system

Abstract

We provide a system that can reduce the workload of the sales force and improve customer satisfaction. [Solution] A system comprising: data collection means for receiving and storing the user's monthly mobile billing data and packet communication data; data preprocessing means for cleaning the collected data, extracting necessary information, and converting it into an appropriate format; data analysis means for analyzing each user's data usage trends and performing clustering using generative artificial intelligence; suggestion generation means for automatically generating the optimal plan or option for the user based on the analysis results; notification means for notifying the user's terminal of the generated plan or option; feedback collection means for collecting and storing feedback provided by the user; and model improvement means for improving the generative artificial intelligence model based on the collected feedback.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the current provision of mobile communication services, it is very laborious and requires a lot of man-hours to propose optimal plans and options for corporate customers and individual customers. Also, in order to grasp the user's data usage trends in detail and propose an optimal plan based on them, advanced data analysis is required. This increases the burden on the sales team and leads to a decrease in customer satisfaction.

Means for Solving the Problems

[0005] This invention provides a system including data collection means, data preprocessing means, data analysis means, proposal generation means, notification means, feedback collection means, and model improvement means. This system collects monthly mobile billing data and packet communication data, preprocesses this data, and analyzes each user's data usage trends using generative artificial intelligence. Based on the analysis results, it generates optimal plans and options and notifies the user's terminal. Furthermore, it collects feedback from users and improves the model based on this feedback to improve the accuracy of future proposals. In this way, by making optimal proposals based on data, it is possible to reduce the workload of the sales force and improve customer satisfaction.

[0006] "Data collection means" refers to systems and processes for receiving and storing users' monthly mobile billing data and packet communication data.

[0007] "Data preprocessing means" refers to systems and processes for cleaning collected data, extracting necessary information, and converting it into an appropriate format.

[0008] "Data analysis methods" refer to systems and processes that use generative artificial intelligence to analyze data usage trends for each user and perform clustering.

[0009] A "proposal generation method" refers to a system or process that automatically generates the optimal plan or option for the user based on the analysis results.

[0010] A "notification method" refers to a system or process for notifying the user's device of the generated plan or options.

[0011] A "feedback collection method" refers to a system or process for collecting and storing feedback provided by users.

[0012] "Model improvement methods" refer to systems and processes that improve the model of a generative artificial intelligence based on collected feedback, thereby enhancing the accuracy of future suggestions. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0016] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

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

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0030] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] Modes for carrying out the invention

[0035] This invention relates to a system including data collection means, data preprocessing means, data analysis means, suggestion generation means, notification means, feedback collection means, and model improvement means. Through this system, it is possible to automatically collect and analyze a user's monthly mobile billing data and packet communication data, and suggest the optimal mobile plan and options.

[0036] System program and processing details

[0037] This system performs a series of processes from data collection to proposal notification as follows:

[0038] 1. Data collection:

[0039] The server receives each user's monthly mobile billing data and packet communication data and stores it in a database.

[0040] Specific example:

[0041] The device automatically collects the user's data usage history and periodically uploads it to the server.

[0042] The server appropriately classifies the received data and stores it for each user.

[0043] 2. Data preprocessing:

[0044] The server preprocesses the collected data. This includes cleaning the data (handling irregular or missing values) and extracting necessary information (such as call duration and data usage).

[0045] Specific example:

[0046] The server standardizes the data format and supplements any missing data.

[0047] The server removes duplicate and erroneous data to maintain data integrity.

[0048] 3. Data Analysis:

[0049] The server uses generative artificial intelligence to analyze data usage trends for each user. This includes pattern analysis and clustering based on the user's usage history.

[0050] Specific example:

[0051] The server detects call duration, data usage time periods, and monthly usage trends.

[0052] The server groups users with similar usage patterns and understands the characteristics of each group.

[0053] 4. Proposal generation:

[0054] Based on the analysis results, the server generates the optimal mobile plan and options for the user. This includes comparing them to the latest market plans and evaluating their cost-effectiveness.

[0055] Specific example:

[0056] The server selects the plan that best suits the user's usage pattern.

[0057] The server will suggest additional options (such as international call packages and large data packages).

[0058] 5. Notice:

[0059] The server notifies the user's device of the generated suggestions. This includes notifications via email or message.

[0060] Specific example:

[0061] The server sends the proposal to the user's terminal in an easy-to-understand format, allowing the user to easily review the content.

[0062] Users can review the proposed plans on their own devices and change them to a more suitable plan.

[0063] 6. Feedback and Improvement:

[0064] Users provide feedback on the proposed plans and options and send it to the server. The server uses this feedback to improve the generative artificial intelligence model and increase the accuracy of future suggestions.

[0065] Specific example:

[0066] Users provide feedback on their satisfaction with the proposed content and offer their opinions.

[0067] The server analyzes the collected feedback and uses it to improve the model.

[0068] In this way, the system can automatically make optimal suggestions based on data, improve customer satisfaction, and significantly reduce the workload of the sales force.

[0069] The following describes the processing flow.

[0070] Step 1: Data Collection

[0071] The server receives each user's monthly mobile billing data and packet communication data.

[0072] The terminal collects data from the user's device in real time and uploads it to the server periodically.

[0073] Step 2: Reading Storage

[0074] The server saves the received data to the appropriate database.

[0075] The server classifies and organizes data based on each user's identification information.

[0076] Step 3: Data Cleaning

[0077] The server checks for irregular or missing values ​​in the data and corrects or deletes them.

[0078] The server identifies and removes duplicate and erroneous data.

[0079] Step 4: Manufacturing Conversion

[0080] The server converts the data into a unified format (e.g., date and time format, unifying units).

[0081] The server extracts necessary information such as call duration, data usage, and current plan.

[0082] Step 5: Pattern Analysis

[0083] The server uses generative artificial intelligence to analyze each user's data usage patterns.

[0084] The server tracks patterns such as call duration, peak data usage times, and monthly usage based on the user's usage history.

[0085] Step 6: Clustering

[0086] The server clusters user usage patterns.

[0087] The server groups users with similar usage patterns and identifies the characteristics of each group.

[0088] Step 7: Selecting a Plan

[0089] The server compares each user's usage patterns with the latest market plans.

[0090] The server will select the plan that best suits the cost-performance ratio and user needs.

[0091] Step 8: Proposing Options

[0092] The server will offer appropriate options (e.g., international call packages, large data packages) in addition to the basic plan.

[0093] The server also takes into account the user's past option usage history.

[0094] Step 9: Generate Notifications

[0095] The server generates the proposal and compiles it into a format that is easy for the user to understand.

[0096] The server creates the proposal in text message or email format.

[0097] Step 10: User Notifications

[0098] The server sends the generated suggestions to the user's terminal.

[0099] Users review the proposed plan on their own devices and consider changing their plan based on the proposal.

[0100] Step 11: Gathering Feedback

[0101] Users provide feedback on the proposed plans and options.

[0102] The device sends the collected feedback to the server.

[0103] Step 12: Model Improvement

[0104] The server analyzes the collected feedback and improves the generative artificial intelligence model.

[0105] The server uses the feedback to improve the accuracy of its next suggestions.

[0106] This series of processes allows the system to gain a detailed understanding of users' data usage patterns and provide optimal plans. This is expected to reduce sales workload and improve customer satisfaction.

[0107] (Example 1)

[0108] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0109] Current mobile communication systems make it difficult for users to choose the optimal mobile plan and options, and there is no mechanism to automatically provide appropriate suggestions. Therefore, users must research complex plans and options themselves, which is time-consuming and laborious. Furthermore, there is no way to improve the system based on user satisfaction with suggested plans and feedback, making it difficult to improve the accuracy of suggestions.

[0110] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0111] In this invention, the server includes data collection means, data preprocessing means, data analysis means, suggestion generation means, notification means, feedback collection means, model improvement means, a user's mobile terminal, means for storing data collected from the server in a database, means for cleaning and normalizing the collected data, means for analyzing data usage trends and performing clustering using generative artificial intelligence, means for generating optimal mobile plans and options, means for notifying the user of the suggested content, and means for collecting user feedback and improving the model. As a result, the user can be automatically suggested the optimal mobile plan and options, saving time and effort. Furthermore, it becomes possible to improve the accuracy of suggestions based on feedback.

[0112] "Data collection means" refers to methods for collecting user mobile billing data, packet communication data, and other similar information.

[0113] "Data preprocessing means" are methods for cleaning and normalizing collected data. This includes checking and processing irregular or missing values, removing duplicate data, and extracting necessary information.

[0114] "Data analysis methods" refer to methods that use generative artificial intelligence to analyze data usage trends for each user and perform clustering.

[0115] The "proposal generation method" is a means of generating the optimal mobile plan and options for the user based on the analysis results.

[0116] "Notification means" refers to a means of notifying the user's device of the generated proposal content.

[0117] "Feedback collection methods" refer to means of collecting feedback from users.

[0118] "Model improvement methods" refer to techniques for improving the model of a generative artificial intelligence based on collected feedback, thereby enhancing the accuracy of suggestions.

[0119] "User's mobile device" refers to a mobile device such as a smartphone or tablet that the user is using.

[0120] A "server" refers to a computer system that is responsible for collecting, storing, processing, analyzing, and improving data models.

[0121] "Means of saving to a database" refers to the means of classifying and organizing collected data and saving it to a database.

[0122] "Means for cleaning and normalizing collected data" refers to means of ensuring data quality through handling irregular or missing values, removing duplicate data, and standardizing data formats.

[0123] "Generative artificial intelligence" refers to artificial intelligence technology that learns patterns from large amounts of data and generates recommendations.

[0124] Clustering is an analytical technique for grouping data based on similarity.

[0125] "Optimal mobile plans and options" refer to cost-effective mobile communication plans and additional options selected based on the user's data usage trends.

[0126] Modes for carrying out the invention

[0127] This invention relates to a system that analyzes a user's mobile data usage and proposes the optimal mobile plan and options. The system is configured as follows, with each component working in coordination.

[0128] First, the user's mobile device collects their mobile billing data and packet data on a monthly basis and uploads it to the server periodically. This includes a function that automatically sends data when the device detects a Wi-Fi connection.

[0129] The server stores the received data in a database. The database is a storage system that helps classify and organize data, and the data is managed under a specific user ID. Next, the server preprocesses the collected data. Cleaning and normalization are performed, such as detecting and correcting irregular or missing values, removing duplicate data, and standardizing the format. For example, if there is abnormally long call duration data, it will be detected and excluded from the dataset.

[0130] Subsequently, the server uses generative artificial intelligence to analyze the data. The generative AI model learns user usage patterns based on past data and analyzes data usage trends for each user. This is done using prompts such as the following:

[0131] Please perform a pattern analysis including the following user data and propose the optimal mobile plan.

[0132] User ID: 12345

[0133] Monthly call time: 300 minutes

[0134] Monthly data usage: 5GB

[0135] Usage time: Primarily from evening to night

[0136] Current plan: Standard plan

[0137] Feedback: "I would like to consider other large-capacity data plans as well."

[0138] Based on the analysis results, the server generates optimal mobile plan and option suggestions. For example, based on call time and data usage, it can suggest the most cost-effective high-capacity data plan for user A. It can also suggest additional options such as international call packages and data increase packages.

[0139] After a proposal is generated, the server sends a notification to the user's device. This is done via email or push notification, and the proposal is presented in an easy-to-understand format. The user receives the notification, reviews the proposal on their device, and can change to an appropriate plan.

[0140] Furthermore, user feedback is collected and sent to the server. Users click on a provided link and answer a feedback form. This form may include questions such as, "Are you satisfied with this plan proposal?" or "Are there any other options you would like to see?" The server can use the collected feedback to improve the generative artificial intelligence model and enhance the accuracy of future proposals.

[0141] As described above, this system can automatically suggest the optimal mobile plan and options to users through a series of processes, from data collection and analysis to suggestions, notifications, and improvements based on feedback. As a result, users can avoid the hassle of conducting their own research, saving time and effort. Furthermore, by continuously collecting and analyzing feedback, the accuracy of suggestions will improve, and customer satisfaction is expected to increase.

[0142] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0143] Step 1: Data Collection

[0144] Input: Mobile billing data and packet communication data stored on the user's mobile device.

[0145] Specific operation: The device automatically collects monthly data usage, call time, number of text messages, etc. The collected data is periodically uploaded to the server when connected to Wi-Fi.

[0146] Output: Raw data uploaded to the server.

[0147] Step 2: Save

[0148] Input: Raw data uploaded from the device.

[0149] Specific operation: The server stores the received data in the database. It verifies that the data has arrived in the correct format, organizes it by user ID, and stores it in the database.

[0150] Output: Organized and categorized database entries.

[0151] Step 3: Data Preprocessing

[0152] Input: Raw data stored in the database.

[0153] Specific actions: The server performs data cleaning, detecting and correcting irregular and missing values. Furthermore, it removes duplicate data and standardizes all data into a common format. For example, if it contains data with unusually long call durations, it will detect and remove it.

[0154] Output: Preprocessed and consistent data.

[0155] Step 4: Normal Analysis

[0156] Input: Pre-processed data.

[0157] Specific operation: The server analyzes data usage trends using a generative AI model. It learns user usage patterns based on past data and performs clustering. It generates prompt messages, inputs them into the generative AI model, and obtains the analysis results.

[0158] Example prompt: "Perform pattern analysis on the following user data and suggest the optimal mobile plan. User ID: 12345, Monthly call time: 300 minutes, Monthly data usage: 5GB, Usage time: Primarily evening to night, Current plan: Standard plan, Feedback: I would also like to consider other high-capacity data plans."

[0159] Output: Analysis results of data usage trends for each user.

[0160] Step 5: Proposal Generation

[0161] Input: Analysis results of data usage trends.

[0162] Specific operation: The server generates optimal mobile plans and options based on the analysis results. It compares plans that correspond to the user's usage patterns with market data and selects the best plan. It creates a proposal that includes additional options (such as international call packages and data bonus packages).

[0163] Output: A list of mobile plans and options to suggest to the user.

[0164] Step 6: Notification

[0165] Input: A list of proposed mobile plans and options.

[0166] Specific operation: The server sends the proposal to the user's device via email or push notification. This allows the user to review the proposal and change to an appropriate plan.

[0167] Specific example: "Send the proposal in an easy-to-understand format to the user's device, allowing them to easily review the content. Users can then review the proposal on their device and make changes to the plan that best suits them."

[0168] Output: The suggested content that will be displayed on the user's device.

[0169] Step 7: Gathering Feedback and Improving the Model

[0170] Input: User feedback.

[0171] Specific operation: The user provides feedback on the proposed plan and options and sends it to the server. The server uses the collected feedback to improve the generated AI model and increase the accuracy of future suggestions.

[0172] Specific example: "Users provide feedback on their satisfaction with the suggestions and offer opinions. The server uses this feedback to improve the generative artificial intelligence model and enhance the accuracy of future suggestions."

[0173] Output: Improved generative AI model.

[0174] Through the processing steps described above, this system automatically proposes the optimal mobile plan and options to the user, improving customer satisfaction and significantly reducing the workload of the sales team.

[0175] (Application Example 1)

[0176] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0177] Modern e-commerce sites are required to leverage users' purchase and browsing history to provide optimal product recommendations and campaign notifications. However, traditional systems often fail to collect and analyze data effectively, resulting in ineffective recommendations. Furthermore, there is a lack of means to effectively utilize user feedback and continuously improve the accuracy of the system's recommendations. Therefore, a more accurate recommendation system is needed to improve user satisfaction.

[0178] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0179] In this invention, the server includes data collection means, data preprocessing means, data analysis means, suggestion generation means, notification means, feedback collection means, model improvement means, and means for suggesting products and services based on the user's usage history. This makes it possible to suggest optimal products and campaigns based on the user's purchase and browsing history, and to improve the system by collecting feedback from the user.

[0180] "Data collection means" refers to methods for automatically collecting data such as users' purchase history and browsing history and providing it to the system.

[0181] "Data preprocessing means" refers to methods for cleaning collected data and checking and processing irregular values ​​and missing values.

[0182] "Data analysis methods" refer to methods for analyzing collected and pre-processed data and clustering user usage trends using generative artificial intelligence.

[0183] A "proposal generation method" is a means of proposing the most suitable products, services, and campaigns based on the analysis results.

[0184] A "notification method" is a means of notifying the user of the generated proposal content.

[0185] "Feedback collection methods" refer to methods for collecting feedback such as user satisfaction and opinions regarding a proposal.

[0186] "Model improvement methods" refer to methods for improving the model of a generative artificial intelligence system in order to improve the accuracy of the system's suggestions using collected feedback.

[0187] "Methods for suggesting products and services based on user usage history" refers to methods for suggesting optimal products and campaigns based on a user's past purchase and browsing history.

[0188] Modes for carrying out the invention

[0189] The system of this invention includes means for data collection, means for data preprocessing, means for data analysis, means for suggestion generation, means for notification, means for feedback collection, means for model improvement, and means for suggesting products and services based on the user's usage history.

[0190] The server first automatically collects user data such as purchase history and browsing history using data collection tools. This data is sent to the system and stored in a database. Next, data preprocessing tools are used to clean the collected data, checking and processing irregular and missing values, and formatting it into an appropriate format. This improves data consistency and quality, enabling accurate subsequent analysis.

[0191] As a means of data analysis, the server uses generative artificial intelligence to analyze the collected data. Clustering technology is used to identify user usage patterns and classify them into groups with common characteristics. This analysis makes it possible to identify the products and services that are most suitable for each user.

[0192] The suggestion generation system generates optimal products and campaigns for users based on the results of data analysis. Specifically, it makes suggestions that take into account the characteristics of each clustered group. In this process, the server also compares the suggestions with the latest products and campaigns available on the market, enabling it to provide the most useful suggestions for the user.

[0193] The generated suggestions are sent to the user via notification methods. The system is designed to allow users to easily review the suggestions via email or push notifications. Users can view the notification content within the application and easily select and purchase the suggested products and services.

[0194] The feedback collection mechanism gathers user satisfaction and opinions on the suggestions. The server uses this feedback to improve the generative artificial intelligence model, thereby enhancing the accuracy of future suggestions. This allows the system to continuously improve and continue providing valuable suggestions to users.

[0195] The specific hardware and software used include:

[0196] Pandas: Used for data preprocessing and formatting.

[0197] Scikit-learn: Used for data analysis and clustering.

[0198] Notification System API: Sends notifications to users.

[0199] Feedback Collection API: Collects feedback from users.

[0200] As a concrete example, there are cases where notifications about seasonal products or discount campaigns are sent based on a specific user's purchase history. In this case, a generative AI model can be used to make highly accurate suggestions by using the following prompt sentences.

[0201] Example of a prompt:

[0202] Based on users' purchasing patterns and browsing trends, suggest the most suitable products and campaigns. For example, suggest winter seasonal products based on their recent browsing history.

[0203] As described above, this system can achieve highly accurate product recommendations based on user usage history and continuous system improvement through feedback.

[0204] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0205] Step 1:

[0206] Data collection

[0207] The server automatically collects data such as user purchase history and browsing history using data collection methods. Data is periodically sent from each terminal to the server and stored in the database. The input for this step is the user's purchase history and browsing history, and the output is the raw data stored in the database.

[0208] Step 2:

[0209] Data preprocessing

[0210] The server uses data preprocessing techniques to clean the collected data. Specifically, it checks for irregular or missing values ​​and handles them appropriately. It also standardizes the data format and extracts necessary information. The input for this step is raw data, and the output is cleaned, preprocessed data in a standardized format.

[0211] Step 3:

[0212] Data analysis

[0213] The server uses data analysis tools to analyze preprocessed data using generative artificial intelligence. Specifically, it identifies user usage trends using clustering methods (e.g., KMeans). Clustering forms user groups with common characteristics. The input for this step is preprocessed data, and the output is the user clustering result.

[0214] Step 4:

[0215] Proposal generation

[0216] The server uses a suggestion generation mechanism to generate optimal products, services, and campaigns for users based on clustering results. Specifically, it compares the latest market information with the user clustering results and provides optimal suggestions for each user group. The inputs to this step are the clustering results and market information, and the output is the generated suggestions.

[0217] Step 5:

[0218] notification

[0219] The server uses notification methods to inform the user of the generated suggestions. Specifically, it allows the user to easily review the suggestions via email or push notifications. The input for this step is the generated suggestions, and the output is the notification sent to the user.

[0220] Step 6:

[0221] Feedback Collection

[0222] The server uses feedback collection methods to gather user satisfaction levels and opinions on suggestions. Specifically, it collects user-provided feedback data and stores it in a database. The input for this step is user feedback, and the output is the collected feedback data.

[0223] Step 7:

[0224] Model improvements

[0225] The server uses model improvement tools to refine the generative artificial intelligence model based on the collected feedback. Specifically, it analyzes the feedback data and trains the model to improve the accuracy of future suggestions. The input for this step is the feedback data, and the output is the improved generative artificial intelligence model.

[0226] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0227] Modes for carrying out the invention

[0228] This invention relates to a system that includes data collection means, data preprocessing means, data analysis means, suggestion generation means, notification means, feedback collection means, model improvement means, and emotion recognition means. Through this system, the system automatically collects and analyzes the user's monthly mobile billing data and packet communication data, and suggests the optimal mobile plan and options. Furthermore, by recognizing the user's emotions and adjusting the suggestions accordingly, it is possible to provide a more personalized service.

[0229] System program and processing details

[0230] This system performs a series of processes, from data collection to suggestion notification and emotion recognition, as follows:

[0231] 1. Data collection:

[0232] The server receives each user's monthly mobile billing data and packet communication data and stores it in a database.

[0233] Specific example:

[0234] The device automatically collects the user's data usage history and periodically uploads it to the server.

[0235] The server appropriately classifies the received data and stores it for each user.

[0236] 2. Data preprocessing:

[0237] The server preprocesses the collected data. This includes cleaning the data (handling irregular or missing values) and extracting necessary information (such as call duration and data usage).

[0238] Specific example:

[0239] The server standardizes the data format and supplements any missing data.

[0240] The server removes duplicate and erroneous data to maintain data integrity.

[0241] 3. Data Analysis:

[0242] The server uses generative artificial intelligence to analyze data usage trends for each user. This includes pattern analysis and clustering based on the user's usage history.

[0243] Specific example:

[0244] The server detects call duration, data usage time periods, and monthly usage trends.

[0245] The server groups users with similar usage patterns and understands the characteristics of each group.

[0246] 4. Emotion recognition:

[0247] The server uses an emotion engine to recognize the user's emotions, based on feedback and other emotional data provided by the user.

[0248] Specific example:

[0249] The user enters their feelings about the proposal (satisfied, dissatisfied, etc.).

[0250] The server analyzes user feedback and extracts emotional information.

[0251] 5. Proposal generation:

[0252] The server generates the optimal mobile plan and options for the user based on analysis results and sentiment information. This includes comparing them to the latest market plans and evaluating their cost-effectiveness.

[0253] Specific example:

[0254] The server selects the plan that best suits the user's usage patterns and emotions.

[0255] The server will suggest additional options (such as international call packages and large data packages).

[0256] 6. Notice:

[0257] The server notifies the user's device of the generated suggestions. This includes notifications via email or message.

[0258] Specific example:

[0259] The server sends the proposal to the user's terminal in an easy-to-understand format, allowing the user to easily review the content.

[0260] Users can review the proposed plans on their own devices and change them to a more suitable plan.

[0261] 7. Feedback and Improvement:

[0262] Users provide feedback on the proposed plans and options and send it to the server. The server uses this feedback to improve the generative artificial intelligence model and increase the accuracy of future suggestions.

[0263] Specific example:

[0264] Users provide feedback on their satisfaction with the proposed content and offer their opinions.

[0265] The server analyzes the collected feedback and uses it to improve the model.

[0266] In this way, this system not only provides data-driven, automated, and optimal suggestions, but also considers the user's emotions, thereby further improving customer satisfaction. This is expected to reduce sales workload and increase customer satisfaction.

[0267] The following describes the processing flow.

[0268] Step 1: Data Collection

[0269] The server receives each user's monthly mobile billing data and packet communication data.

[0270] The device automatically collects data from the user's device and uploads it to the server periodically.

[0271] The server saves the received data to the database.

[0272] Step 2: Reading Storage

[0273] The server stores the received data in the appropriate database and categorizes it by user.

[0274] The server manages to maintain data integrity.

[0275] Step 3: Data Cleaning

[0276] The server cleans the collected data, checking for irregular or missing values ​​and correcting or deleting them.

[0277] The server identifies and removes duplicate and erroneous data.

[0278] Step 4: Manufacturing Conversion

[0279] The server converts data into a unified format (e.g., date and time format, unit unification).

[0280] The server extracts necessary information such as call duration, data usage, and current plan.

[0281] Step 5: Pattern Analysis

[0282] The server uses generative artificial intelligence to analyze the data usage trends of each user.

[0283] The server grasps patterns such as call duration, peak time zones of data usage, and monthly usage from the user's usage history.

[0284] Step 6: Clustering

[0285] The server clusters the user's usage patterns.

[0286] The server groups users with similar usage patterns and identifies the characteristics of each group.

[0287] Step 7: Emotion Recognition

[0288] The server uses an emotion engine to recognize the user's emotions.

[0289] The user inputs their emotions (satisfaction, dissatisfaction, etc.) towards the proposed content.

[0290] The server analyzes the user's feedback and extracts emotion information.

[0291] Step 8: Plan Selection

[0292] The server compares the usage patterns of each user with the latest plans in the market.

[0293] The server selects the plan that is most suitable for cost performance and the user's needs.

[0294] The server adjusts the proposed content considering the emotional information.

[0295] Step 9: Option Proposal

[0296] In addition to the basic plan, the server proposes appropriate options (e.g., international call pack, large-capacity data pack).

[0297] The server also takes into account the user's past option usage history.

[0298] [[ID=I8]] Step 10: Generation of Proposal Notification

[0299] The server generates the proposed content and summarizes it in a user-friendly format.

[0300] The server creates the proposed content in the form of a text message or email.

[0301] Step 11: User Notification

[0302] The server sends the generated proposed content to the user's terminal.

[0303] The user checks the proposed content on their terminal and considers changing the plan based on the proposed content.

[0304] [[ID=I3]]Step 12: Collection of Feedback

[0305] The user provides feedback on the proposed plan and options.

[0306] The terminal sends the collected feedback to the server.

[0307] Step 13: Improvement of the Model

[0308] The server analyzes the collected feedback and improves the model of the generative artificial intelligence.

[0309] The server uses the feedback to improve the accuracy of its next suggestions.

[0310] This series of steps allows the system to gain a detailed understanding of users' data usage patterns and emotions, enabling it to provide personalized and optimal plans. This is expected to reduce sales workload and improve customer satisfaction.

[0311] (Example 2)

[0312] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0313] Modern telecommunications service users face the challenge of choosing the optimal mobile plan to suit their diverse usage patterns and lifestyles. Furthermore, there is a lack of means to provide personalized services that adequately reflect user satisfaction and feedback on proposed plans. Additionally, there is a lack of approaches that consider user emotions, highlighting the need for effective strategies to improve customer satisfaction.

[0314] In Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes data collection means, data preprocessing means, data analysis means, suggestion generation means, notification means, feedback collection means, model improvement means, and emotion recognition means. This makes it possible to analyze the user's data usage patterns and emotions and propose the optimal mobile plan based on them. Furthermore, by utilizing user feedback to improve the accuracy of suggestions, it is possible to provide more personalized services and increase customer satisfaction.

[0315] "Data collection means" refers to a method for automatically receiving users' monthly mobile billing data and packet communication data and storing it in a database.

[0316] "Data preprocessing means" are methods for cleaning collected data and extracting necessary information. This includes handling irregular values ​​and missing values.

[0317] "Data analysis methods" refer to methods that use generative artificial intelligence to analyze data usage trends for each user and perform clustering.

[0318] A "proposal generation method" is a means of generating the optimal mobile plan and options for the user based on analysis results and sentiment information.

[0319] "Notification method" refers to the means of notifying the user's device of the generated proposal content. This includes notifications via email or message.

[0320] A "feedback collection method" is a means of collecting feedback from users regarding the plans and options they have proposed.

[0321] "Model improvement methods" refer to techniques for improving the model of a generative artificial intelligence based on collected feedback, thereby enhancing the accuracy of suggestions in subsequent iterations.

[0322] An "emotion recognition method" is a means of analyzing user feedback and other emotional data to extract user emotional information.

[0323] Modes for carrying out the invention

[0324] This invention relates to a system including data collection means, data preprocessing means, data analysis means, suggestion generation means, notification means, feedback collection means, model improvement means, and emotion recognition means. Through this system, the system automatically collects the user's monthly mobile billing data and packet communication data and suggests the optimal mobile plan and options. Furthermore, by recognizing the user's emotions and adjusting the suggestions accordingly, it is possible to provide a more personalized service.

[0325] Data collection

[0326] The server receives each user's monthly mobile billing data and packet communication data and stores it in a database. A data collection application is installed on the user's device, which automatically collects data and uploads it to the server periodically. The server uses a database management system (e.g., MySQL®) to appropriately classify the received data and store it for each user.

[0327] Specific example:

[0328] The device collects the user's data usage history every night and uploads it to the server.

[0329] The server receives the collected data and saves it to the database based on the reception date and time and the user ID. The data is saved in JSON format.

[0330] Data preprocessing

[0331] The server preprocesses the collected data. This includes cleaning the data (handling irregular or missing values) and extracting necessary information (e.g., call duration, data usage). The server loads the dataset using the Python Pandas library and converts it to a consistent format.

[0332] Specific example:

[0333] The server detects irregular or missing values ​​and removes or fills them in. For example, if an irregular value is found, the record is deleted, and if there are missing values, they are filled in using the surrounding values.

[0334] The server extracts the necessary information from the cleaned data and prepares it for analysis.

[0335] Data analysis

[0336] The server analyzes user-specific data usage trends using generative artificial intelligence (e.g., models from TENSORFLOW®). This includes pattern analysis and clustering based on user usage history.

[0337] Specific example:

[0338] The server uses a pre-trained generative artificial intelligence model to input collected data and analyze the user's data usage patterns.

[0339] The server uses pattern recognition algorithms to analyze data usage patterns, including time of day and monthly usage. This clarifies user usage patterns.

[0340] The server uses clustering techniques to group users with similar usage patterns and understand the characteristics of each group.

[0341] emotion recognition

[0342] The server uses an emotion engine (e.g., an emotion analysis API) to recognize the user's emotions. It analyzes feedback and other emotion data provided by the user to extract emotional information.

[0343] Specific example:

[0344] Users input their opinions on the proposal and their feelings about their current mobile plan (e.g., satisfied, dissatisfied) through the application's interface.

[0345] The server inputs text data (feedback) collected from users into an emotion engine and extracts emotional information (e.g., positive, negative, neutral).

[0346] Proposal generation

[0347] The server generates the optimal mobile plan and options for the user based on analysis results and sentiment information. This includes comparing them to the latest market plans and evaluating their cost-effectiveness.

[0348] Specific example:

[0349] The server runs an algorithm that takes user usage patterns and sentiment data as input to select the optimal mobile plan. This includes comparing it with the latest market plans and evaluating cost-effectiveness.

[0350] The server combines the selected plan with additional options (e.g., international call package, large data package) to generate a final proposal.

[0351] notification

[0352] The server notifies the user's device of the generated suggestions. This includes notifications via email or message.

[0353] Specific example:

[0354] The server sends the generated suggestions to the user via email or message. Email delivery services or dedicated SMTP servers are used for sending emails.

[0355] Users can review the proposed plan on their device and change to the appropriate plan. Push notifications are also used to indicate when a notification has arrived.

[0356] Feedback and Improvement

[0357] Users provide feedback on the proposed plans and options and send it to the server. The server uses this feedback to improve the generative artificial intelligence model, thereby increasing the accuracy of future suggestions.

[0358] Specific example:

[0359] Users enter their satisfaction level and opinions on the proposed content into the application's feedback form and send it to the server.

[0360] The server inputs the collected feedback data into a generative artificial intelligence model, which is then trained and improved. This improves the accuracy of new suggestions.

[0361] Example of a prompt

[0362] Users are asked to provide data in the form of a message such as, "We will suggest the best plan for you based on your monthly data usage and current mobile plan. Please provide your data."

[0363] keyword

[0364] Generative AI model, prompt sentence

[0365] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0366] System program processing flow

[0367] Step 1: Data Collection

[0368] The server receives the user's monthly mobile billing data and packet communication data and stores it in a database. The input is the data sent from the user's terminal, and the output is the organized data stored in the database.

[0369] Specific actions:

[0370] The device collects the user's data usage history using a data collection application every night and uploads it to the server.

[0371] The server stores the received data in JSON format and categorizes it by each user's ID. A database management system (e.g., MySQL) is used to organize and store this information.

[0372] Step 2: Data preprocessing

[0373] The server preprocesses the collected data. The input is the data collected in step 1, and the output is the cleaned data from which the necessary information has been extracted.

[0374] Specific actions:

[0375] The server loads the dataset using the Python Pandas library and converts it to a consistent format.

[0376] The server detects irregular or missing values ​​and removes or fills them in as needed. Specifically, if an irregular value is found, the record is deleted, and if a missing value exists, it is inferred and filled in from the surrounding data.

[0377] Step 3: Data Analysis

[0378] The server analyzes users' data usage trends using generative artificial intelligence (e.g., TensorFlow). The input is the data preprocessed in step 2, and the output is the usage trends and clustering results for each user.

[0379] Specific actions:

[0380] The server uses a trained artificial intelligence model to input data and analyze user usage patterns.

[0381] The server uses pattern recognition algorithms to analyze data usage patterns, including time of day and monthly usage. Based on this information, it identifies user usage patterns.

[0382] The server uses clustering techniques to group users with similar usage patterns and understands the characteristics of each group.

[0383] Step 4: Emotion Recognition

[0384] The server recognizes the user's emotions using an emotion engine (e.g., an emotion analysis API). The input is feedback data provided by the user, and the output is the analyzed emotion information.

[0385] Specific actions:

[0386] Users input their suggestions and their feelings about their current mobile plan through the application's interface. This input is primarily text data.

[0387] The server inputs text data into the emotion engine and extracts emotional information such as positive, negative, and neutral.

[0388] Step 5: Proposal Generation

[0389] The server generates the optimal mobile plan and options for the user based on the analysis results and sentiment information. The input is the results of steps 3 and 4, and the output is a specific plan proposal for the user.

[0390] Specific actions:

[0391] The server uses usage trend data and sentiment data to run an algorithm and generate the optimal mobile plan.

[0392] The server evaluates and compares the latest market plans to select the most cost-effective one. It also proposes combinations with additional options (e.g., international call packages, large data packages).

[0393] Step 6: Notification

[0394] The server notifies the user's terminal of the generated proposal. The input is the proposal data from step 5, and the output is the notification sent to the user's terminal.

[0395] Specific actions:

[0396] The server sends the proposal to the user via email or message. Email delivery services or dedicated SMTP servers are used for sending.

[0397] Users review the proposed plan on their devices and proceed with the necessary steps to change to the appropriate plan. Push notifications are also used for further notification.

[0398] Step 7: Feedback and Improvement

[0399] Users provide feedback on the proposed plans and options and send it to the server. The input is the user's feedback data, and the output is the result of the model's improvement.

[0400] Specific actions:

[0401] Users enter their satisfaction level and opinions on the proposed content into the application's feedback form and send it to the server.

[0402] The server inputs the collected feedback data into a generative artificial intelligence model, which is then trained and improved. This increases the accuracy of new suggestions.

[0403] (Application Example 2)

[0404] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0405] For autonomous vehicles, there is a lack of systematic methods for providing optimal routes and driving tips based on driving history data and sensor data. Furthermore, the technology for recognizing the driver's emotional state in real time and providing advice based on that is still immature.

[0406] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0407] In this invention, the server includes data collection means, data preprocessing means, data analysis means, emotion recognition means, vehicle driving history data collection means, vehicle sensor data collection means, driving route generation means, and driving advice generation means. This makes it possible to comprehensively analyze the driving history data and sensor data of an autonomous vehicle, as well as the emotional state of the driver, and provide the optimal route and driving tips.

[0408] "Data collection means" refers to means for automatically collecting various types of data from users and vehicles.

[0409] "Data preprocessing means" are methods for cleaning collected data and organizing irregular values, missing values, and duplicate data.

[0410] "Data analysis methods" refer to means for analyzing collected and pre-processed data to extract user usage trends and patterns.

[0411] A "proposal generation method" is a means for generating optimal mobile plans, driving routes, and driving advice based on analysis results.

[0412] A "notification method" is a means of notifying users or vehicles of the generated proposal content.

[0413] A "feedback collection method" is a means of collecting feedback from users regarding their suggestions and incorporating it into the system.

[0414] "Model improvement methods" refer to measures taken to improve the artificial intelligence model based on collected feedback and to enhance the accuracy of future suggestions.

[0415] An "emotion recognition tool" is a means of analyzing the user's emotional state and adjusting the suggested content based on that analysis.

[0416] A "vehicle driving history data collection method" is a means for automatically collecting vehicle driving history data.

[0417] A "vehicle sensor data collection means" is a means for automatically collecting sensor data from a vehicle.

[0418] A "driving route generation means" is a means for generating the optimal driving route based on analyzed data.

[0419] A "driving advice generation method" is a means for generating driving advice for a driver based on data analysis and emotion recognition results.

[0420] This invention is a system for comprehensively collecting and analyzing driving history data, sensor data, and the driver's emotional state from an autonomous vehicle, and for generating optimal routes and driving advice. This system includes means involving a server, a terminal, and a user.

[0421] The server collects driving history data and sensor data from users and vehicles through data collection means. This data collection includes GPS data, vehicle speed data, brake data, accelerator data, etc. In addition, the driver's emotional state (e.g., stress, fatigue) is collected through emotion recognition means.

[0422] In the data preprocessing mechanism, the server cleans the collected data and performs processing to impute irregular values ​​and missing values. The preprocessed data is then analyzed by the data analysis mechanism. Here, a generative AI model is used to analyze each user's driving patterns and sensor data trends, and clustering is performed. In addition, emotional data acquired using the emotion recognition mechanism is also analyzed to understand the driver's emotional state.

[0423] Based on these analysis results, the suggestion generation system generates optimal driving routes and driving advice. For example, it selects routes suitable for specific times of day and weather conditions, and provides driving tips and maintenance advice. It also provides advice tailored to the driver's emotional state, supporting them in driving safely and comfortably.

[0424] The notification system sends generated driving routes and advice to the user's device. The user reviews the notification and incorporates the driving routes and advice as needed. Furthermore, the user can provide feedback on the suggestions, which is sent to the server by the feedback collection system.

[0425] Through model improvement mechanisms, the server analyzes collected feedback and improves the generated AI model. This improves the accuracy of future suggestions and enables more personalized driving support.

[0426] As a concrete example, consider a case where driving history data, sensor data, and emotion data associated with a vehicle ID "ABC123" are collected and analyzed.

[0427] As an example of a prompt, you could instruct the generating AI model with a message like, "Collect and analyze vehicle driving history data, sensor data, and driver emotion data to generate the optimal route, driving tips, and emotion-based advice."

[0428] Based on the above, this system can comprehensively analyze the driving history data and sensor data of autonomous vehicles, as well as the driver's emotional state, to provide optimal driving routes and advice.

[0429] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0430] Step 1: Data Collection

[0431] The server automatically collects driving history data, sensor data, and sentiment data from users and vehicles using data collection methods. Examples include GPS data, vehicle speed data, brake data, and accelerator data. Input is raw data from users and vehicles, and output is the collected dataset.

[0432] Step 2: Data Preprocessing

[0433] The server cleans the collected data using data preprocessing techniques. This process ensures data integrity by imputing irregular or missing values. Specifically, it standardizes data formats, imputes missing data, and removes duplicate data. The input is the collected dataset, and the output is the cleaned data.

[0434] Step 3: Data Analysis

[0435] The server analyzes pre-processed data using data analysis tools. Here, a generative AI model is used to analyze user-specific driving patterns and sensor data trends, and clustering is performed. Furthermore, emotional data acquired by emotion recognition tools is also analyzed to understand the driver's emotional state. The input is cleaned data, and the output is the analysis result.

[0436] Step 4: Proposal Generation

[0437] The server uses a suggestion generation mechanism to generate optimal driving routes and driving advice based on the analysis results. For example, it selects routes suitable for specific time periods and weather conditions, and provides driving tips and maintenance advice. It also provides advice tailored to the user's emotional state. The input is the analysis results, and the output is the generated suggestions.

[0438] Step 5: Notification

[0439] The system uses a notification method to send generated driving routes and advice to the user's device. The user reviews the notification and incorporates the driving routes and advice as needed. The input is the generated suggestions, and the output is the notification sent to the user.

[0440] Step 6: Gathering Feedback

[0441] Users provide feedback on the proposed content. This feedback is sent to the server through a feedback collection mechanism. The input is the user's feedback, and the output is the collected feedback data.

[0442] Step 7: Model Improvement

[0443] The server uses model improvement tools to refine the generative AI model based on the collected feedback. This improves the accuracy of the next proposal. The input is the collected feedback data, and the output is the improved generative AI model.

[0444] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0445] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0446] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0447] [Second Embodiment]

[0448] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0449] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0450] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0451] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0452] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0453] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0454] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0455] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0456] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0457] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0458] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0459] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0460] Modes for carrying out the invention

[0461] This invention relates to a system including data collection means, data preprocessing means, data analysis means, suggestion generation means, notification means, feedback collection means, and model improvement means. Through this system, it is possible to automatically collect and analyze a user's monthly mobile billing data and packet communication data, and suggest the optimal mobile plan and options.

[0462] System program and processing details

[0463] This system performs a series of processes from data collection to proposal notification as follows:

[0464] 1. Data collection:

[0465] The server receives each user's monthly mobile billing data and packet communication data and stores it in a database.

[0466] Specific example:

[0467] The device automatically collects the user's data usage history and periodically uploads it to the server.

[0468] The server appropriately classifies the received data and stores it for each user.

[0469] 2. Data preprocessing:

[0470] The server preprocesses the collected data. This includes cleaning the data (handling irregular or missing values) and extracting necessary information (such as call duration and data usage).

[0471] Specific example:

[0472] The server standardizes the data format and supplements any missing data.

[0473] The server removes duplicate and erroneous data to maintain data integrity.

[0474] 3. Data Analysis:

[0475] The server uses generative artificial intelligence to analyze data usage trends for each user. This includes pattern analysis and clustering based on the user's usage history.

[0476] Specific example:

[0477] The server detects call duration, data usage time periods, and monthly usage trends.

[0478] The server groups users with similar usage patterns and understands the characteristics of each group.

[0479] 4. Proposal generation:

[0480] Based on the analysis results, the server generates the optimal mobile plan and options for the user. This includes comparing them to the latest market plans and evaluating their cost-effectiveness.

[0481] Specific example:

[0482] The server selects the plan that best suits the user's usage pattern.

[0483] The server will suggest additional options (such as international call packages and large data packages).

[0484] 5. Notice:

[0485] The server notifies the user's device of the generated suggestions. This includes notifications via email or message.

[0486] Specific example:

[0487] The server sends the proposal to the user's terminal in an easy-to-understand format, allowing the user to easily review the content.

[0488] Users can review the proposed plans on their own devices and change them to a more suitable plan.

[0489] 6. Feedback and Improvement:

[0490] Users provide feedback on the proposed plans and options and send it to the server. The server uses this feedback to improve the generative artificial intelligence model and increase the accuracy of future suggestions.

[0491] Specific example:

[0492] Users provide feedback on their satisfaction with the proposed content and offer their opinions.

[0493] The server analyzes the collected feedback and uses it to improve the model.

[0494] In this way, the system can automatically make optimal suggestions based on data, improve customer satisfaction, and significantly reduce the workload of the sales force.

[0495] The following describes the processing flow.

[0496] Step 1: Data Collection

[0497] The server receives each user's monthly mobile billing data and packet communication data.

[0498] The terminal collects data from the user's device in real time and uploads it to the server periodically.

[0499] Step 2: Reading Storage

[0500] The server saves the received data to the appropriate database.

[0501] The server classifies and organizes data based on each user's identification information.

[0502] Step 3: Data Cleaning

[0503] The server checks for irregular or missing values ​​in the data and corrects or deletes them.

[0504] The server identifies and removes duplicate and erroneous data.

[0505] Step 4: Manufacturing Conversion

[0506] The server converts the data into a unified format (e.g., date and time format, unifying units).

[0507] The server extracts necessary information such as call duration, data usage, and current plan.

[0508] Step 5: Pattern Analysis

[0509] The server uses generative artificial intelligence to analyze each user's data usage patterns.

[0510] The server tracks patterns such as call duration, peak data usage times, and monthly usage based on the user's usage history.

[0511] Step 6: Clustering

[0512] The server clusters user usage patterns.

[0513] The server groups users with similar usage patterns and identifies the characteristics of each group.

[0514] Step 7: Selecting a Plan

[0515] The server compares each user's usage patterns with the latest market plans.

[0516] The server will select the plan that best suits the cost-performance ratio and user needs.

[0517] Step 8: Proposing Options

[0518] The server will offer appropriate options (e.g., international call packages, large data packages) in addition to the basic plan.

[0519] The server also takes into account the user's past option usage history.

[0520] Step 9: Generate Notifications

[0521] The server generates the proposal and compiles it into a format that is easy for the user to understand.

[0522] The server creates the proposal in text message or email format.

[0523] Step 10: User Notifications

[0524] The server sends the generated suggestions to the user's terminal.

[0525] Users review the proposed plan on their own devices and consider changing their plan based on the proposal.

[0526] Step 11: Gathering Feedback

[0527] Users provide feedback on the proposed plans and options.

[0528] The device sends the collected feedback to the server.

[0529] Step 12: Model Improvement

[0530] The server analyzes the collected feedback and improves the generative artificial intelligence model.

[0531] The server uses the feedback to improve the accuracy of its next suggestions.

[0532] This series of processes allows the system to gain a detailed understanding of users' data usage patterns and provide optimal plans. This is expected to reduce sales workload and improve customer satisfaction.

[0533] (Example 1)

[0534] Next, we will describe Example 1. 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".

[0535] Current mobile communication systems make it difficult for users to choose the optimal mobile plan and options, and there is no mechanism to automatically provide appropriate suggestions. Therefore, users must research complex plans and options themselves, which is time-consuming and laborious. Furthermore, there is no way to improve the system based on user satisfaction with suggested plans and feedback, making it difficult to improve the accuracy of suggestions.

[0536] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0537] In this invention, the server includes data collection means, data preprocessing means, data analysis means, suggestion generation means, notification means, feedback collection means, model improvement means, a user's mobile terminal, means for storing data collected from the server in a database, means for cleaning and normalizing the collected data, means for analyzing data usage trends and performing clustering using generative artificial intelligence, means for generating optimal mobile plans and options, means for notifying the user of the suggested content, and means for collecting user feedback and improving the model. As a result, the user can be automatically suggested the optimal mobile plan and options, saving time and effort. Furthermore, it becomes possible to improve the accuracy of suggestions based on feedback.

[0538] "Data collection means" refers to methods for collecting user mobile billing data, packet communication data, and other similar information.

[0539] "Data preprocessing means" are methods for cleaning and normalizing collected data. This includes checking and processing irregular or missing values, removing duplicate data, and extracting necessary information.

[0540] "Data analysis methods" refer to methods that use generative artificial intelligence to analyze data usage trends for each user and perform clustering.

[0541] The "proposal generation method" is a means of generating the optimal mobile plan and options for the user based on the analysis results.

[0542] "Notification means" refers to a means of notifying the user's device of the generated proposal content.

[0543] "Feedback collection methods" refer to means of collecting feedback from users.

[0544] "Model improvement methods" refer to techniques for improving the model of a generative artificial intelligence based on collected feedback, thereby enhancing the accuracy of suggestions.

[0545] "User's mobile device" refers to a mobile device such as a smartphone or tablet that the user is using.

[0546] A "server" refers to a computer system that is responsible for collecting, storing, processing, analyzing, and improving data models.

[0547] "Means of saving to a database" refers to the means of classifying and organizing collected data and saving it to a database.

[0548] "Means for cleaning and normalizing collected data" refers to means of ensuring data quality through handling irregular or missing values, removing duplicate data, and standardizing data formats.

[0549] "Generative artificial intelligence" refers to artificial intelligence technology that learns patterns from large amounts of data and generates recommendations.

[0550] Clustering is an analytical technique for grouping data based on similarity.

[0551] "Optimal mobile plans and options" refer to cost-effective mobile communication plans and additional options selected based on the user's data usage trends.

[0552] Modes for carrying out the invention

[0553] This invention relates to a system that analyzes a user's mobile data usage and proposes the optimal mobile plan and options. The system is configured as follows, with each component working in coordination.

[0554] First, the user's mobile device collects their mobile billing data and packet data on a monthly basis and uploads it to the server periodically. This includes a function that automatically sends data when the device detects a Wi-Fi connection.

[0555] The server stores the received data in a database. The database is a storage system that helps classify and organize data, and the data is managed under a specific user ID. Next, the server preprocesses the collected data. Cleaning and normalization are performed, such as detecting and correcting irregular or missing values, removing duplicate data, and standardizing the format. For example, if there is abnormally long call duration data, it will be detected and excluded from the dataset.

[0556] Subsequently, the server uses generative artificial intelligence to analyze the data. The generative AI model learns user usage patterns based on past data and analyzes data usage trends for each user. This is done using prompts such as the following:

[0557] Please perform a pattern analysis including the following user data and propose the optimal mobile plan.

[0558] User ID: 12345

[0559] Monthly call time: 300 minutes

[0560] Monthly data usage: 5GB

[0561] Usage time: Primarily from evening to night

[0562] Current plan: Standard plan

[0563] Feedback: "I would like to consider other large-capacity data plans as well."

[0564] Based on the analysis results, the server generates optimal mobile plan and option suggestions. For example, based on call time and data usage, it can suggest the most cost-effective high-capacity data plan for user A. It can also suggest additional options such as international call packages and data increase packages.

[0565] After a proposal is generated, the server sends a notification to the user's device. This is done via email or push notification, and the proposal is presented in an easy-to-understand format. The user receives the notification, reviews the proposal on their device, and can change to an appropriate plan.

[0566] Furthermore, user feedback is collected and sent to the server. Users click on a provided link and answer a feedback form. This form may include questions such as, "Are you satisfied with this plan proposal?" or "Are there any other options you would like to see?" The server can use the collected feedback to improve the generative artificial intelligence model and enhance the accuracy of future proposals.

[0567] As described above, this system can automatically suggest the optimal mobile plan and options to users through a series of processes, from data collection and analysis to suggestions, notifications, and improvements based on feedback. As a result, users can avoid the hassle of conducting their own research, saving time and effort. Furthermore, by continuously collecting and analyzing feedback, the accuracy of suggestions will improve, and customer satisfaction is expected to increase.

[0568] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0569] Step 1: Data Collection

[0570] Input: Mobile billing data and packet communication data stored on the user's mobile device.

[0571] Specific operation: The device automatically collects monthly data usage, call time, number of text messages, etc. The collected data is periodically uploaded to the server when connected to Wi-Fi.

[0572] Output: Raw data uploaded to the server.

[0573] Step 2: Save

[0574] Input: Raw data uploaded from the device.

[0575] Specific operation: The server stores the received data in the database. It verifies that the data has arrived in the correct format, organizes it by user ID, and stores it in the database.

[0576] Output: Organized and categorized database entries.

[0577] Step 3: Data Preprocessing

[0578] Input: Raw data stored in the database.

[0579] Specific actions: The server performs data cleaning, detecting and correcting irregular and missing values. Furthermore, it removes duplicate data and standardizes all data into a common format. For example, if it contains data with unusually long call durations, it will detect and remove it.

[0580] Output: Preprocessed and consistent data.

[0581] Step 4: Normal Analysis

[0582] Input: Pre-processed data.

[0583] Specific operation: The server analyzes data usage trends using a generative AI model. It learns user usage patterns based on past data and performs clustering. It generates prompt messages, inputs them into the generative AI model, and obtains the analysis results.

[0584] Example prompt: "Perform pattern analysis on the following user data and suggest the optimal mobile plan. User ID: 12345, Monthly call time: 300 minutes, Monthly data usage: 5GB, Usage time: Primarily evening to night, Current plan: Standard plan, Feedback: I would also like to consider other high-capacity data plans."

[0585] Output: Analysis results of data usage trends for each user.

[0586] Step 5: Proposal Generation

[0587] Input: Analysis results of data usage trends.

[0588] Specific operation: The server generates optimal mobile plans and options based on the analysis results. It compares plans that correspond to the user's usage patterns with market data and selects the best plan. It creates a proposal that includes additional options (such as international call packages and data bonus packages).

[0589] Output: A list of mobile plans and options to suggest to the user.

[0590] Step 6: Notification

[0591] Input: A list of proposed mobile plans and options.

[0592] Specific operation: The server sends the proposal to the user's device via email or push notification. This allows the user to review the proposal and change to an appropriate plan.

[0593] Specific example: "Send the proposal in an easy-to-understand format to the user's device, allowing them to easily review the content. Users can then review the proposal on their device and make changes to the plan that best suits them."

[0594] Output: The suggested content that will be displayed on the user's device.

[0595] Step 7: Gathering Feedback and Improving the Model

[0596] Input: User feedback.

[0597] Specific operation: The user provides feedback on the proposed plan and options and sends it to the server. The server uses the collected feedback to improve the generated AI model and increase the accuracy of future suggestions.

[0598] Specific example: "Users provide feedback on their satisfaction with the suggestions and offer opinions. The server uses this feedback to improve the generative artificial intelligence model and enhance the accuracy of future suggestions."

[0599] Output: Improved generative AI model.

[0600] Through the processing steps described above, this system automatically proposes the optimal mobile plan and options to the user, improving customer satisfaction and significantly reducing the workload of the sales team.

[0601] (Application Example 1)

[0602] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0603] Modern e-commerce sites are required to leverage users' purchase and browsing history to provide optimal product recommendations and campaign notifications. However, traditional systems often fail to collect and analyze data effectively, resulting in ineffective recommendations. Furthermore, there is a lack of means to effectively utilize user feedback and continuously improve the accuracy of the system's recommendations. Therefore, a more accurate recommendation system is needed to improve user satisfaction.

[0604] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0605] In this invention, the server includes data collection means, data preprocessing means, data analysis means, suggestion generation means, notification means, feedback collection means, model improvement means, and means for suggesting products and services based on the user's usage history. This makes it possible to suggest optimal products and campaigns based on the user's purchase and browsing history, and to improve the system by collecting feedback from the user.

[0606] "Data collection means" refers to methods for automatically collecting data such as users' purchase history and browsing history and providing it to the system.

[0607] "Data preprocessing means" refers to methods for cleaning collected data and checking and processing irregular values ​​and missing values.

[0608] "Data analysis methods" refer to methods for analyzing collected and pre-processed data and clustering user usage trends using generative artificial intelligence.

[0609] A "proposal generation method" is a means of proposing the most suitable products, services, and campaigns based on the analysis results.

[0610] A "notification method" is a means of notifying the user of the generated proposal content.

[0611] "Feedback collection methods" refer to methods for collecting feedback such as user satisfaction and opinions regarding a proposal.

[0612] "Model improvement methods" refer to methods for improving the model of a generative artificial intelligence system in order to improve the accuracy of the system's suggestions using collected feedback.

[0613] "Methods for suggesting products and services based on user usage history" refers to methods for suggesting optimal products and campaigns based on a user's past purchase and browsing history.

[0614] Modes for carrying out the invention

[0615] The system of this invention includes means for data collection, means for data preprocessing, means for data analysis, means for suggestion generation, means for notification, means for feedback collection, means for model improvement, and means for suggesting products and services based on the user's usage history.

[0616] The server first automatically collects user data such as purchase history and browsing history using data collection tools. This data is sent to the system and stored in a database. Next, data preprocessing tools are used to clean the collected data, checking and processing irregular and missing values, and formatting it into an appropriate format. This improves data consistency and quality, enabling accurate subsequent analysis.

[0617] As a means of data analysis, the server uses generative artificial intelligence to analyze the collected data. Clustering technology is used to identify user usage patterns and classify them into groups with common characteristics. This analysis makes it possible to identify the products and services that are most suitable for each user.

[0618] The suggestion generation system generates optimal products and campaigns for users based on the results of data analysis. Specifically, it makes suggestions that take into account the characteristics of each clustered group. In this process, the server also compares the suggestions with the latest products and campaigns available on the market, enabling it to provide the most useful suggestions for the user.

[0619] The generated suggestions are sent to the user via notification methods. The system is designed to allow users to easily review the suggestions via email or push notifications. Users can view the notification content within the application and easily select and purchase the suggested products and services.

[0620] The feedback collection mechanism gathers user satisfaction and opinions on the suggestions. The server uses this feedback to improve the generative artificial intelligence model, thereby enhancing the accuracy of future suggestions. This allows the system to continuously improve and continue providing valuable suggestions to users.

[0621] The specific hardware and software used include:

[0622] Pandas: Used for data preprocessing and formatting.

[0623] Scikit-learn: Used for data analysis and clustering.

[0624] Notification System API: Sends notifications to users.

[0625] Feedback Collection API: Collects feedback from users.

[0626] As a concrete example, there are cases where notifications about seasonal products or discount campaigns are sent based on a specific user's purchase history. In this case, a generative AI model can be used to make highly accurate suggestions by using the following prompt sentences.

[0627] Example of a prompt:

[0628] Based on users' purchasing patterns and browsing trends, suggest the most suitable products and campaigns. For example, suggest winter seasonal products based on their recent browsing history.

[0629] As described above, this system can achieve highly accurate product recommendations based on user usage history and continuous system improvement through feedback.

[0630] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0631] Step 1:

[0632] Data collection

[0633] The server automatically collects data such as user purchase history and browsing history using data collection methods. Data is periodically sent from each terminal to the server and stored in the database. The input for this step is the user's purchase history and browsing history, and the output is the raw data stored in the database.

[0634] Step 2:

[0635] Data preprocessing

[0636] The server uses data preprocessing techniques to clean the collected data. Specifically, it checks for irregular or missing values ​​and handles them appropriately. It also standardizes the data format and extracts necessary information. The input for this step is raw data, and the output is cleaned, preprocessed data in a standardized format.

[0637] Step 3:

[0638] Data analysis

[0639] The server uses data analysis tools to analyze preprocessed data using generative artificial intelligence. Specifically, it identifies user usage trends using clustering methods (e.g., KMeans). Clustering forms user groups with common characteristics. The input for this step is preprocessed data, and the output is the user clustering result.

[0640] Step 4:

[0641] Proposal generation

[0642] The server uses a suggestion generation mechanism to generate optimal products, services, and campaigns for users based on clustering results. Specifically, it compares the latest market information with the user clustering results and provides optimal suggestions for each user group. The inputs to this step are the clustering results and market information, and the output is the generated suggestions.

[0643] Step 5:

[0644] notification

[0645] The server uses notification methods to inform the user of the generated suggestions. Specifically, it allows the user to easily review the suggestions via email or push notifications. The input for this step is the generated suggestions, and the output is the notification sent to the user.

[0646] Step 6:

[0647] Feedback Collection

[0648] The server uses feedback collection methods to gather user satisfaction levels and opinions on suggestions. Specifically, it collects user-provided feedback data and stores it in a database. The input for this step is user feedback, and the output is the collected feedback data.

[0649] Step 7:

[0650] Model improvements

[0651] The server uses model improvement tools to refine the generative artificial intelligence model based on the collected feedback. Specifically, it analyzes the feedback data and trains the model to improve the accuracy of future suggestions. The input for this step is the feedback data, and the output is the improved generative artificial intelligence model.

[0652] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0653] Modes for carrying out the invention

[0654] This invention relates to a system that includes data collection means, data preprocessing means, data analysis means, suggestion generation means, notification means, feedback collection means, model improvement means, and emotion recognition means. Through this system, the system automatically collects and analyzes the user's monthly mobile billing data and packet communication data, and suggests the optimal mobile plan and options. Furthermore, by recognizing the user's emotions and adjusting the suggestions accordingly, it is possible to provide a more personalized service.

[0655] System program and processing details

[0656] This system performs a series of processes, from data collection to suggestion notification and emotion recognition, as follows:

[0657] 1. Data collection:

[0658] The server receives each user's monthly mobile billing data and packet communication data and stores it in a database.

[0659] Specific example:

[0660] The device automatically collects the user's data usage history and periodically uploads it to the server.

[0661] The server appropriately classifies the received data and stores it for each user.

[0662] 2. Data preprocessing:

[0663] The server preprocesses the collected data. This includes cleaning the data (handling irregular or missing values) and extracting necessary information (such as call duration and data usage).

[0664] Specific example:

[0665] The server standardizes the data format and supplements any missing data.

[0666] The server removes duplicate and erroneous data to maintain data integrity.

[0667] 3. Data Analysis:

[0668] The server uses generative artificial intelligence to analyze data usage trends for each user. This includes pattern analysis and clustering based on the user's usage history.

[0669] Specific example:

[0670] The server detects call duration, data usage time periods, and monthly usage trends.

[0671] The server groups users with similar usage patterns and understands the characteristics of each group.

[0672] 4. Emotion recognition:

[0673] The server uses an emotion engine to recognize the user's emotions, based on feedback and other emotional data provided by the user.

[0674] Specific example:

[0675] The user enters their feelings about the proposal (satisfied, dissatisfied, etc.).

[0676] The server analyzes user feedback and extracts emotional information.

[0677] 5. Proposal generation:

[0678] The server generates the optimal mobile plan and options for the user based on analysis results and sentiment information. This includes comparing them to the latest market plans and evaluating their cost-effectiveness.

[0679] Specific example:

[0680] The server selects the plan that best suits the user's usage patterns and emotions.

[0681] The server will suggest additional options (such as international call packages and large data packages).

[0682] 6. Notice:

[0683] The server notifies the user's device of the generated suggestions. This includes notifications via email or message.

[0684] Specific example:

[0685] The server sends the proposal to the user's terminal in an easy-to-understand format, allowing the user to easily review the content.

[0686] Users can review the proposed plans on their own devices and change them to a more suitable plan.

[0687] 7. Feedback and Improvement:

[0688] Users provide feedback on the proposed plans and options and send it to the server. The server uses this feedback to improve the generative artificial intelligence model and increase the accuracy of future suggestions.

[0689] Specific example:

[0690] Users provide feedback on their satisfaction with the proposed content and offer their opinions.

[0691] The server analyzes the collected feedback and uses it to improve the model.

[0692] In this way, this system not only provides data-driven, automated, and optimal suggestions, but also considers the user's emotions, thereby further improving customer satisfaction. This is expected to reduce sales workload and increase customer satisfaction.

[0693] The following describes the processing flow.

[0694] Step 1: Data Collection

[0695] The server receives each user's monthly mobile billing data and packet communication data.

[0696] The device automatically collects data from the user's device and uploads it to the server periodically.

[0697] The server saves the received data to the database.

[0698] Step 2: Reading Storage

[0699] The server stores the received data in the appropriate database and categorizes it by user.

[0700] The server manages to maintain data integrity.

[0701] Step 3: Data Cleaning

[0702] The server cleans the collected data, checking for irregular or missing values ​​and correcting or deleting them.

[0703] The server identifies and removes duplicate and erroneous data.

[0704] Step 4: Manufacturing Conversion

[0705] The server converts the data into a unified format (e.g., date and time format, unified units).

[0706] The server extracts necessary information, such as call duration, data usage, and current plan.

[0707] Step 5: Pattern Analysis

[0708] The server uses generative artificial intelligence to analyze each user's data usage patterns.

[0709] The server tracks patterns such as call duration, peak data usage times, and monthly usage based on the user's usage history.

[0710] Step 6: Clustering

[0711] The server clusters user usage patterns.

[0712] The server groups users with similar usage patterns and identifies the characteristics of each group.

[0713] Step 7: Emotion Recognition

[0714] The server uses an emotion engine to recognize the user's emotions.

[0715] The user enters their feelings about the proposal (satisfied, dissatisfied, etc.).

[0716] The server analyzes user feedback and extracts emotional information.

[0717] Step 8: Selecting a Plan

[0718] The server compares each user's usage patterns with the latest market plans.

[0719] The server selects the plan that best suits the cost-performance ratio and user needs.

[0720] The server adjusts the suggestions based on emotional information.

[0721] Step 9: Proposing Options

[0722] The server will offer appropriate options (e.g., international call packages, large data packages) in addition to the basic plan.

[0723] The server also takes into account the user's past option usage history.

[0724] Step 10: Generating the proposal notification

[0725] The server generates the proposal and compiles it into a format that is easy for the user to understand.

[0726] The server creates the proposal in text message or email format.

[0727] Step 11: User Notifications

[0728] The server sends the generated suggestions to the user's terminal.

[0729] Users review the proposed plan on their own devices and consider changing their plan based on the proposal.

[0730] Step 12: Gathering Feedback

[0731] Users provide feedback on the proposed plans and options.

[0732] The device sends the collected feedback to the server.

[0733] Step 13: Model Improvement

[0734] The server analyzes the collected feedback and improves the generative artificial intelligence model.

[0735] The server uses the feedback to improve the accuracy of its next suggestions.

[0736] This series of steps allows the system to gain a detailed understanding of users' data usage patterns and emotions, enabling it to provide personalized and optimal plans. This is expected to reduce sales workload and improve customer satisfaction.

[0737] (Example 2)

[0738] Next, we will describe Example 2. 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".

[0739] Modern telecommunications service users face the challenge of choosing the optimal mobile plan to suit their diverse usage patterns and lifestyles. Furthermore, there is a lack of means to provide personalized services that adequately reflect user satisfaction and feedback on proposed plans. Additionally, there is a lack of approaches that consider user emotions, highlighting the need for effective strategies to improve customer satisfaction.

[0740] In Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes data collection means, data preprocessing means, data analysis means, suggestion generation means, notification means, feedback collection means, model improvement means, and emotion recognition means. This makes it possible to analyze the user's data usage patterns and emotions and propose the optimal mobile plan based on them. Furthermore, by utilizing user feedback to improve the accuracy of suggestions, it is possible to provide more personalized services and increase customer satisfaction.

[0741] "Data collection means" refers to a method for automatically receiving users' monthly mobile billing data and packet communication data and storing it in a database.

[0742] "Data preprocessing means" are methods for cleaning collected data and extracting necessary information. This includes handling irregular values ​​and missing values.

[0743] "Data analysis methods" refer to methods that use generative artificial intelligence to analyze data usage trends for each user and perform clustering.

[0744] A "proposal generation method" is a means of generating the optimal mobile plan and options for the user based on analysis results and sentiment information.

[0745] "Notification method" refers to the means of notifying the user's device of the generated proposal content. This includes notifications via email or message.

[0746] A "feedback collection method" is a means of collecting feedback from users regarding the plans and options they have proposed.

[0747] "Model improvement methods" refer to techniques for improving the model of a generative artificial intelligence based on collected feedback, thereby enhancing the accuracy of suggestions in subsequent iterations.

[0748] An "emotion recognition method" is a means of analyzing user feedback and other emotional data to extract user emotional information.

[0749] Modes for carrying out the invention

[0750] This invention relates to a system including data collection means, data preprocessing means, data analysis means, suggestion generation means, notification means, feedback collection means, model improvement means, and emotion recognition means. Through this system, the system automatically collects the user's monthly mobile billing data and packet communication data and suggests the optimal mobile plan and options. Furthermore, by recognizing the user's emotions and adjusting the suggestions accordingly, it is possible to provide a more personalized service.

[0751] Data collection

[0752] The server receives each user's monthly mobile billing data and packet communication data and stores it in a database. A data collection application is installed on the user's device, which automatically collects data and uploads it to the server periodically. The server uses a database management system (e.g., MySQL) to appropriately classify the received data and store it for each user.

[0753] Specific example:

[0754] The device collects the user's data usage history every night and uploads it to the server.

[0755] The server receives the collected data and saves it to the database based on the reception date and time and the user ID. The data is saved in JSON format.

[0756] Data preprocessing

[0757] The server preprocesses the collected data. This includes cleaning the data (handling irregular or missing values) and extracting necessary information (e.g., call duration, data usage). The server loads the dataset using the Python Pandas library and converts it to a consistent format.

[0758] Specific example:

[0759] The server detects irregular or missing values ​​and removes or fills them in. For example, if an irregular value is found, the record is deleted, and if there are missing values, they are filled in using the surrounding values.

[0760] The server extracts the necessary information from the cleaned data and prepares it for analysis.

[0761] Data analysis

[0762] The server analyzes user-specific data usage trends using generative artificial intelligence (e.g., TensorFlow models). This includes pattern analysis and clustering based on user usage history.

[0763] Specific example:

[0764] The server uses a pre-trained generative artificial intelligence model to input collected data and analyze the user's data usage patterns.

[0765] The server uses pattern recognition algorithms to analyze data usage patterns, including time of day and monthly usage. This clarifies user usage patterns.

[0766] The server uses clustering techniques to group users with similar usage patterns and understand the characteristics of each group.

[0767] emotion recognition

[0768] The server uses an emotion engine (e.g., an emotion analysis API) to recognize the user's emotions. It analyzes feedback and other emotion data provided by the user to extract emotional information.

[0769] Specific example:

[0770] Users input their opinions on the proposal and their feelings about their current mobile plan (e.g., satisfied, dissatisfied) through the application's interface.

[0771] The server inputs text data (feedback) collected from users into an emotion engine and extracts emotional information (e.g., positive, negative, neutral).

[0772] Proposal generation

[0773] The server generates the optimal mobile plan and options for the user based on analysis results and sentiment information. This includes comparing them to the latest market plans and evaluating their cost-effectiveness.

[0774] Specific example:

[0775] The server runs an algorithm that takes user usage patterns and sentiment data as input to select the optimal mobile plan. This includes comparing it with the latest market plans and evaluating cost-effectiveness.

[0776] The server combines the selected plan with additional options (e.g., international call package, large data package) to generate a final proposal.

[0777] notification

[0778] The server notifies the user's device of the generated suggestions. This includes notifications via email or message.

[0779] Specific example:

[0780] The server sends the generated suggestions to the user via email or message. Email delivery services or dedicated SMTP servers are used for sending emails.

[0781] Users can review the proposed plan on their device and change to the appropriate plan. Push notifications are also used to indicate when a notification has arrived.

[0782] Feedback and Improvement

[0783] Users provide feedback on the proposed plans and options and send it to the server. The server uses this feedback to improve the generative artificial intelligence model, thereby increasing the accuracy of future suggestions.

[0784] Specific example:

[0785] Users enter their satisfaction level and opinions on the proposed content into the application's feedback form and send it to the server.

[0786] The server inputs the collected feedback data into a generative artificial intelligence model, which is then trained and improved. This improves the accuracy of new suggestions.

[0787] Example of a prompt

[0788] Users are asked to provide data in the form of a message such as, "We will suggest the best plan for you based on your monthly data usage and current mobile plan. Please provide your data."

[0789] keyword

[0790] Generative AI model, prompt sentence

[0791] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0792] System program processing flow

[0793] Step 1: Data Collection

[0794] The server receives the user's monthly mobile billing data and packet communication data and stores it in a database. The input is the data sent from the user's terminal, and the output is the organized data stored in the database.

[0795] Specific actions:

[0796] The device collects the user's data usage history using a data collection application every night and uploads it to the server.

[0797] The server stores the received data in JSON format and categorizes it by each user's ID. A database management system (e.g., MySQL) is used to organize and store this information.

[0798] Step 2: Data preprocessing

[0799] The server preprocesses the collected data. The input is the data collected in step 1, and the output is the cleaned data from which the necessary information has been extracted.

[0800] Specific actions:

[0801] The server loads the dataset using the Python Pandas library and converts it to a consistent format.

[0802] The server detects irregular or missing values ​​and removes or fills them in as needed. Specifically, if an irregular value is found, the record is deleted, and if a missing value exists, it is inferred and filled in from the surrounding data.

[0803] Step 3: Data Analysis

[0804] The server analyzes users' data usage trends using generative artificial intelligence (e.g., TensorFlow). The input is the data preprocessed in step 2, and the output is the usage trends and clustering results for each user.

[0805] Specific actions:

[0806] The server uses a trained artificial intelligence model to input data and analyze user usage patterns.

[0807] The server uses pattern recognition algorithms to analyze data usage patterns, including time of day and monthly usage. Based on this information, it identifies user usage patterns.

[0808] The server uses clustering techniques to group users with similar usage patterns and understands the characteristics of each group.

[0809] Step 4: Emotion Recognition

[0810] The server recognizes the user's emotions using an emotion engine (e.g., an emotion analysis API). The input is feedback data provided by the user, and the output is the analyzed emotion information.

[0811] Specific actions:

[0812] Users input their suggestions and their feelings about their current mobile plan through the application's interface. This input is primarily text data.

[0813] The server inputs text data into the emotion engine and extracts emotional information such as positive, negative, and neutral.

[0814] Step 5: Proposal Generation

[0815] The server generates the optimal mobile plan and options for the user based on the analysis results and sentiment information. The input is the results of steps 3 and 4, and the output is a specific plan proposal for the user.

[0816] Specific actions:

[0817] The server uses usage trend data and sentiment data to run an algorithm and generate the optimal mobile plan.

[0818] The server evaluates and compares the latest market plans to select the most cost-effective one. It also proposes combinations with additional options (e.g., international call packages, large data packages).

[0819] Step 6: Notification

[0820] The server notifies the user's terminal of the generated proposal. The input is the proposal data from step 5, and the output is the notification sent to the user's terminal.

[0821] Specific actions:

[0822] The server sends the proposal to the user via email or message. Email delivery services or dedicated SMTP servers are used for sending.

[0823] Users review the proposed plan on their devices and proceed with the necessary steps to change to the appropriate plan. Push notifications are also used for further notification.

[0824] Step 7: Feedback and Improvement

[0825] Users provide feedback on the proposed plans and options and send it to the server. The input is the user's feedback data, and the output is the result of the model's improvement.

[0826] Specific actions:

[0827] Users enter their satisfaction level and opinions on the proposed content into the application's feedback form and send it to the server.

[0828] The server inputs the collected feedback data into a generative artificial intelligence model, which is then trained and improved. This increases the accuracy of new suggestions.

[0829] (Application Example 2)

[0830] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0831] For autonomous vehicles, there is a lack of systematic methods for providing optimal routes and driving tips based on driving history data and sensor data. Furthermore, the technology for recognizing the driver's emotional state in real time and providing advice based on that is still immature.

[0832] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0833] In this invention, the server includes data collection means, data preprocessing means, data analysis means, emotion recognition means, vehicle driving history data collection means, vehicle sensor data collection means, driving route generation means, and driving advice generation means. This makes it possible to comprehensively analyze the driving history data and sensor data of an autonomous vehicle, as well as the emotional state of the driver, and provide the optimal route and driving tips.

[0834] "Data collection means" refers to means for automatically collecting various types of data from users and vehicles.

[0835] "Data preprocessing means" are methods for cleaning collected data and organizing irregular values, missing values, and duplicate data.

[0836] "Data analysis methods" refer to means for analyzing collected and pre-processed data to extract user usage trends and patterns.

[0837] A "proposal generation method" is a means for generating optimal mobile plans, driving routes, and driving advice based on analysis results.

[0838] A "notification method" is a means of notifying users or vehicles of the generated proposal content.

[0839] A "feedback collection method" is a means of collecting feedback from users regarding their suggestions and incorporating it into the system.

[0840] "Model improvement methods" refer to measures taken to improve the artificial intelligence model based on collected feedback and to enhance the accuracy of future suggestions.

[0841] An "emotion recognition tool" is a means of analyzing the user's emotional state and adjusting the suggested content based on that analysis.

[0842] A "vehicle driving history data collection method" is a means for automatically collecting vehicle driving history data.

[0843] A "vehicle sensor data collection means" is a means for automatically collecting sensor data from a vehicle.

[0844] A "driving route generation means" is a means for generating the optimal driving route based on analyzed data.

[0845] A "driving advice generation method" is a means for generating driving advice for a driver based on data analysis and emotion recognition results.

[0846] This invention is a system for comprehensively collecting and analyzing driving history data, sensor data, and the driver's emotional state from an autonomous vehicle, and for generating optimal routes and driving advice. This system includes means involving a server, a terminal, and a user.

[0847] The server collects driving history data and sensor data from users and vehicles through data collection means. This data collection includes GPS data, vehicle speed data, brake data, accelerator data, etc. In addition, the driver's emotional state (e.g., stress, fatigue) is collected through emotion recognition means.

[0848] In the data preprocessing mechanism, the server cleans the collected data and performs processing to impute irregular values ​​and missing values. The preprocessed data is then analyzed by the data analysis mechanism. Here, a generative AI model is used to analyze each user's driving patterns and sensor data trends, and clustering is performed. In addition, emotional data acquired using the emotion recognition mechanism is also analyzed to understand the driver's emotional state.

[0849] Based on these analysis results, the suggestion generation system generates optimal driving routes and driving advice. For example, it selects routes suitable for specific times of day and weather conditions, and provides driving tips and maintenance advice. It also provides advice tailored to the driver's emotional state, supporting them in driving safely and comfortably.

[0850] The notification system sends generated driving routes and advice to the user's device. The user reviews the notification and incorporates the driving routes and advice as needed. Furthermore, the user can provide feedback on the suggestions, which is sent to the server by the feedback collection system.

[0851] Through model improvement mechanisms, the server analyzes collected feedback and improves the generated AI model. This improves the accuracy of future suggestions and enables more personalized driving support.

[0852] As a concrete example, consider a case where driving history data, sensor data, and emotion data associated with a vehicle ID "ABC123" are collected and analyzed.

[0853] As an example of a prompt, you could instruct the generating AI model with a message like, "Collect and analyze vehicle driving history data, sensor data, and driver emotion data to generate the optimal route, driving tips, and emotion-based advice."

[0854] Based on the above, this system can comprehensively analyze the driving history data and sensor data of autonomous vehicles, as well as the driver's emotional state, to provide optimal driving routes and advice.

[0855] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0856] Step 1: Data Collection

[0857] The server automatically collects driving history data, sensor data, and sentiment data from users and vehicles using data collection methods. Examples include GPS data, vehicle speed data, brake data, and accelerator data. Input is raw data from users and vehicles, and output is the collected dataset.

[0858] Step 2: Data Preprocessing

[0859] The server cleans the collected data using data preprocessing techniques. This process ensures data integrity by imputing irregular or missing values. Specifically, it standardizes data formats, imputes missing data, and removes duplicate data. The input is the collected dataset, and the output is the cleaned data.

[0860] Step 3: Data Analysis

[0861] The server analyzes pre-processed data using data analysis tools. Here, a generative AI model is used to analyze user-specific driving patterns and sensor data trends, and clustering is performed. Furthermore, emotional data acquired by emotion recognition tools is also analyzed to understand the driver's emotional state. The input is cleaned data, and the output is the analysis result.

[0862] Step 4: Proposal Generation

[0863] The server uses a suggestion generation mechanism to generate optimal driving routes and driving advice based on the analysis results. For example, it selects routes suitable for specific time periods and weather conditions, and provides driving tips and maintenance advice. It also provides advice tailored to the user's emotional state. The input is the analysis results, and the output is the generated suggestions.

[0864] Step 5: Notification

[0865] The system uses a notification method to send generated driving routes and advice to the user's device. The user reviews the notification and incorporates the driving routes and advice as needed. The input is the generated suggestions, and the output is the notification sent to the user.

[0866] Step 6: Gathering Feedback

[0867] Users provide feedback on the proposed content. This feedback is sent to the server through a feedback collection mechanism. The input is the user's feedback, and the output is the collected feedback data.

[0868] Step 7: Model Improvement

[0869] The server uses model improvement tools to refine the generative AI model based on the collected feedback. This improves the accuracy of the next proposal. The input is the collected feedback data, and the output is the improved generative AI model.

[0870] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0871] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0872] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0873] [Third Embodiment]

[0874] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0875] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0876] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0877] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0878] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0879] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0880] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0881] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0882] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0883] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0884] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0885] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0886] Modes for carrying out the invention

[0887] This invention relates to a system including data collection means, data preprocessing means, data analysis means, suggestion generation means, notification means, feedback collection means, and model improvement means. Through this system, it is possible to automatically collect and analyze a user's monthly mobile billing data and packet communication data, and suggest the optimal mobile plan and options.

[0888] System program and processing details

[0889] This system performs a series of processes from data collection to proposal notification as follows:

[0890] 1. Data collection:

[0891] The server receives each user's monthly mobile billing data and packet communication data and stores it in a database.

[0892] Specific example:

[0893] The device automatically collects the user's data usage history and periodically uploads it to the server.

[0894] The server appropriately classifies the received data and stores it for each user.

[0895] 2. Data preprocessing:

[0896] The server preprocesses the collected data. This includes cleaning the data (handling irregular or missing values) and extracting necessary information (such as call duration and data usage).

[0897] Specific example:

[0898] The server standardizes the data format and supplements any missing data.

[0899] The server removes duplicate and erroneous data to maintain data integrity.

[0900] 3. Data Analysis:

[0901] The server uses generative artificial intelligence to analyze data usage trends for each user. This includes pattern analysis and clustering based on the user's usage history.

[0902] Specific example:

[0903] The server detects call duration, data usage time periods, and monthly usage trends.

[0904] The server groups users with similar usage patterns and understands the characteristics of each group.

[0905] 4. Proposal generation:

[0906] Based on the analysis results, the server generates the optimal mobile plan and options for the user. This includes comparing them to the latest market plans and evaluating their cost-effectiveness.

[0907] Specific example:

[0908] The server selects the plan that best suits the user's usage pattern.

[0909] The server will suggest additional options (such as international call packages and large data packages).

[0910] 5. Notice:

[0911] The server notifies the user's device of the generated suggestions. This includes notifications via email or message.

[0912] Specific example:

[0913] The server sends the proposal to the user's terminal in an easy-to-understand format, allowing the user to easily review the content.

[0914] Users can review the proposed plans on their own devices and change them to a more suitable plan.

[0915] 6. Feedback and Improvement:

[0916] Users provide feedback on the proposed plans and options and send it to the server. The server uses this feedback to improve the generative artificial intelligence model and increase the accuracy of future suggestions.

[0917] Specific example:

[0918] Users provide feedback on their satisfaction with the proposed content and offer their opinions.

[0919] The server analyzes the collected feedback and uses it to improve the model.

[0920] In this way, the system can automatically make optimal suggestions based on data, improve customer satisfaction, and significantly reduce the workload of the sales force.

[0921] The following describes the processing flow.

[0922] Step 1: Data Collection

[0923] The server receives each user's monthly mobile billing data and packet communication data.

[0924] The terminal collects data from the user's device in real time and uploads it to the server periodically.

[0925] Step 2: Reading Storage

[0926] The server saves the received data to the appropriate database.

[0927] The server classifies and organizes data based on each user's identification information.

[0928] Step 3: Data Cleaning

[0929] The server checks for irregular or missing values ​​in the data and corrects or deletes them.

[0930] The server identifies and removes duplicate and erroneous data.

[0931] Step 4: Manufacturing Conversion

[0932] The server converts the data into a unified format (e.g., date and time format, unifying units).

[0933] The server extracts necessary information such as call duration, data usage, and current plan.

[0934] Step 5: Pattern Analysis

[0935] The server uses generative artificial intelligence to analyze each user's data usage patterns.

[0936] The server tracks patterns such as call duration, peak data usage times, and monthly usage based on the user's usage history.

[0937] Step 6: Clustering

[0938] The server clusters user usage patterns.

[0939] The server groups users with similar usage patterns and identifies the characteristics of each group.

[0940] Step 7: Selecting a Plan

[0941] The server compares each user's usage patterns with the latest market plans.

[0942] The server will select the plan that best suits the cost-performance ratio and user needs.

[0943] Step 8: Proposing Options

[0944] The server will offer appropriate options (e.g., international call packages, large data packages) in addition to the basic plan.

[0945] The server also takes into account the user's past option usage history.

[0946] Step 9: Generate Notifications

[0947] The server generates the proposal and compiles it into a format that is easy for the user to understand.

[0948] The server creates the proposal in text message or email format.

[0949] Step 10: User Notifications

[0950] The server sends the generated suggestions to the user's terminal.

[0951] Users review the proposed plan on their own devices and consider changing their plan based on the proposal.

[0952] Step 11: Gathering Feedback

[0953] Users provide feedback on the proposed plans and options.

[0954] The device sends the collected feedback to the server.

[0955] Step 12: Model Improvement

[0956] The server analyzes the collected feedback and improves the generative artificial intelligence model.

[0957] The server uses the feedback to improve the accuracy of its next suggestions.

[0958] This series of processes allows the system to gain a detailed understanding of users' data usage patterns and provide optimal plans. This is expected to reduce sales workload and improve customer satisfaction.

[0959] (Example 1)

[0960] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0961] Current mobile communication systems make it difficult for users to choose the optimal mobile plan and options, and there is no mechanism to automatically provide appropriate suggestions. Therefore, users must research complex plans and options themselves, which is time-consuming and laborious. Furthermore, there is no way to improve the system based on user satisfaction with suggested plans and feedback, making it difficult to improve the accuracy of suggestions.

[0962] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0963] In this invention, the server includes data collection means, data preprocessing means, data analysis means, suggestion generation means, notification means, feedback collection means, model improvement means, a user's mobile terminal, means for storing data collected from the server in a database, means for cleaning and normalizing the collected data, means for analyzing data usage trends and performing clustering using generative artificial intelligence, means for generating optimal mobile plans and options, means for notifying the user of the suggested content, and means for collecting user feedback and improving the model. As a result, the user can be automatically suggested the optimal mobile plan and options, saving time and effort. Furthermore, it becomes possible to improve the accuracy of suggestions based on feedback.

[0964] "Data collection means" refers to methods for collecting user mobile billing data, packet communication data, and other similar information.

[0965] "Data preprocessing means" are methods for cleaning and normalizing collected data. This includes checking and processing irregular or missing values, removing duplicate data, and extracting necessary information.

[0966] "Data analysis methods" refer to methods that use generative artificial intelligence to analyze data usage trends for each user and perform clustering.

[0967] The "proposal generation method" is a means of generating the optimal mobile plan and options for the user based on the analysis results.

[0968] "Notification means" refers to a means of notifying the user's device of the generated proposal content.

[0969] "Feedback collection methods" refer to means of collecting feedback from users.

[0970] "Model improvement methods" refer to techniques for improving the model of a generative artificial intelligence based on collected feedback, thereby enhancing the accuracy of suggestions.

[0971] "User's mobile device" refers to a mobile device such as a smartphone or tablet that the user is using.

[0972] A "server" refers to a computer system that is responsible for collecting, storing, processing, analyzing, and improving data models.

[0973] "Means of saving to a database" refers to the means of classifying and organizing collected data and saving it to a database.

[0974] "Means for cleaning and normalizing collected data" refers to means of ensuring data quality through handling irregular or missing values, removing duplicate data, and standardizing data formats.

[0975] "Generative artificial intelligence" refers to artificial intelligence technology that learns patterns from large amounts of data and generates recommendations.

[0976] Clustering is an analytical technique for grouping data based on similarity.

[0977] "Optimal mobile plans and options" refer to cost-effective mobile communication plans and additional options selected based on the user's data usage trends.

[0978] Modes for carrying out the invention

[0979] This invention relates to a system that analyzes a user's mobile data usage and proposes the optimal mobile plan and options. The system is configured as follows, with each component working in coordination.

[0980] First, the user's mobile device collects their mobile billing data and packet data on a monthly basis and uploads it to the server periodically. This includes a function that automatically sends data when the device detects a Wi-Fi connection.

[0981] The server stores the received data in a database. The database is a storage system that helps classify and organize data, and the data is managed under a specific user ID. Next, the server preprocesses the collected data. Cleaning and normalization are performed, such as detecting and correcting irregular or missing values, removing duplicate data, and standardizing the format. For example, if there is abnormally long call duration data, it will be detected and excluded from the dataset.

[0982] Subsequently, the server uses generative artificial intelligence to analyze the data. The generative AI model learns user usage patterns based on past data and analyzes data usage trends for each user. This is done using prompts such as the following:

[0983] Please perform a pattern analysis including the following user data and propose the optimal mobile plan.

[0984] User ID: 12345

[0985] Monthly call time: 300 minutes

[0986] Monthly data usage: 5GB

[0987] Usage time: Primarily from evening to night

[0988] Current plan: Standard plan

[0989] Feedback: "I would like to consider other large-capacity data plans as well."

[0990] Based on the analysis results, the server generates optimal mobile plan and option suggestions. For example, based on call time and data usage, it can suggest the most cost-effective high-capacity data plan for user A. It can also suggest additional options such as international call packages and data increase packages.

[0991] After a proposal is generated, the server sends a notification to the user's device. This is done via email or push notification, and the proposal is presented in an easy-to-understand format. The user receives the notification, reviews the proposal on their device, and can change to an appropriate plan.

[0992] Furthermore, user feedback is collected and sent to the server. Users click on a provided link and answer a feedback form. This form may include questions such as, "Are you satisfied with this plan proposal?" or "Are there any other options you would like to see?" The server can use the collected feedback to improve the generative artificial intelligence model and enhance the accuracy of future proposals.

[0993] As described above, this system can automatically suggest the optimal mobile plan and options to users through a series of processes, from data collection and analysis to suggestions, notifications, and improvements based on feedback. As a result, users can avoid the hassle of conducting their own research, saving time and effort. Furthermore, by continuously collecting and analyzing feedback, the accuracy of suggestions will improve, and customer satisfaction is expected to increase.

[0994] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0995] Step 1: Data Collection

[0996] Input: Mobile billing data and packet communication data stored on the user's mobile device.

[0997] Specific operation: The device automatically collects monthly data usage, call time, number of text messages, etc. The collected data is periodically uploaded to the server when connected to Wi-Fi.

[0998] Output: Raw data uploaded to the server.

[0999] Step 2: Save

[1000] Input: Raw data uploaded from the device.

[1001] Specific operation: The server stores the received data in the database. It verifies that the data has arrived in the correct format, organizes it by user ID, and stores it in the database.

[1002] Output: Organized and categorized database entries.

[1003] Step 3: Data Preprocessing

[1004] Input: Raw data stored in the database.

[1005] Specific actions: The server performs data cleaning, detecting and correcting irregular and missing values. Furthermore, it removes duplicate data and standardizes all data into a common format. For example, if it contains data with unusually long call durations, it will detect and remove it.

[1006] Output: Preprocessed and consistent data.

[1007] Step 4: Normal Analysis

[1008] Input: Pre-processed data.

[1009] Specific operation: The server analyzes data usage trends using a generative AI model. It learns user usage patterns based on past data and performs clustering. It generates prompt messages, inputs them into the generative AI model, and obtains the analysis results.

[1010] Example prompt: "Perform pattern analysis on the following user data and suggest the optimal mobile plan. User ID: 12345, Monthly call time: 300 minutes, Monthly data usage: 5GB, Usage time: Primarily evening to night, Current plan: Standard plan, Feedback: I would also like to consider other high-capacity data plans."

[1011] Output: Analysis results of data usage trends for each user.

[1012] Step 5: Proposal Generation

[1013] Input: Analysis results of data usage trends.

[1014] Specific operation: The server generates optimal mobile plans and options based on the analysis results. It compares plans that correspond to the user's usage patterns with market data and selects the best plan. It creates a proposal that includes additional options (such as international call packages and data bonus packages).

[1015] Output: A list of mobile plans and options to suggest to the user.

[1016] Step 6: Notification

[1017] Input: A list of proposed mobile plans and options.

[1018] Specific operation: The server sends the proposal to the user's device via email or push notification. This allows the user to review the proposal and change to an appropriate plan.

[1019] Specific example: "Send the proposal in an easy-to-understand format to the user's device, allowing them to easily review the content. Users can then review the proposal on their device and make changes to the plan that best suits them."

[1020] Output: The suggested content that will be displayed on the user's device.

[1021] Step 7: Gathering Feedback and Improving the Model

[1022] Input: User feedback.

[1023] Specific operation: The user provides feedback on the proposed plan and options and sends it to the server. The server uses the collected feedback to improve the generated AI model and increase the accuracy of future suggestions.

[1024] Specific example: "Users provide feedback on their satisfaction with the suggestions and offer opinions. The server uses this feedback to improve the generative artificial intelligence model and enhance the accuracy of future suggestions."

[1025] Output: Improved generative AI model.

[1026] Through the processing steps described above, this system automatically proposes the optimal mobile plan and options to the user, improving customer satisfaction and significantly reducing the workload of the sales team.

[1027] (Application Example 1)

[1028] Next, we will explain Application Example 1. In the following explanation, 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."

[1029] Modern e-commerce sites are required to leverage users' purchase and browsing history to provide optimal product recommendations and campaign notifications. However, traditional systems often fail to collect and analyze data effectively, resulting in ineffective recommendations. Furthermore, there is a lack of means to effectively utilize user feedback and continuously improve the accuracy of the system's recommendations. Therefore, a more accurate recommendation system is needed to improve user satisfaction.

[1030] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1031] In this invention, the server includes data collection means, data preprocessing means, data analysis means, suggestion generation means, notification means, feedback collection means, model improvement means, and means for suggesting products and services based on the user's usage history. This makes it possible to suggest optimal products and campaigns based on the user's purchase and browsing history, and to improve the system by collecting feedback from the user.

[1032] "Data collection means" refers to methods for automatically collecting data such as users' purchase history and browsing history and providing it to the system.

[1033] "Data preprocessing means" refers to methods for cleaning collected data and checking and processing irregular values ​​and missing values.

[1034] "Data analysis methods" refer to methods for analyzing collected and pre-processed data and clustering user usage trends using generative artificial intelligence.

[1035] A "proposal generation method" is a means of proposing the most suitable products, services, and campaigns based on the analysis results.

[1036] A "notification method" is a means of notifying the user of the generated proposal content.

[1037] "Feedback collection methods" refer to methods for collecting feedback such as user satisfaction and opinions regarding a proposal.

[1038] "Model improvement methods" refer to methods for improving the model of a generative artificial intelligence system in order to improve the accuracy of the system's suggestions using collected feedback.

[1039] "Methods for suggesting products and services based on user usage history" refers to methods for suggesting optimal products and campaigns based on a user's past purchase and browsing history.

[1040] Modes for carrying out the invention

[1041] The system of this invention includes means for data collection, means for data preprocessing, means for data analysis, means for suggestion generation, means for notification, means for feedback collection, means for model improvement, and means for suggesting products and services based on the user's usage history.

[1042] The server first automatically collects user data such as purchase history and browsing history using data collection tools. This data is sent to the system and stored in a database. Next, data preprocessing tools are used to clean the collected data, checking and processing irregular and missing values, and formatting it into an appropriate format. This improves data consistency and quality, enabling accurate subsequent analysis.

[1043] As a means of data analysis, the server uses generative artificial intelligence to analyze the collected data. Clustering technology is used to identify user usage patterns and classify them into groups with common characteristics. This analysis makes it possible to identify the products and services that are most suitable for each user.

[1044] The suggestion generation system generates optimal products and campaigns for users based on the results of data analysis. Specifically, it makes suggestions that take into account the characteristics of each clustered group. In this process, the server also compares the suggestions with the latest products and campaigns available on the market, enabling it to provide the most useful suggestions for the user.

[1045] The generated suggestions are sent to the user via notification methods. The system is designed to allow users to easily review the suggestions via email or push notifications. Users can view the notification content within the application and easily select and purchase the suggested products and services.

[1046] The feedback collection mechanism gathers user satisfaction and opinions on the suggestions. The server uses this feedback to improve the generative artificial intelligence model, thereby enhancing the accuracy of future suggestions. This allows the system to continuously improve and continue providing valuable suggestions to users.

[1047] The specific hardware and software used include:

[1048] Pandas: Used for data preprocessing and formatting.

[1049] Scikit-learn: Used for data analysis and clustering.

[1050] Notification System API: Sends notifications to users.

[1051] Feedback Collection API: Collects feedback from users.

[1052] As a concrete example, there are cases where notifications about seasonal products or discount campaigns are sent based on a specific user's purchase history. In this case, a generative AI model can be used to make highly accurate suggestions by using the following prompt sentences.

[1053] Example of a prompt:

[1054] Based on users' purchasing patterns and browsing trends, suggest the most suitable products and campaigns. For example, suggest winter seasonal products based on their recent browsing history.

[1055] As described above, this system can achieve highly accurate product recommendations based on user usage history and continuous system improvement through feedback.

[1056] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1057] Step 1:

[1058] Data collection

[1059] The server automatically collects data such as user purchase history and browsing history using data collection methods. Data is periodically sent from each terminal to the server and stored in the database. The input for this step is the user's purchase history and browsing history, and the output is the raw data stored in the database.

[1060] Step 2:

[1061] Data preprocessing

[1062] The server uses data preprocessing techniques to clean the collected data. Specifically, it checks for irregular or missing values ​​and handles them appropriately. It also standardizes the data format and extracts necessary information. The input for this step is raw data, and the output is cleaned, preprocessed data in a standardized format.

[1063] Step 3:

[1064] Data analysis

[1065] The server uses data analysis tools to analyze preprocessed data using generative artificial intelligence. Specifically, it identifies user usage trends using clustering methods (e.g., KMeans). Clustering forms user groups with common characteristics. The input for this step is preprocessed data, and the output is the user clustering result.

[1066] Step 4:

[1067] Proposal generation

[1068] The server uses a suggestion generation mechanism to generate optimal products, services, and campaigns for users based on clustering results. Specifically, it compares the latest market information with the user clustering results and provides optimal suggestions for each user group. The inputs to this step are the clustering results and market information, and the output is the generated suggestions.

[1069] Step 5:

[1070] notification

[1071] The server uses notification methods to inform the user of the generated suggestions. Specifically, it allows the user to easily review the suggestions via email or push notifications. The input for this step is the generated suggestions, and the output is the notification sent to the user.

[1072] Step 6:

[1073] Feedback Collection

[1074] The server uses feedback collection methods to gather user satisfaction levels and opinions on suggestions. Specifically, it collects user-provided feedback data and stores it in a database. The input for this step is user feedback, and the output is the collected feedback data.

[1075] Step 7:

[1076] Model improvements

[1077] The server uses model improvement tools to refine the generative artificial intelligence model based on the collected feedback. Specifically, it analyzes the feedback data and trains the model to improve the accuracy of future suggestions. The input for this step is the feedback data, and the output is the improved generative artificial intelligence model.

[1078] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1079] Modes for carrying out the invention

[1080] This invention relates to a system that includes data collection means, data preprocessing means, data analysis means, suggestion generation means, notification means, feedback collection means, model improvement means, and emotion recognition means. Through this system, the system automatically collects and analyzes the user's monthly mobile billing data and packet communication data, and suggests the optimal mobile plan and options. Furthermore, by recognizing the user's emotions and adjusting the suggestions accordingly, it is possible to provide a more personalized service.

[1081] System program and processing details

[1082] This system performs a series of processes, from data collection to suggestion notification and emotion recognition, as follows:

[1083] 1. Data collection:

[1084] The server receives each user's monthly mobile billing data and packet communication data and stores it in a database.

[1085] Specific example:

[1086] The device automatically collects the user's data usage history and periodically uploads it to the server.

[1087] The server appropriately classifies the received data and stores it for each user.

[1088] 2. Data preprocessing:

[1089] The server preprocesses the collected data. This includes cleaning the data (handling irregular or missing values) and extracting necessary information (such as call duration and data usage).

[1090] Specific example:

[1091] The server standardizes the data format and supplements any missing data.

[1092] The server removes duplicate and erroneous data to maintain data integrity.

[1093] 3. Data Analysis:

[1094] The server uses generative artificial intelligence to analyze data usage trends for each user. This includes pattern analysis and clustering based on the user's usage history.

[1095] Specific example:

[1096] The server detects call duration, data usage time periods, and monthly usage trends.

[1097] The server groups users with similar usage patterns and understands the characteristics of each group.

[1098] 4. Emotion recognition:

[1099] The server uses an emotion engine to recognize the user's emotions, based on feedback and other emotional data provided by the user.

[1100] Specific example:

[1101] The user enters their feelings about the proposal (satisfied, dissatisfied, etc.).

[1102] The server analyzes user feedback and extracts emotional information.

[1103] 5. Proposal generation:

[1104] The server generates the optimal mobile plan and options for the user based on analysis results and sentiment information. This includes comparing them to the latest market plans and evaluating their cost-effectiveness.

[1105] Specific example:

[1106] The server selects the plan that best suits the user's usage patterns and emotions.

[1107] The server will suggest additional options (such as international call packages and large data packages).

[1108] 6. Notice:

[1109] The server notifies the user's device of the generated suggestions. This includes notifications via email or message.

[1110] Specific example:

[1111] The server sends the proposal to the user's terminal in an easy-to-understand format, allowing the user to easily review the content.

[1112] Users can review the proposed plans on their own devices and change them to a more suitable plan.

[1113] 7. Feedback and Improvement:

[1114] Users provide feedback on the proposed plans and options and send it to the server. The server uses this feedback to improve the generative artificial intelligence model and increase the accuracy of future suggestions.

[1115] Specific example:

[1116] Users provide feedback on their satisfaction with the proposed content and offer their opinions.

[1117] The server analyzes the collected feedback and uses it to improve the model.

[1118] In this way, this system not only provides data-driven, automated, and optimal suggestions, but also considers the user's emotions, thereby further improving customer satisfaction. This is expected to reduce sales workload and increase customer satisfaction.

[1119] The following describes the processing flow.

[1120] Step 1: Data Collection

[1121] The server receives each user's monthly mobile billing data and packet communication data.

[1122] The device automatically collects data from the user's device and uploads it to the server periodically.

[1123] The server saves the received data to the database.

[1124] Step 2: Reading Storage

[1125] The server stores the received data in the appropriate database and categorizes it by user.

[1126] The server manages to maintain data integrity.

[1127] Step 3: Data Cleaning

[1128] The server cleans the collected data, checking for irregular or missing values ​​and correcting or deleting them.

[1129] The server identifies and removes duplicate and erroneous data.

[1130] Step 4: Manufacturing Conversion

[1131] The server converts the data into a unified format (e.g., date and time format, unified units).

[1132] The server extracts necessary information, such as call duration, data usage, and current plan.

[1133] Step 5: Pattern Analysis

[1134] The server uses generative artificial intelligence to analyze each user's data usage patterns.

[1135] The server tracks patterns such as call duration, peak data usage times, and monthly usage based on the user's usage history.

[1136] Step 6: Clustering

[1137] The server clusters user usage patterns.

[1138] The server groups users with similar usage patterns and identifies the characteristics of each group.

[1139] Step 7: Emotion Recognition

[1140] The server uses an emotion engine to recognize the user's emotions.

[1141] The user enters their feelings about the proposal (satisfied, dissatisfied, etc.).

[1142] The server analyzes user feedback and extracts emotional information.

[1143] Step 8: Selecting a Plan

[1144] The server compares each user's usage patterns with the latest market plans.

[1145] The server selects the plan that best suits the cost-performance ratio and user needs.

[1146] The server adjusts the suggestions based on emotional information.

[1147] Step 9: Proposing Options

[1148] The server will offer appropriate options (e.g., international call packages, large data packages) in addition to the basic plan.

[1149] The server also takes into account the user's past option usage history.

[1150] Step 10: Generating the proposal notification

[1151] The server generates the proposal and compiles it into a format that is easy for the user to understand.

[1152] The server creates the proposal in text message or email format.

[1153] Step 11: User Notifications

[1154] The server sends the generated suggestions to the user's terminal.

[1155] Users review the proposed plan on their own devices and consider changing their plan based on the proposal.

[1156] Step 12: Gathering Feedback

[1157] Users provide feedback on the proposed plans and options.

[1158] The device sends the collected feedback to the server.

[1159] Step 13: Model Improvement

[1160] The server analyzes the collected feedback and improves the generative artificial intelligence model.

[1161] The server uses the feedback to improve the accuracy of its next suggestions.

[1162] This series of steps allows the system to gain a detailed understanding of users' data usage patterns and emotions, enabling it to provide personalized and optimal plans. This is expected to reduce sales workload and improve customer satisfaction.

[1163] (Example 2)

[1164] Next, we will describe Example 2. 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."

[1165] Modern telecommunications service users face the challenge of choosing the optimal mobile plan to suit their diverse usage patterns and lifestyles. Furthermore, there is a lack of means to provide personalized services that adequately reflect user satisfaction and feedback on proposed plans. Additionally, there is a lack of approaches that consider user emotions, highlighting the need for effective strategies to improve customer satisfaction.

[1166] In Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes data collection means, data preprocessing means, data analysis means, suggestion generation means, notification means, feedback collection means, model improvement means, and emotion recognition means. This makes it possible to analyze the user's data usage patterns and emotions and propose the optimal mobile plan based on them. Furthermore, by utilizing user feedback to improve the accuracy of suggestions, it is possible to provide more personalized services and increase customer satisfaction.

[1167] "Data collection means" refers to a method for automatically receiving users' monthly mobile billing data and packet communication data and storing it in a database.

[1168] "Data preprocessing means" are methods for cleaning collected data and extracting necessary information. This includes handling irregular values ​​and missing values.

[1169] "Data analysis methods" refer to methods that use generative artificial intelligence to analyze data usage trends for each user and perform clustering.

[1170] A "proposal generation method" is a means of generating the optimal mobile plan and options for the user based on analysis results and sentiment information.

[1171] "Notification method" refers to the means of notifying the user's device of the generated proposal content. This includes notifications via email or message.

[1172] A "feedback collection method" is a means of collecting feedback from users regarding the plans and options they have proposed.

[1173] "Model improvement methods" refer to techniques for improving the model of a generative artificial intelligence based on collected feedback, thereby enhancing the accuracy of suggestions in subsequent iterations.

[1174] An "emotion recognition method" is a means of analyzing user feedback and other emotional data to extract user emotional information.

[1175] Modes for carrying out the invention

[1176] This invention relates to a system including data collection means, data preprocessing means, data analysis means, suggestion generation means, notification means, feedback collection means, model improvement means, and emotion recognition means. Through this system, the system automatically collects the user's monthly mobile billing data and packet communication data and suggests the optimal mobile plan and options. Furthermore, by recognizing the user's emotions and adjusting the suggestions accordingly, it is possible to provide a more personalized service.

[1177] Data collection

[1178] The server receives each user's monthly mobile billing data and packet communication data and stores it in a database. A data collection application is installed on the user's device, which automatically collects data and uploads it to the server periodically. The server uses a database management system (e.g., MySQL) to appropriately classify the received data and store it for each user.

[1179] Specific example:

[1180] The device collects the user's data usage history every night and uploads it to the server.

[1181] The server receives the collected data and saves it to the database based on the reception date and time and the user ID. The data is saved in JSON format.

[1182] Data preprocessing

[1183] The server preprocesses the collected data. This includes cleaning the data (handling irregular or missing values) and extracting necessary information (e.g., call duration, data usage). The server loads the dataset using the Python Pandas library and converts it to a consistent format.

[1184] Specific example:

[1185] The server detects irregular or missing values ​​and removes or fills them in. For example, if an irregular value is found, the record is deleted, and if there are missing values, they are filled in using the surrounding values.

[1186] The server extracts the necessary information from the cleaned data and prepares it for analysis.

[1187] Data analysis

[1188] The server analyzes user-specific data usage trends using generative artificial intelligence (e.g., TensorFlow models). This includes pattern analysis and clustering based on user usage history.

[1189] Specific example:

[1190] The server uses a pre-trained generative artificial intelligence model to input collected data and analyze the user's data usage patterns.

[1191] The server uses pattern recognition algorithms to analyze data usage patterns, including time of day and monthly usage. This clarifies user usage patterns.

[1192] The server uses clustering techniques to group users with similar usage patterns and understand the characteristics of each group.

[1193] emotion recognition

[1194] The server uses an emotion engine (e.g., an emotion analysis API) to recognize the user's emotions. It analyzes feedback and other emotion data provided by the user to extract emotional information.

[1195] Specific example:

[1196] Users input their opinions on the proposal and their feelings about their current mobile plan (e.g., satisfied, dissatisfied) through the application's interface.

[1197] The server inputs text data (feedback) collected from users into an emotion engine and extracts emotional information (e.g., positive, negative, neutral).

[1198] Proposal generation

[1199] The server generates the optimal mobile plan and options for the user based on analysis results and sentiment information. This includes comparing them to the latest market plans and evaluating their cost-effectiveness.

[1200] Specific example:

[1201] The server runs an algorithm that takes user usage patterns and sentiment data as input to select the optimal mobile plan. This includes comparing it with the latest market plans and evaluating cost-effectiveness.

[1202] The server combines the selected plan with additional options (e.g., international call package, large data package) to generate a final proposal.

[1203] notification

[1204] The server notifies the user's device of the generated suggestions. This includes notifications via email or message.

[1205] Specific example:

[1206] The server sends the generated suggestions to the user via email or message. Email delivery services or dedicated SMTP servers are used for sending emails.

[1207] Users can review the proposed plan on their device and change to the appropriate plan. Push notifications are also used to indicate when a notification has arrived.

[1208] Feedback and Improvement

[1209] Users provide feedback on the proposed plans and options and send it to the server. The server uses this feedback to improve the generative artificial intelligence model, thereby increasing the accuracy of future suggestions.

[1210] Specific example:

[1211] Users enter their satisfaction level and opinions on the proposed content into the application's feedback form and send it to the server.

[1212] The server inputs the collected feedback data into a generative artificial intelligence model, which is then trained and improved. This improves the accuracy of new suggestions.

[1213] Example of a prompt

[1214] Users are asked to provide data in the form of a message such as, "We will suggest the best plan for you based on your monthly data usage and current mobile plan. Please provide your data."

[1215] keyword

[1216] Generative AI model, prompt sentence

[1217] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1218] System program processing flow

[1219] Step 1: Data Collection

[1220] The server receives the user's monthly mobile billing data and packet communication data and stores it in a database. The input is the data sent from the user's terminal, and the output is the organized data stored in the database.

[1221] Specific actions:

[1222] The device collects the user's data usage history using a data collection application every night and uploads it to the server.

[1223] The server stores the received data in JSON format and categorizes it by each user's ID. A database management system (e.g., MySQL) is used to organize and store this information.

[1224] Step 2: Data preprocessing

[1225] The server preprocesses the collected data. The input is the data collected in step 1, and the output is the cleaned data from which the necessary information has been extracted.

[1226] Specific actions:

[1227] The server loads the dataset using the Python Pandas library and converts it to a consistent format.

[1228] The server detects irregular or missing values ​​and removes or fills them in as needed. Specifically, if an irregular value is found, the record is deleted, and if a missing value exists, it is inferred and filled in from the surrounding data.

[1229] Step 3: Data Analysis

[1230] The server analyzes users' data usage trends using generative artificial intelligence (e.g., TensorFlow). The input is the data preprocessed in step 2, and the output is the usage trends and clustering results for each user.

[1231] Specific actions:

[1232] The server uses a trained artificial intelligence model to input data and analyze user usage patterns.

[1233] The server uses pattern recognition algorithms to analyze data usage patterns, including time of day and monthly usage. Based on this information, it identifies user usage patterns.

[1234] The server uses clustering techniques to group users with similar usage patterns and understands the characteristics of each group.

[1235] Step 4: Emotion Recognition

[1236] The server recognizes the user's emotions using an emotion engine (e.g., an emotion analysis API). The input is feedback data provided by the user, and the output is the analyzed emotion information.

[1237] Specific actions:

[1238] Users input their suggestions and their feelings about their current mobile plan through the application's interface. This input is primarily text data.

[1239] The server inputs text data into the emotion engine and extracts emotional information such as positive, negative, and neutral.

[1240] Step 5: Proposal Generation

[1241] The server generates the optimal mobile plan and options for the user based on the analysis results and sentiment information. The input is the results of steps 3 and 4, and the output is a specific plan proposal for the user.

[1242] Specific actions:

[1243] The server uses usage trend data and sentiment data to run an algorithm and generate the optimal mobile plan.

[1244] The server evaluates and compares the latest market plans to select the most cost-effective one. It also proposes combinations with additional options (e.g., international call packages, large data packages).

[1245] Step 6: Notification

[1246] The server notifies the user's terminal of the generated proposal. The input is the proposal data from step 5, and the output is the notification sent to the user's terminal.

[1247] Specific actions:

[1248] The server sends the proposal to the user via email or message. Email delivery services or dedicated SMTP servers are used for sending.

[1249] Users review the proposed plan on their devices and proceed with the necessary steps to change to the appropriate plan. Push notifications are also used for further notification.

[1250] Step 7: Feedback and Improvement

[1251] Users provide feedback on the proposed plans and options and send it to the server. The input is the user's feedback data, and the output is the result of the model's improvement.

[1252] Specific actions:

[1253] Users enter their satisfaction level and opinions on the proposed content into the application's feedback form and send it to the server.

[1254] The server inputs the collected feedback data into a generative artificial intelligence model, which is then trained and improved. This increases the accuracy of new suggestions.

[1255] (Application Example 2)

[1256] Next, we will explain application example 2. In the following explanation, 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."

[1257] For autonomous vehicles, there is a lack of systematic methods for providing optimal routes and driving tips based on driving history data and sensor data. Furthermore, the technology for recognizing the driver's emotional state in real time and providing advice based on that is still immature.

[1258] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1259] In this invention, the server includes data collection means, data preprocessing means, data analysis means, emotion recognition means, vehicle driving history data collection means, vehicle sensor data collection means, driving route generation means, and driving advice generation means. This makes it possible to comprehensively analyze the driving history data and sensor data of an autonomous vehicle, as well as the emotional state of the driver, and provide the optimal route and driving tips.

[1260] "Data collection means" refers to means for automatically collecting various types of data from users and vehicles.

[1261] "Data preprocessing means" are methods for cleaning collected data and organizing irregular values, missing values, and duplicate data.

[1262] "Data analysis methods" refer to means for analyzing collected and pre-processed data to extract user usage trends and patterns.

[1263] A "proposal generation method" is a means for generating optimal mobile plans, driving routes, and driving advice based on analysis results.

[1264] A "notification method" is a means of notifying users or vehicles of the generated proposal content.

[1265] A "feedback collection method" is a means of collecting feedback from users regarding their suggestions and incorporating it into the system.

[1266] "Model improvement methods" refer to measures taken to improve the artificial intelligence model based on collected feedback and to enhance the accuracy of future suggestions.

[1267] An "emotion recognition tool" is a means of analyzing the user's emotional state and adjusting the suggested content based on that analysis.

[1268] A "vehicle driving history data collection method" is a means for automatically collecting vehicle driving history data.

[1269] A "vehicle sensor data collection means" is a means for automatically collecting sensor data from a vehicle.

[1270] A "driving route generation means" is a means for generating the optimal driving route based on analyzed data.

[1271] A "driving advice generation method" is a means for generating driving advice for a driver based on data analysis and emotion recognition results.

[1272] This invention is a system for comprehensively collecting and analyzing driving history data, sensor data, and the driver's emotional state from an autonomous vehicle, and for generating optimal routes and driving advice. This system includes means involving a server, a terminal, and a user.

[1273] The server collects driving history data and sensor data from users and vehicles through data collection means. This data collection includes GPS data, vehicle speed data, brake data, accelerator data, etc. In addition, the driver's emotional state (e.g., stress, fatigue) is collected through emotion recognition means.

[1274] In the data preprocessing mechanism, the server cleans the collected data and performs processing to impute irregular values ​​and missing values. The preprocessed data is then analyzed by the data analysis mechanism. Here, a generative AI model is used to analyze each user's driving patterns and sensor data trends, and clustering is performed. In addition, emotional data acquired using the emotion recognition mechanism is also analyzed to understand the driver's emotional state.

[1275] Based on these analysis results, the suggestion generation system generates optimal driving routes and driving advice. For example, it selects routes suitable for specific times of day and weather conditions, and provides driving tips and maintenance advice. It also provides advice tailored to the driver's emotional state, supporting them in driving safely and comfortably.

[1276] The notification system sends generated driving routes and advice to the user's device. The user reviews the notification and incorporates the driving routes and advice as needed. Furthermore, the user can provide feedback on the suggestions, which is sent to the server by the feedback collection system.

[1277] Through model improvement mechanisms, the server analyzes collected feedback and improves the generated AI model. This improves the accuracy of future suggestions and enables more personalized driving support.

[1278] As a concrete example, consider a case where driving history data, sensor data, and emotion data associated with a vehicle ID "ABC123" are collected and analyzed.

[1279] As an example of a prompt, you could instruct the generating AI model with a message like, "Collect and analyze vehicle driving history data, sensor data, and driver emotion data to generate the optimal route, driving tips, and emotion-based advice."

[1280] Based on the above, this system can comprehensively analyze the driving history data and sensor data of autonomous vehicles, as well as the driver's emotional state, to provide optimal driving routes and advice.

[1281] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1282] Step 1: Data Collection

[1283] The server automatically collects driving history data, sensor data, and sentiment data from users and vehicles using data collection methods. Examples include GPS data, vehicle speed data, brake data, and accelerator data. Input is raw data from users and vehicles, and output is the collected dataset.

[1284] Step 2: Data Preprocessing

[1285] The server cleans the collected data using data preprocessing techniques. This process ensures data integrity by imputing irregular or missing values. Specifically, it standardizes data formats, imputes missing data, and removes duplicate data. The input is the collected dataset, and the output is the cleaned data.

[1286] Step 3: Data Analysis

[1287] The server analyzes pre-processed data using data analysis tools. Here, a generative AI model is used to analyze user-specific driving patterns and sensor data trends, and clustering is performed. Furthermore, emotional data acquired by emotion recognition tools is also analyzed to understand the driver's emotional state. The input is cleaned data, and the output is the analysis result.

[1288] Step 4: Proposal Generation

[1289] The server uses a suggestion generation mechanism to generate optimal driving routes and driving advice based on the analysis results. For example, it selects routes suitable for specific time periods and weather conditions, and provides driving tips and maintenance advice. It also provides advice tailored to the user's emotional state. The input is the analysis results, and the output is the generated suggestions.

[1290] Step 5: Notification

[1291] The system uses a notification method to send generated driving routes and advice to the user's device. The user reviews the notification and incorporates the driving routes and advice as needed. The input is the generated suggestions, and the output is the notification sent to the user.

[1292] Step 6: Gathering Feedback

[1293] Users provide feedback on the proposed content. This feedback is sent to the server through a feedback collection mechanism. The input is the user's feedback, and the output is the collected feedback data.

[1294] Step 7: Model Improvement

[1295] The server uses model improvement tools to refine the generative AI model based on the collected feedback. This improves the accuracy of the next proposal. The input is the collected feedback data, and the output is the improved generative AI model.

[1296] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1297] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1298] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1299] [Fourth Embodiment]

[1300] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1301] As shown in Figure 7, the 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.

[1302] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1303] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1304] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1305] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1306] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1307] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1308] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1309] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1310] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1311] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1312] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1313] Modes for carrying out the invention

[1314] This invention relates to a system including data collection means, data preprocessing means, data analysis means, suggestion generation means, notification means, feedback collection means, and model improvement means. Through this system, it is possible to automatically collect and analyze a user's monthly mobile billing data and packet communication data, and suggest the optimal mobile plan and options.

[1315] System program and processing details

[1316] This system performs a series of processes from data collection to proposal notification as follows:

[1317] 1. Data collection:

[1318] The server receives each user's monthly mobile billing data and packet communication data and stores it in a database.

[1319] Specific example:

[1320] The device automatically collects the user's data usage history and periodically uploads it to the server.

[1321] The server appropriately classifies the received data and stores it for each user.

[1322] 2. Data preprocessing:

[1323] The server preprocesses the collected data. This includes cleaning the data (handling irregular or missing values) and extracting necessary information (such as call duration and data usage).

[1324] Specific example:

[1325] The server standardizes the data format and supplements any missing data.

[1326] The server removes duplicate and erroneous data to maintain data integrity.

[1327] 3. Data Analysis:

[1328] The server uses generative artificial intelligence to analyze data usage trends for each user. This includes pattern analysis and clustering based on the user's usage history.

[1329] Specific example:

[1330] The server detects call duration, data usage time periods, and monthly usage trends.

[1331] The server groups users with similar usage patterns and understands the characteristics of each group.

[1332] 4. Proposal generation:

[1333] Based on the analysis results, the server generates the optimal mobile plan and options for the user. This includes comparing them to the latest market plans and evaluating their cost-effectiveness.

[1334] Specific example:

[1335] The server selects the plan that best suits the user's usage pattern.

[1336] The server will suggest additional options (such as international call packages and large data packages).

[1337] 5. Notice:

[1338] The server notifies the user's device of the generated suggestions. This includes notifications via email or message.

[1339] Specific example:

[1340] The server sends the proposal to the user's terminal in an easy-to-understand format, allowing the user to easily review the content.

[1341] Users can review the proposed plans on their own devices and change them to a more suitable plan.

[1342] 6. Feedback and Improvement:

[1343] Users provide feedback on the proposed plans and options and send it to the server. The server uses this feedback to improve the generative artificial intelligence model and increase the accuracy of future suggestions.

[1344] Specific example:

[1345] Users provide feedback on their satisfaction with the proposed content and offer their opinions.

[1346] The server analyzes the collected feedback and uses it to improve the model.

[1347] In this way, the system can automatically make optimal suggestions based on data, improve customer satisfaction, and significantly reduce the workload of the sales force.

[1348] The following describes the processing flow.

[1349] Step 1: Data Collection

[1350] The server receives each user's monthly mobile billing data and packet communication data.

[1351] The terminal collects data from the user's device in real time and uploads it to the server periodically.

[1352] Step 2: Reading Storage

[1353] The server saves the received data to the appropriate database.

[1354] The server classifies and organizes data based on each user's identification information.

[1355] Step 3: Data Cleaning

[1356] The server checks for irregular or missing values ​​in the data and corrects or deletes them.

[1357] The server identifies and removes duplicate and erroneous data.

[1358] Step 4: Manufacturing Conversion

[1359] The server converts the data into a unified format (e.g., date and time format, unifying units).

[1360] The server extracts necessary information such as call duration, data usage, and current plan.

[1361] Step 5: Pattern Analysis

[1362] The server uses generative artificial intelligence to analyze each user's data usage patterns.

[1363] The server tracks patterns such as call duration, peak data usage times, and monthly usage based on the user's usage history.

[1364] Step 6: Clustering

[1365] The server clusters user usage patterns.

[1366] The server groups users with similar usage patterns and identifies the characteristics of each group.

[1367] Step 7: Selecting a Plan

[1368] The server compares each user's usage patterns with the latest market plans.

[1369] The server will select the plan that best suits the cost-performance ratio and user needs.

[1370] Step 8: Proposing Options

[1371] The server will offer appropriate options (e.g., international call packages, large data packages) in addition to the basic plan.

[1372] The server also takes into account the user's past option usage history.

[1373] Step 9: Generate Notifications

[1374] The server generates the proposal and compiles it into a format that is easy for the user to understand.

[1375] The server creates the proposal in text message or email format.

[1376] Step 10: User Notifications

[1377] The server sends the generated suggestions to the user's terminal.

[1378] Users review the proposed plan on their own devices and consider changing their plan based on the proposal.

[1379] Step 11: Gathering Feedback

[1380] Users provide feedback on the proposed plans and options.

[1381] The device sends the collected feedback to the server.

[1382] Step 12: Model Improvement

[1383] The server analyzes the collected feedback and improves the generative artificial intelligence model.

[1384] The server uses the feedback to improve the accuracy of its next suggestions.

[1385] This series of processes allows the system to gain a detailed understanding of users' data usage patterns and provide optimal plans. This is expected to reduce sales workload and improve customer satisfaction.

[1386] (Example 1)

[1387] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1388] Current mobile communication systems make it difficult for users to choose the optimal mobile plan and options, and there is no mechanism to automatically provide appropriate suggestions. Therefore, users must research complex plans and options themselves, which is time-consuming and laborious. Furthermore, there is no way to improve the system based on user satisfaction with suggested plans and feedback, making it difficult to improve the accuracy of suggestions.

[1389] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1390] In this invention, the server includes data collection means, data preprocessing means, data analysis means, suggestion generation means, notification means, feedback collection means, model improvement means, a user's mobile terminal, means for storing data collected from the server in a database, means for cleaning and normalizing the collected data, means for analyzing data usage trends and performing clustering using generative artificial intelligence, means for generating optimal mobile plans and options, means for notifying the user of the suggested content, and means for collecting user feedback and improving the model. As a result, the user can be automatically suggested the optimal mobile plan and options, saving time and effort. Furthermore, it becomes possible to improve the accuracy of suggestions based on feedback.

[1391] "Data collection means" refers to methods for collecting user mobile billing data, packet communication data, and other similar information.

[1392] "Data preprocessing means" are methods for cleaning and normalizing collected data. This includes checking and processing irregular or missing values, removing duplicate data, and extracting necessary information.

[1393] "Data analysis methods" refer to methods that use generative artificial intelligence to analyze data usage trends for each user and perform clustering.

[1394] The "proposal generation method" is a means of generating the optimal mobile plan and options for the user based on the analysis results.

[1395] "Notification means" refers to a means of notifying the user's device of the generated proposal content.

[1396] "Feedback collection methods" refer to means of collecting feedback from users.

[1397] "Model improvement methods" refer to techniques for improving the model of a generative artificial intelligence based on collected feedback, thereby enhancing the accuracy of suggestions.

[1398] "User's mobile device" refers to a mobile device such as a smartphone or tablet that the user is using.

[1399] A "server" refers to a computer system that is responsible for collecting, storing, processing, analyzing, and improving data models.

[1400] "Means of saving to a database" refers to the means of classifying and organizing collected data and saving it to a database.

[1401] "Means for cleaning and normalizing collected data" refers to means of ensuring data quality through handling irregular or missing values, removing duplicate data, and standardizing data formats.

[1402] "Generative artificial intelligence" refers to artificial intelligence technology that learns patterns from large amounts of data and generates recommendations.

[1403] Clustering is an analytical technique for grouping data based on similarity.

[1404] "Optimal mobile plans and options" refer to cost-effective mobile communication plans and additional options selected based on the user's data usage trends.

[1405] Modes for carrying out the invention

[1406] This invention relates to a system that analyzes a user's mobile data usage and proposes the optimal mobile plan and options. The system is configured as follows, with each component working in coordination.

[1407] First, the user's mobile device collects their mobile billing data and packet data on a monthly basis and uploads it to the server periodically. This includes a function that automatically sends data when the device detects a Wi-Fi connection.

[1408] The server stores the received data in a database. The database is a storage system that helps classify and organize data, and the data is managed under a specific user ID. Next, the server preprocesses the collected data. Cleaning and normalization are performed, such as detecting and correcting irregular or missing values, removing duplicate data, and standardizing the format. For example, if there is abnormally long call duration data, it will be detected and excluded from the dataset.

[1409] Subsequently, the server uses generative artificial intelligence to analyze the data. The generative AI model learns user usage patterns based on past data and analyzes data usage trends for each user. This is done using prompts such as the following:

[1410] Please perform a pattern analysis including the following user data and propose the optimal mobile plan.

[1411] User ID: 12345

[1412] Monthly call time: 300 minutes

[1413] Monthly data usage: 5GB

[1414] Usage time: Primarily from evening to night

[1415] Current plan: Standard plan

[1416] Feedback: "I would like to consider other large-capacity data plans as well."

[1417] Based on the analysis results, the server generates optimal mobile plan and option suggestions. For example, based on call time and data usage, it can suggest the most cost-effective high-capacity data plan for user A. It can also suggest additional options such as international call packages and data increase packages.

[1418] After a proposal is generated, the server sends a notification to the user's device. This is done via email or push notification, and the proposal is presented in an easy-to-understand format. The user receives the notification, reviews the proposal on their device, and can change to an appropriate plan.

[1419] Furthermore, user feedback is collected and sent to the server. Users click on a provided link and answer a feedback form. This form may include questions such as, "Are you satisfied with this plan proposal?" or "Are there any other options you would like to see?" The server can use the collected feedback to improve the generative artificial intelligence model and enhance the accuracy of future proposals.

[1420] As described above, this system can automatically suggest the optimal mobile plan and options to users through a series of processes, from data collection and analysis to suggestions, notifications, and improvements based on feedback. As a result, users can avoid the hassle of conducting their own research, saving time and effort. Furthermore, by continuously collecting and analyzing feedback, the accuracy of suggestions will improve, and customer satisfaction is expected to increase.

[1421] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1422] Step 1: Data Collection

[1423] Input: Mobile billing data and packet communication data stored on the user's mobile device.

[1424] Specific operation: The device automatically collects monthly data usage, call time, number of text messages, etc. The collected data is periodically uploaded to the server when connected to Wi-Fi.

[1425] Output: Raw data uploaded to the server.

[1426] Step 2: Save

[1427] Input: Raw data uploaded from the device.

[1428] Specific operation: The server stores the received data in the database. It verifies that the data has arrived in the correct format, organizes it by user ID, and stores it in the database.

[1429] Output: Organized and categorized database entries.

[1430] Step 3: Data Preprocessing

[1431] Input: Raw data stored in the database.

[1432] Specific actions: The server performs data cleaning, detecting and correcting irregular and missing values. Furthermore, it removes duplicate data and standardizes all data into a common format. For example, if it contains data with unusually long call durations, it will detect and remove it.

[1433] Output: Preprocessed and consistent data.

[1434] Step 4: Normal Analysis

[1435] Input: Pre-processed data.

[1436] Specific operation: The server analyzes data usage trends using a generative AI model. It learns user usage patterns based on past data and performs clustering. It generates prompt messages, inputs them into the generative AI model, and obtains the analysis results.

[1437] Example prompt: "Perform pattern analysis on the following user data and suggest the optimal mobile plan. User ID: 12345, Monthly call time: 300 minutes, Monthly data usage: 5GB, Usage time: Primarily evening to night, Current plan: Standard plan, Feedback: I would also like to consider other high-capacity data plans."

[1438] Output: Analysis results of data usage trends for each user.

[1439] Step 5: Proposal Generation

[1440] Input: Analysis results of data usage trends.

[1441] Specific operation: The server generates optimal mobile plans and options based on the analysis results. It compares plans that correspond to the user's usage patterns with market data and selects the best plan. It creates a proposal that includes additional options (such as international call packages and data bonus packages).

[1442] Output: A list of mobile plans and options to suggest to the user.

[1443] Step 6: Notification

[1444] Input: A list of proposed mobile plans and options.

[1445] Specific operation: The server sends the proposal to the user's device via email or push notification. This allows the user to review the proposal and change to an appropriate plan.

[1446] Specific example: "Send the proposal in an easy-to-understand format to the user's device, allowing them to easily review the content. Users can then review the proposal on their device and make changes to the plan that best suits them."

[1447] Output: The suggested content that will be displayed on the user's device.

[1448] Step 7: Gathering Feedback and Improving the Model

[1449] Input: User feedback.

[1450] Specific operation: The user provides feedback on the proposed plan and options and sends it to the server. The server uses the collected feedback to improve the generated AI model and increase the accuracy of future suggestions.

[1451] Specific example: "Users provide feedback on their satisfaction with the suggestions and offer opinions. The server uses this feedback to improve the generative artificial intelligence model and enhance the accuracy of future suggestions."

[1452] Output: Improved generative AI model.

[1453] Through the processing steps described above, this system automatically proposes the optimal mobile plan and options to the user, improving customer satisfaction and significantly reducing the workload of the sales team.

[1454] (Application Example 1)

[1455] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1456] Modern e-commerce sites are required to leverage users' purchase and browsing history to provide optimal product recommendations and campaign notifications. However, traditional systems often fail to collect and analyze data effectively, resulting in ineffective recommendations. Furthermore, there is a lack of means to effectively utilize user feedback and continuously improve the accuracy of the system's recommendations. Therefore, a more accurate recommendation system is needed to improve user satisfaction.

[1457] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1458] In this invention, the server includes data collection means, data preprocessing means, data analysis means, suggestion generation means, notification means, feedback collection means, model improvement means, and means for suggesting products and services based on the user's usage history. This makes it possible to suggest optimal products and campaigns based on the user's purchase and browsing history, and to improve the system by collecting feedback from the user.

[1459] "Data collection means" refers to methods for automatically collecting data such as users' purchase history and browsing history and providing it to the system.

[1460] "Data preprocessing means" refers to methods for cleaning collected data and checking and processing irregular values ​​and missing values.

[1461] "Data analysis methods" refer to methods for analyzing collected and pre-processed data and clustering user usage trends using generative artificial intelligence.

[1462] A "proposal generation method" is a means of proposing the most suitable products, services, and campaigns based on the analysis results.

[1463] A "notification method" is a means of notifying the user of the generated proposal content.

[1464] "Feedback collection methods" refer to methods for collecting feedback such as user satisfaction and opinions regarding a proposal.

[1465] "Model improvement methods" refer to methods for improving the model of a generative artificial intelligence system in order to improve the accuracy of the system's suggestions using collected feedback.

[1466] "Methods for suggesting products and services based on user usage history" refers to methods for suggesting optimal products and campaigns based on a user's past purchase and browsing history.

[1467] Modes for carrying out the invention

[1468] The system of this invention includes means for data collection, means for data preprocessing, means for data analysis, means for suggestion generation, means for notification, means for feedback collection, means for model improvement, and means for suggesting products and services based on the user's usage history.

[1469] The server first automatically collects user data such as purchase history and browsing history using data collection tools. This data is sent to the system and stored in a database. Next, data preprocessing tools are used to clean the collected data, checking and processing irregular and missing values, and formatting it into an appropriate format. This improves data consistency and quality, enabling accurate subsequent analysis.

[1470] As a means of data analysis, the server uses generative artificial intelligence to analyze the collected data. Clustering technology is used to identify user usage patterns and classify them into groups with common characteristics. This analysis makes it possible to identify the products and services that are most suitable for each user.

[1471] The suggestion generation system generates optimal products and campaigns for users based on the results of data analysis. Specifically, it makes suggestions that take into account the characteristics of each clustered group. In this process, the server also compares the suggestions with the latest products and campaigns available on the market, enabling it to provide the most useful suggestions for the user.

[1472] The generated suggestions are sent to the user via notification methods. The system is designed to allow users to easily review the suggestions via email or push notifications. Users can view the notification content within the application and easily select and purchase the suggested products and services.

[1473] The feedback collection mechanism gathers user satisfaction and opinions on the suggestions. The server uses this feedback to improve the generative artificial intelligence model, thereby enhancing the accuracy of future suggestions. This allows the system to continuously improve and continue providing valuable suggestions to users.

[1474] The specific hardware and software used include:

[1475] Pandas: Used for data preprocessing and formatting.

[1476] Scikit-learn: Used for data analysis and clustering.

[1477] Notification System API: Sends notifications to users.

[1478] Feedback Collection API: Collects feedback from users.

[1479] As a concrete example, there are cases where notifications about seasonal products or discount campaigns are sent based on a specific user's purchase history. In this case, a generative AI model can be used to make highly accurate suggestions by using the following prompt sentences.

[1480] Example of a prompt:

[1481] Based on users' purchasing patterns and browsing trends, suggest the most suitable products and campaigns. For example, suggest winter seasonal products based on their recent browsing history.

[1482] As described above, this system can achieve highly accurate product recommendations based on user usage history and continuous system improvement through feedback.

[1483] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1484] Step 1:

[1485] Data collection

[1486] The server automatically collects data such as user purchase history and browsing history using data collection methods. Data is periodically sent from each terminal to the server and stored in the database. The input for this step is the user's purchase history and browsing history, and the output is the raw data stored in the database.

[1487] Step 2:

[1488] Data preprocessing

[1489] The server uses data preprocessing techniques to clean the collected data. Specifically, it checks for irregular or missing values ​​and handles them appropriately. It also standardizes the data format and extracts necessary information. The input for this step is raw data, and the output is cleaned, preprocessed data in a standardized format.

[1490] Step 3:

[1491] Data analysis

[1492] The server uses data analysis tools to analyze preprocessed data using generative artificial intelligence. Specifically, it identifies user usage trends using clustering methods (e.g., KMeans). Clustering forms user groups with common characteristics. The input for this step is preprocessed data, and the output is the user clustering result.

[1493] Step 4:

[1494] Proposal generation

[1495] The server uses a suggestion generation mechanism to generate optimal products, services, and campaigns for users based on clustering results. Specifically, it compares the latest market information with the user clustering results and provides optimal suggestions for each user group. The inputs to this step are the clustering results and market information, and the output is the generated suggestions.

[1496] Step 5:

[1497] notification

[1498] The server uses notification methods to inform the user of the generated suggestions. Specifically, it allows the user to easily review the suggestions via email or push notifications. The input for this step is the generated suggestions, and the output is the notification sent to the user.

[1499] Step 6:

[1500] Feedback Collection

[1501] The server uses feedback collection methods to gather user satisfaction levels and opinions on suggestions. Specifically, it collects user-provided feedback data and stores it in a database. The input for this step is user feedback, and the output is the collected feedback data.

[1502] Step 7:

[1503] Model improvements

[1504] The server uses model improvement tools to refine the generative artificial intelligence model based on the collected feedback. Specifically, it analyzes the feedback data and trains the model to improve the accuracy of future suggestions. The input for this step is the feedback data, and the output is the improved generative artificial intelligence model.

[1505] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1506] Modes for carrying out the invention

[1507] This invention relates to a system that includes data collection means, data preprocessing means, data analysis means, suggestion generation means, notification means, feedback collection means, model improvement means, and emotion recognition means. Through this system, the system automatically collects and analyzes the user's monthly mobile billing data and packet communication data, and suggests the optimal mobile plan and options. Furthermore, by recognizing the user's emotions and adjusting the suggestions accordingly, it is possible to provide a more personalized service.

[1508] System program and processing details

[1509] This system performs a series of processes, from data collection to suggestion notification and emotion recognition, as follows:

[1510] 1. Data collection:

[1511] The server receives each user's monthly mobile billing data and packet communication data and stores it in a database.

[1512] Specific example:

[1513] The device automatically collects the user's data usage history and periodically uploads it to the server.

[1514] The server appropriately classifies the received data and stores it for each user.

[1515] 2. Data preprocessing:

[1516] The server preprocesses the collected data. This includes cleaning the data (handling irregular or missing values) and extracting necessary information (such as call duration and data usage).

[1517] Specific example:

[1518] The server standardizes the data format and supplements any missing data.

[1519] The server removes duplicate and erroneous data to maintain data integrity.

[1520] 3. Data Analysis:

[1521] The server uses generative artificial intelligence to analyze data usage trends for each user. This includes pattern analysis and clustering based on the user's usage history.

[1522] Specific example:

[1523] The server detects call duration, data usage time periods, and monthly usage trends.

[1524] The server groups users with similar usage patterns and understands the characteristics of each group.

[1525] 4. Emotion recognition:

[1526] The server uses an emotion engine to recognize the user's emotions, based on feedback and other emotional data provided by the user.

[1527] Specific example:

[1528] The user enters their feelings about the proposal (satisfied, dissatisfied, etc.).

[1529] The server analyzes user feedback and extracts emotional information.

[1530] 5. Proposal generation:

[1531] The server generates the optimal mobile plan and options for the user based on analysis results and sentiment information. This includes comparing them to the latest market plans and evaluating their cost-effectiveness.

[1532] Specific example:

[1533] The server selects the plan that best suits the user's usage patterns and emotions.

[1534] The server will suggest additional options (such as international call packages and large data packages).

[1535] 6. Notice:

[1536] The server notifies the user's device of the generated suggestions. This includes notifications via email or message.

[1537] Specific example:

[1538] The server sends the proposal to the user's terminal in an easy-to-understand format, allowing the user to easily review the content.

[1539] Users can review the proposed plans on their own devices and change them to a more suitable plan.

[1540] 7. Feedback and Improvement:

[1541] Users provide feedback on the proposed plans and options and send it to the server. The server uses this feedback to improve the generative artificial intelligence model and increase the accuracy of future suggestions.

[1542] Specific example:

[1543] Users provide feedback on their satisfaction with the proposed content and offer their opinions.

[1544] The server analyzes the collected feedback and uses it to improve the model.

[1545] In this way, this system not only provides data-driven, automated, and optimal suggestions, but also considers the user's emotions, thereby further improving customer satisfaction. This is expected to reduce sales workload and increase customer satisfaction.

[1546] The following describes the processing flow.

[1547] Step 1: Data Collection

[1548] The server receives each user's monthly mobile billing data and packet communication data.

[1549] The device automatically collects data from the user's device and uploads it to the server periodically.

[1550] The server saves the received data to the database.

[1551] Step 2: Reading Storage

[1552] The server stores the received data in the appropriate database and categorizes it by user.

[1553] The server manages to maintain data integrity.

[1554] Step 3: Data Cleaning

[1555] The server cleans the collected data, checking for irregular or missing values ​​and correcting or deleting them.

[1556] The server identifies and removes duplicate and erroneous data.

[1557] Step 4: Manufacturing Conversion

[1558] The server converts the data into a unified format (e.g., date and time format, unified units).

[1559] The server extracts necessary information, such as call duration, data usage, and current plan.

[1560] Step 5: Pattern Analysis

[1561] The server uses generative artificial intelligence to analyze each user's data usage patterns.

[1562] The server tracks patterns such as call duration, peak data usage times, and monthly usage based on the user's usage history.

[1563] Step 6: Clustering

[1564] The server clusters user usage patterns.

[1565] The server groups users with similar usage patterns and identifies the characteristics of each group.

[1566] Step 7: Emotion Recognition

[1567] The server uses an emotion engine to recognize the user's emotions.

[1568] The user enters their feelings about the proposal (satisfied, dissatisfied, etc.).

[1569] The server analyzes user feedback and extracts emotional information.

[1570] Step 8: Selecting a Plan

[1571] The server compares each user's usage patterns with the latest market plans.

[1572] The server selects the plan that best suits the cost-performance ratio and user needs.

[1573] The server adjusts the suggestions based on emotional information.

[1574] Step 9: Proposing Options

[1575] The server will offer appropriate options (e.g., international call packages, large data packages) in addition to the basic plan.

[1576] The server also takes into account the user's past option usage history.

[1577] Step 10: Generating the proposal notification

[1578] The server generates the proposal and compiles it into a format that is easy for the user to understand.

[1579] The server creates the proposal in text message or email format.

[1580] Step 11: User Notifications

[1581] The server sends the generated suggestions to the user's terminal.

[1582] Users review the proposed plan on their own devices and consider changing their plan based on the proposal.

[1583] Step 12: Gathering Feedback

[1584] Users provide feedback on the proposed plans and options.

[1585] The device sends the collected feedback to the server.

[1586] Step 13: Model Improvement

[1587] The server analyzes the collected feedback and improves the generative artificial intelligence model.

[1588] The server uses the feedback to improve the accuracy of its next suggestions.

[1589] This series of steps allows the system to gain a detailed understanding of users' data usage patterns and emotions, enabling it to provide personalized and optimal plans. This is expected to reduce sales workload and improve customer satisfaction.

[1590] (Example 2)

[1591] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1592] Modern telecommunications service users face the challenge of choosing the optimal mobile plan to suit their diverse usage patterns and lifestyles. Furthermore, there is a lack of means to provide personalized services that adequately reflect user satisfaction and feedback on proposed plans. Additionally, there is a lack of approaches that consider user emotions, highlighting the need for effective strategies to improve customer satisfaction.

[1593] In Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes data collection means, data preprocessing means, data analysis means, suggestion generation means, notification means, feedback collection means, model improvement means, and emotion recognition means. This makes it possible to analyze the user's data usage patterns and emotions and propose the optimal mobile plan based on them. Furthermore, by utilizing user feedback to improve the accuracy of suggestions, it is possible to provide more personalized services and increase customer satisfaction.

[1594] "Data collection means" refers to a method for automatically receiving users' monthly mobile billing data and packet communication data and storing it in a database.

[1595] "Data preprocessing means" are methods for cleaning collected data and extracting necessary information. This includes handling irregular values ​​and missing values.

[1596] "Data analysis methods" refer to methods that use generative artificial intelligence to analyze data usage trends for each user and perform clustering.

[1597] A "proposal generation method" is a means of generating the optimal mobile plan and options for the user based on analysis results and sentiment information.

[1598] "Notification method" refers to the means of notifying the user's device of the generated proposal content. This includes notifications via email or message.

[1599] A "feedback collection method" is a means of collecting feedback from users regarding the plans and options they have proposed.

[1600] "Model improvement methods" refer to techniques for improving the model of a generative artificial intelligence based on collected feedback, thereby enhancing the accuracy of suggestions in subsequent iterations.

[1601] An "emotion recognition method" is a means of analyzing user feedback and other emotional data to extract user emotional information.

[1602] Modes for carrying out the invention

[1603] This invention relates to a system including data collection means, data preprocessing means, data analysis means, suggestion generation means, notification means, feedback collection means, model improvement means, and emotion recognition means. Through this system, the system automatically collects the user's monthly mobile billing data and packet communication data and suggests the optimal mobile plan and options. Furthermore, by recognizing the user's emotions and adjusting the suggestions accordingly, it is possible to provide a more personalized service.

[1604] Data collection

[1605] The server receives each user's monthly mobile billing data and packet communication data and stores it in a database. A data collection application is installed on the user's device, which automatically collects data and uploads it to the server periodically. The server uses a database management system (e.g., MySQL) to appropriately classify the received data and store it for each user.

[1606] Specific example:

[1607] The device collects the user's data usage history every night and uploads it to the server.

[1608] The server receives the collected data and saves it to the database based on the reception date and time and the user ID. The data is saved in JSON format.

[1609] Data preprocessing

[1610] The server preprocesses the collected data. This includes cleaning the data (handling irregular or missing values) and extracting necessary information (e.g., call duration, data usage). The server loads the dataset using the Python Pandas library and converts it to a consistent format.

[1611] Specific example:

[1612] The server detects irregular or missing values ​​and removes or fills them in. For example, if an irregular value is found, the record is deleted, and if there are missing values, they are filled in using the surrounding values.

[1613] The server extracts the necessary information from the cleaned data and prepares it for analysis.

[1614] Data analysis

[1615] The server analyzes user-specific data usage trends using generative artificial intelligence (e.g., TensorFlow models). This includes pattern analysis and clustering based on user usage history.

[1616] Specific example:

[1617] The server uses a pre-trained generative artificial intelligence model to input collected data and analyze the user's data usage patterns.

[1618] The server uses pattern recognition algorithms to analyze data usage patterns, including time of day and monthly usage. This clarifies user usage patterns.

[1619] The server uses clustering techniques to group users with similar usage patterns and understand the characteristics of each group.

[1620] emotion recognition

[1621] The server uses an emotion engine (e.g., an emotion analysis API) to recognize the user's emotions. It analyzes feedback and other emotion data provided by the user to extract emotional information.

[1622] Specific example:

[1623] Users input their opinions on the proposal and their feelings about their current mobile plan (e.g., satisfied, dissatisfied) through the application's interface.

[1624] The server inputs text data (feedback) collected from users into an emotion engine and extracts emotional information (e.g., positive, negative, neutral).

[1625] Proposal generation

[1626] The server generates the optimal mobile plan and options for the user based on analysis results and sentiment information. This includes comparing them to the latest market plans and evaluating their cost-effectiveness.

[1627] Specific example:

[1628] The server runs an algorithm that takes user usage patterns and sentiment data as input to select the optimal mobile plan. This includes comparing it with the latest market plans and evaluating cost-effectiveness.

[1629] The server combines the selected plan with additional options (e.g., international call package, large data package) to generate a final proposal.

[1630] notification

[1631] The server notifies the user's device of the generated suggestions. This includes notifications via email or message.

[1632] Specific example:

[1633] The server sends the generated suggestions to the user via email or message. Email delivery services or dedicated SMTP servers are used for sending emails.

[1634] Users can review the proposed plan on their device and change to the appropriate plan. Push notifications are also used to indicate when a notification has arrived.

[1635] Feedback and Improvement

[1636] Users provide feedback on the proposed plans and options and send it to the server. The server uses this feedback to improve the generative artificial intelligence model, thereby increasing the accuracy of future suggestions.

[1637] Specific example:

[1638] Users enter their satisfaction level and opinions on the proposed content into the application's feedback form and send it to the server.

[1639] The server inputs the collected feedback data into a generative artificial intelligence model, which is then trained and improved. This improves the accuracy of new suggestions.

[1640] Example of a prompt

[1641] Users are asked to provide data in the form of a message such as, "We will suggest the best plan for you based on your monthly data usage and current mobile plan. Please provide your data."

[1642] keyword

[1643] Generative AI model, prompt sentence

[1644] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1645] System program processing flow

[1646] Step 1: Data Collection

[1647] The server receives the user's monthly mobile billing data and packet communication data and stores it in a database. The input is the data sent from the user's terminal, and the output is the organized data stored in the database.

[1648] Specific actions:

[1649] The device collects the user's data usage history using a data collection application every night and uploads it to the server.

[1650] The server stores the received data in JSON format and categorizes it by each user's ID. A database management system (e.g., MySQL) is used to organize and store this information.

[1651] Step 2: Data preprocessing

[1652] The server preprocesses the collected data. The input is the data collected in step 1, and the output is the cleaned data from which the necessary information has been extracted.

[1653] Specific actions:

[1654] The server loads the dataset using the Python Pandas library and converts it to a consistent format.

[1655] The server detects irregular or missing values ​​and removes or fills them in as needed. Specifically, if an irregular value is found, the record is deleted, and if a missing value exists, it is inferred and filled in from the surrounding data.

[1656] Step 3: Data Analysis

[1657] The server analyzes users' data usage trends using generative artificial intelligence (e.g., TensorFlow). The input is the data preprocessed in step 2, and the output is the usage trends and clustering results for each user.

[1658] Specific actions:

[1659] The server uses a trained artificial intelligence model to input data and analyze user usage patterns.

[1660] The server uses pattern recognition algorithms to analyze data usage patterns, including time of day and monthly usage. Based on this information, it identifies user usage patterns.

[1661] The server uses clustering techniques to group users with similar usage patterns and understands the characteristics of each group.

[1662] Step 4: Emotion Recognition

[1663] The server recognizes the user's emotions using an emotion engine (e.g., an emotion analysis API). The input is feedback data provided by the user, and the output is the analyzed emotion information.

[1664] Specific actions:

[1665] Users input their suggestions and their feelings about their current mobile plan through the application's interface. This input is primarily text data.

[1666] The server inputs text data into the emotion engine and extracts emotional information such as positive, negative, and neutral.

[1667] Step 5: Proposal Generation

[1668] The server generates the optimal mobile plan and options for the user based on the analysis results and sentiment information. The input is the results of steps 3 and 4, and the output is a specific plan proposal for the user.

[1669] Specific actions:

[1670] The server uses usage trend data and sentiment data to run an algorithm and generate the optimal mobile plan.

[1671] The server evaluates and compares the latest market plans to select the most cost-effective one. It also proposes combinations with additional options (e.g., international call packages, large data packages).

[1672] Step 6: Notification

[1673] The server notifies the user's terminal of the generated proposal. The input is the proposal data from step 5, and the output is the notification sent to the user's terminal.

[1674] Specific actions:

[1675] The server sends the proposal to the user via email or message. Email delivery services or dedicated SMTP servers are used for sending.

[1676] Users review the proposed plan on their devices and proceed with the necessary steps to change to the appropriate plan. Push notifications are also used for further notification.

[1677] Step 7: Feedback and Improvement

[1678] Users provide feedback on the proposed plans and options and send it to the server. The input is the user's feedback data, and the output is the result of the model's improvement.

[1679] Specific actions:

[1680] Users enter their satisfaction level and opinions on the proposed content into the application's feedback form and send it to the server.

[1681] The server inputs the collected feedback data into a generative artificial intelligence model, which is then trained and improved. This increases the accuracy of new suggestions.

[1682] (Application Example 2)

[1683] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1684] For autonomous vehicles, there is a lack of systematic methods for providing optimal routes and driving tips based on driving history data and sensor data. Furthermore, the technology for recognizing the driver's emotional state in real time and providing advice based on that is still immature.

[1685] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1686] In this invention, the server includes data collection means, data preprocessing means, data analysis means, emotion recognition means, vehicle driving history data collection means, vehicle sensor data collection means, driving route generation means, and driving advice generation means. This makes it possible to comprehensively analyze the driving history data and sensor data of an autonomous vehicle, as well as the emotional state of the driver, and provide the optimal route and driving tips.

[1687] "Data collection means" refers to means for automatically collecting various types of data from users and vehicles.

[1688] "Data preprocessing means" are methods for cleaning collected data and organizing irregular values, missing values, and duplicate data.

[1689] "Data analysis methods" refer to means for analyzing collected and pre-processed data to extract user usage trends and patterns.

[1690] A "proposal generation method" is a means for generating optimal mobile plans, driving routes, and driving advice based on analysis results.

[1691] A "notification method" is a means of notifying users or vehicles of the generated proposal content.

[1692] A "feedback collection method" is a means of collecting feedback from users regarding their suggestions and incorporating it into the system.

[1693] "Model improvement methods" refer to measures taken to improve the artificial intelligence model based on collected feedback and to enhance the accuracy of future suggestions.

[1694] An "emotion recognition tool" is a means of analyzing the user's emotional state and adjusting the suggested content based on that analysis.

[1695] A "vehicle driving history data collection method" is a means for automatically collecting vehicle driving history data.

[1696] A "vehicle sensor data collection means" is a means for automatically collecting sensor data from a vehicle.

[1697] A "driving route generation means" is a means for generating the optimal driving route based on analyzed data.

[1698] A "driving advice generation method" is a means for generating driving advice for a driver based on data analysis and emotion recognition results.

[1699] This invention is a system for comprehensively collecting and analyzing driving history data, sensor data, and the driver's emotional state from an autonomous vehicle, and for generating optimal routes and driving advice. This system includes means involving a server, a terminal, and a user.

[1700] The server collects driving history data and sensor data from users and vehicles through data collection means. This data collection includes GPS data, vehicle speed data, brake data, accelerator data, etc. In addition, the driver's emotional state (e.g., stress, fatigue) is collected through emotion recognition means.

[1701] In the data preprocessing mechanism, the server cleans the collected data and performs processing to impute irregular values ​​and missing values. The preprocessed data is then analyzed by the data analysis mechanism. Here, a generative AI model is used to analyze each user's driving patterns and sensor data trends, and clustering is performed. In addition, emotional data acquired using the emotion recognition mechanism is also analyzed to understand the driver's emotional state.

[1702] Based on these analysis results, the suggestion generation system generates optimal driving routes and driving advice. For example, it selects routes suitable for specific times of day and weather conditions, and provides driving tips and maintenance advice. It also provides advice tailored to the driver's emotional state, supporting them in driving safely and comfortably.

[1703] The notification system sends generated driving routes and advice to the user's device. The user reviews the notification and incorporates the driving routes and advice as needed. Furthermore, the user can provide feedback on the suggestions, which is sent to the server by the feedback collection system.

[1704] Through model improvement mechanisms, the server analyzes collected feedback and improves the generated AI model. This improves the accuracy of future suggestions and enables more personalized driving support.

[1705] As a concrete example, consider a case where driving history data, sensor data, and emotion data associated with a vehicle ID "ABC123" are collected and analyzed.

[1706] As an example of a prompt, you could instruct the generating AI model with a message like, "Collect and analyze vehicle driving history data, sensor data, and driver emotion data to generate the optimal route, driving tips, and emotion-based advice."

[1707] Based on the above, this system can comprehensively analyze the driving history data and sensor data of autonomous vehicles, as well as the driver's emotional state, to provide optimal driving routes and advice.

[1708] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1709] Step 1: Data Collection

[1710] The server automatically collects driving history data, sensor data, and sentiment data from users and vehicles using data collection methods. Examples include GPS data, vehicle speed data, brake data, and accelerator data. Input is raw data from users and vehicles, and output is the collected dataset.

[1711] Step 2: Data Preprocessing

[1712] The server cleans the collected data using data preprocessing techniques. This process ensures data integrity by imputing irregular or missing values. Specifically, it standardizes data formats, imputes missing data, and removes duplicate data. The input is the collected dataset, and the output is the cleaned data.

[1713] Step 3: Data Analysis

[1714] The server analyzes pre-processed data using data analysis tools. Here, a generative AI model is used to analyze user-specific driving patterns and sensor data trends, and clustering is performed. Furthermore, emotional data acquired by emotion recognition tools is also analyzed to understand the driver's emotional state. The input is cleaned data, and the output is the analysis result.

[1715] Step 4: Proposal Generation

[1716] The server uses a suggestion generation mechanism to generate optimal driving routes and driving advice based on the analysis results. For example, it selects routes suitable for specific time periods and weather conditions, and provides driving tips and maintenance advice. It also provides advice tailored to the user's emotional state. The input is the analysis results, and the output is the generated suggestions.

[1717] Step 5: Notification

[1718] The system uses a notification method to send generated driving routes and advice to the user's device. The user reviews the notification and incorporates the driving routes and advice as needed. The input is the generated suggestions, and the output is the notification sent to the user.

[1719] Step 6: Gathering Feedback

[1720] Users provide feedback on the proposed content. This feedback is sent to the server through a feedback collection mechanism. The input is the user's feedback, and the output is the collected feedback data.

[1721] Step 7: Model Improvement

[1722] The server uses model improvement tools to refine the generative AI model based on the collected feedback. This improves the accuracy of the next proposal. The input is the collected feedback data, and the output is the improved generative AI model.

[1723] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1724] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1725] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1726] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1727] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1728] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1729] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1730] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1731] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1732] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1733] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1734] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1735] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1736] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1737] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1738] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1739] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1740] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1741] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1742] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1743] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1744] The following is further disclosed regarding the embodiments described above.

[1745] (Claim 1)

[1746] Data collection means,

[1747] Data preprocessing means,

[1748] Data analysis methods,

[1749] Proposal generation means and

[1750] Notification methods,

[1751] Methods for collecting feedback,

[1752] Model improvement methods,

[1753] A system that includes this.

[1754] (Claim 2)

[1755] The system according to claim 1, wherein the data preprocessing means includes means for checking and processing irregular values ​​and missing values.

[1756] (Claim 3)

[1757] The system according to claim 1, wherein the data analysis means includes means for analyzing the data usage trends of each user using generative artificial intelligence and performing clustering.

[1758] "Example 1"

[1759] (Claim 1)

[1760] Data collection means,

[1761] Data preprocessing means,

[1762] Data analysis methods,

[1763] Proposal generation means and

[1764] Notification methods,

[1765] Methods for collecting feedback,

[1766] Model improvement methods,

[1767] The user's mobile device and

[1768] A means of storing data collected from a server in a database,

[1769] A means for cleaning and normalizing the collected data,

[1770] A method for analyzing data usage trends and performing clustering using generative artificial intelligence,

[1771] A means for generating the optimal mobile plan and options,

[1772] A means of notifying the user of the proposed content,

[1773] A means of collecting user feedback and improving the model,

[1774] A system that includes this.

[1775] (Claim 2)

[1776] The system according to claim 1, wherein the data preprocessing means includes means for checking and processing irregular values ​​and missing values, deleting duplicate data, and extracting necessary information.

[1777] (Claim 3)

[1778] The system according to claim 1, wherein the data analysis means includes means for analyzing the data usage trends of each user using generative artificial intelligence, learning usage patterns based on past data, and performing clustering.

[1779] "Application Example 1"

[1780] (Claim 1)

[1781] Data collection means,

[1782] Data preprocessing means,

[1783] Data analysis methods,

[1784] Proposal generation means and

[1785] Notification methods,

[1786] Methods for collecting feedback,

[1787] Model improvement methods,

[1788] A means of suggesting products and services based on the user's usage history,

[1789] A system that includes this.

[1790] (Claim 2)

[1791] The system according to claim 1, wherein the data preprocessing means includes means for checking and processing irregular values ​​and missing values.

[1792] (Claim 3)

[1793] The system according to claim 1, wherein the data analysis means includes means for analyzing the data usage trends of each user using generative artificial intelligence and performing clustering.

[1794] "Example 2 of combining an emotion engine"

[1795] (Claim 1)

[1796] Data collection means,

[1797] Data preprocessing means,

[1798] Data analysis methods,

[1799] Proposal generation means and

[1800] Notification methods,

[1801] Methods for collecting feedback,

[1802] Model improvement methods,

[1803] Means of recognizing emotions,

[1804] A system that includes this.

[1805] (Claim 2)

[1806] The system according to claim 1, wherein the data preprocessing means includes means for checking and processing irregular values ​​and missing values.

[1807] (Claim 3)

[1808] The system according to claim 1, wherein the data analysis means includes means for analyzing the data usage trends of each user using generative artificial intelligence and performing clustering.

[1809] "Application example 2 when combining with an emotional engine"

[1810] (Claim 1)

[1811] Data collection means,

[1812] Data preprocessing means,

[1813] Data analysis methods,

[1814] Proposal generation means and

[1815] Notification methods,

[1816] Methods for collecting feedback,

[1817] Model improvement methods,

[1818] Means of recognizing emotions,

[1819] A means for collecting vehicle driving history data,

[1820] A means for collecting vehicle sensor data,

[1821] Driving route generation means,

[1822] A means for generating driving advice,

[1823] A system that includes this.

[1824] (Claim 2)

[1825] The system according to claim 1, wherein the data preprocessing means includes means for checking and processing irregular values ​​and missing values.

[1826] (Claim 3)

[1827] The system according to claim 1, wherein the data analysis means includes means for analyzing the data usage trends of each user using generative artificial intelligence and performing clustering. [Explanation of Symbols]

[1828] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A data collection method that receives and stores the user's monthly mobile billing data and packet communication data, A data preprocessing means for cleaning collected data, extracting necessary information, and converting it into an appropriate format, A data analysis method that uses generative artificial intelligence to analyze data usage trends for each user and perform clustering, A proposal generation means that automatically generates the optimal plan or option for the user based on the analysis results, A notification method that notifies the user's device of the generated plan or options, A feedback collection means for collecting and storing user feedback, Based on the collected feedback, a model improvement method is provided to improve the model of the generative artificial intelligence, A system that includes this.

2. The system according to claim 1, wherein the data preprocessing means includes means for checking and processing irregular values ​​and missing values.

3. The system according to claim 1, wherein the data analysis means includes means for analyzing the data usage trends of each user using generative artificial intelligence and performing clustering.

Images