1).

[0119] System Overview

[0120] This system collects data such as user communication charges, startup times, and application usage time, and analyzes it on a server to understand the user's behavioral patterns and make suggestions to improve their quality of life. Specifically, the system consists of the steps of data collection by the device, data transmission to the server, data preprocessing and analysis on the server, and proposal generation and distribution.

[0121] Data collection implementation

[0122] The device records the user's communication charges, startup times, and app usage time at regular intervals. For example, it records the amount of time the user used a particular app over a certain period of time and the data communication charges consumed during that time. This data is stored in a database or temporary file within the device. A program for collecting and recording data is installed on the device. This program uses a scheduler to collect data every hour and saves it in a database (e.g., SQLite).

[0123] Data transmission and storage practices

[0124] The terminal sends the collected data to the server at a fixed interval (for example, at midnight every day). The sent data is converted into an appropriate format (for example, JSON or CSV). The server analyzes and stores the received data in a database (for example, MySQL (registered trademark)). To send the data, the terminal makes an HTTP request, and the sent data is received by the server's REST API.

[0125] Data Preprocessing Embodiments

[0126] The server performs preprocessing on the received data. This preprocessing includes missing data completion, outlier detection and removal, and data normalization. This preprocessing is performed using the Python Pandas library. Data normalization is performed using MinMaxScaler from scikit-learn.

[0127] Data Analysis Embodiments

[0128] Once the preprocessing is complete, the data is analyzed by artificial intelligence (AI) installed on the server. The AI ​​performs detailed analysis of user behavior patterns and extracts specific issues (for example, times of high usage or peak times for communication charges). Machine learning algorithms such as K-means clustering are used for the analysis.

[0129] Suggestion Generation Embodiments

[0130] Based on the analysis results, the server's AI generates specific action suggestions for the user. For example, it may generate the following suggestion: "Reducing app use by one hour after midnight could increase sleep time by approximately 30 hours over the course of a month." Natural language processing technology is used to generate suggestions, for example, by inputting a prompt sentence to generate a suggestion using a generative AI model (such as GPT-3 (registered trademark)).

[0131] Embodiments of Proposal Delivery

[0132] The server sends the generated suggestions to the device and notifies the user. The device displays the suggestions via push notification, allowing the user to check their details. The user can also tap the notification to view the detailed suggestions within the app.

[0133] Specific examples

[0134] Example 1: Suggestions for users with high late-night usage

[0135] 1. The device measures the user's app usage data every night after midnight and records usage data every hour.

[0136] 2. The device sends one week of data to the server.

[0137] 3. The server receives the data, imputes missing values, and removes outliers.

[0138] 4. The server compiles usage time from midnight onwards for one week, and AI analyzes the user's usage patterns.

[0139] 5. The AI ​​identifies that "the average usage after midnight is 120 minutes per week" and automatically generates an improvement suggestion (reducing usage time by 60 minutes).

[0140] 6. The server generates a suggestion to the device, saying, "If you reduce your usage time after midnight by one hour, you will increase your sleep time by a total of 30 hours in one month." and sends it to the device.

[0141] 7. The device will then push a notification to the user with the suggestions, which the user can then review in the app.

[0142] Example 2: Suggestions for users with excessive data usage

[0143] 1. The device collects the user's data usage data for one month.

[0144] 2. The device sends the collected data to the server, which includes information on daily communication charges and apps used.

[0145] 3. The server receives the data and pre-processes it for analysis.

[0146] 4. AI will analyze and identify which specific streaming apps are taking up the majority of your data usage.

[0147] 5. The server generates a suggestion that suggests limiting the use of certain streaming apps to Wi-Fi or using data saving features to reduce data charges.

[0148] 6. The server sends the generated proposal to the device and notifies the user.

[0149] 7. Users can reduce data costs by checking notifications and reviewing how they use streaming apps.

[0150] Prompt Sentence Examples

[0151] "Collect app usage data after midnight for one month, analyze users' usage patterns, and generate lifestyle improvement suggestions."

[0152] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0153] Step 1: Collect data

[0154] Input: User's data charges, startup time, app usage time

[0155] How it works: The device runs a program that periodically records data charges, startup times, and app usage time.

[0156] Data processing: Data charges, startup time, and app usage time are saved in a database or temporary file.

[0157] Output: Data stored in the device's internal database or temporary files

[0158] Specific operation: The scheduler installed on the device measures the current communication charges, startup time, and application usage time every hour and stores them in an SQLite database (e.g., "2023-10-01 12:00: Application A 30 minutes").

[0159] Step 2: Sending data

[0160] Input: Data stored on the device about communication charges, startup time, and app usage time

[0161] Operation: The device converts the collected data into JSON format at regular intervals (for example, at midnight every day) and sends it to the server.

[0162] Data processing: Convert the data into JSON format.

[0163] Output: JSON data sent to the server

[0164] Specific operation: Every day at midnight, the device reads the current day's data from the SQLite database, converts the data to JSON format using the Python json module, and then sends it to the server via an HTTP request (e.g., {"2023-10-01": {"App A": 120, "App B": 30}}).

[0165] Step 3: Store your data

[0166] Input: JSON data sent to the server

[0167] How it works: The server parses the data it receives and stores it in a secure database.

[0168] Data processing: Parse the JSON data and convert it into a format that can be inserted into the database.

[0169] Output: Data stored in the database on the server

[0170] Specific operation: The server parses the received JSON data using Python's json module, generates an SQL statement to insert into the MySQL database, and executes it (e.g., INSERT INTO user_data VALUES ("2023-10-01", "App A", 120, "App B", 30)).

[0171] Step 4: Preprocessing the data

[0172] Input: Data stored in the database on the server

[0173] How it works: The server imputes missing data, detects and removes outliers, and normalizes the data.

[0174] Data processing: Impute missing data, remove outliers, and normalize data.

[0175] Output: Preprocessed data

[0176] Specific operation: The data is read into a data frame format using Python's Pandas library, missing values ​​are filled in using the fillna method, outliers are removed using conditional search, and the data is normalized using MinMaxScaler (e.g., {"App A": 0.5, "App B": 0.2}).

[0177] Step 5: Analyze the data

[0178] Input: Preprocessed data

[0179] How it works: The AI ​​installed on the server uses pre-processed data to analyze user behavior patterns.

[0180] Data computation: Use an AI model (e.g., K-means clustering) to separate the data into clusters.

[0181] Output: User behavior pattern analysis results

[0182] Specific operation: K-means clustering is performed using Python's Scikit-learn library, and user data is classified into each cluster (e.g., cluster 0 = users with high usage during the late night hours).

[0183] Step 6: Proposal Generation

[0184] Input: User behavior pattern analysis results

[0185] Action: The server's artificial intelligence generates specific action suggestions based on the analysis results.

[0186] Data calculation: A prompt sentence is input into a generative AI model (e.g., GPT-3) to generate a suggested sentence.

[0187] Output: Generated suggestion

[0188] Specific operation: Based on the analysis result that "there is a lot of usage after midnight," the generative AI model inputs the prompt sentence "Please generate a proposal to reduce app usage after midnight," and generates a proposal sentence (e.g., "Reducing app usage after midnight by one hour could increase sleep time by approximately 30 hours in a month").

[0189] Step 7: Distributing the proposal

[0190] Input: Generated suggestion

[0191] Behavior: The server generates a proposal, sends it to the device, and notifies the user.

[0192] Data processing: Convert the proposal into a notification format and send it to the terminal.

[0193] Output: Proposal notification displayed on the user's device

[0194] Specific operation: The server converts the suggestion text into JSON format and sends it to the device via an HTTP request. The device then generates a push notification based on the received JSON and notifies the user (e.g., notification message: "If you reduce app usage after midnight by one hour, you will gain approximately 30 hours of sleep in one month").

[0195] (Application example 1)

[0196] 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."

[0197] Users spend a lot of time and data charges using applications on smartphones and other devices, which can result in a decline in their quality of life. Furthermore, a bias in data charges and usage time toward specific apps can lead to wasteful usage and negatively impact health. However, it is difficult for users to recognize these patterns of behavior, making it difficult to take appropriate measures to improve them. Therefore, there is a need for a system that can analyze users' application usage patterns and automatically provide specific suggestions for optimally managing data charges and usage time.

[0198] 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.

[0199] In this invention, the server includes means for collecting data such as user communication charges, startup times, and application usage time; means for transmitting the collected data to the server; means for preprocessing the received data in the server; artificial intelligence means for analyzing the preprocessed data; means for analyzing the viewing patterns of specific applications and generating specific suggestions for the user; and means for delivering the generated suggestions to the user's device. This enables detailed analysis of user behavior patterns and automatically generates and delivers practical suggestions for optimizing communication charges and usage time. For example, if a user uses an application excessively during a certain time period, the system can suggest that the user use that time for other activities. Furthermore, recommending viewing content that consumes a lot of data over a Wi-Fi connection can also contribute to saving communication charges.

[0200] "Communication charges" are the costs incurred when a user communicates data via an Internet connection.

[0201] "Launch time" refers to the time when an application is started on a device.

[0202] "Time in app" refers to the total amount of time a user spends using a particular application.

[0203] "Means of collecting data" refers to the mechanism for obtaining information such as user data charges, startup time, and app usage time.

[0204] "Means for transmitting to a server" refers to a mechanism for sending collected data to a remote server via a communication network such as the Internet.

[0205] "Preprocessing means" refers to a mechanism for performing processes such as removing unnecessary data, filling in missing values, and normalizing data in order to improve the quality of collected data.

[0206] "Artificial Intelligence Tools" means AI techniques used to analyze pre-processed data and discover specific patterns or trends.

[0207] The "means for generating suggestions" is a mechanism for creating improvement measures and action suggestions for users based on data analyzed by artificial intelligence.

[0208] "Means of delivery to user's device" refers to a mechanism for notifying the user of the generated suggestions on their device, such as a smartphone or tablet.

[0209] "Behavioral patterns" refer to a series of usage trends and habits, such as how a user uses applications and at what times they consume the most data.

[0210] "Viewing patterns" are information that indicates the tendency of users to view what types of content at what times.

[0211] "Wi-Fi environment" refers to a network environment that connects to the Internet using wireless LAN.

[0212] "Data-intensive content" refers to applications such as video and streaming services that require large amounts of internet data.

[0213] "Use for other activities" refers to engaging in alternative activities such as exercise, reading, or sleep instead of using the application during a particular time period.

[0214] System Overview

[0215] This invention is a system that collects data such as user communication charges, startup times, and application usage time, and analyzes it on a server to provide specific action suggestions to users. The system has the functions of data collection, data transmission, preprocessing, AI analysis, proposal generation, and proposal distribution.

[0216] Data collection

[0217] The device records the user's data usage, startup time, and app usage time at regular intervals. For example, it records the time the user uses a particular app and the amount of data usage. This information is stored in an internal database.

[0218] Data transmission

[0219] The collected data, including communication charges, startup time, and usage time, is sent from the device to a server at regular intervals. The server converts the received data into an appropriate format and stores it securely.

[0220] Data Preprocessing

[0221] The server reads the received data and performs preprocessing, including filling in missing data, removing outliers, and normalizing the data, thereby improving the accuracy of the analysis.

[0222] Data analysis

[0223] Once preprocessed, the data is analyzed by AI installed on the server. The AI ​​analyzes user behavior patterns in detail and extracts viewing patterns and peak times for data charges. For example, by identifying viewing frequency and data consumption by time of day, it is possible to understand user behavior trends.

[0224] Proposal generation

[0225] The server's AI then generates specific action suggestions for the user based on the analysis results, including:

[0226] Suggestions to repurpose screen time for other activities during certain times

[0227] We recommend watching data-intensive content in a Wi-Fi environment.

[0228] Proposal distribution

[0229] The server sends the generated suggestions to the device and displays them to the user via push notification, where the user can view the details of the suggestions within the app.

[0230] Hardware and software details

[0231] Hardware: Smartphones (e.g., iPhone (registered trademark), Android (registered trademark) devices), servers

[0232] Software: Python 3.9, JSON format, standard library

[0233] Specific examples

[0234] For example, if a user frequently watches videos late at night, the AI ​​will analyze this pattern and generate a suggestion such as, "You watch too much after midnight. By reducing your viewing time by one hour, you can gain approximately 30 hours of sleep per month." Also, if a specific streaming app is taking up a large portion of your data charges, the AI ​​will suggest, "To reduce data charges, we recommend limiting the use of this streaming app to Wi-Fi environments."

[0235] Prompt Sentence Examples

[0236] "Recently, app usage late at night has increased. Reducing usage after midnight by one hour is predicted to increase sleep time by approximately 30 hours per month. Based on this, please output code that suggests reducing viewing during specific times. For example, something implemented in Python would be good."

[0237] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0238] Step 1:

[0239] The device collects data such as the user's data charges, startup time, and app usage time at regular intervals. The inputs include the time the user starts each app (startup time), the amount of time the application is used (usage time), and the data charges incurred during use. This data is stored in an internal database. For example, if a user starts YouTube (registered trademark) at 10:00 AM, watches it for 30 minutes, and uses 50 MB of data during that time, that information will be recorded.

[0240] Step 2:

[0241] The device periodically sends the collected data to the server. The data is sent over the communication network and converted into an appropriate format, such as JSON. The input is the data collected in step 1, and the output is the data sent to the server. This data includes specific app names, usage time, communication charges, launch date and time, etc.

[0242] Step 3:

[0243] The server reads the received data and performs preprocessing. The input is the unprocessed data sent from the terminal. Preprocessing involves filling in missing data, detecting and removing outliers, and normalizing the data. For example, if data for a certain date and time is missing, it is filled in with the average value from the past. Outliers are values ​​that are clearly outside the normal range and are removed. Data normalization involves converting all data into a unified range from 0 to 1. The output is a dataset after preprocessing has been completed.

[0244] Step 4:

[0245] The server inputs the preprocessed data into an AI model for analysis. The input is the preprocessed data, and the AI ​​analyzes the user's behavioral patterns. For example, it can determine how much data is being used during a specific time period, or which applications are being used most frequently at which times. The output is a detailed analysis of the user's behavioral patterns.

[0246] Step 5:

[0247] The server generates specific action suggestions for the user based on the analysis results. The input is the analysis results of the artificial intelligence model. For example, if a user uses a lot of applications late at night, the server automatically generates a suggestion to reduce that usage time. Specifically, the server generates a suggestion such as, "If you reduce viewing after midnight by one hour, you can gain approximately 30 additional hours of sleep per month." The output is an action suggestion for the user.

[0248] Step 6:

[0249] The server sends the generated suggestions to the user's device and displays them via push notification. The input is the generated suggestions, and the output is the notification displayed on the user's device. Specifically, the device displays a notification saying, "By reducing app usage after midnight, you will get more sleep and improve your quality of life." The user can check the detailed suggestions within the app.

[0250] 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.

[0251] System Overview

[0252] The present invention is a system that collects data such as user communication charges, startup times, and application usage times, and combines this with an emotion engine that recognizes user emotions to make specific suggestions for improving the user's quality of life. Specific embodiments of the system are described below.

[0253] Data collection implementation

[0254] The device records the user's data usage, startup time, app usage time, and emotional data at regular intervals, including:

[0255] The time and duration of each app usage.

[0256] Data charges consumed.

[0257] It uses a camera and microphone to recognize emotions from the user's facial expressions and voice.

[0258] This data is stored in a database or temporary file within the device.

[0259] Data transmission and storage practices

[0260] The collected data is sent from the device to a server at regular intervals. This data includes communication charges, startup time, app usage time, and emotional data. The server stores the received data in an appropriate format and performs security checks to ensure safety.

[0261] Data Preprocessing Embodiments

[0262] The server reads and pre-processes the received data, which includes:

[0263] Imputing missing data: A method of imputing using past average values.

[0264] Outlier detection and removal: Remove abnormally high or low values.

[0265] Data normalization: Scaling data values ​​to the range 0 to 1.

[0266] Emotion data analysis: Extract emotional elements such as goodwill, badwill, and stress.

[0267] Data Analysis Embodiments

[0268] Once the preprocessing is complete, the data is comprehensively analyzed by the AI ​​installed on the server. The AI ​​analyzes the following items, for example:

[0269] Frequency of app use by time of day.

[0270] Peak communication times.

[0271] Startup and usage time trends.

[0272] The relationship between emotional data and usage behavior.

[0273] Suggestion Generation Embodiments

[0274] The server's AI generates specific action suggestions for the user based on the analysis results. The suggestions are expressed in natural language and formatted in a way that is easy for the user to understand. For example,

[0275] "Recently, app use after midnight has been increasing. Reducing app use by one hour after midnight is predicted to result in an increase of approximately 30 hours of sleep per month."

[0276] "70% of data usage is spent on certain streaming apps. By only using them when connected to Wi-Fi, you can significantly reduce your data usage."

[0277] "We've noticed an increase in stress recently. Please schedule times to avoid using apps to relax."

[0278] Embodiments of Proposal Delivery

[0279] The server generates a proposal and sends it to the device. When sending, the data is formatted and checked to ensure the proposal is transmitted correctly. The device then notifies the user of the proposal. This is typically displayed as a push notification or an in-app message. The user can then view the proposal in detail by checking the notification.

[0280] Specific examples

[0281] Example 1: Suggestions for users who experience high late-night usage and increased stress

[0282] 1. The device measures the user's app usage data and emotional data every night after midnight and records the usage data and emotional data every hour.

[0283] 2. The device sends one week of data to the server. For example, "2023-10-01 00:00: 120 minutes of use, high stress level" or "2023-10-02 00:00: 110 minutes of use, medium stress level."

[0284] 3. The server preprocesses the data and analyzes usage time and stress levels after midnight.

[0285] 4. The AI ​​identifies that "the average amount of use after midnight is 120 minutes per week, which indicates a high stress level," and automatically generates suggestions to reduce stress and usage time.

[0286] 5. The server sends a suggestion to the device that "reducing usage time after midnight by one hour will improve stress levels and increase sleep by approximately 30 hours per month."

[0287] 6. The device will then send a push notification to the user with the suggestions, and the user can view the details of the suggestions in the app.

[0288] Example 2: Suggestions for users with excessive data usage and negative emotions

[0289] 1. The device collects the user's data usage and emotion data for one month.

[0290] 2. The device sends the collected data to a server, including daily data usage, apps used, and emotional data.

[0291] 3. The server pre-processes the data and analyzes key traffic drivers and sentiment.

[0292] 4. AI identifies that certain streaming apps consume a large portion of data usage and negative emotions frequently arise while using them.

[0293] 5. The server sends a suggestion to the device suggesting that users limit the use of certain streaming apps to Wi-Fi and use data-saving features to reduce data charges and alleviate negative emotions.

[0294] 6. Users will be encouraged to review their notifications and how they use streaming apps to reduce data costs and improve their mood.

[0295] The above is a detailed description of an embodiment of the present invention, which allows users to understand their own behavioral patterns and emotions in detail and receive specific suggestions to improve their quality of life.

[0296] The processing flow will be explained below.

[0297] Step 1:

[0298] The device collects data on the user's data usage, startup time, app usage time, and emotional data. Emotional data is obtained by analyzing the user's facial expressions and voice using the camera and microphone. For example, the emotion engine can recognize emotions such as stress, joy, and excitement from the user's facial expressions and tone of voice while using the app.

[0299] Step 2:

[0300] The data collected by the device is stored in an internal database or temporary file. At this stage, the data is checked for completeness and duplication, and the data format is unified if necessary.

[0301] Step 3:

[0302] The device periodically (e.g., daily or weekly) transmits the stored data to the server via the network. HTTP or HTTPS is used as the communication protocol, and the transmitted data includes communication charges, startup time, application usage time, and emotional data.

[0303] Step 4:

[0304] The server receives the received data and performs security checks (e.g., data encryption, integrity check) to ensure that the data has not been tampered with or leaked.

[0305] Step 5:

[0306] The server saves the received data in a database. Common formats such as JSON and CSV are used for saving. When saving, the consistency of each data item is rechecked to ensure there is no duplication or missing data.

[0307] Step 6:

[0308] The server pre-processes the data, which includes:

[0309] Imputing missing data: For example, imputing missing data with historical average values.

[0310] Outlier detection and removal: Filter out data that deviates significantly from normal usage patterns.

[0311] Data normalization: Scaling data values ​​to the range 0 to 1.

[0312] Emotion data analysis: Extracting emotional elements (e.g., stress, joy, excitement) from facial and voice data.

[0313] Step 7:

[0314] The server inputs the pre-processed data into the AI ​​model for comprehensive analysis, specifically analyzing the following:

[0315] Frequency of app use by time of day.

[0316] Peak communication times.

[0317] Startup and usage time trends.

[0318] The relationship between emotional data and usage behavior.

[0319] Step 8:

[0320] The server's AI generates specific action suggestions for the user based on the analysis results. The suggestions are expressed in natural language and formatted in a way that is easy for the user to understand. For example, the following suggestions are automatically generated:

[0321] "Recently, app use after midnight has been increasing. Reducing app use by one hour after midnight is predicted to result in an increase of approximately 30 hours of sleep per month."

[0322] "70% of data usage is spent on certain streaming apps. By only using them when connected to Wi-Fi, you can significantly reduce your data usage."

[0323] "We've noticed an increase in stress recently. Please schedule times to avoid using apps to relax."

[0324] Step 9:

[0325] The server sends the generated proposal to the device. When sending, the data format is checked to ensure that the proposal content is transmitted correctly.

[0326] Step 10:

[0327] The device will notify the user of the suggestions, typically as a push notification or in-app message. The user can then view the suggestions in detail by checking the notification.

[0328] Step 11:

[0329] Users can review the notifications and take action based on the suggestions, such as avoiding late-night app use to ensure they get enough sleep or limiting streaming app use to Wi-Fi.

[0330] These are the specific processing steps of the program, which allow users to gain a detailed understanding of their own behavioral patterns and emotional state and receive specific suggestions to improve their quality of life.

[0331] Example 2

[0332] 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."

[0333] Conventional systems could only collect and analyze data such as user data charges, startup times, and app usage time, making it difficult to provide specific suggestions that took user emotions into account. Furthermore, the collected data often contained missing data or outliers, making accurate analysis impossible. Furthermore, the suggestions made to users were limited, making it difficult to provide specific action suggestions that would improve users' quality of life.

[0334] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting a user's communication charges, startup time, application usage time, and emotional data; means for transmitting the collected data to the server at regular intervals; means for preprocessing the received data in the server, which includes filling in missing data, detecting and removing outliers, normalizing data, and analyzing emotional data; AI means for analyzing the preprocessed data for frequency of use by time period, peak times of communication charges, trends in startup time and usage time, and correlations between emotional data and usage behavior; means for generating specific suggestions for the user based on the analysis results; and means for delivering the generated suggestions to the user's terminal. This makes it possible to make specific suggestions taking into account the user's behavioral patterns and emotions, thereby providing a comprehensive system for improving the user's quality of life.

[0335] "User" refers to an individual or group that uses the system and whose communication charges, startup time, app usage time, and emotional data are collected.

[0336] "Communication charges" refers to charges based on the amount of data transferred when a user uses a communication service.

[0337] "Startup time" refers to the time when the user starts operating the terminal and the time when each application is launched.

[0338] "App time" refers to the total time a user spends using a particular application.

[0339] "Emotion data" refers to emotional information obtained from the user's facial expressions and voice.

[0340] A "terminal" is a communication device or computer used by a user, and is a device that collects communication charges, usage time, and emotional data.

[0341] "Server" means the computer system that receives, stores, pre-processes and analyzes the collected data.

[0342] "Means of collection" refers to the device's ability to collect data on the user's data usage, startup time, app usage time, and emotional data.

[0343] "Transmitting means" refers to the function of the terminal to transmit collected data to the server.

[0344] The "preprocessing means" refers to a function that performs the following on the received data: complementing missing data, detecting and removing outliers, normalizing data, and analyzing emotion data.

[0345] "Missing data completion" refers to the process of using past average values, etc. to make up for any shortfalls in collected data.

[0346] "Outlier detection and removal" refers to the process of identifying and removing extremely high or low values ​​(outliers) when they are included in collected data.

[0347] "Data normalization" is the process of converting the scale of data into the range of 0 to 1.

[0348] "Emotion data analysis" refers to the process of analyzing emotion data obtained from facial expressions and voice to extract specific emotional elements (such as goodwill, badwill, stress, etc.).

[0349] "AI means" refers to an artificial intelligence function that uses pre-processed data to analyze frequency of use by time period, peak times for communication charges, trends in startup time and usage time, and the relationship between emotional data and usage behavior.

[0350] "Means for generating" refers to the function of creating specific suggestions for users based on the analysis results.

[0351] The "means for delivering" refers to a function for sending the generated proposal to the user's terminal.

[0352] MODE FOR CARRYING OUT THE INVENTION

[0353] System Overview

[0354] This invention is a system that collects data on users' communication charges, startup times, application usage times, and emotional data, and analyzes this data to provide specific suggestions for improving the user's quality of life. This system operates by combining a terminal and a server. The detailed configuration and processing flow of the system are described below.

[0355] Configuring Data Collection

[0356] The device collects data on each user's data usage, app launch time, app usage time, and emotional data. The device can be a smartphone, tablet, PC, or other common device. This includes specific hardware and software such as:

[0357] Data collection is performed using the application's logging function.

[0358] Network monitoring software is used to collect communication charge data.

[0359] To collect emotion data, the device's camera and microphone are used, and facial expression recognition software and voice analysis software (e.g., OpenCV, TENSORFLOW (registered trademark)) are implemented.

[0360] Configuring data transmission and storage

[0361] The device sends the collected data to the server at regular intervals. The server receives the data and stores it securely. A secure communication protocol (e.g., SSL / TLS) is used to transmit the data, and the data is converted into a standard format such as JSON or XML. The server stores this data in a database (e.g., MySQL, MongoDB) and performs security checks.

[0362] Data preprocessing configuration

[0363] The server pre-processes the received data, which includes the following steps:

[0364] Imputing missing data: Use historical average values ​​to fill in missing data.

[0365] Outlier detection and removal: Statistical methods are used to detect and remove anomalous data points.

[0366] Data normalization: Scale and standardize the data to the range 0 to 1.

[0367] Emotion data analysis: Analyze emotion data using machine learning models (e.g., BERT, LSTM) to extract specific emotion elements.

[0368] Configuring Data Analysis

[0369] The server performs comprehensive analysis using AI based on the pre-processed data. The AI ​​analyzes:

[0370] Frequency of app use by time of day

[0371] Peak communication charge times

[0372] Boot time and usage time trends

[0373] Relationship between emotional data and usage behavior

[0374] This allows for detailed analysis of user behavior patterns and emotions.

[0375] Configuring Proposal Generation

[0376] The AI ​​installed on the server generates specific action suggestions based on the analysis results. The suggestions are expressed in natural language and formatted in a way that is easy for users to understand. For example:

[0377] "Recently, app use after midnight has increased. Reducing app use by one hour after midnight would result in an increase of approximately 30 hours of sleep per month."

[0378] "70% of data usage is spent on certain streaming apps. By only using them when connected to Wi-Fi, you can significantly reduce your data usage."

[0379] "You've been experiencing increased stress lately. Try scheduling time off your app use to relax."

[0380] Configuring Proposal Delivery

[0381] The server sends the generated proposal to the device. The data format is checked to ensure the proposal content is transmitted correctly, and the user is notified via a push notification or in-app message. The user can then view the detailed proposal content.

[0382] Specific examples

[0383] Example 1: Suggestions for users who experience high late-night usage and increased stress

[0384] 1. The device records the user's app usage data and emotional data every night after midnight.

[0385] 2. The device sends this data for one week to the server. For example, "2023-10-01 00:00: 120 minutes of use, high stress level" or "2023-10-02 00:00: 110 minutes of use, medium stress level."

[0386] 3. The server preprocesses the data and analyzes usage time and stress levels after midnight.

[0387] 4. As a result of the analysis, the AI ​​determines that "the average amount of use after midnight is 120 minutes per week, which indicates a high stress level," and suggests reducing stress and reducing usage time.

[0388] 5. The server generates a suggestion to the device: "Reducing usage time after midnight by one hour will improve stress levels and increase sleep by approximately 30 hours per month."

[0389] 6. The device will send a push notification to the user with the suggestions, and the user can view the details of the suggestions in the app.

[0390] Example 2: Suggestions for users with excessive data usage and negative emotions

[0391] 1. The device collects the user's data usage and emotional data for one month.

[0392] 2. The device sends the collected data to the server, including daily data usage, apps used, and emotional data.

[0393] 3. The server pre-processes the data and analyzes key traffic drivers and sentiment.

[0394] 4. AI identifies that certain streaming apps consume a large portion of data usage and negative emotions frequently arise while using them.

[0395] 5. The server generates a suggestion to the device, suggesting that the user limit the use of certain streaming apps to Wi-Fi and utilize data-saving features to reduce data charges and alleviate negative emotions, and sends it to the device.

[0396] 6. Users will be encouraged to review their notifications and how they use streaming apps to reduce data costs and improve their mood.

[0397] The above is a detailed description of the embodiment of the present invention. This system allows users to understand their own behavioral patterns and emotions in detail and receive specific suggestions to improve their quality of life.

[0398] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0399] Step 1: Data collection

[0400] The device will collect data on the user's data usage, startup time, app usage time, and emotional data at regular intervals. This step includes the following specific actions:

[0401] Input: User's app usage, communication data, facial expression and voice data

[0402] Data processing: Record the start and end times of each app and calculate usage time. Record communication data using network monitoring software. Extract emotions from the user's facial expressions and voice using facial recognition and voice analysis software.

[0403] Output: Each piece of data (usage time, communication volume, emotional data) is recorded in the device's database.

[0404] Step 2: Send data

[0405] The device sends the collected data to the server at regular intervals. This step includes the following specific operations:

[0406] Input: Data usage, startup time, app usage time, emotional data stored on the device

[0407] Data processing: Convert data into JSON or XML format. Send data securely using SSL / TLS protocol.

[0408] Output: Data sent to the server

[0409] Step 3: Store your data

[0410] The server stores the received data in the appropriate database and performs security checks. This step includes the following specific actions:

[0411] Input: Various data sent from the device (communication charges, startup time, app usage time, emotional data)

[0412] Data processing: Data is stored in a database (e.g., MySQL, MongoDB) and security checks such as SQL injection protection and data encryption are performed.

[0413] Output: Securely stored data

[0414] Step 4: Data Preprocessing

[0415] The server pre-processes the received data. This step includes the following specific actions:

[0416] Input: Each stored data (communication charges, startup time, app usage time, emotional data)

[0417] Data processing:

[0418] Imputing missing data: Imputing missing data using historical average values.

[0419] Outlier detection and removal: Statistical methods (e.g., standard deviation) are used to detect and remove outliers.

[0420] Data normalization: Scale all data to the range 0 to 1.

[0421] Sentiment data analysis: Using machine learning models (e.g., BERT, LSTM), we analyze the sentiment data and extract specific sentiment elements.

[0422] Output: Preprocessed data

[0423] Step 5: Data analysis

[0424] The AI ​​on the server performs comprehensive analysis based on the pre-processed data. This step includes the following specific actions:

[0425] Input: Preprocessed data (frequency of use, communication charges, startup time, emotion data)

[0426] Data processing:

[0427] Analysis of usage frequency by time of day: Calculate the number of times the app is used during each time period.

[0428] Identifying peak hours for communication charges: Communication data is aggregated by hour and the time period with the highest value is identified.

[0429] Startup and usage trend analysis: Long-term usage patterns are analyzed using statistical methods.

[0430] Correlation analysis between emotional data and usage behavior: Analyze the correlation between emotional data and app usage data.

[0431] Output: Analysis results

[0432] Step 6: Proposal Generation

[0433] The server's AI generates specific action suggestions based on the analysis results. This step includes the following specific actions:

[0434] Input: Analysis results

[0435] Data processing: The analysis results are converted into natural language and specific suggestions are generated. For example, a suggestion such as, "Recently, your app use after midnight has increased. If you reduce your app use after midnight by one hour, you will gain approximately 30 hours of sleep per month."

[0436] Output: Generated proposals

[0437] Step 7: Distributing the proposal

[0438] The server sends the generated proposal to the device and notifies the user. This step includes the following specific actions:

[0439] Input: Generated proposals

[0440] Data processing: Check the data format to ensure the proposed content is conveyed correctly, and send it as a push notification or in-app message.

[0441] Output: Suggestion notification sent to user

[0442] This is the specific flow of the process that the program of this system performs. Users can confirm the suggestions and take action to improve their quality of life.

[0443] (Application example 2)

[0444] 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."

[0445] Modern consumers generate vast amounts of data through their use of applications and devices, but there is a lack of systems that can effectively utilize this data to improve their quality of life. Furthermore, there is a lack of systems that can analyze customer behavior and emotions in real time in physical stores and display optimal product recommendations and advertisements. This situation results in missed opportunities to improve customer satisfaction and sales promotions. Furthermore, improving quality of life by collecting and analyzing emotional data and providing specific, individualized recommendations to users is also an important challenge.

[0446] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0447] In this invention, the server includes means for collecting data on user communication charges, startup times, application usage times, and emotion data, means for transmitting the collected data to the server, means for preprocessing the data received by the server, AI means for analyzing the preprocessed data, means for generating specific proposals for the user based on the analysis results, means for distributing the generated proposals to the user's terminal, means for collecting customer gaze data, movement path data, and product viewing time in a physical store, and means for analyzing the collected customer data in real time and displaying product proposals and advertisements to the customer. This not only makes specific proposals to improve the user's quality of life, but also enables optimal product proposals and advertisements to be displayed based on the customer's behavior and emotions in a physical store.

[0448] "Communication charges" are the communication costs incurred when a user sends or receives data via an Internet connection.

[0449] "Launch time" refers to the time when an application is launched by a user.

[0450] "Application Time" means the total time a user spends using a particular application.

[0451] "Emotional data" is emotional information extracted through analysis based on the user's facial expressions and voice.

[0452] "Gaze data" refers to data that indicates the direction and object the user is looking at.

[0453] "Movement path data" refers to data that indicates how a user moves within a space.

[0454] "Product View Time" refers to the amount of time a user spends looking at a particular product.

[0455] "Preprocessing" refers to the preparation of data prior to analysis, such as filling in missing data, removing outliers, and normalizing data.

[0456] "AI Methods" refers to artificial intelligence techniques used to analyze incoming data and find patterns and trends.

[0457] "Specific suggestions" refers to proposing actions or improvements that are beneficial to users based on the analysis results.

[0458] System Overview

[0459] The system of the present invention collects data on users' communication charges, startup times, application usage times, and emotional data, and uses this data to make suggestions for improving quality of life. It also includes a function to collect customer behavioral and emotional data in physical stores and make product suggestions and display advertisements in real time.

[0460] Data collection

[0461] The device is equipped with a means for collecting communication charges, startup time, application usage time, and emotional data. Emotional data is recognized from the user's facial expressions and voice using a camera and microphone. This data is recorded in the device's internal database or in a temporary file.

[0462] Data transmission and storage

[0463] The device periodically sends the collected data to the server, which stores the data in an appropriate format and performs security checks.

[0464] Data Preprocessing

[0465] The server pre-processes the received data, which includes:

[0466] Imputing missing data: Imputing with the historical average value.

[0467] Outlier detection and removal: Remove abnormally high or low values.

[0468] Data normalization: Scaling data values ​​to the range 0 to 1.

[0469] Emotion data analysis: Extract emotional elements such as likes, dislikes, and stress.

[0470] Data analysis

[0471] The pre-processed data is then analyzed by AI on the server. The AI ​​analyzes:

[0472] Frequency of application usage by time of day.

[0473] Peak communication times.

[0474] Startup and usage time trends.

[0475] The relationship between emotional data and usage behavior.

[0476] The relationship between customer gaze data, product viewing time, and movement path.

[0477] Proposal generation

[0478] The server's AI generates suggestions for the user based on the analysis results. The suggestions are expressed in natural language. For example:

[0479] "Recently, app use after midnight has increased. Reducing app use by one hour after midnight would result in an increase of approximately 30 hours of sleep per month."

[0480] "70% of our data usage is spent on certain streaming apps. By only using them when connected to Wi-Fi, we can significantly reduce our data usage."

[0481] "We've noticed an increase in stress recently. Please schedule times to take time off from apps to relax."

[0482] In real time, in-store customers will be shown suggestions such as:

[0483] "Get a 20% off coupon when you purchase this new product."

[0484] "Do you have a question about an item in this area? Would you like me to page a sales associate?"

[0485] Proposal distribution

[0486] The server sends the generated suggestions to the device, which then displays the suggestions to the user as push notifications or in-app messages. The user can then view the detailed suggestions on the device.

[0487] Specific examples

[0488] Example 1: Suggestions for users who use the service frequently late at night and experience increased stress

[0489] 1. The device measures the user's app usage data and emotional data every night after midnight and records the usage data and emotional data every hour.

[0490] 2. The device sends one week of data to the server. For example, it might send the following: "2023-10-01 00:00: 120 minutes of use, high stress level", "2023-10-02 00:00: 110 minutes of use, medium stress level", etc.

[0491] 3. The server preprocesses the data and analyzes usage time and stress levels after midnight.

[0492] 4. The AI ​​identifies that "the average amount of use after midnight is 120 minutes per week, which indicates a high stress level," and automatically generates suggestions to reduce stress and usage time.

[0493] 5. The server sends a suggestion to the device that "reducing usage time after midnight by one hour will improve stress levels and increase sleep by approximately 30 hours per month."

[0494] 6. The device will then send a push notification to the user with the suggestions, and the user can view the details of the suggestions in the app.

[0495] Example 2: An attractive offer for a new product

[0496] 1. A customer puts on smart glasses and enters the store.

[0497] 2. Smart glasses track customers' gazes and detect when they linger on a particular shelf for an extended period of time.

[0498] 3. Recognize the positive emotion of curiosity in the customer's facial expression.

[0499] 4. The server analyzes this data and determines that "this new product is generating interest."

[0500] 5. "Purchase this new product and receive a 20% off coupon" will be displayed on the smart glasses display.

[0501] Prompt Sentence Examples

[0502] When a customer wears smart glasses and enters a store, the glasses will track the customer's gaze. If the customer lingers on a specific shelf for a long time and detects a positive emotion indicating "curiosity," the following suggestion will be displayed: "Buy this new product and receive a 20% off coupon."

[0503] As described above, the present invention makes it possible to effectively utilize user behavioral and emotional data to provide specific suggestions for improving quality of life. It also makes it possible to provide appropriate product suggestions and advertisements to customers in real time in brick-and-mortar stores.

[0504] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0505] Step 1:

[0506] Data collection

[0507] The device collects data on the user's data usage, startup time, application usage time, and emotional data. It uses a camera and microphone to recognize the user's facial expressions and voice. This data is recorded in temporary files or an internal database.

[0508] Input: User's communication charges, startup time, application usage time, facial expression data, voice data

[0509] Output: Collected data (communication charges, startup time, application usage time, emotional data)

[0510] Step 2:

[0511] Data transmission

[0512] The device periodically sends the collected data to the server, where it is encrypted to ensure data security.

[0513] Input: Collected data (communication charges, startup time, application usage time, emotional data)

[0514] Output: Data sent to the server

[0515] Step 3:

[0516] Data storage and security checks

[0517] The server stores the received data in the appropriate format and performs security checks, including verifying data integrity and detecting unauthorized access.

[0518] Input: Data sent to the server

[0519] Output: Data that has undergone security checks, data stored in the database on the server

[0520] Step 4:

[0521] Data Preprocessing

[0522] The server preprocesses the received data, interpolating missing data with historical averages and removing outliers, scaling the data to a range of 0 to 1, and analyzing the emotion data to extract emotional elements such as likes, dislikes, and stress.

[0523] Input: Data stored on the server

[0524] Output: Preprocessed data (imputed data, outlier-removed data, normalized data, analyzed sentiment data)

[0525] Step 5:

[0526] Data analysis

[0527] The AI ​​installed on the server analyzes the pre-processed data, including frequency of application use by time of day, peak times for communication charges, trends in startup time and usage time, correlations between emotional data and usage behavior, and correlations between gaze data, product viewing time, and movement routes.

[0528] Input: Preprocessed data

[0529] Output: Analysis results (frequency of use, peak times for communication charges, trends, correlations with emotion data, correlations with gaze data)

[0530] Step 6:

[0531] Proposal generation

[0532] Based on the analysis results, the server's AI generates specific suggestions for the user, expressed in natural language based on the user's behavioral patterns and emotional data.

[0533] Input: Analysis results

[0534] Output: Generated suggestions (suggestions in natural language format)

[0535] Step 7:

[0536] Proposal distribution

[0537] The server sends the generated suggestions to the device, which then displays the suggestions to the user as push notifications or in-app messages.

[0538] Input: Generated proposals

[0539] Output: Proposals delivered to the user's device, and the displayed proposals

[0540] Step 8:

[0541] Real-time product suggestions

[0542] In brick-and-mortar stores, smart glasses track customers' gaze data and send it to a server, which analyzes it to identify their level of interest in products and display product suggestions and advertisements in real time.

[0543] Input: gaze data, movement path data

[0544] Output: Product offers and advertisements displayed to customers

[0545] Through these steps, the system can effectively utilize behavioral and emotional data of users and customers to make specific suggestions to improve their quality of life.

[0546] 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.

[0547] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0548] 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.

[0549] [Second embodiment]

[0550] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0551] 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.

[0552] 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).

[0553] 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.

[0554] 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.

[0555] 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).

[0556] 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.

[0557] 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.

[0558] 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.

[0559] 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.

[0560] 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.

[0561] 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."

[0562] System Overview

[0563] The present invention is a system that collects data such as user communication charges, startup times, and application usage times, and analyzes the data using a server to provide specific suggestions for improving the user's quality of life. Specific embodiments of the system are described below.

[0564] Data collection implementation

[0565] The device records the user's data usage, startup time, and app usage time at regular intervals (e.g., every hour or every day). For example, it records the amount of time a user uses a particular app over a certain period of time and the amount of data usage during that time. This data is stored in a database or temporary file within the device.

[0566] Data transmission and storage practices

[0567] The collected data is sent from the device to the server at regular intervals (e.g., daily or weekly). The data sent here includes communication charges, startup time, and app usage time. The server converts the received data into an appropriate format (e.g., JSON, CSV) and saves it in a database for safekeeping.

[0568] Data Preprocessing Embodiments

[0569] The server reads the received data and performs pre-processing, which may include the following:

[0570] Imputing missing data: For example, if data is missing for a specific time period, impute that portion with the historical average or median.

[0571] Outlier detection and removal: For example, removing values ​​that deviate significantly from normal usage patterns.

[0572] Data normalization: Adjusting data values ​​to a uniform scale (e.g., converting them to the range 0 to 1).

[0573] Data Analysis Embodiments

[0574] Once preprocessed, the data is analyzed by AI installed on the server. The AI ​​analyzes user behavior patterns in detail and identifies specific issues. For example, it identifies the frequency of app use by time of day and peak times for data charges. It also analyzes trends in launch times and usage duration to uncover user usage trends.

[0575] Suggestion Generation Embodiments

[0576] The server's AI generates specific action suggestions for the user based on the analysis results. For example, the following suggestions may be generated:

[0577] "Recently, app use after midnight has been increasing. Reducing app use by one hour after midnight is expected to increase sleep time by approximately 30 hours per month."

[0578] "70% of data usage is used for certain streaming apps. By using them only when connected to Wi-Fi, you can significantly reduce your data usage."

[0579] Embodiments of Proposal Delivery

[0580] Finally, the server sends the generated proposal to the device and notifies the user. The device displays the proposal to the user via a push notification, allowing the user to review its contents. If necessary, the user can view the proposal details within the app.

[0581] Specific examples

[0582] Example 1: Suggestions for users with high late-night usage

[0583] 1. The device measures the user's app usage data every night after midnight and records usage data every hour.

[0584] 2. The device sends one week's worth of data to the server. For example, "2023-10-01 00:00: 120 minutes", "2023-10-02 00:00: 110 minutes", etc.

[0585] 3. The server receives the data, imputes missing values, and removes outliers if necessary.

[0586] 4. The server compiles usage time from midnight onwards for one week, and AI analyzes the user's usage patterns.

[0587] 5. The AI ​​identifies that "the average usage after midnight is 120 minutes per week" and automatically generates an improvement suggestion (reducing usage time by 60 minutes).

[0588] 6. The server generates a suggestion to the device, saying, "If you reduce your usage time after midnight by one hour, you will increase your sleep time by a total of 30 hours in one month." and sends it to the device.

[0589] 7. The device will then push a notification to the user with the suggestions, which the user can then review in the app.

[0590] Example 2: Suggestions for users with excessive data usage

[0591] 1. The device collects the user's data usage data for one month.

[0592] 2. The device sends the collected data to the server, which includes information on daily communication charges and apps used.

[0593] 3. The server receives the data and pre-processes it for analysis.

[0594] 4. AI will analyze and identify which specific streaming apps are taking up the majority of your data usage.

[0595] 5. The server generates a suggestion that suggests limiting the use of certain streaming apps to Wi-Fi or using data saving features to reduce data charges.

[0596] 6. The server sends the generated proposal to the device and notifies the user.

[0597] 7. Users can reduce data costs by checking notifications and reviewing how they use streaming apps.

[0598] The above is a specific description of the embodiment of the present invention. This system allows users to understand their own behavioral patterns and receive appropriate suggestions for improving their lifestyle.

[0599] The processing flow will be explained below.

[0600] Step 1:

[0601] The device collects the user's data usage, startup time, and app usage time. This data is recorded at regular intervals (e.g., hourly or daily). Specifically, the device's log function is used to record the start and end times of each app's use, the amount of data consumed, etc.

[0602] Step 2:

[0603] The data collected by the device is stored in a temporary file or an internal database. At this stage, the data is checked for duplication or format inconsistencies, and the data format is unified if necessary.

[0604] Step 3:

[0605] The device periodically (e.g. daily or weekly) transmits stored data to the server via the network. The transmitted data includes communication charges, startup time, and application usage time. HTTP or HTTPS is used as the communication protocol.

[0606] Step 4:

[0607] The server receives the received data and performs security checks (e.g., data encryption, integrity checks) to ensure that the data has not been tampered with.

[0608] Step 5:

[0609] The server saves the received data in the database. Common formats such as JSON and CSV are used for saving. When saving, the consistency of each data item is rechecked.

[0610] Step 6:

[0611] The server performs data preprocessing, such as imputing missing data (e.g., imputing with historical average values), detecting and removing outliers, and normalizing data (e.g., scaling to a range of 0 to 1).

[0612] Step 7:

[0613] The server inputs the preprocessed data into the AI ​​model for analysis, which analyzes the frequency of app use by time of day, peak times for data usage, and trends in startup and usage time.

[0614] Step 8:

[0615] The server's AI generates specific suggestions for users based on the analysis results. The suggestions are expressed in natural language and formatted in a way that is easy for users to understand. For example, "Recently, your app usage after midnight has increased. If you reduce your app usage by one hour after midnight, it is predicted that you will gain approximately 30 hours of sleep per month."

[0616] Step 9:

[0617] The server sends the generated proposal to the device. When sending, the data format is checked to ensure that the proposal content is transmitted correctly.

[0618] Step 10:

[0619] The device will notify the user of the suggestions, typically as a push notification or in-app message. The user can then view the details of the suggestions by checking the notification.

[0620] Step 11:

[0621] Users can check the notification and change their behavior based on the suggestions, for example, by refraining from using apps late at night to ensure they get enough sleep.

[0622] These are the specific processing steps of the program. Through this series of processes, users can gain a detailed understanding of their own behavioral patterns and receive specific suggestions for improving their quality of life.

[0623] Example 1

[0624] 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."

[0625] In systems that collect and analyze data on users' communication charges and app usage time, it can be difficult to generate effective lifestyle improvement proposals using existing methods. In particular, it is difficult to understand missing data, the presence of outliers, and user behavior patterns in detail to generate specific and effective proposals.

[0626] 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.

[0627] In this invention, the server includes means for collecting data such as user communication charges, startup times, and application usage times, means for transmitting the collected data to the server, and means for preprocessing the received data in the server, which enables detailed analysis of user behavior patterns, completion and removal of missing data and outliers, and normalization to a unified scale.

[0628] The server also includes an artificial intelligence unit that analyzes the preprocessed data, a unit that generates specific suggestions for the user based on the analysis results, and a unit that delivers the generated suggestions to the user's terminal, thereby providing the user with specific and effective suggestions for action.

[0629] "User's communication charges" means the total amount of data communication usage and charges incurred when a User uses the communication service.

[0630] "Boot time" is the time it takes for a particular application or device to start and become available for use, and the cumulative time that the application or device is running.

[0631] "App time" is the amount of time a particular application is actually used by a user.

[0632] "Means for collecting data" refers to a device or program that records information such as a user's communication charges, startup time, and application usage time at regular intervals.

[0633] "Means for transmitting data" refers to a device or program for transferring collected data to a database or server.

[0634] The "preprocessing means" is a device or program for imputing missing data, removing outliers, and normalizing the received data.

[0635] "Artificial intelligence means" refers to artificial intelligence technology that uses collected and pre-processed data to analyze user behavior patterns and generate specific suggestions based on the analysis results.

[0636] The "means for generating specific suggestions" is a device or program for generating action suggestions for users based on the analysis results using artificial intelligence technology.

[0637] "Means for distributing to terminal" means a device or program for transferring the proposal generated by the server to the user's terminal and notifying the user.

[0638] "Recording means" means a device or program that records the user's currently running apps and their running time at regular intervals.

[0639] A "means for completing missing data" is a device or program that, when there is a gap in the collected data, fills in the gaps with past data, estimated values, etc.

[0640] An "outlier removal means" is a device or program that detects data that deviates significantly from normal usage patterns and removes them from the analysis.

[0641] A "means for normalization" is a device or program that converts data values ​​to a uniform scale (e.g., a range of 0 to 1).

[0642] System Overview

[0643] This system collects data such as user communication charges, startup times, and application usage time, and analyzes it on a server to understand the user's behavioral patterns and make suggestions to improve their quality of life. Specifically, the system consists of the steps of data collection by the device, data transmission to the server, data preprocessing and analysis on the server, and proposal generation and distribution.

[0644] Data collection implementation

[0645] The device records the user's communication charges, startup times, and app usage time at regular intervals. For example, it records the amount of time the user used a particular app over a certain period of time and the data communication charges consumed during that time. This data is stored in a database or temporary file within the device. A program for collecting and recording data is installed on the device. This program uses a scheduler to collect data every hour and saves it in a database (e.g., SQLite).

[0646] Data transmission and storage practices

[0647] The device sends the collected data to the server at a fixed interval (for example, at midnight every day). The data is converted into an appropriate format (for example, JSON or CSV). The server analyzes and stores the received data in a database (for example, MySQL). To send the data, the device makes an HTTP request, and the sent data is received by the server's REST API.

[0648] Data Preprocessing Embodiments

[0649] The server performs preprocessing on the received data. This preprocessing includes missing data completion, outlier detection and removal, and data normalization. This preprocessing is performed using the Python Pandas library. Data normalization is performed using MinMaxScaler from scikit-learn.

[0650] Data Analysis Embodiments

[0651] Once the preprocessing is complete, the data is analyzed by artificial intelligence (AI) installed on the server. The AI ​​performs detailed analysis of user behavior patterns and extracts specific issues (for example, times of high usage or peak times for communication charges). Machine learning algorithms such as K-means clustering are used for the analysis.

[0652] Suggestion Generation Embodiments

[0653] The server's AI generates specific action suggestions for the user based on the analysis results. For example, it could generate the following suggestion: "Reducing app use by one hour after midnight could increase sleep time by approximately 30 hours over the course of a month." Natural language processing technology is used to generate suggestions, for example, by inputting a prompt sentence to generate a suggestion using a generative AI model (such as GPT-3).

[0654] Embodiments of Proposal Delivery

[0655] The server sends the generated suggestions to the device and notifies the user. The device displays the suggestions via push notification, allowing the user to check their details. The user can also tap the notification to view the detailed suggestions within the app.

[0656] Specific examples

[0657] Example 1: Suggestions for users with high late-night usage

[0658] 1. The device measures the user's app usage data every night after midnight and records usage data every hour.

[0659] 2. The device sends one week of data to the server.

[0660] 3. The server receives the data, imputes missing values, and removes outliers.

[0661] 4. The server compiles usage time from midnight onwards for one week, and AI analyzes the user's usage patterns.

[0662] 5. The AI ​​identifies that "the average usage after midnight is 120 minutes per week" and automatically generates an improvement suggestion (reducing usage time by 60 minutes).

[0663] 6. The server generates a suggestion to the device, saying, "If you reduce your usage time after midnight by one hour, you will increase your sleep time by a total of 30 hours in one month." and sends it to the device.

[0664] 7. The device will then push a notification to the user with the suggestions, which the user can then review in the app.

[0665] Example 2: Suggestions for users with excessive data usage

[0666] 1. The device collects the user's data usage data for one month.

[0667] 2. The device sends the collected data to the server, which includes information on daily communication charges and apps used.

[0668] 3. The server receives the data and pre-processes it for analysis.

[0669] 4. AI will analyze and identify which specific streaming apps are taking up the majority of your data usage.

[0670] 5. The server generates a suggestion that suggests limiting the use of certain streaming apps to Wi-Fi or using data saving features to reduce data charges.

[0671] 6. The server sends the generated proposal to the device and notifies the user.

[0672] 7. Users can reduce data costs by checking notifications and reviewing how they use streaming apps.

[0673] Prompt Sentence Examples

[0674] "Collect app usage data after midnight for one month, analyze users' usage patterns, and generate lifestyle improvement suggestions."

[0675] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0676] Step 1: Collect data

[0677] Input: User's data charges, startup time, app usage time

[0678] How it works: The device runs a program that periodically records data charges, startup times, and app usage time.

[0679] Data processing: Data charges, startup time, and app usage time are saved in a database or temporary file.

[0680] Output: Data stored in the device's internal database or temporary files

[0681] Specific operation: The scheduler installed on the device measures the current communication charges, startup time, and application usage time every hour and stores them in an SQLite database (e.g., "2023-10-01 12:00: Application A 30 minutes").

[0682] Step 2: Sending data

[0683] Input: Data stored on the device about communication charges, startup time, and app usage time

[0684] Operation: The device converts the collected data into JSON format at regular intervals (for example, at midnight every day) and sends it to the server.

[0685] Data processing: Convert the data into JSON format.

[0686] Output: JSON data sent to the server

[0687] Specific operation: Every day at midnight, the device reads the current day's data from the SQLite database, converts the data to JSON format using the Python json module, and then sends it to the server via an HTTP request (e.g., {"2023-10-01": {"App A": 120, "App B": 30}}).

[0688] Step 3: Store your data

[0689] Input: JSON data sent to the server

[0690] How it works: The server parses the data it receives and stores it in a secure database.

[0691] Data processing: Parse the JSON data and convert it into a format that can be inserted into the database.

[0692] Output: Data stored in the database on the server

[0693] Specific operation: The server parses the received JSON data using Python's json module, generates an SQL statement to insert into the MySQL database, and executes it (e.g., INSERT INTO user_data VALUES ("2023-10-01", "App A", 120, "App B", 30)).

[0694] Step 4: Preprocessing the data

[0695] Input: Data stored in the database on the server

[0696] How it works: The server imputes missing data, detects and removes outliers, and normalizes the data.

[0697] Data processing: Impute missing data, remove outliers, and normalize data.

[0698] Output: Preprocessed data

[0699] Specific operation: The data is read into a data frame format using Python's Pandas library, missing values ​​are filled in using the fillna method, outliers are removed using conditional search, and the data is normalized using MinMaxScaler (e.g., {"App A": 0.5, "App B": 0.2}).

[0700] Step 5: Analyze the data

[0701] Input: Preprocessed data

[0702] How it works: The AI ​​installed on the server uses pre-processed data to analyze user behavior patterns.

[0703] Data computation: Use an AI model (e.g., K-means clustering) to separate the data into clusters.

[0704] Output: User behavior pattern analysis results

[0705] Specific operation: K-means clustering is performed using Python's Scikit-learn library, and user data is classified into each cluster (e.g., cluster 0 = users with high usage during the late night hours).

[0706] Step 6: Proposal Generation

[0707] Input: User behavior pattern analysis results

[0708] Action: The server's artificial intelligence generates specific action suggestions based on the analysis results.

[0709] Data calculation: A prompt sentence is input into a generative AI model (e.g., GPT-3) to generate a suggested sentence.

[0710] Output: Generated suggestion

[0711] Specific operation: Based on the analysis result that "there is a lot of usage after midnight," the generative AI model inputs the prompt sentence "Please generate a proposal to reduce app usage after midnight," and generates a proposal sentence (e.g., "Reducing app usage after midnight by one hour could increase sleep time by approximately 30 hours in a month").

[0712] Step 7: Distributing the proposal

[0713] Input: Generated suggestion

[0714] Behavior: The server generates a proposal, sends it to the device, and notifies the user.

[0715] Data processing: Convert the proposal into a notification format and send it to the terminal.

[0716] Output: Proposal notification displayed on the user's device

[0717] Specific operation: The server converts the suggestion text into JSON format and sends it to the device via an HTTP request. The device then generates a push notification based on the received JSON and notifies the user (e.g., notification message: "If you reduce app usage after midnight by one hour, you will gain approximately 30 hours of sleep in one month").

[0718] (Application example 1)

[0719] 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."

[0720] Users spend a lot of time and data charges using applications on smartphones and other devices, which can result in a decline in their quality of life. Furthermore, a bias in data charges and usage time toward specific apps can lead to wasteful usage and negatively impact health. However, it is difficult for users to recognize these patterns of behavior, making it difficult to take appropriate measures to improve them. Therefore, there is a need for a system that can analyze users' application usage patterns and automatically provide specific suggestions for optimally managing data charges and usage time.

[0721] 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.

[0722] In this invention, the server includes means for collecting data such as user communication charges, startup times, and application usage time; means for transmitting the collected data to the server; means for preprocessing the received data in the server; artificial intelligence means for analyzing the preprocessed data; means for analyzing the viewing patterns of specific applications and generating specific suggestions for the user; and means for delivering the generated suggestions to the user's device. This enables detailed analysis of user behavior patterns and automatically generates and delivers practical suggestions for optimizing communication charges and usage time. For example, if a user uses an application excessively during a certain time period, the system can suggest that the user use that time for other activities. Furthermore, recommending viewing content that consumes a lot of data over a Wi-Fi connection can also contribute to saving communication charges.

[0723] "Communication charges" are the costs incurred when a user communicates data via an Internet connection.

[0724] "Launch time" refers to the time when an application is started on a device.

[0725] "Time in app" refers to the total amount of time a user spends using a particular application.

[0726] "Means of collecting data" refers to the mechanism for obtaining information such as user data charges, startup time, and app usage time.

[0727] "Means for transmitting to a server" refers to a mechanism for sending collected data to a remote server via a communication network such as the Internet.

[0728] "Preprocessing means" refers to a mechanism for performing processes such as removing unnecessary data, filling in missing values, and normalizing data in order to improve the quality of collected data.

[0729] "Artificial Intelligence Tools" means AI techniques used to analyze pre-processed data and discover specific patterns or trends.

[0730] The "means for generating suggestions" is a mechanism for creating improvement measures and action suggestions for users based on data analyzed by artificial intelligence.

[0731] "Means of delivery to user's device" refers to a mechanism for notifying the user of the generated suggestions on their device, such as a smartphone or tablet.

[0732] "Behavioral patterns" refer to a series of usage trends and habits, such as how a user uses applications and at what times they consume the most data.

[0733] "Viewing patterns" are information that indicates the tendency of users to view what types of content at what times.

[0734] "Wi-Fi environment" refers to a network environment that connects to the Internet using wireless LAN.

[0735] "Data-intensive content" refers to applications such as video and streaming services that require large amounts of internet data.

[0736] "Use for other activities" refers to engaging in alternative activities such as exercise, reading, or sleep instead of using the application during a particular time period.

[0737] System Overview

[0738] This invention is a system that collects data such as user communication charges, startup times, and application usage time, and analyzes it on a server to provide specific action suggestions to users. The system has the functions of data collection, data transmission, preprocessing, AI analysis, proposal generation, and proposal distribution.

[0739] Data collection

[0740] The device records the user's data usage, startup time, and app usage time at regular intervals. For example, it records the time the user uses a particular app and the amount of data usage. This information is stored in an internal database.

[0741] Data transmission

[0742] The collected data, including communication charges, startup time, and usage time, is sent from the device to a server at regular intervals. The server converts the received data into an appropriate format and stores it securely.

[0743] Data Preprocessing

[0744] The server reads the received data and performs preprocessing, including filling in missing data, removing outliers, and normalizing the data, thereby improving the accuracy of the analysis.

[0745] Data analysis

[0746] Once preprocessed, the data is analyzed by AI installed on the server. The AI ​​analyzes user behavior patterns in detail and extracts viewing patterns and peak times for data charges. For example, by identifying viewing frequency and data consumption by time of day, it is possible to understand user behavior trends.

[0747] Proposal generation

[0748] The server's AI then generates specific action suggestions for the user based on the analysis results, including:

[0749] Suggestions to repurpose screen time for other activities during certain times

[0750] We recommend watching data-intensive content in a Wi-Fi environment.

[0751] Proposal distribution

[0752] The server sends the generated suggestions to the device and displays them to the user via push notification, where the user can view the details of the suggestions within the app.

[0753] Hardware and software details

[0754] Hardware: Smartphones (e.g. iPhone, Android devices), servers

[0755] Software: Python 3.9, JSON format, standard library

[0756] Specific examples

[0757] For example, if a user frequently watches videos late at night, the AI ​​will analyze this pattern and generate a suggestion such as, "You watch too much after midnight. By reducing your viewing time by one hour, you can gain approximately 30 hours of sleep per month." Also, if a specific streaming app is taking up a large portion of your data charges, the AI ​​will suggest, "To reduce data charges, we recommend limiting the use of this streaming app to Wi-Fi environments."

[0758] Prompt Sentence Examples

[0759] "Recently, app usage late at night has increased. Reducing usage after midnight by one hour is predicted to increase sleep time by approximately 30 hours per month. Based on this, please output code that suggests reducing viewing during specific times. For example, something implemented in Python would be good."

[0760] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0761] Step 1:

[0762] The device collects data such as the user's data charges, startup time, and app usage time at regular intervals. The inputs are the time the user starts each app (startup time), the amount of time the application is used (usage time), and the data charges incurred during use. This data is stored in an internal database. For example, if a user starts YouTube at 10 a.m., watches it for 30 minutes, and uses 50 MB of data during that time, that information will be recorded.

[0763] Step 2:

[0764] The device periodically sends the collected data to the server. The data is sent over the communication network and converted into an appropriate format, such as JSON. The input is the data collected in step 1, and the output is the data sent to the server. This data includes specific app names, usage time, communication charges, launch date and time, etc.

[0765] Step 3:

[0766] The server reads the received data and performs preprocessing. The input is the unprocessed data sent from the terminal. Preprocessing involves filling in missing data, detecting and removing outliers, and normalizing the data. For example, if data for a certain date and time is missing, it is filled in with the average value from the past. Outliers are values ​​that are clearly outside the normal range and are removed. Data normalization involves converting all data into a unified range from 0 to 1. The output is a dataset after preprocessing has been completed.

[0767] Step 4:

[0768] The server inputs the preprocessed data into an AI model for analysis. The input is the preprocessed data, and the AI ​​analyzes the user's behavioral patterns. For example, it can determine how much data is being used during a specific time period, or which applications are being used most frequently at which times. The output is a detailed analysis of the user's behavioral patterns.

[0769] Step 5:

[0770] The server generates specific action suggestions for the user based on the analysis results. The input is the analysis results of the artificial intelligence model. For example, if a user uses a lot of applications late at night, the server automatically generates a suggestion to reduce that usage time. Specifically, the server generates a suggestion such as, "If you reduce viewing after midnight by one hour, you can gain approximately 30 additional hours of sleep per month." The output is an action suggestion for the user.

[0771] Step 6:

[0772] The server sends the generated suggestions to the user's device and displays them via push notification. The input is the generated suggestions, and the output is the notification displayed on the user's device. Specifically, the device displays a notification saying, "By reducing app usage after midnight, you will get more sleep and improve your quality of life." The user can check the detailed suggestions within the app.

[0773] 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.

[0774] System Overview

[0775] The present invention is a system that collects data such as user communication charges, startup times, and application usage times, and combines this with an emotion engine that recognizes user emotions to make specific suggestions for improving the user's quality of life. Specific embodiments of the system are described below.

[0776] Data collection implementation

[0777] The device records the user's data usage, startup time, app usage time, and emotional data at regular intervals, including:

[0778] The time and duration of each app usage.

[0779] Data charges consumed.

[0780] It uses a camera and microphone to recognize emotions from the user's facial expressions and voice.

[0781] This data is stored in a database or temporary file within the device.

[0782] Data transmission and storage practices

[0783] The collected data is sent from the device to a server at regular intervals. This data includes communication charges, startup time, app usage time, and emotional data. The server stores the received data in an appropriate format and performs security checks to ensure safety.

[0784] Data Preprocessing Embodiments

[0785] The server reads and pre-processes the received data, which includes:

[0786] Imputing missing data: A method of imputing using past average values.

[0787] Outlier detection and removal: Remove abnormally high or low values.

[0788] Data normalization: Scaling data values ​​to the range 0 to 1.

[0789] Emotion data analysis: Extract emotional elements such as goodwill, badwill, and stress.

[0790] Data Analysis Embodiments

[0791] Once the preprocessing is complete, the data is comprehensively analyzed by the AI ​​installed on the server. The AI ​​analyzes the following items, for example:

[0792] Frequency of app use by time of day.

[0793] Peak communication times.

[0794] Startup and usage time trends.

[0795] The relationship between emotional data and usage behavior.

[0796] Suggestion Generation Embodiments

[0797] The server's AI generates specific action suggestions for the user based on the analysis results. The suggestions are expressed in natural language and formatted in a way that is easy for the user to understand. For example,

[0798] "Recently, app use after midnight has been increasing. Reducing app use by one hour after midnight is predicted to result in an increase of approximately 30 hours of sleep per month."

[0799] "70% of data usage is spent on certain streaming apps. By only using them when connected to Wi-Fi, you can significantly reduce your data usage."

[0800] "We've noticed an increase in stress recently. Please schedule times to avoid using apps to relax."

[0801] Embodiments of Proposal Delivery

[0802] The server generates a proposal and sends it to the device. When sending, the data is formatted and checked to ensure the proposal is transmitted correctly. The device then notifies the user of the proposal. This is typically displayed as a push notification or an in-app message. The user can then view the proposal in detail by checking the notification.

[0803] Specific examples

[0804] Example 1: Suggestions for users who experience high late-night usage and increased stress

[0805] 1. The device measures the user's app usage data and emotional data every night after midnight and records the usage data and emotional data every hour.

[0806] 2. The device sends one week of data to the server. For example, "2023-10-01 00:00: 120 minutes of use, high stress level" or "2023-10-02 00:00: 110 minutes of use, medium stress level."

[0807] 3. The server preprocesses the data and analyzes usage time and stress levels after midnight.

[0808] 4. The AI ​​identifies that "the average amount of use after midnight is 120 minutes per week, which indicates a high stress level," and automatically generates suggestions to reduce stress and usage time.

[0809] 5. The server sends a suggestion to the device that "reducing usage time after midnight by one hour will improve stress levels and increase sleep by approximately 30 hours per month."

[0810] 6. The device will then send a push notification to the user with the suggestions, and the user can view the details of the suggestions in the app.

[0811] Example 2: Suggestions for users with excessive data usage and negative emotions

[0812] 1. The device collects the user's data usage and emotion data for one month.

[0813] 2. The device sends the collected data to a server, including daily data usage, apps used, and emotional data.

[0814] 3. The server pre-processes the data and analyzes key traffic drivers and sentiment.

[0815] 4. AI identifies that certain streaming apps consume a large portion of data usage and negative emotions frequently arise while using them.

[0816] 5. The server sends a suggestion to the device suggesting that users limit the use of certain streaming apps to Wi-Fi and use data-saving features to reduce data charges and alleviate negative emotions.

[0817] 6. Users will be encouraged to review their notifications and how they use streaming apps to reduce data costs and improve their mood.

[0818] The above is a detailed description of an embodiment of the present invention, which allows users to understand their own behavioral patterns and emotions in detail and receive specific suggestions to improve their quality of life.

[0819] The processing flow will be explained below.

[0820] Step 1:

[0821] The device collects data on the user's data usage, startup time, app usage time, and emotional data. Emotional data is obtained by analyzing the user's facial expressions and voice using the camera and microphone. For example, the emotion engine can recognize emotions such as stress, joy, and excitement from the user's facial expressions and tone of voice while using the app.

[0822] Step 2:

[0823] The data collected by the device is stored in an internal database or temporary file. At this stage, the data is checked for completeness and duplication, and the data format is unified if necessary.

[0824] Step 3:

[0825] The device periodically (e.g., daily or weekly) transmits the stored data to the server via the network. HTTP or HTTPS is used as the communication protocol, and the transmitted data includes communication charges, startup time, application usage time, and emotional data.

[0826] Step 4:

[0827] The server receives the received data and performs security checks (e.g., data encryption, integrity check) to ensure that the data has not been tampered with or leaked.

[0828] Step 5:

[0829] The server saves the received data in a database. Common formats such as JSON and CSV are used for saving. When saving, the consistency of each data item is rechecked to ensure there is no duplication or missing data.

[0830] Step 6:

[0831] The server pre-processes the data, which includes:

[0832] Imputing missing data: For example, imputing missing data with historical average values.

[0833] Outlier detection and removal: Filter out data that deviates significantly from normal usage patterns.

[0834] Data normalization: Scaling data values ​​to the range 0 to 1.

[0835] Emotion data analysis: Extracting emotional elements (e.g., stress, joy, excitement) from facial and voice data.

[0836] Step 7:

[0837] The server inputs the pre-processed data into the AI ​​model for comprehensive analysis, specifically analyzing the following:

[0838] Frequency of app use by time of day.

[0839] Peak communication times.

[0840] Startup and usage time trends.

[0841] The relationship between emotional data and usage behavior.

[0842] Step 8:

[0843] The server's AI generates specific action suggestions for the user based on the analysis results. The suggestions are expressed in natural language and formatted in a way that is easy for the user to understand. For example, the following suggestions are automatically generated:

[0844] "Recently, app use after midnight has been increasing. Reducing app use by one hour after midnight is predicted to result in an increase of approximately 30 hours of sleep per month."

[0845] "70% of data usage is spent on certain streaming apps. By only using them when connected to Wi-Fi, you can significantly reduce your data usage."

[0846] "We've noticed an increase in stress recently. Please schedule times to avoid using apps to relax."

[0847] Step 9:

[0848] The server sends the generated proposal to the device. When sending, the data format is checked to ensure that the proposal content is transmitted correctly.

[0849] Step 10:

[0850] The device will notify the user of the suggestions, typically as a push notification or in-app message. The user can then view the suggestions in detail by checking the notification.

[0851] Step 11:

[0852] Users can review the notifications and take action based on the suggestions, such as avoiding late-night app use to ensure they get enough sleep or limiting streaming app use to Wi-Fi.

[0853] These are the specific processing steps of the program, which allow users to gain a detailed understanding of their own behavioral patterns and emotional state and receive specific suggestions to improve their quality of life.

[0854] Example 2

[0855] 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."

[0856] Conventional systems could only collect and analyze data such as user data charges, startup times, and app usage time, making it difficult to provide specific suggestions that took user emotions into account. Furthermore, the collected data often contained missing data or outliers, making accurate analysis impossible. Furthermore, the suggestions made to users were limited, making it difficult to provide specific action suggestions that would improve users' quality of life.

[0857] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting a user's communication charges, startup time, application usage time, and emotional data; means for transmitting the collected data to the server at regular intervals; means for preprocessing the received data in the server, which includes filling in missing data, detecting and removing outliers, normalizing data, and analyzing emotional data; AI means for analyzing the preprocessed data for frequency of use by time period, peak times of communication charges, trends in startup time and usage time, and correlations between emotional data and usage behavior; means for generating specific suggestions for the user based on the analysis results; and means for delivering the generated suggestions to the user's terminal. This makes it possible to make specific suggestions taking into account the user's behavioral patterns and emotions, thereby providing a comprehensive system for improving the user's quality of life.

[0858] "User" refers to an individual or group that uses the system and whose communication charges, startup time, app usage time, and emotional data are collected.

[0859] "Communication charges" refers to charges based on the amount of data transferred when a user uses a communication service.

[0860] "Startup time" refers to the time when the user starts operating the terminal and the time when each application is launched.

[0861] "App time" refers to the total time a user spends using a particular application.

[0862] "Emotion data" refers to emotional information obtained from the user's facial expressions and voice.

[0863] A "terminal" is a communication device or computer used by a user, and is a device that collects communication charges, usage time, and emotional data.

[0864] "Server" means the computer system that receives, stores, pre-processes and analyzes the collected data.

[0865] "Means of collection" refers to the device's ability to collect data on the user's data usage, startup time, app usage time, and emotional data.

[0866] "Transmitting means" refers to the function of the terminal to transmit collected data to the server.

[0867] The "preprocessing means" refers to a function that performs the following on the received data: complementing missing data, detecting and removing outliers, normalizing data, and analyzing emotion data.

[0868] "Missing data completion" refers to the process of using past average values, etc. to make up for any shortfalls in collected data.

[0869] "Outlier detection and removal" refers to the process of identifying and removing extremely high or low values ​​(outliers) when they are included in collected data.

[0870] "Data normalization" is the process of converting the scale of data into the range of 0 to 1.

[0871] "Emotion data analysis" refers to the process of analyzing emotion data obtained from facial expressions and voice to extract specific emotional elements (such as goodwill, badwill, stress, etc.).

[0872] "AI means" refers to an artificial intelligence function that uses pre-processed data to analyze frequency of use by time period, peak times for communication charges, trends in startup time and usage time, and the relationship between emotional data and usage behavior.

[0873] "Means for generating" refers to the function of creating specific suggestions for users based on the analysis results.

[0874] The "means for delivering" refers to a function for sending the generated proposal to the user's terminal.

[0875] MODE FOR CARRYING OUT THE INVENTION

[0876] System Overview

[0877] This invention is a system that collects data on users' communication charges, startup times, application usage times, and emotional data, and analyzes this data to provide specific suggestions for improving the user's quality of life. This system operates by combining a terminal and a server. The detailed configuration and processing flow of the system are described below.

[0878] Configuring Data Collection

[0879] The device collects data on each user's data usage, app launch time, app usage time, and emotional data. The device can be a smartphone, tablet, PC, or other common device. This includes specific hardware and software such as:

[0880] Data collection is performed using the application's logging function.

[0881] Network monitoring software is used to collect communication charge data.

[0882] To collect emotion data, the device's camera and microphone are used, and facial expression recognition software and voice analysis software (e.g., OpenCV, TensorFlow) are implemented.

[0883] Configuring data transmission and storage

[0884] The device sends the collected data to the server at regular intervals. The server receives the data and stores it securely. A secure communication protocol (e.g., SSL / TLS) is used to transmit the data, and the data is converted into a standard format such as JSON or XML. The server stores this data in a database (e.g., MySQL, MongoDB) and performs security checks.

[0885] Data preprocessing configuration

[0886] The server pre-processes the received data, which includes the following steps:

[0887] Imputing missing data: Use historical average values ​​to fill in missing data.

[0888] Outlier detection and removal: Statistical methods are used to detect and remove anomalous data points.

[0889] Data normalization: Scale and standardize the data to the range 0 to 1.

[0890] Emotion data analysis: Analyze emotion data using machine learning models (e.g., BERT, LSTM) to extract specific emotion elements.

[0891] Configuring Data Analysis

[0892] The server performs comprehensive analysis using AI based on the pre-processed data. The AI ​​analyzes:

[0893] Frequency of app use by time of day

[0894] Peak communication charge times

[0895] Boot time and usage time trends

[0896] Relationship between emotional data and usage behavior

[0897] This allows for detailed analysis of user behavior patterns and emotions.

[0898] Configuring Proposal Generation

[0899] The AI ​​installed on the server generates specific action suggestions based on the analysis results. The suggestions are expressed in natural language and formatted in a way that is easy for users to understand. For example:

[0900] "Recently, app use after midnight has increased. Reducing app use by one hour after midnight would result in an increase of approximately 30 hours of sleep per month."

[0901] "70% of data usage is spent on certain streaming apps. By only using them when connected to Wi-Fi, you can significantly reduce your data usage."

[0902] "You've been experiencing increased stress lately. Try scheduling time off your app use to relax."

[0903] Configuring Proposal Delivery

[0904] The server sends the generated proposal to the device. The data format is checked to ensure the proposal content is transmitted correctly, and the user is notified via a push notification or in-app message. The user can then view the detailed proposal content.

[0905] Specific examples

[0906] Example 1: Suggestions for users who experience high late-night usage and increased stress

[0907] 1. The device records the user's app usage data and emotional data every night after midnight.

[0908] 2. The device sends this data for one week to the server. For example, "2023-10-01 00:00: 120 minutes of use, high stress level" or "2023-10-02 00:00: 110 minutes of use, medium stress level."

[0909] 3. The server preprocesses the data and analyzes usage time and stress levels after midnight.

[0910] 4. As a result of the analysis, the AI ​​determines that "the average amount of use after midnight is 120 minutes per week, which indicates a high stress level," and suggests reducing stress and reducing usage time.

[0911] 5. The server generates a suggestion to the device: "Reducing usage time after midnight by one hour will improve stress levels and increase sleep by approximately 30 hours per month."

[0912] 6. The device will send a push notification to the user with the suggestions, and the user can view the details of the suggestions in the app.

[0913] Example 2: Suggestions for users with excessive data usage and negative emotions

[0914] 1. The device collects the user's data usage and emotional data for one month.

[0915] 2. The device sends the collected data to the server, including daily data usage, apps used, and emotional data.

[0916] 3. The server pre-processes the data and analyzes key traffic drivers and sentiment.

[0917] 4. AI identifies that certain streaming apps consume a large portion of data usage and negative emotions frequently arise while using them.

[0918] 5. The server generates a suggestion to the device, suggesting that the user limit the use of certain streaming apps to Wi-Fi and utilize data-saving features to reduce data charges and alleviate negative emotions, and sends it to the device.

[0919] 6. Users will be encouraged to review their notifications and how they use streaming apps to reduce data costs and improve their mood.

[0920] The above is a detailed description of the embodiment of the present invention. This system allows users to understand their own behavioral patterns and emotions in detail and receive specific suggestions to improve their quality of life.

[0921] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0922] Step 1: Data collection

[0923] The device will collect data on the user's data usage, startup time, app usage time, and emotional data at regular intervals. This step includes the following specific actions:

[0924] Input: User's app usage, communication data, facial expression and voice data

[0925] Data processing: Record the start and end times of each app and calculate usage time. Record communication data using network monitoring software. Extract emotions from the user's facial expressions and voice using facial recognition and voice analysis software.

[0926] Output: Each piece of data (usage time, communication volume, emotional data) is recorded in the device's database.

[0927] Step 2: Send data

[0928] The device sends the collected data to the server at regular intervals. This step includes the following specific operations:

[0929] Input: Data usage, startup time, app usage time, emotional data stored on the device

[0930] Data processing: Convert data into JSON or XML format. Send data securely using SSL / TLS protocol.

[0931] Output: Data sent to the server

[0932] Step 3: Store your data

[0933] The server stores the received data in the appropriate database and performs security checks. This step includes the following specific actions:

[0934] Input: Various data sent from the device (communication charges, startup time, app usage time, emotional data)

[0935] Data processing: Data is stored in a database (e.g., MySQL, MongoDB) and security checks such as SQL injection protection and data encryption are performed.

[0936] Output: Securely stored data

[0937] Step 4: Data Preprocessing

[0938] The server pre-processes the received data. This step includes the following specific actions:

[0939] Input: Each stored data (communication charges, startup time, app usage time, emotional data)

[0940] Data processing:

[0941] Imputing missing data: Imputing missing data using historical average values.

[0942] Outlier detection and removal: Statistical methods (e.g., standard deviation) are used to detect and remove outliers.

[0943] Data normalization: Scale all data to the range 0 to 1.

[0944] Sentiment data analysis: Using machine learning models (e.g., BERT, LSTM), we analyze the sentiment data and extract specific sentiment elements.

[0945] Output: Preprocessed data

[0946] Step 5: Data analysis

[0947] The AI ​​on the server performs comprehensive analysis based on the pre-processed data. This step includes the following specific actions:

[0948] Input: Preprocessed data (frequency of use, communication charges, startup time, emotion data)

[0949] Data processing:

[0950] Analysis of usage frequency by time of day: Calculate the number of times the app is used during each time period.

[0951] Identifying peak hours for communication charges: Communication data is aggregated by hour and the time period with the highest value is identified.

[0952] Startup and usage trend analysis: Long-term usage patterns are analyzed using statistical methods.

[0953] Correlation analysis between emotional data and usage behavior: Analyze the correlation between emotional data and app usage data.

[0954] Output: Analysis results

[0955] Step 6: Proposal Generation

[0956] The server's AI generates specific action suggestions based on the analysis results. This step includes the following specific actions:

[0957] Input: Analysis results

[0958] Data processing: The analysis results are converted into natural language and specific suggestions are generated. For example, a suggestion such as, "Recently, your app use after midnight has increased. If you reduce your app use after midnight by one hour, you will gain approximately 30 hours of sleep per month."

[0959] Output: Generated proposals

[0960] Step 7: Distributing the proposal

[0961] The server sends the generated proposal to the device and notifies the user. This step includes the following specific actions:

[0962] Input: Generated proposals

[0963] Data processing: Check the data format to ensure the proposed content is conveyed correctly, and send it as a push notification or in-app message.

[0964] Output: Suggestion notification sent to user

[0965] This is the specific flow of the process that the program of this system performs. Users can confirm the suggestions and take action to improve their quality of life.

[0966] (Application example 2)

[0967] 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."

[0968] Modern consumers generate vast amounts of data through their use of applications and devices, but there is a lack of systems that can effectively utilize this data to improve their quality of life. Furthermore, there is a lack of systems that can analyze customer behavior and emotions in real time in physical stores and display optimal product recommendations and advertisements. This situation results in missed opportunities to improve customer satisfaction and sales promotions. Furthermore, improving quality of life by collecting and analyzing emotional data and providing specific, individualized recommendations to users is also an important challenge.

[0969] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0970] In this invention, the server includes means for collecting data on user communication charges, startup times, application usage times, and emotion data, means for transmitting the collected data to the server, means for preprocessing the data received by the server, AI means for analyzing the preprocessed data, means for generating specific proposals for the user based on the analysis results, means for distributing the generated proposals to the user's terminal, means for collecting customer gaze data, movement path data, and product viewing time in a physical store, and means for analyzing the collected customer data in real time and displaying product proposals and advertisements to the customer. This not only makes specific proposals to improve the user's quality of life, but also enables optimal product proposals and advertisements to be displayed based on the customer's behavior and emotions in a physical store.

[0971] "Communication charges" are the communication costs incurred when a user sends or receives data via an Internet connection.

[0972] "Launch time" refers to the time when an application is launched by a user.

[0973] "Application Time" means the total time a user spends using a particular application.

[0974] "Emotional data" is emotional information extracted through analysis based on the user's facial expressions and voice.

[0975] "Gaze data" refers to data that indicates the direction and object the user is looking at.

[0976] "Movement path data" refers to data that indicates how a user moves within a space.

[0977] "Product View Time" refers to the amount of time a user spends looking at a particular product.

[0978] "Preprocessing" refers to the preparation of data prior to analysis, such as filling in missing data, removing outliers, and normalizing data.

[0979] "AI Methods" refers to artificial intelligence techniques used to analyze incoming data and find patterns and trends.

[0980] "Specific suggestions" refers to proposing actions or improvements that are beneficial to users based on the analysis results.

[0981] System Overview

[0982] The system of the present invention collects data on users' communication charges, startup times, application usage times, and emotional data, and uses this data to make suggestions for improving quality of life. It also includes a function to collect customer behavioral and emotional data in physical stores and make product suggestions and display advertisements in real time.

[0983] Data collection

[0984] The device is equipped with a means for collecting communication charges, startup time, application usage time, and emotional data. Emotional data is recognized from the user's facial expressions and voice using a camera and microphone. This data is recorded in the device's internal database or in a temporary file.

[0985] Data transmission and storage

[0986] The device periodically sends the collected data to the server, which stores the data in an appropriate format and performs security checks.

[0987] Data Preprocessing

[0988] The server pre-processes the received data, which includes:

[0989] Imputing missing data: Imputing with the historical average value.

[0990] Outlier detection and removal: Remove abnormally high or low values.

[0991] Data normalization: Scaling data values ​​to the range 0 to 1.

[0992] Emotion data analysis: Extract emotional elements such as likes, dislikes, and stress.

[0993] Data analysis

[0994] The pre-processed data is then analyzed by AI on the server. The AI ​​analyzes:

[0995] Frequency of application usage by time of day.

[0996] Peak communication times.

[0997] Startup and usage time trends.

[0998] The relationship between emotional data and usage behavior.

[0999] The relationship between customer gaze data, product viewing time, and movement path.

[1000] Proposal generation

[1001] The server's AI generates suggestions for the user based on the analysis results. The suggestions are expressed in natural language. For example:

[1002] "Recently, app use after midnight has increased. Reducing app use by one hour after midnight would result in an increase of approximately 30 hours of sleep per month."

[1003] "70% of our data usage is spent on certain streaming apps. By only using them when connected to Wi-Fi, we can significantly reduce our data usage."

[1004] "We've noticed an increase in stress recently. Please schedule times to take time off from apps to relax."

[1005] In real time, in-store customers will be shown suggestions such as:

[1006] "Get a 20% off coupon when you purchase this new product."

[1007] "Do you have a question about an item in this area? Would you like me to page a sales associate?"

[1008] Proposal distribution

[1009] The server sends the generated suggestions to the device, which then displays the suggestions to the user as push notifications or in-app messages. The user can then view the detailed suggestions on the device.

[1010] Specific examples

[1011] Example 1: Suggestions for users who use the service frequently late at night and experience increased stress

[1012] 1. The device measures the user's app usage data and emotional data every night after midnight and records the usage data and emotional data every hour.

[1013] 2. The device sends one week of data to the server. For example, it might send the following: "2023-10-01 00:00: 120 minutes of use, high stress level", "2023-10-02 00:00: 110 minutes of use, medium stress level", etc.

[1014] 3. The server preprocesses the data and analyzes usage time and stress levels after midnight.

[1015] 4. The AI ​​identifies that "the average amount of use after midnight is 120 minutes per week, which indicates a high stress level," and automatically generates suggestions to reduce stress and usage time.

[1016] 5. The server sends a suggestion to the device that "reducing usage time after midnight by one hour will improve stress levels and increase sleep by approximately 30 hours per month."

[1017] 6. The device will then send a push notification to the user with the suggestions, and the user can view the details of the suggestions in the app.

[1018] Example 2: An attractive offer for a new product

[1019] 1. A customer puts on smart glasses and enters the store.

[1020] 2. Smart glasses track customers' gazes and detect when they linger on a particular shelf for an extended period of time.

[1021] 3. Recognize the positive emotion of curiosity in the customer's facial expression.

[1022] 4. The server analyzes this data and determines that "this new product is generating interest."

[1023] 5. "Purchase this new product and receive a 20% off coupon" will be displayed on the smart glasses display.

[1024] Prompt Sentence Examples

[1025] When a customer wears smart glasses and enters a store, the glasses will track the customer's gaze. If the customer lingers on a specific shelf for a long time and detects a positive emotion indicating "curiosity," the following suggestion will be displayed: "Buy this new product and receive a 20% off coupon."

[1026] As described above, the present invention makes it possible to effectively utilize user behavioral and emotional data to provide specific suggestions for improving quality of life. It also makes it possible to provide appropriate product suggestions and advertisements to customers in real time in brick-and-mortar stores.

[1027] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1028] Step 1:

[1029] Data collection

[1030] The device collects data on the user's data usage, startup time, application usage time, and emotional data. It uses a camera and microphone to recognize the user's facial expressions and voice. This data is recorded in temporary files or an internal database.

[1031] Input: User's communication charges, startup time, application usage time, facial expression data, voice data

[1032] Output: Collected data (communication charges, startup time, application usage time, emotional data)

[1033] Step 2:

[1034] Data transmission

[1035] The device periodically sends the collected data to the server, where it is encrypted to ensure data security.

[1036] Input: Collected data (communication charges, startup time, application usage time, emotional data)

[1037] Output: Data sent to the server

[1038] Step 3:

[1039] Data storage and security checks

[1040] The server stores the received data in the appropriate format and performs security checks, including verifying data integrity and detecting unauthorized access.

[1041] Input: Data sent to the server

[1042] Output: Data that has undergone security checks, data stored in the database on the server

[1043] Step 4:

[1044] Data Preprocessing

[1045] The server preprocesses the received data, interpolating missing data with historical averages and removing outliers, scaling the data to a range of 0 to 1, and analyzing the emotion data to extract emotional elements such as likes, dislikes, and stress.

[1046] Input: Data stored on the server

[1047] Output: Preprocessed data (imputed data, outlier-removed data, normalized data, analyzed sentiment data)

[1048] Step 5:

[1049] Data analysis

[1050] The AI ​​installed on the server analyzes the pre-processed data, including frequency of application use by time of day, peak times for communication charges, trends in startup time and usage time, correlations between emotional data and usage behavior, and correlations between gaze data, product viewing time, and movement routes.

[1051] Input: Preprocessed data

[1052] Output: Analysis results (frequency of use, peak times for communication charges, trends, correlations with emotion data, correlations with gaze data)

[1053] Step 6:

[1054] Proposal generation

[1055] Based on the analysis results, the server's AI generates specific suggestions for the user, expressed in natural language based on the user's behavioral patterns and emotional data.

[1056] Input: Analysis results

[1057] Output: Generated suggestions (suggestions in natural language format)

[1058] Step 7:

[1059] Proposal distribution

[1060] The server sends the generated suggestions to the device, which then displays the suggestions to the user as push notifications or in-app messages.

[1061] Input: Generated proposals

[1062] Output: Proposals delivered to the user's device, and the displayed proposals

[1063] Step 8:

[1064] Real-time product suggestions

[1065] In brick-and-mortar stores, smart glasses track customers' gaze data and send it to a server, which analyzes it to identify their level of interest in products and display product suggestions and advertisements in real time.

[1066] Input: gaze data, movement path data

[1067] Output: Product offers and advertisements displayed to customers

[1068] Through these steps, the system can effectively utilize behavioral and emotional data of users and customers to make specific suggestions to improve their quality of life.

[1069] 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.

[1070] 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.

[1071] 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.

[1072] [Third embodiment]

[1073] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1074] 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.

[1075] 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).

[1076] 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.

[1077] 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.

[1078] 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).

[1079] 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.

[1080] 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.

[1081] 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.

[1082] 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.

[1083] 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.

[1084] 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."

[1085] System Overview

[1086] The present invention is a system that collects data such as user communication charges, startup times, and application usage times, and analyzes the data using a server to provide specific suggestions for improving the user's quality of life. Specific embodiments of the system are described below.

[1087] Data collection implementation

[1088] The device records the user's data usage, startup time, and app usage time at regular intervals (e.g., every hour or every day). For example, it records the amount of time a user uses a particular app over a certain period of time and the amount of data usage during that time. This data is stored in a database or temporary file within the device.

[1089] Data transmission and storage practices

[1090] The collected data is sent from the device to the server at regular intervals (e.g., daily or weekly). The data sent here includes communication charges, startup time, and app usage time. The server converts the received data into an appropriate format (e.g., JSON, CSV) and saves it in a database for safekeeping.

[1091] Data Preprocessing Embodiments

[1092] The server reads the received data and performs pre-processing, which may include the following:

[1093] Imputing missing data: For example, if data is missing for a specific time period, impute that portion with the historical average or median.

[1094] Outlier detection and removal: For example, removing values ​​that deviate significantly from normal usage patterns.

[1095] Data normalization: Adjusting data values ​​to a uniform scale (e.g., converting them to the range 0 to 1).

[1096] Data Analysis Embodiments

[1097] Once preprocessed, the data is analyzed by AI installed on the server. The AI ​​analyzes user behavior patterns in detail and identifies specific issues. For example, it identifies the frequency of app use by time of day and peak times for data charges. It also analyzes trends in launch times and usage duration to uncover user usage trends.

[1098] Suggestion Generation Embodiments

[1099] The server's AI generates specific action suggestions for the user based on the analysis results. For example, the following suggestions may be generated:

[1100] "Recently, app use after midnight has been increasing. Reducing app use by one hour after midnight is expected to increase sleep time by approximately 30 hours per month."

[1101] "70% of data usage is used for certain streaming apps. By using them only when connected to Wi-Fi, you can significantly reduce your data usage."

[1102] Embodiments of Proposal Delivery

[1103] Finally, the server sends the generated proposal to the device and notifies the user. The device displays the proposal to the user via a push notification, allowing the user to review its contents. If necessary, the user can view the proposal details within the app.

[1104] Specific examples

[1105] Example 1: Suggestions for users with high late-night usage

[1106] 1. The device measures the user's app usage data every night after midnight and records usage data every hour.

[1107] 2. The device sends one week's worth of data to the server. For example, "2023-10-01 00:00: 120 minutes", "2023-10-02 00:00: 110 minutes", etc.

[1108] 3. The server receives the data, imputes missing values, and removes outliers if necessary.

[1109] 4. The server compiles usage time from midnight onwards for one week, and AI analyzes the user's usage patterns.

[1110] 5. The AI ​​identifies that "the average usage after midnight is 120 minutes per week" and automatically generates an improvement suggestion (reducing usage time by 60 minutes).

[1111] 6. The server generates a suggestion to the device, saying, "If you reduce your usage time after midnight by one hour, you will increase your sleep time by a total of 30 hours in one month." and sends it to the device.

[1112] 7. The device will then push a notification to the user with the suggestions, which the user can then review in the app.

[1113] Example 2: Suggestions for users with excessive data usage

[1114] 1. The device collects the user's data usage data for one month.

[1115] 2. The device sends the collected data to the server, which includes information on daily communication charges and apps used.

[1116] 3. The server receives the data and pre-processes it for analysis.

[1117] 4. AI will analyze and identify which specific streaming apps are taking up the majority of your data usage.

[1118] 5. The server generates a suggestion that suggests limiting the use of certain streaming apps to Wi-Fi or using data saving features to reduce data charges.

[1119] 6. The server sends the generated proposal to the device and notifies the user.

[1120] 7. Users can reduce data costs by checking notifications and reviewing how they use streaming apps.

[1121] The above is a specific description of the embodiment of the present invention. This system allows users to understand their own behavioral patterns and receive appropriate suggestions for improving their lifestyle.

[1122] The processing flow will be explained below.

[1123] Step 1:

[1124] The device collects the user's data usage, startup time, and app usage time. This data is recorded at regular intervals (e.g., hourly or daily). Specifically, the device's log function is used to record the start and end times of each app's use, the amount of data consumed, etc.

[1125] Step 2:

[1126] The data collected by the device is stored in a temporary file or an internal database. At this stage, the data is checked for duplication or format inconsistencies, and the data format is unified if necessary.

[1127] Step 3:

[1128] The device periodically (e.g. daily or weekly) transmits stored data to the server via the network. The transmitted data includes communication charges, startup time, and application usage time. HTTP or HTTPS is used as the communication protocol.

[1129] Step 4:

[1130] The server receives the received data and performs security checks (e.g., data encryption, integrity checks) to ensure that the data has not been tampered with.

[1131] Step 5:

[1132] The server saves the received data in the database. Common formats such as JSON and CSV are used for saving. When saving, the consistency of each data item is rechecked.

[1133] Step 6:

[1134] The server performs data preprocessing, such as imputing missing data (e.g., imputing with historical average values), detecting and removing outliers, and normalizing data (e.g., scaling to a range of 0 to 1).

[1135] Step 7:

[1136] The server inputs the preprocessed data into the AI ​​model for analysis, which analyzes the frequency of app use by time of day, peak times for data usage, and trends in startup and usage time.

[1137] Step 8:

[1138] The server's AI generates specific suggestions for users based on the analysis results. The suggestions are expressed in natural language and formatted in a way that is easy for users to understand. For example, "Recently, your app usage after midnight has increased. If you reduce your app usage by one hour after midnight, it is predicted that you will gain approximately 30 hours of sleep per month."

[1139] Step 9:

[1140] The server sends the generated proposal to the device. When sending, the data format is checked to ensure that the proposal content is transmitted correctly.

[1141] Step 10:

[1142] The device will notify the user of the suggestions, typically as a push notification or in-app message. The user can then view the details of the suggestions by checking the notification.

[1143] Step 11:

[1144] Users can check the notification and change their behavior based on the suggestions, for example, by refraining from using apps late at night to ensure they get enough sleep.

[1145] These are the specific processing steps of the program. Through this series of processes, users can gain a detailed understanding of their own behavioral patterns and receive specific suggestions for improving their quality of life.

[1146] Example 1

[1147] 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."

[1148] In systems that collect and analyze data on users' communication charges and app usage time, it can be difficult to generate effective lifestyle improvement proposals using existing methods. In particular, it is difficult to understand missing data, the presence of outliers, and user behavior patterns in detail to generate specific and effective proposals.

[1149] 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.

[1150] In this invention, the server includes means for collecting data such as user communication charges, startup times, and application usage times, means for transmitting the collected data to the server, and means for preprocessing the received data in the server, which enables detailed analysis of user behavior patterns, completion and removal of missing data and outliers, and normalization to a unified scale.

[1151] The server also includes an artificial intelligence unit that analyzes the preprocessed data, a unit that generates specific suggestions for the user based on the analysis results, and a unit that delivers the generated suggestions to the user's terminal, thereby providing the user with specific and effective suggestions for action.

[1152] "User's communication charges" means the total amount of data communication usage and charges incurred when a User uses the communication service.

[1153] "Boot time" is the time it takes for a particular application or device to start and become available for use, and the cumulative time that the application or device is running.

[1154] "App time" is the amount of time a particular application is actually used by a user.

[1155] "Means for collecting data" refers to a device or program that records information such as a user's communication charges, startup time, and application usage time at regular intervals.

[1156] "Means for transmitting data" refers to a device or program for transferring collected data to a database or server.

[1157] The "preprocessing means" is a device or program for imputing missing data, removing outliers, and normalizing the received data.

[1158] "Artificial intelligence means" refers to artificial intelligence technology that uses collected and pre-processed data to analyze user behavior patterns and generate specific suggestions based on the analysis results.

[1159] The "means for generating specific suggestions" is a device or program for generating action suggestions for users based on the analysis results using artificial intelligence technology.

[1160] "Means for distributing to terminal" means a device or program for transferring the proposal generated by the server to the user's terminal and notifying the user.

[1161] "Recording means" means a device or program that records the user's currently running apps and their running time at regular intervals.

[1162] A "means for completing missing data" is a device or program that, when there is a gap in the collected data, fills in the gaps with past data, estimated values, etc.

[1163] An "outlier removal means" is a device or program that detects data that deviates significantly from normal usage patterns and removes them from the analysis.

[1164] A "means for normalization" is a device or program that converts data values ​​to a uniform scale (e.g., a range of 0 to 1).

[1165] System Overview

[1166] This system collects data such as user communication charges, startup times, and application usage time, and analyzes it on a server to understand the user's behavioral patterns and make suggestions to improve their quality of life. Specifically, the system consists of the steps of data collection by the device, data transmission to the server, data preprocessing and analysis on the server, and proposal generation and distribution.

[1167] Data collection implementation

[1168] The device records the user's communication charges, startup times, and app usage time at regular intervals. For example, it records the amount of time the user used a particular app over a certain period of time and the data communication charges consumed during that time. This data is stored in a database or temporary file within the device. A program for collecting and recording data is installed on the device. This program uses a scheduler to collect data every hour and saves it in a database (e.g., SQLite).

[1169] Data transmission and storage practices

[1170] The device sends the collected data to the server at a fixed interval (for example, at midnight every day). The data is converted into an appropriate format (for example, JSON or CSV). The server analyzes and stores the received data in a database (for example, MySQL). To send the data, the device makes an HTTP request, and the sent data is received by the server's REST API.

[1171] Data Preprocessing Embodiments

[1172] The server performs preprocessing on the received data. This preprocessing includes missing data completion, outlier detection and removal, and data normalization. This preprocessing is performed using the Python Pandas library. Data normalization is performed using MinMaxScaler from scikit-learn.

[1173] Data Analysis Embodiments

[1174] Once the preprocessing is complete, the data is analyzed by artificial intelligence (AI) installed on the server. The AI ​​performs detailed analysis of user behavior patterns and extracts specific issues (for example, times of high usage or peak times for communication charges). Machine learning algorithms such as K-means clustering are used for the analysis.

[1175] Suggestion Generation Embodiments

[1176] The server's AI generates specific action suggestions for the user based on the analysis results. For example, it could generate the following suggestion: "Reducing app use by one hour after midnight could increase sleep time by approximately 30 hours over the course of a month." Natural language processing technology is used to generate suggestions, for example, by inputting a prompt sentence to generate a suggestion using a generative AI model (such as GPT-3).

[1177] Embodiments of Proposal Delivery

[1178] The server sends the generated suggestions to the device and notifies the user. The device displays the suggestions via push notification, allowing the user to check their details. The user can also tap the notification to view the detailed suggestions within the app.

[1179] Specific examples

[1180] Example 1: Suggestions for users with high late-night usage

[1181] 1. The device measures the user's app usage data every night after midnight and records usage data every hour.

[1182] 2. The device sends one week of data to the server.

[1183] 3. The server receives the data, imputes missing values, and removes outliers.

[1184] 4. The server compiles usage time from midnight onwards for one week, and AI analyzes the user's usage patterns.

[1185] 5. The AI ​​identifies that "the average usage after midnight is 120 minutes per week" and automatically generates an improvement suggestion (reducing usage time by 60 minutes).

[1186] 6. The server generates a suggestion to the device, saying, "If you reduce your usage time after midnight by one hour, you will increase your sleep time by a total of 30 hours in one month." and sends it to the device.

[1187] 7. The device will then push a notification to the user with the suggestions, which the user can then review in the app.

[1188] Example 2: Suggestions for users with excessive data usage

[1189] 1. The device collects the user's data usage data for one month.

[1190] 2. The device sends the collected data to the server, which includes information on daily communication charges and apps used.

[1191] 3. The server receives the data and pre-processes it for analysis.

[1192] 4. AI will analyze and identify which specific streaming apps are taking up the majority of your data usage.

[1193] 5. The server generates a suggestion that suggests limiting the use of certain streaming apps to Wi-Fi or using data saving features to reduce data charges.

[1194] 6. The server sends the generated proposal to the device and notifies the user.

[1195] 7. Users can reduce data costs by checking notifications and reviewing how they use streaming apps.

[1196] Prompt Sentence Examples

[1197] "Collect app usage data after midnight for one month, analyze users' usage patterns, and generate lifestyle improvement suggestions."

[1198] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1199] Step 1: Collect data

[1200] Input: User's data charges, startup time, app usage time

[1201] How it works: The device runs a program that periodically records data charges, startup times, and app usage time.

[1202] Data processing: Data charges, startup time, and app usage time are saved in a database or temporary file.

[1203] Output: Data stored in the device's internal database or temporary files

[1204] Specific operation: The scheduler installed on the device measures the current communication charges, startup time, and application usage time every hour and stores them in an SQLite database (e.g., "2023-10-01 12:00: Application A 30 minutes").

[1205] Step 2: Sending data

[1206] Input: Data stored on the device about communication charges, startup time, and app usage time

[1207] Operation: The device converts the collected data into JSON format at regular intervals (for example, at midnight every day) and sends it to the server.

[1208] Data processing: Convert the data into JSON format.

[1209] Output: JSON data sent to the server

[1210] Specific operation: Every day at midnight, the device reads the current day's data from the SQLite database, converts the data to JSON format using the Python json module, and then sends it to the server via an HTTP request (e.g., {"2023-10-01": {"App A": 120, "App B": 30}}).

[1211] Step 3: Store your data

[1212] Input: JSON data sent to the server

[1213] How it works: The server parses the data it receives and stores it in a secure database.

[1214] Data processing: Parse the JSON data and convert it into a format that can be inserted into the database.

[1215] Output: Data stored in the database on the server

[1216] Specific operation: The server parses the received JSON data using Python's json module, generates an SQL statement to insert into the MySQL database, and executes it (e.g., INSERT INTO user_data VALUES ("2023-10-01", "App A", 120, "App B", 30)).

[1217] Step 4: Preprocessing the data

[1218] Input: Data stored in the database on the server

[1219] How it works: The server imputes missing data, detects and removes outliers, and normalizes the data.

[1220] Data processing: Impute missing data, remove outliers, and normalize data.

[1221] Output: Preprocessed data

[1222] Specific operation: The data is read into a data frame format using Python's Pandas library, missing values ​​are filled in using the fillna method, outliers are removed using conditional search, and the data is normalized using MinMaxScaler (e.g., {"App A": 0.5, "App B": 0.2}).

[1223] Step 5: Analyze the data

[1224] Input: Preprocessed data

[1225] How it works: The AI ​​installed on the server uses pre-processed data to analyze user behavior patterns.

[1226] Data computation: Use an AI model (e.g., K-means clustering) to separate the data into clusters.

[1227] Output: User behavior pattern analysis results

[1228] Specific operation: K-means clustering is performed using Python's Scikit-learn library, and user data is classified into each cluster (e.g., cluster 0 = users with high usage during the late night hours).

[1229] Step 6: Proposal Generation

[1230] Input: User behavior pattern analysis results

[1231] Action: The server's artificial intelligence generates specific action suggestions based on the analysis results.

[1232] Data calculation: A prompt sentence is input into a generative AI model (e.g., GPT-3) to generate a suggested sentence.

[1233] Output: Generated suggestion

[1234] Specific operation: Based on the analysis result that "there is a lot of usage after midnight," the generative AI model inputs the prompt sentence "Please generate a proposal to reduce app usage after midnight," and generates a proposal sentence (e.g., "Reducing app usage after midnight by one hour could increase sleep time by approximately 30 hours in a month").

[1235] Step 7: Distributing the proposal

[1236] Input: Generated suggestion

[1237] Behavior: The server generates a proposal, sends it to the device, and notifies the user.

[1238] Data processing: Convert the proposal into a notification format and send it to the terminal.

[1239] Output: Proposal notification displayed on the user's device

[1240] Specific operation: The server converts the suggestion text into JSON format and sends it to the device via an HTTP request. The device then generates a push notification based on the received JSON and notifies the user (e.g., notification message: "If you reduce app usage after midnight by one hour, you will gain approximately 30 hours of sleep in one month").

[1241] (Application example 1)

[1242] 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."

[1243] Users spend a lot of time and data charges using applications on smartphones and other devices, which can result in a decline in their quality of life. Furthermore, a bias in data charges and usage time toward specific apps can lead to wasteful usage and negatively impact health. However, it is difficult for users to recognize these patterns of behavior, making it difficult to take appropriate measures to improve them. Therefore, there is a need for a system that can analyze users' application usage patterns and automatically provide specific suggestions for optimally managing data charges and usage time.

[1244] 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.

[1245] In this invention, the server includes means for collecting data such as user communication charges, startup times, and application usage time; means for transmitting the collected data to the server; means for preprocessing the received data in the server; artificial intelligence means for analyzing the preprocessed data; means for analyzing the viewing patterns of specific applications and generating specific suggestions for the user; and means for delivering the generated suggestions to the user's device. This enables detailed analysis of user behavior patterns and automatically generates and delivers practical suggestions for optimizing communication charges and usage time. For example, if a user uses an application excessively during a certain time period, the system can suggest that the user use that time for other activities. Furthermore, recommending viewing content that consumes a lot of data over a Wi-Fi connection can also contribute to saving communication charges.

[1246] "Communication charges" are the costs incurred when a user communicates data via an Internet connection.

[1247] "Launch time" refers to the time when an application is started on a device.

[1248] "Time in app" refers to the total amount of time a user spends using a particular application.

[1249] "Means of collecting data" refers to the mechanism for obtaining information such as user data charges, startup time, and app usage time.

[1250] "Means for transmitting to a server" refers to a mechanism for sending collected data to a remote server via a communication network such as the Internet.

[1251] "Preprocessing means" refers to a mechanism for performing processes such as removing unnecessary data, filling in missing values, and normalizing data in order to improve the quality of collected data.

[1252] "Artificial Intelligence Tools" means AI techniques used to analyze pre-processed data and discover specific patterns or trends.

[1253] The "means for generating suggestions" is a mechanism for creating improvement measures and action suggestions for users based on data analyzed by artificial intelligence.

[1254] "Means of delivery to user's device" refers to a mechanism for notifying the user of the generated suggestions on their device, such as a smartphone or tablet.

[1255] "Behavioral patterns" refer to a series of usage trends and habits, such as how a user uses applications and at what times they consume the most data.

[1256] "Viewing patterns" are information that indicates the tendency of users to view what types of content at what times.

[1257] "Wi-Fi environment" refers to a network environment that connects to the Internet using wireless LAN.

[1258] "Data-intensive content" refers to applications such as video and streaming services that require large amounts of internet data.

[1259] "Use for other activities" refers to engaging in alternative activities such as exercise, reading, or sleep instead of using the application during a particular time period.

[1260] System Overview

[1261] This invention is a system that collects data such as user communication charges, startup times, and application usage time, and analyzes it on a server to provide specific action suggestions to users. The system has the functions of data collection, data transmission, preprocessing, AI analysis, proposal generation, and proposal distribution.

[1262] Data collection

[1263] The device records the user's data usage, startup time, and app usage time at regular intervals. For example, it records the time the user uses a particular app and the amount of data usage. This information is stored in an internal database.

[1264] Data transmission

[1265] The collected data, including communication charges, startup time, and usage time, is sent from the device to a server at regular intervals. The server converts the received data into an appropriate format and stores it securely.

[1266] Data Preprocessing

[1267] The server reads the received data and performs preprocessing, including filling in missing data, removing outliers, and normalizing the data, thereby improving the accuracy of the analysis.

[1268] Data analysis

[1269] Once preprocessed, the data is analyzed by AI installed on the server. The AI ​​analyzes user behavior patterns in detail and extracts viewing patterns and peak times for data charges. For example, by identifying viewing frequency and data consumption by time of day, it is possible to understand user behavior trends.

[1270] Proposal generation

[1271] The server's AI then generates specific action suggestions for the user based on the analysis results, including:

[1272] Suggestions to repurpose screen time for other activities during certain times

[1273] We recommend watching data-intensive content in a Wi-Fi environment.

[1274] Proposal distribution

[1275] The server sends the generated suggestions to the device and displays them to the user via push notification, where the user can view the details of the suggestions within the app.

[1276] Hardware and software details

[1277] Hardware: Smartphones (e.g. iPhone, Android devices), servers

[1278] Software: Python 3.9, JSON format, standard library

[1279] Specific examples

[1280] For example, if a user frequently watches videos late at night, the AI ​​will analyze this pattern and generate a suggestion such as, "You watch too much after midnight. By reducing your viewing time by one hour, you can gain approximately 30 hours of sleep per month." Also, if a specific streaming app is taking up a large portion of your data charges, the AI ​​will suggest, "To reduce data charges, we recommend limiting the use of this streaming app to Wi-Fi environments."

[1281] Prompt Sentence Examples

[1282] "Recently, app usage late at night has increased. Reducing usage after midnight by one hour is predicted to increase sleep time by approximately 30 hours per month. Based on this, please output code that suggests reducing viewing during specific times. For example, something implemented in Python would be good."

[1283] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1284] Step 1:

[1285] The device collects data such as the user's data charges, startup time, and app usage time at regular intervals. The inputs are the time the user starts each app (startup time), the amount of time the application is used (usage time), and the data charges incurred during use. This data is stored in an internal database. For example, if a user starts YouTube at 10 a.m., watches it for 30 minutes, and uses 50 MB of data during that time, that information will be recorded.

[1286] Step 2:

[1287] The device periodically sends the collected data to the server. The data is sent over the communication network and converted into an appropriate format, such as JSON. The input is the data collected in step 1, and the output is the data sent to the server. This data includes specific app names, usage time, communication charges, launch date and time, etc.

[1288] Step 3:

[1289] The server reads the received data and performs preprocessing. The input is the unprocessed data sent from the terminal. Preprocessing involves filling in missing data, detecting and removing outliers, and normalizing the data. For example, if data for a certain date and time is missing, it is filled in with the average value from the past. Outliers are values ​​that are clearly outside the normal range and are removed. Data normalization involves converting all data into a unified range from 0 to 1. The output is a dataset after preprocessing has been completed.

[1290] Step 4:

[1291] The server inputs the preprocessed data into an AI model for analysis. The input is the preprocessed data, and the AI ​​analyzes the user's behavioral patterns. For example, it can determine how much data is being used during a specific time period, or which applications are being used most frequently at which times. The output is a detailed analysis of the user's behavioral patterns.

[1292] Step 5:

[1293] The server generates specific action suggestions for the user based on the analysis results. The input is the analysis results of the artificial intelligence model. For example, if a user uses a lot of applications late at night, the server automatically generates a suggestion to reduce that usage time. Specifically, the server generates a suggestion such as, "If you reduce viewing after midnight by one hour, you can gain approximately 30 additional hours of sleep per month." The output is an action suggestion for the user.

[1294] Step 6:

[1295] The server sends the generated suggestions to the user's device and displays them via push notification. The input is the generated suggestions, and the output is the notification displayed on the user's device. Specifically, the device displays a notification saying, "By reducing app usage after midnight, you will get more sleep and improve your quality of life." The user can check the detailed suggestions within the app.

[1296] 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.

[1297] System Overview

[1298] The present invention is a system that collects data such as user communication charges, startup times, and application usage times, and combines this with an emotion engine that recognizes user emotions to make specific suggestions for improving the user's quality of life. Specific embodiments of the system are described below.

[1299] Data collection implementation

[1300] The device records the user's data usage, startup time, app usage time, and emotional data at regular intervals, including:

[1301] The time and duration of each app usage.

[1302] Data charges consumed.

[1303] It uses a camera and microphone to recognize emotions from the user's facial expressions and voice.

[1304] This data is stored in a database or temporary file within the device.

[1305] Data transmission and storage practices

[1306] The collected data is sent from the device to a server at regular intervals. This data includes communication charges, startup time, app usage time, and emotional data. The server stores the received data in an appropriate format and performs security checks to ensure safety.

[1307] Data Preprocessing Embodiments

[1308] The server reads and pre-processes the received data, which includes:

[1309] Imputing missing data: A method of imputing using past average values.

[1310] Outlier detection and removal: Remove abnormally high or low values.

[1311] Data normalization: Scaling data values ​​to the range 0 to 1.

[1312] Emotion data analysis: Extract emotional elements such as goodwill, badwill, and stress.

[1313] Data Analysis Embodiments

[1314] Once the preprocessing is complete, the data is comprehensively analyzed by the AI ​​installed on the server. The AI ​​analyzes the following items, for example:

[1315] Frequency of app use by time of day.

[1316] Peak communication times.

[1317] Startup and usage time trends.

[1318] The relationship between emotional data and usage behavior.

[1319] Suggestion Generation Embodiments

[1320] The server's AI generates specific action suggestions for the user based on the analysis results. The suggestions are expressed in natural language and formatted in a way that is easy for the user to understand. For example,

[1321] "Recently, app use after midnight has been increasing. Reducing app use by one hour after midnight is predicted to result in an increase of approximately 30 hours of sleep per month."

[1322] "70% of data usage is spent on certain streaming apps. By only using them when connected to Wi-Fi, you can significantly reduce your data usage."

[1323] "We've noticed an increase in stress recently. Please schedule times to avoid using apps to relax."

[1324] Embodiments of Proposal Delivery

[1325] The server generates a proposal and sends it to the device. When sending, the data is formatted and checked to ensure the proposal is transmitted correctly. The device then notifies the user of the proposal. This is typically displayed as a push notification or an in-app message. The user can then view the proposal in detail by checking the notification.

[1326] Specific examples

[1327] Example 1: Suggestions for users who experience high late-night usage and increased stress

[1328] 1. The device measures the user's app usage data and emotional data every night after midnight and records the usage data and emotional data every hour.

[1329] 2. The device sends one week of data to the server. For example, "2023-10-01 00:00: 120 minutes of use, high stress level" or "2023-10-02 00:00: 110 minutes of use, medium stress level."

[1330] 3. The server preprocesses the data and analyzes usage time and stress levels after midnight.

[1331] 4. The AI ​​identifies that "the average amount of use after midnight is 120 minutes per week, which indicates a high stress level," and automatically generates suggestions to reduce stress and usage time.

[1332] 5. The server sends a suggestion to the device that "reducing usage time after midnight by one hour will improve stress levels and increase sleep by approximately 30 hours per month."

[1333] 6. The device will then send a push notification to the user with the suggestions, and the user can view the details of the suggestions in the app.

[1334] Example 2: Suggestions for users with excessive data usage and negative emotions

[1335] 1. The device collects the user's data usage and emotion data for one month.

[1336] 2. The device sends the collected data to a server, including daily data usage, apps used, and emotional data.

[1337] 3. The server pre-processes the data and analyzes key traffic drivers and sentiment.

[1338] 4. AI identifies that certain streaming apps consume a large portion of data usage and negative emotions frequently arise while using them.

[1339] 5. The server sends a suggestion to the device suggesting that users limit the use of certain streaming apps to Wi-Fi and use data-saving features to reduce data charges and alleviate negative emotions.

[1340] 6. Users will be encouraged to review their notifications and how they use streaming apps to reduce data costs and improve their mood.

[1341] The above is a detailed description of an embodiment of the present invention, which allows users to understand their own behavioral patterns and emotions in detail and receive specific suggestions to improve their quality of life.

[1342] The processing flow will be explained below.

[1343] Step 1:

[1344] The device collects data on the user's data usage, startup time, app usage time, and emotional data. Emotional data is obtained by analyzing the user's facial expressions and voice using the camera and microphone. For example, the emotion engine can recognize emotions such as stress, joy, and excitement from the user's facial expressions and tone of voice while using the app.

[1345] Step 2:

[1346] The data collected by the device is stored in an internal database or temporary file. At this stage, the data is checked for completeness and duplication, and the data format is unified if necessary.

[1347] Step 3:

[1348] The device periodically (e.g., daily or weekly) transmits the stored data to the server via the network. HTTP or HTTPS is used as the communication protocol, and the transmitted data includes communication charges, startup time, application usage time, and emotional data.

[1349] Step 4:

[1350] The server receives the received data and performs security checks (e.g., data encryption, integrity check) to ensure that the data has not been tampered with or leaked.

[1351] Step 5:

[1352] The server saves the received data in a database. Common formats such as JSON and CSV are used for saving. When saving, the consistency of each data item is rechecked to ensure there is no duplication or missing data.

[1353] Step 6:

[1354] The server pre-processes the data, which includes:

[1355] Imputing missing data: For example, imputing missing data with historical average values.

[1356] Outlier detection and removal: Filter out data that deviates significantly from normal usage patterns.

[1357] Data normalization: Scaling data values ​​to the range 0 to 1.

[1358] Emotion data analysis: Extracting emotional elements (e.g., stress, joy, excitement) from facial and voice data.

[1359] Step 7:

[1360] The server inputs the pre-processed data into the AI ​​model for comprehensive analysis, specifically analyzing the following:

[1361] Frequency of app use by time of day.

[1362] Peak communication times.

[1363] Startup and usage time trends.

[1364] The relationship between emotional data and usage behavior.

[1365] Step 8:

[1366] The server's AI generates specific action suggestions for the user based on the analysis results. The suggestions are expressed in natural language and formatted in a way that is easy for the user to understand. For example, the following suggestions are automatically generated:

[1367] "Recently, app use after midnight has been increasing. Reducing app use by one hour after midnight is predicted to result in an increase of approximately 30 hours of sleep per month."

[1368] "70% of data usage is spent on certain streaming apps. By only using them when connected to Wi-Fi, you can significantly reduce your data usage."

[1369] "We've noticed an increase in stress recently. Please schedule times to avoid using apps to relax."

[1370] Step 9:

[1371] The server sends the generated proposal to the device. When sending, the data format is checked to ensure that the proposal content is transmitted correctly.

[1372] Step 10:

[1373] The device will notify the user of the suggestions, typically as a push notification or in-app message. The user can then view the suggestions in detail by checking the notification.

[1374] Step 11:

[1375] Users can review the notifications and take action based on the suggestions, such as avoiding late-night app use to ensure they get enough sleep or limiting streaming app use to Wi-Fi.

[1376] These are the specific processing steps of the program, which allow users to gain a detailed understanding of their own behavioral patterns and emotional state and receive specific suggestions to improve their quality of life.

[1377] Example 2

[1378] 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."

[1379] Conventional systems could only collect and analyze data such as user data charges, startup times, and app usage time, making it difficult to provide specific suggestions that took user emotions into account. Furthermore, the collected data often contained missing data or outliers, making accurate analysis impossible. Furthermore, the suggestions made to users were limited, making it difficult to provide specific action suggestions that would improve users' quality of life.

[1380] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting a user's communication charges, startup time, application usage time, and emotional data; means for transmitting the collected data to the server at regular intervals; means for preprocessing the received data in the server, which includes filling in missing data, detecting and removing outliers, normalizing data, and analyzing emotional data; AI means for analyzing the preprocessed data for frequency of use by time period, peak times of communication charges, trends in startup time and usage time, and correlations between emotional data and usage behavior; means for generating specific suggestions for the user based on the analysis results; and means for delivering the generated suggestions to the user's terminal. This makes it possible to make specific suggestions taking into account the user's behavioral patterns and emotions, thereby providing a comprehensive system for improving the user's quality of life.

[1381] "User" refers to an individual or group that uses the system and whose communication charges, startup time, app usage time, and emotional data are collected.

[1382] "Communication charges" refers to charges based on the amount of data transferred when a user uses a communication service.

[1383] "Startup time" refers to the time when the user starts operating the terminal and the time when each application is launched.

[1384] "App time" refers to the total time a user spends using a particular application.

[1385] "Emotion data" refers to emotional information obtained from the user's facial expressions and voice.

[1386] A "terminal" is a communication device or computer used by a user, and is a device that collects communication charges, usage time, and emotional data.

[1387] "Server" means the computer system that receives, stores, pre-processes and analyzes the collected data.

[1388] "Means of collection" refers to the device's ability to collect data on the user's data usage, startup time, app usage time, and emotional data.

[1389] "Transmitting means" refers to the function of the terminal to transmit collected data to the server.

[1390] The "preprocessing means" refers to a function that performs the following on the received data: complementing missing data, detecting and removing outliers, normalizing data, and analyzing emotion data.

[1391] "Missing data completion" refers to the process of using past average values, etc. to make up for any shortfalls in collected data.

[1392] "Outlier detection and removal" refers to the process of identifying and removing extremely high or low values ​​(outliers) when they are included in collected data.

[1393] "Data normalization" is the process of converting the scale of data into the range of 0 to 1.

[1394] "Emotion data analysis" refers to the process of analyzing emotion data obtained from facial expressions and voice to extract specific emotional elements (such as goodwill, badwill, stress, etc.).

[1395] "AI means" refers to an artificial intelligence function that uses pre-processed data to analyze frequency of use by time period, peak times for communication charges, trends in startup time and usage time, and the relationship between emotional data and usage behavior.

[1396] "Means for generating" refers to the function of creating specific suggestions for users based on the analysis results.

[1397] The "means for delivering" refers to a function for sending the generated proposal to the user's terminal.

[1398] MODE FOR CARRYING OUT THE INVENTION

[1399] System Overview

[1400] This invention is a system that collects data on users' communication charges, startup times, application usage times, and emotional data, and analyzes this data to provide specific suggestions for improving the user's quality of life. This system operates by combining a terminal and a server. The detailed configuration and processing flow of the system are described below.

[1401] Configuring Data Collection

[1402] The device collects data on each user's data usage, app launch time, app usage time, and emotional data. The device can be a smartphone, tablet, PC, or other common device. This includes specific hardware and software such as:

[1403] Data collection is performed using the application's logging function.

[1404] Network monitoring software is used to collect communication charge data.

[1405] To collect emotion data, the device's camera and microphone are used, and facial expression recognition software and voice analysis software (e.g., OpenCV, TensorFlow) are implemented.

[1406] Configuring data transmission and storage

[1407] The device sends the collected data to the server at regular intervals. The server receives the data and stores it securely. A secure communication protocol (e.g., SSL / TLS) is used to transmit the data, and the data is converted into a standard format such as JSON or XML. The server stores this data in a database (e.g., MySQL, MongoDB) and performs security checks.

[1408] Data preprocessing configuration

[1409] The server pre-processes the received data, which includes the following steps:

[1410] Imputing missing data: Use historical average values ​​to fill in missing data.

[1411] Outlier detection and removal: Statistical methods are used to detect and remove anomalous data points.

[1412] Data normalization: Scale and standardize the data to the range 0 to 1.

[1413] Emotion data analysis: Analyze emotion data using machine learning models (e.g., BERT, LSTM) to extract specific emotion elements.

[1414] Configuring Data Analysis

[1415] The server performs comprehensive analysis using AI based on the pre-processed data. The AI ​​analyzes:

[1416] Frequency of app use by time of day

[1417] Peak communication charge times

[1418] Boot time and usage time trends

[1419] Relationship between emotional data and usage behavior

[1420] This allows for detailed analysis of user behavior patterns and emotions.

[1421] Configuring Proposal Generation

[1422] The AI ​​installed on the server generates specific action suggestions based on the analysis results. The suggestions are expressed in natural language and formatted in a way that is easy for users to understand. For example:

[1423] "Recently, app use after midnight has increased. Reducing app use by one hour after midnight would result in an increase of approximately 30 hours of sleep per month."

[1424] "70% of data usage is spent on certain streaming apps. By only using them when connected to Wi-Fi, you can significantly reduce your data usage."

[1425] "You've been experiencing increased stress lately. Try scheduling time off your app use to relax."

[1426] Configuring Proposal Delivery

[1427] The server sends the generated proposal to the device. The data format is checked to ensure the proposal content is transmitted correctly, and the user is notified via a push notification or in-app message. The user can then view the detailed proposal content.

[1428] Specific examples

[1429] Example 1: Suggestions for users who experience high late-night usage and increased stress

[1430] 1. The device records the user's app usage data and emotional data every night after midnight.

[1431] 2. The device sends this data for one week to the server. For example, "2023-10-01 00:00: 120 minutes of use, high stress level" or "2023-10-02 00:00: 110 minutes of use, medium stress level."

[1432] 3. The server preprocesses the data and analyzes usage time and stress levels after midnight.

[1433] 4. As a result of the analysis, the AI ​​determines that "the average amount of use after midnight is 120 minutes per week, which indicates a high stress level," and suggests reducing stress and reducing usage time.

[1434] 5. The server generates a suggestion to the device: "Reducing usage time after midnight by one hour will improve stress levels and increase sleep by approximately 30 hours per month."

[1435] 6. The device will send a push notification to the user with the suggestions, and the user can view the details of the suggestions in the app.

[1436] Example 2: Suggestions for users with excessive data usage and negative emotions

[1437] 1. The device collects the user's data usage and emotional data for one month.

[1438] 2. The device sends the collected data to the server, including daily data usage, apps used, and emotional data.

[1439] 3. The server pre-processes the data and analyzes key traffic drivers and sentiment.

[1440] 4. AI identifies that certain streaming apps consume a large portion of data usage and negative emotions frequently arise while using them.

[1441] 5. The server generates a suggestion to the device, suggesting that the user limit the use of certain streaming apps to Wi-Fi and utilize data-saving features to reduce data charges and alleviate negative emotions, and sends it to the device.

[1442] 6. Users will be encouraged to review their notifications and how they use streaming apps to reduce data costs and improve their mood.

[1443] The above is a detailed description of the embodiment of the present invention. This system allows users to understand their own behavioral patterns and emotions in detail and receive specific suggestions to improve their quality of life.

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

[1445] Step 1: Data collection

[1446] The device will collect data on the user's data usage, startup time, app usage time, and emotional data at regular intervals. This step includes the following specific actions:

[1447] Input: User's app usage, communication data, facial expression and voice data

[1448] Data processing: Record the start and end times of each app and calculate usage time. Record communication data using network monitoring software. Extract emotions from the user's facial expressions and voice using facial recognition and voice analysis software.

[1449] Output: Each piece of data (usage time, communication volume, emotional data) is recorded in the device's database.

[1450] Step 2: Send data

[1451] The device sends the collected data to the server at regular intervals. This step includes the following specific operations:

[1452] Input: Data usage, startup time, app usage time, emotional data stored on the device

[1453] Data processing: Convert data into JSON or XML format. Send data securely using SSL / TLS protocol.

[1454] Output: Data sent to the server

[1455] Step 3: Store your data

[1456] The server stores the received data in the appropriate database and performs security checks. This step includes the following specific actions:

[1457] Input: Various data sent from the device (communication charges, startup time, app usage time, emotional data)

[1458] Data processing: Data is stored in a database (e.g., MySQL, MongoDB) and security checks such as SQL injection protection and data encryption are performed.

[1459] Output: Securely stored data

[1460] Step 4: Data Preprocessing

[1461] The server pre-processes the received data. This step includes the following specific actions:

[1462] Input: Each stored data (communication charges, startup time, app usage time, emotional data)

[1463] Data processing:

[1464] Imputing missing data: Imputing missing data using historical average values.

[1465] Outlier detection and removal: Statistical methods (e.g., standard deviation) are used to detect and remove outliers.

[1466] Data normalization: Scale all data to the range 0 to 1.

[1467] Sentiment data analysis: Using machine learning models (e.g., BERT, LSTM), we analyze the sentiment data and extract specific sentiment elements.

[1468] Output: Preprocessed data

[1469] Step 5: Data analysis

[1470] The AI ​​on the server performs comprehensive analysis based on the pre-processed data. This step includes the following specific actions:

[1471] Input: Preprocessed data (frequency of use, communication charges, startup time, emotion data)

[1472] Data processing:

[1473] Analysis of usage frequency by time of day: Calculate the number of times the app is used during each time period.

[1474] Identifying peak hours for communication charges: Communication data is aggregated by hour and the time period with the highest value is identified.

[1475] Startup and usage trend analysis: Long-term usage patterns are analyzed using statistical methods.

[1476] Correlation analysis between emotional data and usage behavior: Analyze the correlation between emotional data and app usage data.

[1477] Output: Analysis results

[1478] Step 6: Proposal Generation

[1479] The server's AI generates specific action suggestions based on the analysis results. This step includes the following specific actions:

[1480] Input: Analysis results

[1481] Data processing: The analysis results are converted into natural language and specific suggestions are generated. For example, a suggestion such as, "Recently, your app use after midnight has increased. If you reduce your app use after midnight by one hour, you will gain approximately 30 hours of sleep per month."

[1482] Output: Generated proposals

[1483] Step 7: Distributing the proposal

[1484] The server sends the generated proposal to the device and notifies the user. This step includes the following specific actions:

[1485] Input: Generated proposals

[1486] Data processing: Check the data format to ensure the proposed content is conveyed correctly, and send it as a push notification or in-app message.

[1487] Output: Suggestion notification sent to user

[1488] This is the specific flow of the process that the program of this system performs. Users can confirm the suggestions and take action to improve their quality of life.

[1489] (Application example 2)

[1490] 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."

[1491] Modern consumers generate vast amounts of data through their use of applications and devices, but there is a lack of systems that can effectively utilize this data to improve their quality of life. Furthermore, there is a lack of systems that can analyze customer behavior and emotions in real time in physical stores and display optimal product recommendations and advertisements. This situation results in missed opportunities to improve customer satisfaction and sales promotions. Furthermore, improving quality of life by collecting and analyzing emotional data and providing specific, individualized recommendations to users is also an important challenge.

[1492] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1493] In this invention, the server includes means for collecting data on user communication charges, startup times, application usage times, and emotion data, means for transmitting the collected data to the server, means for preprocessing the data received by the server, AI means for analyzing the preprocessed data, means for generating specific proposals for the user based on the analysis results, means for distributing the generated proposals to the user's terminal, means for collecting customer gaze data, movement path data, and product viewing time in a physical store, and means for analyzing the collected customer data in real time and displaying product proposals and advertisements to the customer. This not only makes specific proposals to improve the user's quality of life, but also enables optimal product proposals and advertisements to be displayed based on the customer's behavior and emotions in a physical store.

[1494] "Communication charges" are the communication costs incurred when a user sends or receives data via an Internet connection.

[1495] "Launch time" refers to the time when an application is launched by a user.

[1496] "Application Time" means the total time a user spends using a particular application.

[1497] "Emotional data" is emotional information extracted through analysis based on the user's facial expressions and voice.

[1498] "Gaze data" refers to data that indicates the direction and object the user is looking at.

[1499] "Movement path data" refers to data that indicates how a user moves within a space.

[1500] "Product View Time" refers to the amount of time a user spends looking at a particular product.

[1501] "Preprocessing" refers to the preparation of data prior to analysis, such as filling in missing data, removing outliers, and normalizing data.

[1502] "AI Methods" refers to artificial intelligence techniques used to analyze incoming data and find patterns and trends.

[1503] "Specific suggestions" refers to proposing actions or improvements that are beneficial to users based on the analysis results.

[1504] System Overview

[1505] The system of the present invention collects data on users' communication charges, startup times, application usage times, and emotional data, and uses this data to make suggestions for improving quality of life. It also includes a function to collect customer behavioral and emotional data in physical stores and make product suggestions and display advertisements in real time.

[1506] Data collection

[1507] The device is equipped with a means for collecting communication charges, startup time, application usage time, and emotional data. Emotional data is recognized from the user's facial expressions and voice using a camera and microphone. This data is recorded in the device's internal database or in a temporary file.

[1508] Data transmission and storage

[1509] The device periodically sends the collected data to the server, which stores the data in an appropriate format and performs security checks.

[1510] Data Preprocessing

[1511] The server pre-processes the received data, which includes:

[1512] Imputing missing data: Imputing with the historical average value.

[1513] Outlier detection and removal: Remove abnormally high or low values.

[1514] Data normalization: Scaling data values ​​to the range 0 to 1.

[1515] Emotion data analysis: Extract emotional elements such as likes, dislikes, and stress.

[1516] Data analysis

[1517] The pre-processed data is then analyzed by AI on the server. The AI ​​analyzes:

[1518] Frequency of application usage by time of day.

[1519] Peak communication times.

[1520] Startup and usage time trends.

[1521] The relationship between emotional data and usage behavior.

[1522] The relationship between customer gaze data, product viewing time, and movement path.

[1523] Proposal generation

[1524] The server's AI generates suggestions for the user based on the analysis results. The suggestions are expressed in natural language. For example:

[1525] "Recently, app use after midnight has increased. Reducing app use by one hour after midnight would result in an increase of approximately 30 hours of sleep per month."

[1526] "70% of our data usage is spent on certain streaming apps. By only using them when connected to Wi-Fi, we can significantly reduce our data usage."

[1527] "We've noticed an increase in stress recently. Please schedule times to take time off from apps to relax."

[1528] In real time, in-store customers will be shown suggestions such as:

[1529] "Get a 20% off coupon when you purchase this new product."

[1530] "Do you have a question about an item in this area? Would you like me to page a sales associate?"

[1531] Proposal distribution

[1532] The server sends the generated suggestions to the device, which then displays the suggestions to the user as push notifications or in-app messages. The user can then view the detailed suggestions on the device.

[1533] Specific examples

[1534] Example 1: Suggestions for users who use the service frequently late at night and experience increased stress

[1535] 1. The device measures the user's app usage data and emotional data every night after midnight and records the usage data and emotional data every hour.

[1536] 2. The device sends one week of data to the server. For example, it might send the following: "2023-10-01 00:00: 120 minutes of use, high stress level", "2023-10-02 00:00: 110 minutes of use, medium stress level", etc.

[1537] 3. The server preprocesses the data and analyzes usage time and stress levels after midnight.

[1538] 4. The AI ​​identifies that "the average amount of use after midnight is 120 minutes per week, which indicates a high stress level," and automatically generates suggestions to reduce stress and usage time.

[1539] 5. The server sends a suggestion to the device that "reducing usage time after midnight by one hour will improve stress levels and increase sleep by approximately 30 hours per month."

[1540] 6. The device will then send a push notification to the user with the suggestions, and the user can view the details of the suggestions in the app.

[1541] Example 2: An attractive offer for a new product

[1542] 1. A customer puts on smart glasses and enters the store.

[1543] 2. Smart glasses track customers' gazes and detect when they linger on a particular shelf for an extended period of time.

[1544] 3. Recognize the positive emotion of curiosity in the customer's facial expression.

[1545] 4. The server analyzes this data and determines that "this new product is generating interest."

[1546] 5. "Purchase this new product and receive a 20% off coupon" will be displayed on the smart glasses display.

[1547] Prompt Sentence Examples

[1548] When a customer wears smart glasses and enters a store, the glasses will track the customer's gaze. If the customer lingers on a specific shelf for a long time and detects a positive emotion indicating "curiosity," the following suggestion will be displayed: "Buy this new product and receive a 20% off coupon."

[1549] As described above, the present invention makes it possible to effectively utilize user behavioral and emotional data to provide specific suggestions for improving quality of life. It also makes it possible to provide appropriate product suggestions and advertisements to customers in real time in brick-and-mortar stores.

[1550] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1551] Step 1:

[1552] Data collection

[1553] The device collects data on the user's data usage, startup time, application usage time, and emotional data. It uses a camera and microphone to recognize the user's facial expressions and voice. This data is recorded in temporary files or an internal database.

[1554] Input: User's communication charges, startup time, application usage time, facial expression data, voice data

[1555] Output: Collected data (communication charges, startup time, application usage time, emotional data)

[1556] Step 2:

[1557] Data transmission

[1558] The device periodically sends the collected data to the server, where it is encrypted to ensure data security.

[1559] Input: Collected data (communication charges, startup time, application usage time, emotional data)

[1560] Output: Data sent to the server

[1561] Step 3:

[1562] Data storage and security checks

[1563] The server stores the received data in the appropriate format and performs security checks, including verifying data integrity and detecting unauthorized access.

[1564] Input: Data sent to the server

[1565] Output: Data that has undergone security checks, data stored in the database on the server

[1566] Step 4:

[1567] Data Preprocessing

[1568] The server preprocesses the received data, interpolating missing data with historical averages and removing outliers, scaling the data to a range of 0 to 1, and analyzing the emotion data to extract emotional elements such as likes, dislikes, and stress.

[1569] Input: Data stored on the server

[1570] Output: Preprocessed data (imputed data, outlier-removed data, normalized data, analyzed sentiment data)

[1571] Step 5:

[1572] Data analysis

[1573] The AI ​​installed on the server analyzes the pre-processed data, including frequency of application use by time of day, peak times for communication charges, trends in startup time and usage time, correlations between emotional data and usage behavior, and correlations between gaze data, product viewing time, and movement routes.

[1574] Input: Preprocessed data

[1575] Output: Analysis results (frequency of use, peak times for communication charges, trends, correlations with emotion data, correlations with gaze data)

[1576] Step 6:

[1577] Proposal generation

[1578] Based on the analysis results, the server's AI generates specific suggestions for the user, expressed in natural language based on the user's behavioral patterns and emotional data.

[1579] Input: Analysis results

[1580] Output: Generated suggestions (suggestions in natural language format)

[1581] Step 7:

[1582] Proposal distribution

[1583] The server sends the generated suggestions to the device, which then displays the suggestions to the user as push notifications or in-app messages.

[1584] Input: Generated proposals

[1585] Output: Proposals delivered to the user's device, and the displayed proposals

[1586] Step 8:

[1587] Real-time product suggestions

[1588] In brick-and-mortar stores, smart glasses track customers' gaze data and send it to a server, which analyzes it to identify their level of interest in products and display product suggestions and advertisements in real time.

[1589] Input: gaze data, movement path data

[1590] Output: Product offers and advertisements displayed to customers

[1591] Through these steps, the system can effectively utilize behavioral and emotional data of users and customers to make specific suggestions to improve their quality of life.

[1592] 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.

[1593] 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.

[1594] 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.

[1595] [Fourth embodiment]

[1596] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1597] 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.

[1598] 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).

[1599] 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.

[1600] 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.

[1601] 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).

[1602] 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.

[1603] 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.

[1604] 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.

[1605] 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.

[1606] 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.

[1607] 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.

[1608] 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."

[1609] System Overview

[1610] The present invention is a system that collects data such as user communication charges, startup times, and application usage times, and analyzes the data using a server to provide specific suggestions for improving the user's quality of life. Specific embodiments of the system are described below.

[1611] Data collection implementation

[1612] The device records the user's data usage, startup time, and app usage time at regular intervals (e.g., every hour or every day). For example, it records the amount of time a user uses a particular app over a certain period of time and the amount of data usage during that time. This data is stored in a database or temporary file within the device.

[1613] Data transmission and storage practices

[1614] The collected data is sent from the device to the server at regular intervals (e.g., daily or weekly). The data sent here includes communication charges, startup time, and app usage time. The server converts the received data into an appropriate format (e.g., JSON, CSV) and saves it in a database for safekeeping.

[1615] Data Preprocessing Embodiments

[1616] The server reads the received data and performs pre-processing, which may include the following:

[1617] Imputing missing data: For example, if data is missing for a specific time period, impute that portion with the historical average or median.

[1618] Outlier detection and removal: For example, removing values ​​that deviate significantly from normal usage patterns.

[1619] Data normalization: Adjusting data values ​​to a uniform scale (e.g., converting them to the range 0 to 1).

[1620] Data Analysis Embodiments

[1621] Once preprocessed, the data is analyzed by AI installed on the server. The AI ​​analyzes user behavior patterns in detail and identifies specific issues. For example, it identifies the frequency of app use by time of day and peak times for data charges. It also analyzes trends in launch times and usage duration to uncover user usage trends.

[1622] Suggestion Generation Embodiments

[1623] The server's AI generates specific action suggestions for the user based on the analysis results. For example, the following suggestions may be generated:

[1624] "Recently, app use after midnight has been increasing. Reducing app use by one hour after midnight is expected to increase sleep time by approximately 30 hours per month."

[1625] "70% of data usage is used for certain streaming apps. By using them only when connected to Wi-Fi, you can significantly reduce your data usage."

[1626] Embodiments of Proposal Delivery

[1627] Finally, the server sends the generated proposal to the device and notifies the user. The device displays the proposal to the user via a push notification, allowing the user to review its contents. If necessary, the user can view the proposal details within the app.

[1628] Specific examples

[1629] Example 1: Suggestions for users with high late-night usage

[1630] 1. The device measures the user's app usage data every night after midnight and records usage data every hour.

[1631] 2. The device sends one week's worth of data to the server. For example, "2023-10-01 00:00: 120 minutes", "2023-10-02 00:00: 110 minutes", etc.

[1632] 3. The server receives the data, imputes missing values, and removes outliers if necessary.

[1633] 4. The server compiles usage time from midnight onwards for one week, and AI analyzes the user's usage patterns.

[1634] 5. The AI ​​identifies that "the average usage after midnight is 120 minutes per week" and automatically generates an improvement suggestion (reducing usage time by 60 minutes).

[1635] 6. The server generates a suggestion to the device, saying, "If you reduce your usage time after midnight by one hour, you will increase your sleep time by a total of 30 hours in one month." and sends it to the device.

[1636] 7. The device will then push a notification to the user with the suggestions, which the user can then review in the app.

[1637] Example 2: Suggestions for users with excessive data usage

[1638] 1. The device collects the user's data usage data for one month.

[1639] 2. The device sends the collected data to the server, which includes information on daily communication charges and apps used.

[1640] 3. The server receives the data and pre-processes it for analysis.

[1641] 4. AI will analyze and identify which specific streaming apps are taking up the majority of your data usage.

[1642] 5. The server generates a suggestion that suggests limiting the use of certain streaming apps to Wi-Fi or using data saving features to reduce data charges.

[1643] 6. The server sends the generated proposal to the device and notifies the user.

[1644] 7. Users can reduce data costs by checking notifications and reviewing how they use streaming apps.

[1645] The above is a specific description of the embodiment of the present invention. This system allows users to understand their own behavioral patterns and receive appropriate suggestions for improving their lifestyle.

[1646] The processing flow will be explained below.

[1647] Step 1:

[1648] The device collects the user's data usage, startup time, and app usage time. This data is recorded at regular intervals (e.g., hourly or daily). Specifically, the device's log function is used to record the start and end times of each app's use, the amount of data consumed, etc.

[1649] Step 2:

[1650] The data collected by the device is stored in a temporary file or an internal database. At this stage, the data is checked for duplication or format inconsistencies, and the data format is unified if necessary.

[1651] Step 3:

[1652] The device periodically (e.g. daily or weekly) transmits stored data to the server via the network. The transmitted data includes communication charges, startup time, and application usage time. HTTP or HTTPS is used as the communication protocol.

[1653] Step 4:

[1654] The server receives the received data and performs security checks (e.g., data encryption, integrity checks) to ensure that the data has not been tampered with.

[1655] Step 5:

[1656] The server saves the received data in the database. Common formats such as JSON and CSV are used for saving. When saving, the consistency of each data item is rechecked.

[1657] Step 6:

[1658] The server performs data preprocessing, such as imputing missing data (e.g., imputing with historical average values), detecting and removing outliers, and normalizing data (e.g., scaling to a range of 0 to 1).

[1659] Step 7:

[1660] The server inputs the preprocessed data into the AI ​​model for analysis, which analyzes the frequency of app use by time of day, peak times for data usage, and trends in startup and usage time.

[1661] Step 8:

[1662] The server's AI generates specific suggestions for users based on the analysis results. The suggestions are expressed in natural language and formatted in a way that is easy for users to understand. For example, "Recently, your app usage after midnight has increased. If you reduce your app usage by one hour after midnight, it is predicted that you will gain approximately 30 hours of sleep per month."

[1663] Step 9:

[1664] The server sends the generated proposal to the device. When sending, the data format is checked to ensure that the proposal content is transmitted correctly.

[1665] Step 10:

[1666] The device will notify the user of the suggestions, typically as a push notification or in-app message. The user can then view the details of the suggestions by checking the notification.

[1667] Step 11:

[1668] Users can check the notification and change their behavior based on the suggestions, for example, by refraining from using apps late at night to ensure they get enough sleep.

[1669] These are the specific processing steps of the program. Through this series of processes, users can gain a detailed understanding of their own behavioral patterns and receive specific suggestions for improving their quality of life.

[1670] Example 1

[1671] 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."

[1672] In systems that collect and analyze data on users' communication charges and app usage time, it can be difficult to generate effective lifestyle improvement proposals using existing methods. In particular, it is difficult to understand missing data, the presence of outliers, and user behavior patterns in detail to generate specific and effective proposals.

[1673] 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.

[1674] In this invention, the server includes means for collecting data such as user communication charges, startup times, and application usage times, means for transmitting the collected data to the server, and means for preprocessing the received data in the server, which enables detailed analysis of user behavior patterns, completion and removal of missing data and outliers, and normalization to a unified scale.

[1675] The server also includes an artificial intelligence unit that analyzes the preprocessed data, a unit that generates specific suggestions for the user based on the analysis results, and a unit that delivers the generated suggestions to the user's terminal, thereby providing the user with specific and effective suggestions for action.

[1676] "User's communication charges" means the total amount of data communication usage and charges incurred when a User uses the communication service.

[1677] "Boot time" is the time it takes for a particular application or device to start and become available for use, and the cumulative time that the application or device is running.

[1678] "App time" is the amount of time a particular application is actually used by a user.

[1679] "Means for collecting data" refers to a device or program that records information such as a user's communication charges, startup time, and application usage time at regular intervals.

[1680] "Means for transmitting data" refers to a device or program for transferring collected data to a database or server.

[1681] The "preprocessing means" is a device or program for imputing missing data, removing outliers, and normalizing the received data.

[1682] "Artificial intelligence means" refers to artificial intelligence technology that uses collected and pre-processed data to analyze user behavior patterns and generate specific suggestions based on the analysis results.

[1683] The "means for generating specific suggestions" is a device or program for generating action suggestions for users based on the analysis results using artificial intelligence technology.

[1684] "Means for distributing to terminal" means a device or program for transferring the proposal generated by the server to the user's terminal and notifying the user.

[1685] "Recording means" means a device or program that records the user's currently running apps and their running time at regular intervals.

[1686] A "means for completing missing data" is a device or program that, when there is a gap in the collected data, fills in the gaps with past data, estimated values, etc.

[1687] An "outlier removal means" is a device or program that detects data that deviates significantly from normal usage patterns and removes them from the analysis.

[1688] A "means for normalization" is a device or program that converts data values ​​to a uniform scale (e.g., a range of 0 to 1).

[1689] System Overview

[1690] This system collects data such as user communication charges, startup times, and application usage time, and analyzes it on a server to understand the user's behavioral patterns and make suggestions to improve their quality of life. Specifically, the system consists of the steps of data collection by the device, data transmission to the server, data preprocessing and analysis on the server, and proposal generation and distribution.

[1691] Data collection implementation

[1692] The device records the user's communication charges, startup times, and app usage time at regular intervals. For example, it records the amount of time the user used a particular app over a certain period of time and the data communication charges consumed during that time. This data is stored in a database or temporary file within the device. A program for collecting and recording data is installed on the device. This program uses a scheduler to collect data every hour and saves it in a database (e.g., SQLite).

[1693] Data transmission and storage practices

[1694] The device sends the collected data to the server at a fixed interval (for example, at midnight every day). The data is converted into an appropriate format (for example, JSON or CSV). The server analyzes and stores the received data in a database (for example, MySQL). To send the data, the device makes an HTTP request, and the sent data is received by the server's REST API.

[1695] Data Preprocessing Embodiments

[1696] The server performs preprocessing on the received data. This preprocessing includes missing data completion, outlier detection and removal, and data normalization. This preprocessing is performed using the Python Pandas library. Data normalization is performed using MinMaxScaler from scikit-learn.

[1697] Data Analysis Embodiments

[1698] Once the preprocessing is complete, the data is analyzed by artificial intelligence (AI) installed on the server. The AI ​​performs detailed analysis of user behavior patterns and extracts specific issues (for example, times of high usage or peak times for communication charges). Machine learning algorithms such as K-means clustering are used for the analysis.

[1699] Suggestion Generation Embodiments

[1700] The server's AI generates specific action suggestions for the user based on the analysis results. For example, it could generate the following suggestion: "Reducing app use by one hour after midnight could increase sleep time by approximately 30 hours over the course of a month." Natural language processing technology is used to generate suggestions, for example, by inputting a prompt sentence to generate a suggestion using a generative AI model (such as GPT-3).

[1701] Embodiments of Proposal Delivery

[1702] The server sends the generated suggestions to the device and notifies the user. The device displays the suggestions via push notification, allowing the user to check their details. The user can also tap the notification to view the detailed suggestions within the app.

[1703] Specific examples

[1704] Example 1: Suggestions for users with high late-night usage

[1705] 1. The device measures the user's app usage data every night after midnight and records usage data every hour.

[1706] 2. The device sends one week of data to the server.

[1707] 3. The server receives the data, imputes missing values, and removes outliers.

[1708] 4. The server compiles usage time from midnight onwards for one week, and AI analyzes the user's usage patterns.

[1709] 5. The AI ​​identifies that "the average usage after midnight is 120 minutes per week" and automatically generates an improvement suggestion (reducing usage time by 60 minutes).

[1710] 6. The server generates a suggestion to the device, saying, "If you reduce your usage time after midnight by one hour, you will increase your sleep time by a total of 30 hours in one month." and sends it to the device.

[1711] 7. The device will then push a notification to the user with the suggestions, which the user can then review in the app.

[1712] Example 2: Suggestions for users with excessive data usage

[1713] 1. The device collects the user's data usage data for one month.

[1714] 2. The device sends the collected data to the server, which includes information on daily communication charges and apps used.

[1715] 3. The server receives the data and pre-processes it for analysis.

[1716] 4. AI will analyze and identify which specific streaming apps are taking up the majority of your data usage.

[1717] 5. The server generates a suggestion that suggests limiting the use of certain streaming apps to Wi-Fi or using data saving features to reduce data charges.

[1718] 6. The server sends the generated proposal to the device and notifies the user.

[1719] 7. Users can reduce data costs by checking notifications and reviewing how they use streaming apps.

[1720] Prompt Sentence Examples

[1721] "Collect app usage data after midnight for one month, analyze users' usage patterns, and generate lifestyle improvement suggestions."

[1722] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1723] Step 1: Collect data

[1724] Input: User's data charges, startup time, app usage time

[1725] How it works: The device runs a program that periodically records data charges, startup times, and app usage time.

[1726] Data processing: Data charges, startup time, and app usage time are saved in a database or temporary file.

[1727] Output: Data stored in the device's internal database or temporary files

[1728] Specific operation: The scheduler installed on the device measures the current communication charges, startup time, and application usage time every hour and stores them in an SQLite database (e.g., "2023-10-01 12:00: Application A 30 minutes").

[1729] Step 2: Sending data

[1730] Input: Data stored on the device about communication charges, startup time, and app usage time

[1731] Operation: The device converts the collected data into JSON format at regular intervals (for example, at midnight every day) and sends it to the server.

[1732] Data processing: Convert the data into JSON format.

[1733] Output: JSON data sent to the server

[1734] Specific operation: Every day at midnight, the device reads the current day's data from the SQLite database, converts the data to JSON format using the Python json module, and then sends it to the server via an HTTP request (e.g., {"2023-10-01": {"App A": 120, "App B": 30}}).

[1735] Step 3: Store your data

[1736] Input: JSON data sent to the server

[1737] How it works: The server parses the data it receives and stores it in a secure database.

[1738] Data processing: Parse the JSON data and convert it into a format that can be inserted into the database.

[1739] Output: Data stored in the database on the server

[1740] Specific operation: The server parses the received JSON data using Python's json module, generates an SQL statement to insert into the MySQL database, and executes it (e.g., INSERT INTO user_data VALUES ("2023-10-01", "App A", 120, "App B", 30)).

[1741] Step 4: Preprocessing the data

[1742] Input: Data stored in the database on the server

[1743] How it works: The server imputes missing data, detects and removes outliers, and normalizes the data.

[1744] Data processing: Impute missing data, remove outliers, and normalize data.

[1745] Output: Preprocessed data

[1746] Specific operation: The data is read into a data frame format using Python's Pandas library, missing values ​​are filled in using the fillna method, outliers are removed using conditional search, and the data is normalized using MinMaxScaler (e.g., {"App A": 0.5, "App B": 0.2}).

[1747] Step 5: Analyze the data

[1748] Input: Preprocessed data

[1749] How it works: The AI ​​installed on the server uses pre-processed data to analyze user behavior patterns.

[1750] Data computation: Use an AI model (e.g., K-means clustering) to separate the data into clusters.

[1751] Output: User behavior pattern analysis results

[1752] Specific operation: K-means clustering is performed using Python's Scikit-learn library, and user data is classified into each cluster (e.g., cluster 0 = users with high usage during the late night hours).

[1753] Step 6: Proposal Generation

[1754] Input: User behavior pattern analysis results

[1755] Action: The server's artificial intelligence generates specific action suggestions based on the analysis results.

[1756] Data calculation: A prompt sentence is input into a generative AI model (e.g., GPT-3) to generate a suggested sentence.

[1757] Output: Generated suggestion

[1758] Specific operation: Based on the analysis result that "there is a lot of usage after midnight," the generative AI model inputs the prompt sentence "Please generate a proposal to reduce app usage after midnight," and generates a proposal sentence (e.g., "Reducing app usage after midnight by one hour could increase sleep time by approximately 30 hours in a month").

[1759] Step 7: Distributing the proposal

[1760] Input: Generated suggestion

[1761] Behavior: The server generates a proposal, sends it to the device, and notifies the user.

[1762] Data processing: Convert the proposal into a notification format and send it to the terminal.

[1763] Output: Proposal notification displayed on the user's device

[1764] Specific operation: The server converts the suggestion text into JSON format and sends it to the device via an HTTP request. The device then generates a push notification based on the received JSON and notifies the user (e.g., notification message: "If you reduce app usage after midnight by one hour, you will gain approximately 30 hours of sleep in one month").

[1765] (Application example 1)

[1766] 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."

[1767] Users spend a lot of time and data charges using applications on smartphones and other devices, which can result in a decline in their quality of life. Furthermore, a bias in data charges and usage time toward specific apps can lead to wasteful usage and negatively impact health. However, it is difficult for users to recognize these patterns of behavior, making it difficult to take appropriate measures to improve them. Therefore, there is a need for a system that can analyze users' application usage patterns and automatically provide specific suggestions for optimally managing data charges and usage time.

[1768] 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.

[1769] In this invention, the server includes means for collecting data such as user communication charges, startup times, and application usage time; means for transmitting the collected data to the server; means for preprocessing the received data in the server; artificial intelligence means for analyzing the preprocessed data; means for analyzing the viewing patterns of specific applications and generating specific suggestions for the user; and means for delivering the generated suggestions to the user's device. This enables detailed analysis of user behavior patterns and automatically generates and delivers practical suggestions for optimizing communication charges and usage time. For example, if a user uses an application excessively during a certain time period, the system can suggest that the user use that time for other activities. Furthermore, recommending viewing content that consumes a lot of data over a Wi-Fi connection can also contribute to saving communication charges.

[1770] "Communication charges" are the costs incurred when a user communicates data via an Internet connection.

[1771] "Launch time" refers to the time when an application is started on a device.

[1772] "Time in app" refers to the total amount of time a user spends using a particular application.

[1773] "Means of collecting data" refers to the mechanism for obtaining information such as user data charges, startup time, and app usage time.

[1774] "Means for transmitting to a server" refers to a mechanism for sending collected data to a remote server via a communication network such as the Internet.

[1775] "Preprocessing means" refers to a mechanism for performing processes such as removing unnecessary data, filling in missing values, and normalizing data in order to improve the quality of collected data.

[1776] "Artificial Intelligence Tools" means AI techniques used to analyze pre-processed data and discover specific patterns or trends.

[1777] The "means for generating suggestions" is a mechanism for creating improvement measures and action suggestions for users based on data analyzed by artificial intelligence.

[1778] "Means of delivery to user's device" refers to a mechanism for notifying the user of the generated suggestions on their device, such as a smartphone or tablet.

[1779] "Behavioral patterns" refer to a series of usage trends and habits, such as how a user uses applications and at what times they consume the most data.

[1780] "Viewing patterns" are information that indicates the tendency of users to view what types of content at what times.

[1781] "Wi-Fi environment" refers to a network environment that connects to the Internet using wireless LAN.

[1782] "Data-intensive content" refers to applications such as video and streaming services that require large amounts of internet data.

[1783] "Use for other activities" refers to engaging in alternative activities such as exercise, reading, or sleep instead of using the application during a particular time period.

[1784] System Overview

[1785] This invention is a system that collects data such as user communication charges, startup times, and application usage time, and analyzes it on a server to provide specific action suggestions to users. The system has the functions of data collection, data transmission, preprocessing, AI analysis, proposal generation, and proposal distribution.

[1786] Data collection

[1787] The device records the user's data usage, startup time, and app usage time at regular intervals. For example, it records the time the user uses a particular app and the amount of data usage. This information is stored in an internal database.

[1788] Data transmission

[1789] The collected data, including communication charges, startup time, and usage time, is sent from the device to a server at regular intervals. The server converts the received data into an appropriate format and stores it securely.

[1790] Data Preprocessing

[1791] The server reads the received data and performs preprocessing, including filling in missing data, removing outliers, and normalizing the data, thereby improving the accuracy of the analysis.

[1792] Data analysis

[1793] Once preprocessed, the data is analyzed by AI installed on the server. The AI ​​analyzes user behavior patterns in detail and extracts viewing patterns and peak times for data charges. For example, by identifying viewing frequency and data consumption by time of day, it is possible to understand user behavior trends.

[1794] Proposal generation

[1795] The server's AI then generates specific action suggestions for the user based on the analysis results, including:

[1796] Suggestions to repurpose screen time for other activities during certain times

[1797] We recommend watching data-intensive content in a Wi-Fi environment.

[1798] Proposal distribution

[1799] The server sends the generated suggestions to the device and displays them to the user via push notification, where the user can view the details of the suggestions within the app.

[1800] Hardware and software details

[1801] Hardware: Smartphones (e.g. iPhone, Android devices), servers

[1802] Software: Python 3.9, JSON format, standard library

[1803] Specific examples

[1804] For example, if a user frequently watches videos late at night, the AI ​​will analyze this pattern and generate a suggestion such as, "You watch too much after midnight. By reducing your viewing time by one hour, you can gain approximately 30 hours of sleep per month." Also, if a specific streaming app is taking up a large portion of your data charges, the AI ​​will suggest, "To reduce data charges, we recommend limiting the use of this streaming app to Wi-Fi environments."

[1805] Prompt Sentence Examples

[1806] "Recently, app usage late at night has increased. Reducing usage after midnight by one hour is predicted to increase sleep time by approximately 30 hours per month. Based on this, please output code that suggests reducing viewing during specific times. For example, something implemented in Python would be good."

[1807] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1808] Step 1:

[1809] The device collects data such as the user's data charges, startup time, and app usage time at regular intervals. The inputs are the time the user starts each app (startup time), the amount of time the application is used (usage time), and the data charges incurred during use. This data is stored in an internal database. For example, if a user starts YouTube at 10 a.m., watches it for 30 minutes, and uses 50 MB of data during that time, that information will be recorded.

[1810] Step 2:

[1811] The device periodically sends the collected data to the server. The data is sent over the communication network and converted into an appropriate format, such as JSON. The input is the data collected in step 1, and the output is the data sent to the server. This data includes specific app names, usage time, communication charges, launch date and time, etc.

[1812] Step 3:

[1813] The server reads the received data and performs preprocessing. The input is the unprocessed data sent from the terminal. Preprocessing involves filling in missing data, detecting and removing outliers, and normalizing the data. For example, if data for a certain date and time is missing, it is filled in with the average value from the past. Outliers are values ​​that are clearly outside the normal range and are removed. Data normalization involves converting all data into a unified range from 0 to 1. The output is a dataset after preprocessing has been completed.

[1814] Step 4:

[1815] The server inputs the preprocessed data into an AI model for analysis. The input is the preprocessed data, and the AI ​​analyzes the user's behavioral patterns. For example, it can determine how much data is being used during a specific time period, or which applications are being used most frequently at which times. The output is a detailed analysis of the user's behavioral patterns.

[1816] Step 5:

[1817] The server generates specific action suggestions for the user based on the analysis results. The input is the analysis results of the artificial intelligence model. For example, if a user uses a lot of applications late at night, the server automatically generates a suggestion to reduce that usage time. Specifically, the server generates a suggestion such as, "If you reduce viewing after midnight by one hour, you can gain approximately 30 additional hours of sleep per month." The output is an action suggestion for the user.

[1818] Step 6:

[1819] The server sends the generated suggestions to the user's device and displays them via push notification. The input is the generated suggestions, and the output is the notification displayed on the user's device. Specifically, the device displays a notification saying, "By reducing app usage after midnight, you will get more sleep and improve your quality of life." The user can check the detailed suggestions within the app.

[1820] 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.

[1821] System Overview

[1822] The present invention is a system that collects data such as user communication charges, startup times, and application usage times, and combines this with an emotion engine that recognizes user emotions to make specific suggestions for improving the user's quality of life. Specific embodiments of the system are described below.

[1823] Data collection implementation

[1824] The device records the user's data usage, startup time, app usage time, and emotional data at regular intervals, including:

[1825] The time and duration of each app usage.

[1826] Data charges consumed.

[1827] It uses a camera and microphone to recognize emotions from the user's facial expressions and voice.

[1828] This data is stored in a database or temporary file within the device.

[1829] Data transmission and storage practices

[1830] The collected data is sent from the device to a server at regular intervals. This data includes communication charges, startup time, app usage time, and emotional data. The server stores the received data in an appropriate format and performs security checks to ensure safety.

[1831] Data Preprocessing Embodiments

[1832] The server reads and pre-processes the received data, which includes:

[1833] Imputing missing data: A method of imputing using past average values.

[1834] Outlier detection and removal: Remove abnormally high or low values.

[1835] Data normalization: Scaling data values ​​to the range 0 to 1.

[1836] Emotion data analysis: Extract emotional elements such as goodwill, badwill, and stress.

[1837] Data Analysis Embodiments

[1838] Once the preprocessing is complete, the data is comprehensively analyzed by the AI ​​installed on the server. The AI ​​analyzes the following items, for example:

[1839] Frequency of app use by time of day.

[1840] Peak communication times.

[1841] Startup and usage time trends.

[1842] The relationship between emotional data and usage behavior.

[1843] Suggestion Generation Embodiments

[1844] The server's AI generates specific action suggestions for the user based on the analysis results. The suggestions are expressed in natural language and formatted in a way that is easy for the user to understand. For example,

[1845] "Recently, app use after midnight has been increasing. Reducing app use by one hour after midnight is predicted to result in an increase of approximately 30 hours of sleep per month."

[1846] "70% of data usage is spent on certain streaming apps. By only using them when connected to Wi-Fi, you can significantly reduce your data usage."

[1847] "We've noticed an increase in stress recently. Please schedule times to avoid using apps to relax."

[1848] Embodiments of Proposal Delivery

[1849] The server generates a proposal and sends it to the device. When sending, the data is formatted and checked to ensure the proposal is transmitted correctly. The device then notifies the user of the proposal. This is typically displayed as a push notification or an in-app message. The user can then view the proposal in detail by checking the notification.

[1850] Specific examples

[1851] Example 1: Suggestions for users who experience high late-night usage and increased stress

[1852] 1. The device measures the user's app usage data and emotional data every night after midnight and records the usage data and emotional data every hour.

[1853] 2. The device sends one week of data to the server. For example, "2023-10-01 00:00: 120 minutes of use, high stress level" or "2023-10-02 00:00: 110 minutes of use, medium stress level."

[1854] 3. The server preprocesses the data and analyzes usage time and stress levels after midnight.

[1855] 4. The AI ​​identifies that "the average amount of use after midnight is 120 minutes per week, which indicates a high stress level," and automatically generates suggestions to reduce stress and usage time.

[1856] 5. The server sends a suggestion to the device that "reducing usage time after midnight by one hour will improve stress levels and increase sleep by approximately 30 hours per month."

[1857] 6. The device will then send a push notification to the user with the suggestions, and the user can view the details of the suggestions in the app.

[1858] Example 2: Suggestions for users with excessive data usage and negative emotions

[1859] 1. The device collects the user's data usage and emotion data for one month.

[1860] 2. The device sends the collected data to a server, including daily data usage, apps used, and emotional data.

[1861] 3. The server pre-processes the data and analyzes key traffic drivers and sentiment.

[1862] 4. AI identifies that certain streaming apps consume a large portion of data usage and negative emotions frequently arise while using them.

[1863] 5. The server sends a suggestion to the device suggesting that users limit the use of certain streaming apps to Wi-Fi and use data-saving features to reduce data charges and alleviate negative emotions.

[1864] 6. Users will be encouraged to review their notifications and how they use streaming apps to reduce data costs and improve their mood.

[1865] The above is a detailed description of an embodiment of the present invention, which allows users to understand their own behavioral patterns and emotions in detail and receive specific suggestions to improve their quality of life.

[1866] The processing flow will be explained below.

[1867] Step 1:

[1868] The device collects data on the user's data usage, startup time, app usage time, and emotional data. Emotional data is obtained by analyzing the user's facial expressions and voice using the camera and microphone. For example, the emotion engine can recognize emotions such as stress, joy, and excitement from the user's facial expressions and tone of voice while using the app.

[1869] Step 2:

[1870] The data collected by the device is stored in an internal database or temporary file. At this stage, the data is checked for completeness and duplication, and the data format is unified if necessary.

[1871] Step 3:

[1872] The device periodically (e.g., daily or weekly) transmits the stored data to the server via the network. HTTP or HTTPS is used as the communication protocol, and the transmitted data includes communication charges, startup time, application usage time, and emotional data.

[1873] Step 4:

[1874] The server receives the received data and performs security checks (e.g., data encryption, integrity check) to ensure that the data has not been tampered with or leaked.

[1875] Step 5:

[1876] The server saves the received data in a database. Common formats such as JSON and CSV are used for saving. When saving, the consistency of each data item is rechecked to ensure there is no duplication or missing data.

[1877] Step 6:

[1878] The server pre-processes the data, which includes:

[1879] Imputing missing data: For example, imputing missing data with historical average values.

[1880] Outlier detection and removal: Filter out data that deviates significantly from normal usage patterns.

[1881] Data normalization: Scaling data values ​​to the range 0 to 1.

[1882] Emotion data analysis: Extracting emotional elements (e.g., stress, joy, excitement) from facial and voice data.

[1883] Step 7:

[1884] The server inputs the pre-processed data into the AI ​​model for comprehensive analysis, specifically analyzing the following:

[1885] Frequency of app use by time of day.

[1886] Peak communication times.

[1887] Startup and usage time trends.

[1888] The relationship between emotional data and usage behavior.

[1889] Step 8:

[1890] The server's AI generates specific action suggestions for the user based on the analysis results. The suggestions are expressed in natural language and formatted in a way that is easy for the user to understand. For example, the following suggestions are automatically generated:

[1891] "Recently, app use after midnight has been increasing. Reducing app use by one hour after midnight is predicted to result in an increase of approximately 30 hours of sleep per month."

[1892] "70% of data usage is spent on certain streaming apps. By only using them when connected to Wi-Fi, you can significantly reduce your data usage."

[1893] "We've noticed an increase in stress recently. Please schedule times to avoid using apps to relax."

[1894] Step 9:

[1895] The server sends the generated proposal to the device. When sending, the data format is checked to ensure that the proposal content is transmitted correctly.

[1896] Step 10:

[1897] The device will notify the user of the suggestions, typically as a push notification or in-app message. The user can then view the suggestions in detail by checking the notification.

[1898] Step 11:

[1899] Users can review the notifications and take action based on the suggestions, such as avoiding late-night app use to ensure they get enough sleep or limiting streaming app use to Wi-Fi.

[1900] These are the specific processing steps of the program, which allow users to gain a detailed understanding of their own behavioral patterns and emotional state and receive specific suggestions to improve their quality of life.

[1901] Example 2

[1902] 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."

[1903] Conventional systems could only collect and analyze data such as user data charges, startup times, and app usage time, making it difficult to provide specific suggestions that took user emotions into account. Furthermore, the collected data often contained missing data or outliers, making accurate analysis impossible. Furthermore, the suggestions made to users were limited, making it difficult to provide specific action suggestions that would improve users' quality of life.

[1904] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for collecting a user's communication charges, startup time, application usage time, and emotional data; means for transmitting the collected data to the server at regular intervals; means for preprocessing the received data in the server, which includes filling in missing data, detecting and removing outliers, normalizing data, and analyzing emotional data; AI means for analyzing the preprocessed data for frequency of use by time period, peak times of communication charges, trends in startup time and usage time, and correlations between emotional data and usage behavior; means for generating specific suggestions for the user based on the analysis results; and means for delivering the generated suggestions to the user's terminal. This makes it possible to make specific suggestions taking into account the user's behavioral patterns and emotions, thereby providing a comprehensive system for improving the user's quality of life.

[1905] "User" refers to an individual or group that uses the system and whose communication charges, startup time, app usage time, and emotional data are collected.

[1906] "Communication charges" refers to charges based on the amount of data transferred when a user uses a communication service.

[1907] "Startup time" refers to the time when the user starts operating the terminal and the time when each application is launched.

[1908] "App time" refers to the total time a user spends using a particular application.

[1909] "Emotion data" refers to emotional information obtained from the user's facial expressions and voice.

[1910] A "terminal" is a communication device or computer used by a user, and is a device that collects communication charges, usage time, and emotional data.

[1911] "Server" means the computer system that receives, stores, pre-processes and analyzes the collected data.

[1912] "Means of collection" refers to the device's ability to collect data on the user's data usage, startup time, app usage time, and emotional data.

[1913] "Transmitting means" refers to the function of the terminal to transmit collected data to the server.

[1914] The "preprocessing means" refers to a function that performs the following on the received data: complementing missing data, detecting and removing outliers, normalizing data, and analyzing emotion data.

[1915] "Missing data completion" refers to the process of using past average values, etc. to make up for any shortfalls in collected data.

[1916] "Outlier detection and removal" refers to the process of identifying and removing extremely high or low values ​​(outliers) when they are included in collected data.

[1917] "Data normalization" is the process of converting the scale of data into the range of 0 to 1.

[1918] "Emotion data analysis" refers to the process of analyzing emotion data obtained from facial expressions and voice to extract specific emotional elements (such as goodwill, badwill, stress, etc.).

[1919] "AI means" refers to an artificial intelligence function that uses pre-processed data to analyze frequency of use by time period, peak times for communication charges, trends in startup time and usage time, and the relationship between emotional data and usage behavior.

[1920] "Means for generating" refers to the function of creating specific suggestions for users based on the analysis results.

[1921] The "means for delivering" refers to a function for sending the generated proposal to the user's terminal.

[1922] MODE FOR CARRYING OUT THE INVENTION

[1923] System Overview

[1924] This invention is a system that collects data on users' communication charges, startup times, application usage times, and emotional data, and analyzes this data to provide specific suggestions for improving the user's quality of life. This system operates by combining a terminal and a server. The detailed configuration and processing flow of the system are described below.

[1925] Configuring Data Collection

[1926] The device collects data on each user's data usage, app launch time, app usage time, and emotional data. The device can be a smartphone, tablet, PC, or other common device. This includes specific hardware and software such as:

[1927] Data collection is performed using the application's logging function.

[1928] Network monitoring software is used to collect communication charge data.

[1929] To collect emotion data, the device's camera and microphone are used, and facial expression recognition software and voice analysis software (e.g., OpenCV, TensorFlow) are implemented.

[1930] Configuring data transmission and storage

[1931] The device sends the collected data to the server at regular intervals. The server receives the data and stores it securely. A secure communication protocol (e.g., SSL / TLS) is used to transmit the data, and the data is converted into a standard format such as JSON or XML. The server stores this data in a database (e.g., MySQL, MongoDB) and performs security checks.

[1932] Data preprocessing configuration

[1933] The server pre-processes the received data, which includes the following steps:

[1934] Imputing missing data: Use historical average values ​​to fill in missing data.

[1935] Outlier detection and removal: Statistical methods are used to detect and remove anomalous data points.

[1936] Data normalization: Scale and standardize the data to the range 0 to 1.

[1937] Emotion data analysis: Analyze emotion data using machine learning models (e.g., BERT, LSTM) to extract specific emotion elements.

[1938] Configuring Data Analysis

[1939] The server performs comprehensive analysis using AI based on the pre-processed data. The AI ​​analyzes:

[1940] Frequency of app use by time of day

[1941] Peak communication charge times

[1942] Boot time and usage time trends

[1943] Relationship between emotional data and usage behavior

[1944] This allows for detailed analysis of user behavior patterns and emotions.

[1945] Configuring Proposal Generation

[1946] The AI ​​installed on the server generates specific action suggestions based on the analysis results. The suggestions are expressed in natural language and formatted in a way that is easy for users to understand. For example:

[1947] "Recently, app use after midnight has increased. Reducing app use by one hour after midnight would result in an increase of approximately 30 hours of sleep per month."

[1948] "70% of data usage is spent on certain streaming apps. By only using them when connected to Wi-Fi, you can significantly reduce your data usage."

[1949] "You've been experiencing increased stress lately. Try scheduling time off your app use to relax."

[1950] Configuring Proposal Delivery

[1951] The server sends the generated proposal to the device. The data format is checked to ensure the proposal content is transmitted correctly, and the user is notified via a push notification or in-app message. The user can then view the detailed proposal content.

[1952] Specific examples

[1953] Example 1: Suggestions for users who experience high late-night usage and increased stress

[1954] 1. The device records the user's app usage data and emotional data every night after midnight.

[1955] 2. The device sends this data for one week to the server. For example, "2023-10-01 00:00: 120 minutes of use, high stress level" or "2023-10-02 00:00: 110 minutes of use, medium stress level."

[1956] 3. The server preprocesses the data and analyzes usage time and stress levels after midnight.

[1957] 4. As a result of the analysis, the AI ​​determines that "the average amount of use after midnight is 120 minutes per week, which indicates a high stress level," and suggests reducing stress and reducing usage time.

[1958] 5. The server generates a suggestion to the device: "Reducing usage time after midnight by one hour will improve stress levels and increase sleep by approximately 30 hours per month."

[1959] 6. The device will send a push notification to the user with the suggestions, and the user can view the details of the suggestions in the app.

[1960] Example 2: Suggestions for users with excessive data usage and negative emotions

[1961] 1. The device collects the user's data usage and emotional data for one month.

[1962] 2. The device sends the collected data to the server, including daily data usage, apps used, and emotional data.

[1963] 3. The server pre-processes the data and analyzes key traffic drivers and sentiment.

[1964] 4. AI identifies that certain streaming apps consume a large portion of data usage and negative emotions frequently arise while using them.

[1965] 5. The server generates a suggestion to the device, suggesting that the user limit the use of certain streaming apps to Wi-Fi and utilize data-saving features to reduce data charges and alleviate negative emotions, and sends it to the device.

[1966] 6. Users will be encouraged to review their notifications and how they use streaming apps to reduce data costs and improve their mood.

[1967] The above is a detailed description of the embodiment of the present invention. This system allows users to understand their own behavioral patterns and emotions in detail and receive specific suggestions to improve their quality of life.

[1968] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1969] Step 1: Data collection

[1970] The device will collect data on the user's data usage, startup time, app usage time, and emotional data at regular intervals. This step includes the following specific actions:

[1971] Input: User's app usage, communication data, facial expression and voice data

[1972] Data processing: Record the start and end times of each app and calculate usage time. Record communication data using network monitoring software. Extract emotions from the user's facial expressions and voice using facial recognition and voice analysis software.

[1973] Output: Each piece of data (usage time, communication volume, emotional data) is recorded in the device's database.

[1974] Step 2: Send data

[1975] The device sends the collected data to the server at regular intervals. This step includes the following specific operations:

[1976] Input: Data usage, startup time, app usage time, emotional data stored on the device

[1977] Data processing: Convert data into JSON or XML format. Send data securely using SSL / TLS protocol.

[1978] Output: Data sent to the server

[1979] Step 3: Store your data

[1980] The server stores the received data in the appropriate database and performs security checks. This step includes the following specific actions:

[1981] Input: Various data sent from the device (communication charges, startup time, app usage time, emotional data)

[1982] Data processing: Data is stored in a database (e.g., MySQL, MongoDB) and security checks such as SQL injection protection and data encryption are performed.

[1983] Output: Securely stored data

[1984] Step 4: Data Preprocessing

[1985] The server pre-processes the received data. This step includes the following specific actions:

[1986] Input: Each stored data (communication charges, startup time, app usage time, emotional data)

[1987] Data processing:

[1988] Imputing missing data: Imputing missing data using historical average values.

[1989] Outlie...

Claims

1. A means of collecting data such as user communication charges, startup time, and app usage time, means for transmitting the collected data to a server; means for preprocessing received data in the server; AI means for analyzing the pre-processed data; means for generating specific recommendations to the user based on the analysis results; means for delivering the generated proposals to a user terminal; A system including:

2. 2. The system according to claim 1, further comprising means for supplementing missing data from the collected data.

3. 2. The system according to claim 1, further comprising means for identifying trends in frequency of use by time period, peak times of communication charges, activation times and usage times in order to analyze user behavior patterns.

Images